WO2011110491A1

WO2011110491A1 - A non-invasive system and method for diagnosing and eliminating white coat hypertention and white coat effect in a patient

Info

Publication number: WO2011110491A1
Application number: PCT/EP2011/053294
Authority: WO
Inventors: Vicente Jorge Ribas Ripoll
Original assignee: Sabirmedical, S.L.
Priority date: 2010-03-09
Filing date: 2011-03-04
Publication date: 2011-09-15

Abstract

A non-invasive system for measuring blood pressure of a patient with elimination of WCH and WCE, said system consisting of: a blood pressure module consisting of a PPG for measuring changes in a tissue volume in a predetermined location of the patient, and generating an electrical signal associated with said changes in the tissue volume; a calculation device with a processor, the device in communication with the module; a first storage in communication with the device containing instructions for receiving the electrical signal and to process the same by performing at least one operation selected from: (i) calculation of a set of measurement parameters from the electrical signal based on at least one auto-regressive moving average (ARMA) model; (ii) generation of a fixed length data vector consisting of the set of measurement and clinical parameters; (iii) storage in a database the data vector and other data vectors; and, (iv) performing a regression based on a "Random Forest" algorithm by using the data vector and the database, the blood pressure being calculated; and; a second storage in communication with said device containing instructions for diagnosing the WCH and the WCE and to characterize the profile of the WCH and the WCE according to a diagnosis protocol; wherein the instructions of said second storage are further adapted to provide a "real" blood pressure measurement which is not biased by the WCH and WCE by eliminating the profile of the WCH and the WCE from the estimated blood pressure measurement.

Description

A NON-INVASIVE SYSTEM AND METHOD FOR DIAGNOSING AND ELIMINATING WHITE COAT HYPERTENTION AND WHITE COAT EFFECT IN A PATIENT FIELD OF THE INVENTION

The present invention generally relates to a non-invasive system, and more specifically pertains to a system and a method for monitoring of a patient's blood pressure.

BACKGROUND OF THE INVENTION

Physicians monitor various physiological parameters in their patients and use the results of such monitoring as an important tool to evaluate the patients' health. The monitoring of cardiovascular function is particularly valuable and is performed on a very widespread basis. Accurate measurement of blood pressure and other physiological signals allow for careful diagnosis of medical problems. Monitoring cardiovascular functions, such as blood pressure, can allow a physician to diagnose conditions such as hypertension (increased blood pressure) which may result from processes such as aging or disease.

The heart functions as a pump which moves blood through the circulatory system by a regulated sequence of contractions. The heart ejects blood into the aorta. The blood then flows through the arteries, arterioles, and capillaries to the tissues where the blood delivers oxygen and other nutrients and removes carbon dioxide and other waste products from the tissues. The blood returns to the heart and the lungs where carbon dioxide is expelled from the body and oxygen is again transported into the body. The human body regulates blood pressure throughout the circulatory system to facilitate efficient delivery of blood to the tissues.

Blood pressure is the pressure exerted by circulating blood on the walls of blood vessels, and is one of the principal vital signs. During each heartbeat, BP varies between a maximum (systolic) and a minimum (diastolic) pressure. The mean BP decreases as the circulating blood moves away from the heart through arteries, has its greatest decrease in the small arteries and arterioles, and continues to decrease as the blood moves through the capillaries and back to the heart through veins. The blood pressure ranges from a systolic blood pressure (SBP) 120 mmHg and a diastolic pressure (DBP) 80 mmHg.

Figure 1 shows a typical record of the pulsations of pressure taken from by an invasive catheterization in the root of the aorta. The normal systolic blood pressure (SBP) of a young adult is approximately 120 mm Hg while the diastolic blood pressure (DBP) is approximately 80 mmHg. The difference between the two pressures is called the pulse pressure (PP) and under normal conditions is approximately 40 mmHg.

To measure blood pressure in humans is not reasonable to use an invasive catheterization in a main channel, as discussed above, except in critical cases (patients with severe homodynamic compromise, such as patients with septic shock or multi-organic failure). In its place, the blood pressure is usually measured by the noninvasive auscultatory (Korotkoff sounds) and oscillometric measurements which are simpler and quicker than invasive measurements. These two techniques require less expertise in fitting, have virtually no complications, and are less unpleasant and painful for the patient. However, noninvasive methods may yield somewhat lower accuracy and small systematic differences in numerical results. Non-invasive measurement methods are more commonly used for routine examinations and monitoring.

The Auscultatory method: The auscultatory method (from the Latin for listening) uses a stethoscope and a sphygmomanometer. This comprises an inflatable cuff placed around the upper arm at roughly the same vertical height as the heart, attached to a mercury or aneroid manometer. The mercury manometer measures the height of a column of mercury, giving an absolute result without need for calibration, and consequently not subject to the errors and drift of calibration which affect other methods. The use of mercury manometers is often required in clinical trials and for the clinical measurement of hypertension in high risk patients. According to this method, a cuff of appropriate size is fitted smoothly and snugly, and then inflated manually by repeatedly squeezing a rubber bulb until the artery is completely occluded. Listening with the stethoscope to the brachial artery at the elbow, the examiner slowly releases the pressure in the cuff. When blood just starts to flow in the artery, the turbulent flow creates a "whooshing" or pounding (first Korotkoff sound). The pressure at which this sound is first heard is the systolic BP. The cuff pressure is further released until no sound can be heard (fifth Korotkoff sound), at the diastolic arterial pressure. The auscultatory method has been predominant since the beginning of BP measurements but is in some cases is being replaced by other noninvasive techniques.

The Oscillometry method: Was first demonstrated in 1876 and involves the observation of oscillations in the sphygmomanometer cuff pressure which are caused by the oscillations of blood flow, i.e. the pulse. The electronic version of this method is sometimes used in long-term measurements and general practice. It uses a sphygmomanometer cuff like the auscultatory method, but with an electronic pressure sensor (transducer) to observe cuff pressure oscillations, electronics to automatically interpret them, and automatic inflation and deflation of the cuff. The pressure sensor should be calibrated periodically to maintain accuracy. The Oscillometric measurement requires less skill than the auscultatory technique, and may be suitable for use by untrained staff and for automated patient home monitoring.

According to this method, the cuff is inflated to a pressure initially in excess of the systolic arterial pressure, and then reduces to below diastolic pressure over a period of about 30 seconds. When the blood flow is nil (cuff pressure exceeding systolic pressure) or unimpeded (cuff pressure below diastolic pressure), cuff pressure will be essentially constant. It is essential that the cuff size is correct: undersized cuffs may yield too high a pressure, whereas oversized cuffs yield too low a pressure. When blood flow is present, but restricted, the cuff pressure, which is monitored by the pressure sensor, will vary periodically in synchrony with the cyclic expansion and contraction of the brachial artery, i.e., it will oscillate. The values of systolic and diastolic pressure are computed, not actually measured from the raw data, using an algorithm; the computed results are displayed.

A novel field for measuring blood pressure via a photoplethysmograph (PPG) is evolving in the last years. A photoplethysmograph (PPG) is an optically obtained plethysmograph. The photoplethysmograph is a tool that uses an emitter-receiver pair to determine blood flow. A light emitting diode is used to transmit light through the skin. The receiver picks up the transmitted signal, which is then analyzed with signal processing techniques. The pulse wave is produced by the changes in blood volume in the arteries and capillaries. Changes in blood volume produce changes in the optical absorption of the transmitted signal. The light transmitted through the tissue can be highly scattered or absorbed depending on the tissue. The detector, which is positioned on the surface of the skin, can detect the reflection or transmission of waves from various depths and from highly absorbing or weakly absorbing tissues. Regardless of the absorbency of the tissues and skin, it is assumed that the amount of light absorbed and/or reflected by these tissues will remain constant. With this assumption in mind, it can then be assumed that the only change in the absorption or reflection of the transmitted light will be from the increase or decrease of the blood volume in the arteries and capillaries. The measured volume change is actually an average of all of the arteries and capillaries in the space being measured. The signal that is received is dependent on the tissue type, skin type, position of the receiver and transmitter, blood volume content of the arteries and capillaries, and the properties of the sensor and receiver. The output is proportional to blood flow. In fact, the PPG can be regarded as a low cost technique for measuring changes in blood volume at the micro vascular (usually a finger or the lobe of the ear) applied in a non-invasive manner to the skin of a subject.

There are several patents regarding the use of PPG, derived by various means, for indirect estimation of blood pressure.

US patent 5,237,997 discloses a method for continuous measurement of mean arterial pressure (MAP) from the transit time of pulses in a PPG signal received from the ear lobe. The SBP and DBP are also derived from measuring the blood volume density in the ear lobe. This invention requires a calibration of the values of the blood pressure by conventional methods (e.g., Oscillometric, Korotkoff).

US patent 5,865,755 and US patent 5,857,975 describe a method for the determination of the SBP and the DBP from ECG and PPG signals. The blood pressure is calculated from the arrival times of pulses, the waveform volume and the heart rate for each pulse. These patents use the time difference between the R wave of the ECG and the beginning of the PPG pulse together for the determination of the blood pressure.

US Patent 2006/0074322 discloses a system for measuring blood pressure without a cuff based on the principle of photoplethysmograph (PPG). Although this patent discloses a system for measuring blood pressure without a cuff, it requires calibration for each user based on the principles oscillometric and Korotkoff.

Despite the large number of patents using the PPG signal as a basic principle of their operation, the systems of these patens require calibration by conventional methods for measurement of blood pressure (e.g., Oscillometric, Korotkoff, etc.). Therefore, the present invention discloses a system for continuous non-invasive monitoring of blood pressure, which does not require calibration by an additional system like a sphygmomanometer.

The "white coat hypertension" (WCH) is a phenomenon in which a patient exhibits elevated blood pressure in a clinical setting (e.g., the doctor's office) but not in other settings (e.g., at home). This is discussed, for example, in the article by Carel R A, et al., JAMA (1998), Vol. 271, No. 3.

WCH should not be confused with 'white coat effect' (WCE), which represents an increase in blood pressure during the clinic visit compared to with the mean daytime blood pressure and occurs in patients with sustained or normalized hypertension, treated or untreated. Therefore, the WCE is a measure of blood pressure change, whereas WCH is a measure of blood pressure level.

Blood pressure does not remain constant over time. Not only does BP fluctuate during the pumping cycle of the heart, but it is also influenced by a wide range of factors. These factors include activity level, temperature, pain, the presence of drugs, recent eating or drinking, recent smoking and stress. Although many of these transient factors are easily controlled, such as by restriction of food intake prior to measurement, the impact of stress and anxiety which stimulates the patient's body 'fight or flight' response is not so readily managed in the WCH.

The presence of WCH is of utmost concern since it can lead to diagnostic errors and prescription of unnecessary hypertensive medication. According to what was estimated by various academic researches, the proportion of hypertensive patients with WCH is between 15% and 30%. These people may have white coat hypertension that goes unrecognized which could mean being wrongly diagnosed as having high blood pressure and receiving unnecessary treatment. The WCH may be reduce with familiarity of the patient with the physician, environment, and/or technology. Foe example, it has been shown that the blood pressure readings of patients taken by a physician in a clinical environment on two different days two weeks apart tend to drop with time (James et al., The reproducibility of average ambulatory, home, and clinical pressures, Hypertension, Vol. 11, No. 6, Part 1, pp. 545-549, 1999).

White coat hypertension (WCH) has been recognized as a clinical entity approximately since 1987. Sometimes, the WCH is also referred to white coat effect (WCE). The phenomenon was decribed by Riva-Rocci (Riva-Rocci S. Un nuovo Sfigmomenometro. Gaz Med Torino 1896; 47: 981-996) more than 100 years ago and has further been studied and illustrated by Ayman and Goldshine (Ayman D, Goldshine AD. Blood pressure determinations by patients with essential hypertension. Am J Med Sci 1940; 200: 465-474.) in the 1940s and by Sokolow et al (Sokolow M, Werdegar D, Kain HK, Hinman AT. Relationship between level of blood pressure measured casually and by portable recorders and severity of complications in essential hypertension. Circulation 1966; 34: 279- 298.) in the 1960s. However, despite this long awareness the knowledge of the adverse effects of WCE is only sparse and particularly the prognosis of WCH remains unsettled. Only a few longitudinal studies have been performed in this field (e.g., Verdecchia P et al. Ambulatory blood pressure. An independent predictor of prognosis in essential hypertension. Hypertension 1994; 24: 793-801.) and so far the prospective data imply that WCH is a low-risk condition. In all the studies, white coat hypertensives (WCHs) developed fewer cardiovascular events than the established hypertensives (EHs), and in the two studies that included control individuals, these were found to have the same event rate as the WCH patients.

Until a few years ago, the only method of screening for hypertension was the measurement of blood pressure by a physician, using a sphygmomanometer, in the physician's office of a primary healthcare facility. One single pressure recording in the office gives, at best, a rough estimate of a person's usual blood pressure, and measurements are often influenced by the interaction between the patient and the physician. It is, therefore, paradoxical that arterial hypertension should be diagnosed on the basis of a few occasional blood pressure measurements, with the consequence that patients may be placed on antihypertensive treatment for the rest of their lives.

Ambulatory blood pressure monitoring (ABPM) was introduced more than 40 years ago, and is now fully accepted as a clinically useful method. These days, ambulatory blood pressure systems are to be found both in hospitals and in numerous general practices all over the world. They are used to diagnose hypertension based on numerous recordings, and their advantage is that ambulatory blood pressure readings have lower variability than those taken in the physician's office. If the ambulatory blood pressure reading is normal, compared with an elevated reading in a clinic, the patient has WCH. According to experts in the field of blood pressure, the real blood pressure of a patient can only be detected by ABPM or self-monitoring, when there are no specific predisposing factors. For people with WCH and no evidence of cardiovascular disease or comorbidities such as diabetes or renal disease, most experts agree that the best policy is to monitor their clinic blood pressure regularly, with self-monitoring at home, and repeat ABPM at one- to two-yearly intervals.

In the light of the presented above, it is therefore a long felt need to develop a noninvasive system for diagnosing the white coat hypertension (WCH) and the white coat effect (WCE) in a patient, which is based on a plethysmograph measurement and does not require calibration by additional system. It is also a long felt need to develop a non-invasive system for eliminating the white coat hypertension (WCH) and the white coat effect (WCE) in a patient, and thereby providing an accurate measurement of blood pressure which is not biased by said WCH and said WCE.

This system should be convenient and fast in operation, user friendly, and with precise measurement abilities.

SUMMARY OF THE INVENTION

It is one object of the present invention to provide a non-invasive system for measuring blood pressure of a patient with elimination of white coat hypertension (WCH) and white coat effect (WCE), said system comprising:

a. a blood pressure module comprising a plethysmograph for measuring changes in a tissue volume in a predetermined location of said patient, and generating an electrical signal associated with said changes in said tissue volume;

b. a computing means with a processor, said computing means is in communication with said blood pressure module;

c. a first storage in communication with said computing means containing programmed executable instructions configured to receive said electrical signal and to process the same by performing at least one operation selected from: (i) calculation of a set of measurement parameters from said electrical signal based on at least one auto-regressive moving average (ARMA) model; (ii) generation of a fixed length data vector comprising said set of measurement parameters and clinical parameters of said patient; (iii) storage in a communicable database said data vector and other data vectors; and, (iv) performing a classification based on a "Random Forest" algorithm by using said data vector and said database, such that the blood pressure of said patient is estimated; and,

d. a second storage in communication with said computing means containing programmed executable instructions adapted to diagnose said WCH and said WCE in said patient and to characterize the profile of said WCH and said WCE in said patient according to a diagnosis protocol;

It is within the scope of the present invention that the programmed executable instructions of said second storage further adapted to provide a "real" blood pressure measurement which is not biased by said WCH and WCE by eliminating said profile of said WCH and said WCE from said estimated blood pressure measurement of said patient.

It is another object of the present invention to provide the system as defined above, wherein said profile of said WCH and said WCE in said patient is characterized by a time-dependent amplitude of the difference between a blood pressure of said patient in office settings and a blood pressure of said patient in other settings.

It is another object of the present invention to provide a method for measuring blood pressure of a patient with elimination of white coat hypertension (WCH) and white coat effect (WCE), said method comprising steps of:

a. obtaining a non-invasive system for diagnosing a WCH and WCE and in a patient, said system comprising: (i) a blood pressure module comprising a plethysmograph; (ii) a computing means with a processor, said computing means is in communication with said blood pressure module; (iii) a first storage in communication with said computing means containing programmed executable instructions configured to receive said electrical signal and to process the same; and, (iv) a second storage in communication with said computing means containing programmed executable instructions adapted to diagnose said WCH and said WCE in said patient and to characterize the profile of said WCH and said WCE in said patient according to a diagnosis protocol;

b. measuring changes in a tissue volume in a predetermined location of said patient, and generating an electrical signal associated with said changes in said tissue volume via said blood pressure module;

c. calculating of a set of measurement parameters from said electrical signal based on at least one auto-regressive moving average (ARMA) model;

d. obtaining a set of clinical parameters of said patient;

e. generating a fixed length data vector comprising said set of measurement parameters and clinical parameters of said patient;

f. storing said data vector in a communicable database, said database further comprising other data vectors;

g. performing a classification based on a "Random Forest" algorithm by using said data vector and said database, and thereby estimating said blood pressure of said patient; h. diagnosing said WCH and said WCE in said patient according to a diagnostic protocol by said second storage;

i. eliminating said profile of said WCH and said WCE from said estimated blood pressure measurement of said patient; and,

j. providing a "real" blood pressure measurement which is not biased by said WCH and WCE; and,

It is another object of the present invention to provide the method as defined above, which further comprises step of characterizing said profile by calculating the time-dependent amplitude of the difference between a blood pressure of said patient in office settings and a blood pressure of said patient in other settings.

It is another object of the present invention to provide a non-invasive system for diagnosing white coat hypertension (WCH) and white coat effect (WCE) in a patient, said system comprising:

c. a first storage in communication with said computing means containing programmed executable instructions configured to receive said electrical signal and to process the same by performing at least one operation selected from: (i) calculation of a set of measurement parameters from said electrical signal based on at least one auto-regressive moving average (ARMA) model; (ii) generation of a fixed length data vector comprising said set of measurement parameters and clinical parameters of said patient; (iii) storage in a communicable database said data vector and other data vectors; and, (iv) performing a classification based on a "Random Forest" algorithm by using said data vector and said database, such that the blood pressure of said patient is estimated;

It is within the scope of the present invention that the system further comprises a second storage in communication with said computing means containing programmed executable instructions adapted to diagnose said WCH and said WCE in said patient according to a diagnosis protocol, and to differentiate patients with sustained or normalized hypertension and patients with WCH and WCE.

It is another object of the present invention to provide the system as defined above, wherein said blood pressure module is selected from a group consisting of: a photoplethysmograph (PPG), a pulse oximeter, an acoustic plethysmograph, a mechanical plethysmograph, or any combination thereof.

It is another object of the present invention to provide the system as defined above, wherein said system does not require calibration via an additional blood measurement technique.

It is another object of the present invention to provide the system as defined above, wherein said at least one auto-regressive moving average (ARMA) model is a Teager-Kaiser operator.

It is another object of the present invention to provide the system as defined above, wherein said clinical parameters of said patient are selected from a group consisting of: sex, age, weight, height, food consumption, time of day, BMI, weight divided by age, weight divided by Heart Rate (HR), height divided by HR, HR divided by age, height divided by age, age divided by the BMI, HR divided by body mass index, or any combination thereof.

It is another object of the present invention to provide the system as defined above, wherein said first storage is further adapted for performing error reduction of said blood pressure estimated via said "Random Forests" algorithm.

It is another object of the present invention to provide the system as defined above, wherein said computing means is selected from a group consisting of: a DSP system, FPGA, microcontroller, or any combination thereof.

It is another object of the present invention to provide the system as defined above, wherein said second storage is further adapted to detect when the WCH and the WCE are reduced.

It is another object of the present invention to provide the system as defined above, wherein said blood pressure of said patient is selected from a group consisting of: a systolic blood pressure (SBP), a diastolic blood pressure (DBP), a mean arterial pressure (MAP), or any combination thereof.

It is another object of the present invention to provide the system as defined above, wherein said programmed executable instructions of said second storage adapted to differentiate between a patient with WCH and WCE, and a patient with sustained or normalized hypertension with a precision of at least about 90%.

It is another object of the present invention to provide the system as defined above, wherein said diagnosis protocol is adapted to locate a decrease in said blood pressure of said patient in other settings, after a predetermined series of readings and over a predetermined period of time, and to compare said decrease to a predetermined value of blood pressure measured in office settings, said predetermined value is associated with WCE.

It is another object of the present invention to provide the system as defined above, wherein said predetermined value is selected from a group consisting of: systolic blood pressure (SBP) is about 20 mmHg, diastolic blood pressure (DBP) is about 10 mmHg, or any combination thereof.

It is another object of the present invention to provide the system as defined above, wherein said diagnosis protocol is adapted to determine that the measured blood pressure after a predetermined series of readings and over a predetermined period of time is substantially above an elevated blood pressure level in office settings and is substantially below a normal blood pressure level in other settings, such that said patient is diagnosed with WCH.

It is another object of the present invention to provide the system as defined above, wherein said elevated blood pressure level is selected from a group consisting of: systolic blood pressure (SBP) is about 140 mmHg, diastolic blood pressure (DBP) is about 90 mmHg, or any combination thereof; said normal blood pressure level is selected from a group consisting of: systolic blood pressure (SBP) is about 135 mmHg, diastolic blood pressure (DBP) is about 85 mmHg, or any combination thereof,

It is another object of the present invention to provide the system as defined above, wherein the mode of operation of said system is selected from: ambulatory, continuous, discrete, or any combination thereof.

It is another object of the present invention to provide the system as defined above, wherein said system is adapted to be operated: in the doctor's office, at home, at work, a hospital, or any combination thereof.

It is another object of the present invention to provide the system as defined above, wherein said second storage further adapted to perform a statistical analysis to detect said WCH and said WCE in said patient.

It is another object of the present invention to provide the system as defined above, wherein said first storage and said second storage are integrated.

It is another object of the present invention to provide the system as defined above, wherein said second storage is further adapted to register the settings in which said system is operated, said settings selected from a group consisting of: the location measurement, the kind of person who performs the measurement, such that the settings are classified to two classes: office settings and other settings; further wherein said system is adapted to diagnose said WCH and said WCE in said patient according to said diagnosis protocol and said settings.

It is another object of the present invention to provide a non-invasive method for diagnosing white coat hypertension (WCH) and white coat effect (WCE) in a patient, said method comprising step of:

a. obtaining a non-invasive system for diagnosing a WCH and WCE and in a patient, said system comprising: (i) a blood pressure module comprising a plethysmograph; (ii) a computing means with a processor, said computing means is in communication with said blood pressure module; (iii) a first storage in communication with said computing means containing programmed executable instructions configured to receive said electrical signal and to process the same; and, (iv) a second storage in communication with said computing means containing programmed executable instructions adapted to detect said WCH in said patient according to a diagnosis protocol;

b. measuring changes in a tissue volume in a predetermined location of said patient, and generating an electrical signal associated with said changes in said tissue volume via said blood pressure module; c. calculating of a set of measurement parameters from said electrical signal based on at least one auto-regressive moving average (ARMA) model;

d. obtaining a set of clinical parameters of said patient;

e. generation of a fixed length data vector comprising said set of measurement parameters and clinical parameters of said patient;

g. performing a classification based on a "Random Forest" algorithm by using said data vector and said database, and thereby determining said blood pressure of said patient is estimated;

h. diagnosing said WCH and said WCE in said patient according to a diagnostic protocol by said second storage; and,

i. differentiating patients with sustained or normalized hypertension and patients with WCH and WCE;

It is another object of the present invention to provide the method as defined above, further comprising step of selecting said blood pressure module from a group consisting of: a photoplethysmograph (PPG), a pulse oximeter, an acoustic plethysmograph, a mechanical plethysmograph, or any combination thereof.

It is another object of the present invention to provide the method as defined above, wherein said method does not require an additional step of calibrating said system via an additional blood measurement technique.

It is another object of the present invention to provide the method as defined above, wherein said at least one auto-regressive moving average (ARMA) model is a Teager-Kaiser operator.

It is another object of the present invention to provide the method as defined above, further comprising step of selecting said clinical parameters of said patient from a group consisting of: sex, age, weight, height, food consumption, time of day, BMI, weight divided by age, weight divided by Heart Rate (HR), height divided by HR, HR divided by age, height divided by age, age divided by the BMI, HR divided by body mass index, or any combination thereof.

It is another object of the present invention to provide the method as defined above, wherein said method further comprising a step of performing error reduction of said blood pressure estimated via said "Random Forests" algorithm by said first storage.

It is another object of the present invention to provide the method as defined above, further comprising step of selecting said computing means from a group consisting of: a DSP system, FPGA, microcontroller, or any combination thereof. It is another object of the present invention to provide the method as defined above, further comprising a step of detecting when the WCH and the WCE is reduced by said second storage.

It is another object of the present invention to provide the method as defined above, further comprising step of selecting said blood pressure of said patient from a group consisting of: a systolic blood pressure (SBP), a diastolic blood pressure (DBP), a mean arterial pressure (MAP), or any combination thereof.

It is another object of the present invention to provide the method as defined above, wherein said step of differentiating patients with sustained or normalized hypertension and patients with WCH and WCE is performed with a precision of at least about 90%.

It is another object of the present invention to provide the method as defined above, further comprising a step of locating a decrease in said blood pressure of said patient after a predetermined series of readings and over a predetermined period of time according to said diagnostic protocol, and comparing said decrease to a predetermined value, said predetermined value is associated with WCE.

It is another object of the present invention to provide the method as defined above, further comprising a step of selecting said predetermined value from a group consisting of: systolic blood pressure (SBP) is about 20 mmHg, diastolic blood pressure (DBP) is about 10 mmHg, or any combination thereof.

It is another object of the present invention to provide the method as defined above, further comprising step of determining that the measured blood pressure after a predetermined series of readings and over a predetermined period of time is above a predetermined level of blood pressure according to said diagnostic protocol, and thereby diagnosing said patient with WCH.

It is another object of the present invention to provide the method as defined above, further comprising step of selecting said predetermined level from a group consisting of: systolic blood pressure (SBP) is about 140 mmHg, diastolic blood pressure (DBP) is about 90 mmHg, or any combination thereof.

It is another object of the present invention to provide the method as defined above, further comprising step of selecting the mode of operation of said system is selected from: ambulatory, continuous, discrete, or any combination thereof.

It is another object of the present invention to provide the method as defined above, further comprising step of selecting the location of operation of said system from: the doctor's office, at home, at work, a hospital, or any combination thereof. It is another object of the present invention to provide the method as defined above, further comprising step of performing statistical analysis to detect said WCH in said patient by said second storage.

It is another object of the present invention to provide the method as defined above, further comprising step of registering the settings in which said system is operated, said settings selected from a group consisting of: the location measurement, the kind of person who performs the measurement, and thereby classifying said settings to two classes: office settings and other settings, and diagnosing said WCH and said WCE in said patient according to said diagnosis protocol and said settings.

It is another object of the present invention to provide a non-invasive system for measuring blood pressure of a patient with elimination of white coat hypertension (WCH) and white coat effect (WCE), said system comprising:

a. a PPG based blood pressure system for estimation of the patient's blood pressure; and,

b. a second storage in communication with the computing means containing programmed executable instructions adapted to: (i) diagnose the WCH and said WCE in said patient; (ii) characterize the profile of the WCH and the WCE in said patient according to a diagnosis protocol; and, (iii) to provide a "real" blood pressure measurement which is not biased by the WCH and WCE by eliminating the profile of the WCH and the WCE from the estimated blood pressure measurement of the patient;

It is within the scope of the invention that said estimation of said patient's blood pressure is performed via a "Random Forest" algorithm which is adapted to receive a fixed length data vector comprising a set of measurement parameters and clinical parameters, said measurement parameters are based on at least one auto-regressive moving average (ARMA) model of the signals received from said PPG, the clinical parameters are received from the patient.

obtaining a PPG based blood pressure system for estimation of the patient's blood pressure;

estimating the blood pressure of the patient via said system;

diagnosing the WCH and the WCE in said patient according to a diagnostic protocol by a second storage located within the system; and, eliminating the profile of the WCH and the WCE from the estimated blood pressure measurement of the patient, thereby providing a "real" blood pressure measurement which is not biased by the WCH and the WCE.

It is within the scope of the invention that the step of estimation of the blood pressure of the patient is performed via a "Random Forest" algorithm which is adapted to receive a fixed length data vector comprising a set of measurement parameters and clinical parameters, the measurement parameters are based on at least one auto-regressive moving average (ARMA) model of the signals received from said PPG, the clinical parameters are received from the patient.

a. a PPG based blood pressure system for estimation of said patient's blood pressure; and

b. a storage in communication with said blood pressure system containing programmed executable instructions adapted to diagnose said WCH and said WCE in said patient according to a diagnosis protocol;

It is within the scope of the present invention that the estimation of said patient's blood pressure is performed via a "Random Forest" algorithm which is adapted to receive a fixed length data vector comprising a set of measurement parameters and clinical parameters, said measurement parameters are based on at least one auto-regressive moving average (ARMA) model of the signals received from said PPG, said clinical parameters are received from said patient.

a. a PPG based blood pressure system for estimation of said patient's blood pressure, said estimation of said patient's blood pressure being performed via a "Random Forest" algorithm adapted to receive a fixed length data vector comprising a set of measurement parameters and clinical parameters, said measurement parameters are based on at least one auto- regressive moving average (ARMA) model of the signals received from said PPG, said clinical parameters are received from said patient; and

It is within the scope of the present invention that the non-invasive system for diagnosing white coat hypertension (WCH) and white coat effect (WCE) in a patient system does not require calibration via an additional blood measurement technique.

c. a first storage in communication with said computing means containing programmed executable instructions configured to receive said electrical signal and to process the same by performing at least one operation selected from: (i) calculation of a set of measurement parameters from said electrical signal based on at least one auto-regressive moving average (ARMA) model; (ii) generation of a fixed length data vector comprising said set of measurement parameters and clinical parameters of said patient; (iii) storage in a communicable database said data vector and other data vectors; and, (iv) performing a classification based on a SVM algorithm by using said data vector and said database, such that the blood pressure of said patient is estimated; and,

d. a second storage in communication with said computing means containing programmed executable instructions adapted to diagnose said WCH and said

WCE in said patient and to characterize the profile of said WCH and said WCE in said patient according to a diagnosis protocol;

It is within the scope of the present invention that the programmed executable instructions of said second storage are further adapted to provide a "real" blood pressure measurement which is not biased by said WCH and WCE by eliminating said profile of said WCH and said WCE from said estimated blood pressure measurement of said patient.

It is another object of the present invention to provide the system as defined above, wherein said first storage is further adapted for performing error reduction of said blood pressure estimated via said SVM algorithm.

It is another object of the present invention to provide the system as defined above, wherein said blood pressure of said patient is selected from a group consisting of: a systolic blood pressure (SBP), a diastolic blood pressure (DBP), a mean arterial pressure (MAP), or any combination thereof. It is another object of the present invention to provide the system as defined above, wherein said programmed executable instructions of said second storage adapted to differentiate between a patient with WCH and WCE, and a patient with sustained or normalized hypertension with a precision of at least about 90%.

It is another object of the present invention to provide the system as defined above, wherein said elevated blood pressure level is selected from a group consisting of: systolic blood pressure (SBP) is about 140 mmHg, diastolic blood pressure (DBP) is about 90 mmHg, or any combination thereof; said normal blood pressure level is selected from a group consisting of: systolic blood pressure (SBP) is about 135 mmHg, diastolic blood pressure (DBP) is about 85 mmHg, or any combination thereof.

It is another object of the present invention to provide the system as defined above, wherein said system is adapted to be operated in a location selected from a group consisting of: in the doctor's office, at home, at work, a hospital, or any combination thereof.

c. calculating a set of measurement parameters from said electrical signal, wherein said set of measurement parameters is based on at least one auto-regressive moving average (ARMA) model;

d. obtaining a set of clinical parameters of said patient;

g. performing a classification, wherein said classification is based on a

SVM algorithm by using said data vector and said database, and thereby estimating said blood pressure of said patient;

i. eliminating said profile of said WCH and said WCE from said estimated blood pressure measurement of said patient, thereby providing a "real" blood pressure measurement which is not biased by said WCH and WCE.

It is another object of the present invention to provide the method as defined above, further comprising step of characterizing said profile by calculating the time-dependent amplitude of the difference between a blood pressure of said patient in office settings and a blood pressure of said patient in other settings.

It is another object of the present invention to provide the method as defined above, wherein said method further comprising a step of performing error reduction of said blood pressure estimated via said SVM algorithm by said first storage.

It is another object of the present invention to provide the method as defined above, further comprising step of selecting said computing means from a group consisting of: a DSP system, FPGA, microcontroller, or any combination thereof.

It is another object of the present invention to provide the method as defined above, further comprising a step of detecting when the WCH and the WCE is reduced by said second storage.

It is another object of the present invention to provide the method as defined above, further comprising a step of locating a decrease in said blood pressure of said patient after a predetermined series of readings and over a predetermined period of time according to said diagnostic protocol, and comparing said decrease to a predetermined value, said predetermined value is associated with WCE. It is another object of the present invention to provide the method as defined above, further comprising a step of selecting said predetermined value from a group consisting of: systolic blood pressure (SBP) is about 20 mmHg, diastolic blood pressure (DBP) is about 10 mmHg, or any combination thereof.

It is another object of the present invention to provide the method as defined above, wherein said profile of said WCH and said WCE in said patient is characterized by a time-dependent amplitude of the difference between a blood pressure of said patient in office settings and a blood pressure of said patient in other settings.

It is another object of the present invention to provide a non-invasive method for diagnosing white coat hypertension (WCH) and white coat effect (WCE) in a patient, said system comprising:

b. a computing means with a processor, said computing means is in communication with said blood pressure module; and,

c. a first storage in communication with said computing means containing programmed executable instructions configured to receive said electrical signal and to process the same by performing at least one operation selected from: (i) calculation of a set of measurement parameters from said electrical signal based on at least one auto-regressive moving average (ARMA) model; (ii) generation of a fixed length data vector comprising said set of measurement parameters and clinical parameters of said patient; (iii) storage in a communicable database said data vector and other data vectors; and, (iv) performing a classification based on a SVM algorithm by using said data vector and said database, such that the blood pressure of said patient is estimated;

It is another object of the present invention to provide the system as defined above, wherein said programmed executable instructions of said second storage adapted to differentiate between a patient with WCH and WCE, and a patient with sustained or normalized hypertension with a precision of at least about 90%. It is another object of the present invention to provide the system as defined above, wherein said diagnosis protocol is adapted to locate a decrease in said blood pressure of said patient in other settings, after a predetermined series of readings and over a predetermined period of time, and to compare said decrease to a predetermined value of blood pressure measured in office settings, said predetermined value is associated with WCE.

It is another object of the present invention to provide a non-invasive method for diagnosing white coat hypertension (WCH) and white coat effect (WCE) in a patient, said method comprising steps of:

a. obtaining a non-invasive system for diagnosing a WCH and WCE and in a patient, said system comprising: (i) a blood pressure module comprising a plethysmograph; (ii) a computing means with a processor, said computing means is in communication with said blood pressure module; (iii) a first storage in communication with said computing means containing programmed executable instructions configured to receive said electrical signal and to process the same; and, (iv) a second storage in communication with said computing means containing programmed executable instructions adapted to detect said WCH in said patient according to a diagnosis protocol; b. measuring changes in a tissue volume in a predetermined location of said patient, and generating an electrical signal associated with said changes in said tissue volume via said blood pressure module;

c. calculating of a set of measurement parameters from said electrical signal based on at least one auto-regressive moving average (ARMA) model; d. obtaining a set of clinical parameters of said patient;

e. generating a fixed length data vector comprising said set of measurement parameters and clinical parameters of said patient; f. storing said data vector in a communicable database, said database further comprising other data vectors;

g. performing a classification based on a SVM algorithm by using said data vector and said database, and thereby estimating said blood pressure of said patient;

i. differentiating patients with sustained or normalized hypertension and patients with WCH and WCE.

It is another object of the present invention to provide the method as defined above, further comprising step of selecting said predetermined level from a group consisting of: systolic blood pressure (SBP) is about 140 mmHg, diastolic blood pressure (DBP) is about 90 mmHg, or any combination thereof. It is another object of the present invention to provide the method as defined above, further comprising step of selecting the mode of operation of said system is selected from: ambulatory, continuous, discrete, or any combination thereof.

It is another object of the present invention to provide the method as defined above, further comprising step of selecting the location of operation of said system from: the doctor's office, at home, at work, a hospital, or any combination thereof.

It is another object of the present invention to provide the method as defined above, further comprising step of performing statistical analysis to detect said WCH in said patient by said second storage.

a. a PPG based blood pressure system for estimation of said patient's blood pressure; and,

b. a second storage in communication with said computing means containing programmed executable instructions adapted to: (i) diagnose said WCH and said WCE in said patient; (ii) characterize the profile of said WCH and said WCE in said patient according to a diagnosis protocol; and, (iii) to provide a "real" blood pressure measurement which is not biased by said WCH and WCE by eliminating said profile of said WCH and said WCE from said estimated blood pressure measurement of said patient;

It is within the scope of the present invention that the estimation of said patient's blood pressure is performed via a SVM algorithm which is adapted to receive a fixed length data vector comprising a set of measurement parameters and clinical parameters, said measurement parameters are based on at least one auto- regressive moving average (ARMA) model of the signals received from said PPG, said clinical parameters are received from said patient.

a. obtaining a PPG based blood pressure system for estimation of said patient's blood pressure;

b. estimating the blood pressure of said patient via said system;

c. diagnosing said WCH and said WCE in said patient according to a diagnostic protocol by a second storage located within said system; and, d. eliminating said profile of said WCH and said WCE from said estimated blood pressure measurement of said patient, thereby providing a "real" blood pressure measurement which is not biased by said WCH and WCE.

It is within the scope of the present invention that the step of estimation of the blood pressure of said patient is performed via a SVM algorithm which is adapted to receive a fixed length data vector comprising a set of measurement parameters and clinical parameters, said measurement parameters are based on at least one auto-regressive moving average (ARMA) model of the signals received from said PPG, said clinical parameters are received from said patient.

a. a PPG based blood pressure system for estimation of said patient's blood pressure, said estimation of said patient's blood pressure being performed via a SVM algorithm adapted to receive a fixed length data vector comprising a set of measurement parameters and clinical parameters, said measurement parameters are based on at least one auto-regressive moving average (ARMA) model of the signals received from said PPG, said clinical parameters are received from said patient; and

BRIEF DESCRIPTION OF THE FIGURES

For a better understanding of the invention and to show how the same may be carried into effect, reference will now be made, purely by way of example, to the accompanying drawings in which like numerals designate corresponding elements or sections throughout.

With specific reference now to the drawings in detail, it is stressed that the particulars shown are by way of example and for purposes of illustrative discussion of the preferred embodiments of the present invention only, and are presented in the cause of providing what is believed to be the most useful and readily understood description of the principles and conceptual aspects of the invention. In this regard, no attempt is made to show structural details of the invention in more detail than is necessary for a fundamental understanding of the invention, the description taken with the drawings making apparent to those skilled in the art how the several forms of the invention may be embodied in practice. In the accompanying drawings:

FIG. 1 is a schematic illustration of a profile of a patient's blood pressure obtained by invasive catheterization.

FIG. 2 is a block diagram of the system and the method of the present invention for estimation of blood pressure.

FIG. 3 is a schematic illustration of a profile of a PPG signal as measured the signal of the present invention.

FIG. 4 is a schematic illustration is a block diagram of the pre-processing step of the method of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

Before explaining at least one embodiment of the invention in detail, it is to be understood that the invention is not limited in its application to the details of construction and the arrangement of the components set forth in the following description or illustrated in the drawings. The invention is applicable to other embodiments or of being practiced or carried out in various ways. Also, it is to be understood that the phraseology and terminology employed herein is for the purpose of description and should not be regarded as limiting.

The term "WCH" refers hereinafter to a 'white coat hypertension'. It is a phenomenon in which a patient exhibits elevated blood pressure in a clinical setting (e.g., the doctor's office) but not in other settings (e.g., at home).

The term 'WCE' refers hereinafter to a 'white coat effect'. It is a phenomenon in which patient's systolic blood pressure is at least about 20 mmHg and/or diastolic blood pressure is at least about 10 mmHg lower at home than in the doctor's office. The term plethysmograph' is an instrument for measuring changes in volume within an organ or whole body.

The term "PPG" refers hereinafter to a photoplethysmograph which produces signals that are associated with changes in blood volume in the arteries and capillaries.

The term "ABPM" refers hereinafter to ambulatory blood pressure monitoring.

The term "SBP" refers hereinafter to the systolic blood pressure of a patient.

The term "DBP" refers hereinafter to the diastolic blood pressure of a patient.

The term "MBP" refers hereinafter to the mean blood pressure of a patient.

The term "PP" refers hereinafter to pulse pressure which is the difference between systolic and diastolic blood pressure.

The term "ARMA" refers hereinafter to auto regressive moving average.

The term "AR" refers hereinafter to auto regressive.

The term "MA" refers hereinafter to moving average.

The term "WCH and WCE" refers hereinafter to: a diagnosed WCH and WCE at same time and in the same patient, a diagnosed WCH without diagnosed WCE at same time and in the same patient, and a diagnosed WCE without diagnosed WCH at same time and in the same patient.

The term "office settings' refers hereinafter to settings which can influence on the measured blood pressure level, such as: the doctor's office, the hospital, etc. Moreover, the term "office settings' refers hereinafter to settings in which a measurement is performed by a doctor or a physician without the dependency of the measurement location.

The term "other settings' refers hereinafter to settings which different than the office setting, and in which the measure blood pressure should not be influenced. Moreover, the term "other settings' refers hereinafter to settings in which a measurement is not performed by a doctor or a physician, but by somebody else (e.g., the person himself, a nurse, a relative, etc.) without the dependency of the measurement location. The term "SVM" refers hereinafter to Support Vector Machine algorithm.

The term 'about' refers hereinafter to a measure with precision of ±20%.

The core of the invention is to provide a system and method for blood pressure measurements without the need for calibration. Such a system is able to diagnose white coat hypertension (WCH) and white coat effect (WCE) in said patient and to differentiate patients with sustained or normalized hypertension and patients with WCH and WCE. Moreover, the system of the present invention is adapted to "real" blood pressure measurement which is not biased by said WCH and WCE (in case of patient with diagnosed WCE and/or WCH).

According to one embodiment of the invention, the system of the present invention disclosed hereinafter is a non-invasive system for measuring blood pressure of a patient with elimination of white coat hypertension (WCH) and white coat effect (WCE). The system comprises:

a. A blood pressure module comprising a plethysmograph for measuring changes in a tissue volume in a predetermined location of said patient, and generating an electrical signal associated with said changes in said tissue volume.

b. A computing means with a processor. The computing means is in communication with the blood pressure module.

c. A first storage in communication with the computing means containing programmed executable instructions configured to receive the electrical signal and to process the same by performing at least one operation selected from: (i) calculation of a set of measurement parameters from said electrical signal based on at least one auto-regressive moving average (ARMA) model; (ii) generation of a fixed length data vector comprising the set of measurement parameters and clinical parameters of the patient; (iii) storage in a communicable database the data vector and other data vectors; and, (iv) performing a classification based on a "Random Forest" algorithm by using the data vector and the database, such that the blood pressure of the patient is estimated.

d. A second storage in communication with the computing means containing programmed executable instructions adapted to diagnose the WCH and the WCE in the patient and to characterize the profile of the WCH and the WCE in the patient according to a diagnosis protocol.

The system further comprises programmed executable instructions of said second storage which are adapted to provide a "real" blood pressure measurement which is not biased by the WCH and WCE by eliminating the profile of the WCH and the WCE from the estimated blood pressure measurement of the patient.

According to another embodiment of the present invention, the system of the present invention disclosed hereinafter is a non-invasive system for diagnosing white coat hypertension (WCH) and white coat effect (WCE) in a patient. The system comprises:

a. A blood pressure module which comprises a plethysmograph for measuring changes in a tissue volume in a predetermined location of the patient, and generating an electrical signal associated with the changes in the tissue volume.

c. A first storage in communication with the computing means containing programmed executable instructions configured to receive the electrical signal and to process the same by performing at least one operation selected from: (i) calculation of a set of measurement parameters from the electrical signal based on at least one auto-regressive moving average (ARMA) model; (ii) generation of a fixed length data vector comprising the set of measurement parameters and clinical parameters of the patient; (iii) storage in a communicable database the data vector and other data vectors; and, (iv) performing a classification based on a "Random Forest" algorithm by using the data vector and the database, such that the blood pressure of the patient is estimated.

The system further comprises a second storage in communication with said computing means containing programmed executable instructions adapted to diagnose the WCH and the WCE in the patient according to a diagnosis protocol, and to differentiate patients with sustained or normalized hypertension and patients with WCH and WCE.

As disclosed in the background of the invention, the terms 'white coat hypertension' (WCH) and a 'white coat effect' (WCE) in some circumstances pertain to the same meaning, and in some circumstances to a different meaning.

The present invention discloses a non-invasive system for diagnosing a white coat hypertension (WCH) and a white coat effect (WCE) in a patient. The diagnosis of WCH and WCE are performed by the system of the present invention, following a measurement of the patient's blood pressure in a non-invasive manner. This diagnosis is performed by an analysis of the levels of said blood pressure.

The system of the present invention comprises the following components:

a. A blood pressure module. This module is a sensor module which comprises a plethysmograph for measuring changes in a tissue volume in a predetermined location of said patient (e.g., finger, the lobe of the ear, etc.), and generating an electrical signal associated with the changes in the tissue volume. According to some embodiments, the blood pressure module is selected from a group consisting of: a photoplethysmograph (PPG), a pulse oximeter, an acoustic plethysmograph, a mechanical plethysmograph, or any combination thereof. According to the preferred embodiment of the invention, the plethysmograph is a PPG.

b. A computing means with a processor. The computing means is in communication with the blood pressure module by means of wires or by wireless means which are well known in the art.

c. A first storage in communication with the computing means containing programmed executable instructions (algorithm) configured to receive the electrical signal and to process the same.

d. A second storage in communication with the computing means containing programmed executable instructions (algorithm) adapted to detect the WCH and WCE in said patient according to a diagnosis protocol, and to differentiate patients with sustained or normalized hypertension and patients with WCH and WCE. As part of the processing of the electrical signal by the algorithm of the first storage, the following operations are performed:

(i) Calculation of a set of measurement parameters from said electrical signal based on at least one auto-regressive moving average (ARMA) model.

(ii) Generation of a fixed length data vector comprising said set of measurement parameters and clinical parameters of said patient.

(iii) Storage in a communicable database said data vector and other data vectors.

(iv) Classification based on a "Random Forest" algorithm by using said data vector and said database, such that the blood pressure of said patient is estimated.

A main advantage of the present invention over the prior art, is not only that it is based on a non-invasive precise measurement of blood pressure, but also on the fact that the system does not require calibration with additional techniques and devices. These advantages combined with main object of the present invention to diagnose WCH and WCE, and to differentiate patients with sustained or normalized hypertension and patients with WCH and WCE turn the present invention to novel and non-obvious.

The mathematical and physical theory behind the algorithm which is stored in the first storage for the determination of the patient's blood pressure is discussed in the present document below.

Blood pressure determination by the system of the present invention (the algorithm of the first storage):

As mentioned above, according to the preferred embodiment of the present invention the PPG which is located within the blood pressure module is adapted to create a PPG signal which is associated with changes in blood volume in the arteries and capillaries. According to the preferred embodiment of the invention the blood pressure module is adapted to be located on the patients' finger.

The system of the present invention is based on the assumption that there is a relationship between the PPG signal and the blood pressure of a patient. According to the present invention, this relationship is derived from a data extracted from the PPG signal and the statistical data of the patient himself.

The system of the present invention estimates the blood pressure of a patient according to an estimated decision function. Since the PPG signal is characterized by a variable length, one of the objects of the present invention is to produce a fixed length data vector for each measurement. This data vector contains parameters which are derived from the PPG signal and additional parameter which are associated with the clinical information of the patient. The parameters which are derived from the PPG signal might be for example: the shape of the signal (e.g., auto-regression coefficients, moving average, etc.), distance between pulses, the variance of the signal, the energy of the signal, the changes in the energy of the signal, etc. The clinical information of the patient might be for example: sex, age, weight, height, health information, etc.

According to some embodiments, the estimated decision function of the present invention according to which the blood pressure is estimated, is the well known "Random Forests" algorithm. That is opposed to other machine learning and pattern recognition techniques such as: regression and decision trees (CART), 'Splines', and Neural Networks.

The 'Random forests' algorithm is a classifier based on the generation of a parallel set of decision trees which estimate the function of a random selection of variables. This algorithm operates in the following way: the 'Random Forests' algorithm grows many classification trees; to classify a new object from an input vector, an input vector is put down in each of the trees in the forest; each tree gives a classification, and we say the tree "votes" for that class; and, the forest chooses the classification having the most votes (over all the trees in the forest).

The implementation of the system of the present invention for measurement of blood pressure, consists of two distinct phases. The first phase is the training phase of the system, which is performed only once and therefore does not require calibration later. This phase consists of obtaining a database with information on various parameters of different patients which includes their personal parameters such as: sex, weight, age, etc., along with the records of their PPG signals. This information is used for the estimation of the parameters of the decision trees which are stored in said database of the system.

The second phase consists of loading the information of all the trees obtained in the training phase, and recording the PPG signal of the patient at the time of the measurement along with other clinical parameters such as: sex, weight, age, etc. In this phase, the system processes the PPG signal of the patients, and generates a fixed length data vector. Additionally to the processed data received from said PPG signal, the data vector also comprises said other variables of said patient.

Reference in now made to FIG. 2, where schematically illustrated one embodiment of the steps according to which the system of the present invention calculates the blood pressure of a patient. According the first step 10, the PPG sensor captures the PPG signal from the measurement location in a patient (e.g., a finger, ear lobe, etc.). Said PPG signal is associated with the oxygen saturation (Sp02) signal which is received via a pulse oximeter. In other words, said PPG sensor might be also used as a pulse oximeter. In the following pre-processing step 12, the PPG signal is processed and measurement parameters are extracted from the signal, and the measurement parameters are combined with other clinical parameters 11 of said patient. In pre-processing step 12, the extraction of measurement parameters from the PPG signal is based on a stochastic model of the physiology of the circulatory system as presented in the background of the invention. In the following step of estimation 14, a fixed length vector which comprises the measurement parameters and the clinical parameters of the patient is inputted to the estimation function which is based on the "Random Forests" algorithm. In this step, basic blood pressure parameters (SBP, DBP, and MAP) and other various functions which are related to error estimation are estimated. In the postprocessing step 16, the final values of the blood pressure (SBP, DBP, and MAP) are calculated following a correction of the basic blood pressure parameters (SBP, DBP, and MAP) via said various functions which are related to error estimation. These various function are adapted to reduce the systematic error (bias) of the system.

According to some embodiments, the signal in step 10 is obtained by a PPG sensor unit which is a simple, noninvasive and low cost sensor for the detection of volume changes in a tissue.

The PPG sensor comprises two main light elements: (/) at least one source for illumination of the tissue (e.g., the skin); (//) at least one photo detector which is able to measure small variations in light intensity associated with changes in tissue perfusion at level of detection. The PPG sensor is adapted for (/) emitting a light beam to an organ of the patient; (//) detecting the reflected light beam; and, (/^' ) converting the detected light beam into an electrical signal.

The PPG is normally used in non-invasive measurements and operates in the wavelength of infrared or near-infrared (NIR). A typical waveform of a PPG sensor is illustrated in FIG. 3.

The PPG signal comprises a physiological pulsatile waveform (AC component) attributed to changes in blood volume synchronous with each heartbeat. This component is superimposed on another component of basal low frequency (DC component) related to the respiratory rate, the activity of the central nervous system and thermoregulation. According to the signal in FIG. 3, the fundamental frequency of the AC component is around 1 Hz (depending on the cardiac rhythm).

The interaction between light and biological tissues is complex and includes processes such as optical scattering, absorption, reflection, transmission and fluorescence.

According to one embodiment of the present invention, the light of the PPG sensor is in the NIR (e.g., close to 805 nm).

As illustrated in FIG. 3, the PPG signal has two distinct phases: the anacrotic phase, which represents the increase in the pulse, and the catacrotic phase, representing the fall of the pulse. The first phase is related to the systolic phase of the blood pressure and the second phase is related to diastolic phase of the blood pressure.

The PPG signal of the present invention uses the oxygen saturation (Sp0₂) which can be obtained by the illumination of a tissue in the red and NIR wavelengths. Typically, the systems which calculate the oxygen saturation, are switching between two wavelengths for the determination of the oxygen saturation. The oxygen saturation can be obtained by the illumination of the tissue in the red and the NIR wavelengths. The amplitudes of the two wavelengths are sensitive to changes in Sp0₂ due to the difference in absorption of light in Hb0₂ and Hb for each one of the wavelengths. The Sp0₂ can be obtained from the ratio between the amplitudes, and the AC and DC components of the PPG signal.

The following is a derivation of equations according to which the Sp0₂ can be calculated from the PPG signal.

In pulse oximetery, the light intensity (T) transmitted through tissue is commonly referred to as a DC signal and is a function of the optical properties of tissue (i.e., the absorption coefficient μ_α and scattering coefficient μ₅ ). The arterial pulse produces periodic variations in the concentrations of oxy and deoxy hemoglobin, resulting in turn in periodic variations in the absorption coefficient.

Variations in intensity of the AC component of the PPG can be written as follows:

Λ( ; = Δ 1 ™····"····· , Δ

' ·' .·, <·· -ν·.,

(I)

The PPG signal is proportional to the physiological variation of light intensity, which in turn is a function of the scattering and absorption coefficients ( μ_α and μ₃ respectively). Variations Δμ_α can be written as a linear variation of the concentrations of oxy and deoxy hemoglobin ( ^Ac _ox and Ac_deox ): Δμ * a

As the ratios of extinction ε_οχ and £_deox (i.e. fraction of light lost as a result of scattering and absorption per unit distance in a particular environment) of the oxy and deoxy hemoglobin are estimated. Based on the above equations, the arterial oxygen saturation (Sp02) is given by:

The expression of Sp02 in terms of the AC component can be obtained by direct application of equations (I) and (III) at selected wavelengths (red and NIR): 1

d Τ ( NIR )

dV_a >M\ AC; R

(V).

GT R ) AC!

Normalizing the AC component to the DC component to offset the effects of low frequency non-synchronous changes in the blood, you get:

AC(R)

i?

AC (NIR)

DC (NIR)

Including this parameter in (IV) it is obtained:

² ₁ kRE_ox(NIR)-£_ox(i?) ₍V|)

kR_£deox(NIR)--_£deox(R)

where

AT(NIR)

DC (NIR)

A_T_(R_)

Where ^Ar(^N^^R)and ΔΤ(/?) correspond to the equation (I) evaluated at the wavelengths R and NIR.

Although the equation (VI) is an exact solution for Sp02, k can not be evaluated because (^ is not available. However, k and R are functions of the optical properties of tissue is possible to express k as a function of R. In more particular, it is possible to express k as a linear equation of the form: k=aR+b (Vll). This implies a linear regression calibration factor derived empirically but assuming a plane wave of intensity P, the absorption coefficient is defined as: dP =¾ Pdz (viii)

Where dP is the differential change in the intensity of a light beam passing through a infinitesimal dz in with a uniform absorption coefficient ¾ . Therefore, integrating over z we get the Beer-Lambert law:

^P=^Po^ (IX)

Assuming that ^{T 'r} P equation (VII) is reduced to k = 1, which is the preferred approach according to which the pulse oximetry is measured in the present invention.

The PPG signal which is obtained by the system of the present invention is used as input to the pre-processing step 12 of the system of the present invention whose main function is to establish a stochastic model of the circulatory function.

As discussed in the background of this invention, the spread of the pulse pressure (PP) should be taken into consideration throughout the analysis of the PPG signal. Given the physiological process, which generates the pulse, Auto regressive moving average (ARMA) models are used in the present invention in order to characterize the mechanism of the generation of the PP. Moreover, there are also parameters which affect the shape and the propagation of the PP. These parameters are related to: cardiac output, heart rate, cardiac synchrony, respiratory rate, metabolic function, etc.

Reference is now made to FIG. 4, which illustrates the steps which are performed by the system of the present invention in the pre-processing algorithm following which the fixed length vector of measurement and clinical parameters is created. In step 20 of the pre-processing step 12, a stochastic modeling via Auto- regressive moving average (ARMA) is performed. Given a time series of data PPG(n), the Auto-regressive moving average (ARMA) model is a tool for understanding and, perhaps, predicting future values in this series. The model consists of two parts, an auto regressive (AR) part and a moving average (MA) part. The model is then referred to as the ARMA(p,q) model where p is the order of the autoregressive (AR) part and q is the order of the moving average (MA) part.

The PPG signal of the present invention which is PPG time series: PPG(n), PPG

(n-1) PPG (n-M) can be modeled as an AR process of order p = M if it satisfies the following equation:

PPG(n)+a_QPPG(n-l)+-- - +a_MPPG(n-M)=w(n) (X) where the coefficients °' ' ^'!'^{! \}J are the AR parameters and ^vi^nl is the target. The term a^ PC^-JO j_{s tne} p_rocj_uct of the coefficient ^α« , and PVG (n-k) _where k = 1, .., M. Equation (X) can be rewritten as:

PPG ( n ) =v, PPG ( n-1 ) +v₂ PPG ( n-2 )+· · · +v_M PPG( n - M ) +w (n) (XI) where v_k=-a_k .

From the above equation , it follows that the current value of the pulse PPG⁽n) j_s equal to a finite linear combination of previous values ( PPG (n-k) ) p|_{us an error} term prediction. Therefore, rewriting the equation (X) as a linear convolution, we obtain:

M

Without loss of generality, it can be defined that ^ao~~^ , as the Z-transform of the predictor filter is given by:

M

A(zj (XIII).

n = 0

PPGi z) j_s defined as the Z- transformed of the PPG signal, and:

A(z)PPG(z)=W(z) (XIV)

where

M

W(z)=∑ v(n)z^"n (XV).

n = 0

Regarding the MA component of order q = K the PPG signal can be described as the response of a discrete linear filter excited by a gaussian white noise. Therefore, the response of the MA filter is written as: PPG_MA(n)=e(n)+b₁e(n-l) + "-+b_Ke(n-K) (XVI) where the constants ^i' ^b2'^{" " "}'^bid are called parameters MA and ^e(ⁿ) is a the white noise error term and the variance &². Therefore, integration of equations (XII) and (XVI) together gives:

P 1

PPG(n)=e(n) +∑a_kPPG(n-k)+∑ b_ke(n-/ ) (XVII)

k= 0 k= 0

be ^ei^{n 1} error terms of model ARMA (q, p). Taking the Z transform of (XVII) gives: PPG (XVIII)

Since the first terms of the AR and MA vectors can be without loss of generality equal to 1, the ARMA (q, p) filter in step 20, as illustrated in FIG.4 is given by:

where A (z) and B (z) are the AR and MA components, respectively.

Totally, it can be concluded that in step 20 of FIG.4, a stochastic modeling via ARMA is applied on the PPG signal in the form of the filter H(z).

According to a specific embodiment of the present invention, the ARMA model of the present invention applies orders of q and p which are q = 1 and p = 5. According to other embodiments, any other order of p and q between 4 and 12 might be used.

According to some embodiments of the present invention, The ARMA model is using the Wold decomposition and the Levinson-Durbin recursion to generate the filter H (z) and the inverse filter 1/H(z) which is implemented on the signal in step 22 of FIG.4 Moreover, additional statistical calculation are performed in step 24 of FIG.4. The results of the statistical calculation of step 24 are stored in the fixed sized vector v().

In step 26 of FIG.4, to model nonlinear interactions such as the PP, the present invention uses the Teager-Kaiser operator.

In this case, without loss of generality, consider the PPG signal as a pulse modulated AM-FM signal (modulated in amplitude and frequency) of the type: PPG ( t ) - a ( t^■) cos J w ( T ) dr (XX)

o

Being ^a )and ithe instantaneous amplitude and frequency of PPG. The Teague-Kaiser operator of a given signal is defined by:

Ψ[χ(ΐ )]=[*^' {t)f-x{t)x (t) (XXI). x (_f , ) ₌ dxft)

where ^dt

This operator applied to the AM-FM modulated signal from equation (XX) is the instantaneous energy of the source that produces the oscillation of the PPG i.e.,

W[WG{ :)]∞a²{t)w²(t) (χχμ)_ι where the approximation error is negligible if the instantaneous amplitude ^Q )and instantaneous frequency ^W(£-J does not vary too fast with respect to the average value ^W ) , as is the case with the PPG pulse.

In step 28 of FIG.4, an AR process of order p is implemented on ^l [PPG(f)| with a filter H'(z). According to a preferred embodiment of the present invention, the AR model uses order of p which is p = 5. According to other embodiments, this order may also be any number between 4 and 12.

Once the stochastic models based on a model ARMA (q, p) are calculated (in steps 20, 22, and 24) and ARMA (q, p) model on the Teague-Kaiser operator (26 and 28), the present invention calculates the heart rate (HR) and cardiac synchrony (i.e. heart rate variability) from the PPG signal in step 30. According to a preferred embodiment of the present invention, the heart rate correlations which are calculated in step 30 by an autocorrelation function (with time windows between 2 seconds and 5 minutes) are applied on the signal.

In step 32 of FIG.4, the zero crossings of the PPG signal are calculated, and later used in vector V\ⁿ) .

Finally, in step 34 of FIG. 4, a collection of clinical parameters related to the patient is performed. These parameters might be: Sex, age, weight, height, food consumption, time of day, BMI, Weight divided by age, Weight divided by HR, Height divided by HR, HR divided by age, Height divided by age, Age divided by the BMI , HR divided by body mass index.

These parameter, or at least part of them are stores in the fixed sized vector V ( n ) _

Totally, following step 20, 22, 24, 26, 28, 30, 32, and 34, feature vector of fixed size V ( ⁿ ) is created, and the blood pressure can be estimated in step 14 by the "Random Forests" classifier.

As presented above, the system of the present invention has an advantage over the prior art as being not requiring calibration in order to estimate the blood pressure. This is achieved via the "Random Forests" classification algorithm which is previously trained.

The "Random Forests" is a classifier consisting of a set of classifiers with a tree structure ·^{/! (} '-^{(: ,} 1 . · · · _wnere ®fc are random vectors which are independent and identically distributed (II D). Each vector ¾ is adapted to provide a single vote for the most popular class of the input vector V(). This approach presents a clear advantage in terms of reliability compared to other classifiers which are based on a single tree and do not impose any restriction on the functional relationship between the pulse and blood pressure levels.

The "Random Forests" algorithm used in the present invention is generated by the growth of decision trees which are based on the random vector ^Θ such that the predictor Λ ( ν,Θ ) outputs numerical values. This random vector ^Θ associated with each tree provides a random distribution at each node while also providing information on the random sampling of the training base, resulting in different subsets of data for each tree. Based on this result, the error of the "Random Forests" classifier used in the present invention is given by: PE -E_¼y ( Y--h( V) )² (xxiii).

Since the error of the "Random Forest" is lower than a single decision tree, defining: γ- ν,Θ )

Υ- ν,Θ' ) (xxiv) the following is received:

PE ( forest ) < pPE ( arbol ) (XXV)

Each tree has a different generalization error and P represents the correlation between the residues identified in (XXIV). This fact implies that a lower correlation between the residues (XXIV) results in better estimates. According to the present invention, the minimum correlation is given by the random sampling process of the feature vector at each node of the tree that is trained by the system. According to some embodiments, to further reduce the error of the classifier, the present invention estimates the parameters of interest (SBP, DBP and MAP) as linear combinations of them.

The "Random Forests" consist of a set of decision trees CART-type ( 'Classification and Regression Trees ", by its initials in English), altered to introduce systematic errors (XXV) on each one and then, through a system of 'bootstrap' a systematic variation (both random processes are modeled by the parameter ⁰ in the analysis of predictor ν,Θ) ) j e systematic error different in each realization is introduced by two mechanisms:

1. Random choice at each node a subset of attributes so that you can not establish a statistically equivalent to the partitions made between different nodes in such trees so that each tree will behave differently. 2. Leave the trees to grow up. In this case the trees are so similar to lookup table- based rules. Due to the sampling of attributes, tables are seeking different structure.

The result of this process is that each tree will present a different error.

Moreover, these two changes, each tree is trained with a sample of type 'bootstrap' (ie a sample is taken from the input data, which leads to that part of the input data while missing and another part is repeated). This effect of 'bootstrap' introduces variability, when making estimates of the average offset. The overall result of these features which are part of the post-processing step 16, where the systematic error and variability of the error can be compensated quite easily more accurate than other estimators of functions (XXVII). In this system, the base is a tree classifier, which decides on the basis of levels, making it robust against input distributions with 'outliers' or heterogeneous data types (such as the present invention).

According to a preferred embodiment of the present invention, in the postprocessing step 16 of FIG. 3 is to take random samples from two 47-level node (which may also implement changes between 2 and 47) and size of a 'bootstrap' which is 100. According to another embodiments, the 'bootstrap' may be between a size of 25 to a size of 500.

According to some embodiments, the computing means of the present invention is selected from a group consisting of: a DSP system, FPGA, microcontroller, or any combination thereof.

WCH and WCE diagnosis by system of the present invention:

According to some embodiments of the invention, the second storage, which is in communication with the computing means contains programmed executable instructions (algorithm) adapted to detect the WCH and WCE in the patient according to a diagnosis protocol. This diagnostic protocol can also differentiate patients with sustained or normalized hypertension and patients with WCH and WCE.

Following the estimation of the patient's blood pressure (e.g., SBP, DBP, MBP), the record of the aforementioned blood pressure may be analyzed by the system in order to determine whether said patient has WCH and WCE or one of them. This analysis is performed via the algorithm stored in the second storage of the system.

The diagnostic protocol which is stored in said second storage comprising a set of rules and threshold according to which the WCH and the WCE are diagnosed. The following are examples of parameters according to which the diagnostic protocol is operated:

The time parameter: The system may be operated for a predetermined length of time which can vary for example from minutes (e.g., 15, 30 min.) to days (e.g., 24 hours, 48 hours, etc). The length of the time parameter may influence on the precision of said diagnosis. According to the preferred embodiment of the invention, the system is operated with time parameter of about 24 hours. Mode of operation: The system may be operated in different modes of operation (e.g., ambulatory, continuous, discrete). For example, a continuous or ambulatory (ABMP) mode may be used when the person is sent home with the system attached to his body, and a precise measurement of blood pressure is needed (e.g., a reading which is takes every a few seconds). A discrete mode may be used when the blood pressure is measure every a few minutes or hours. According to the preferred embodiment of the invention, the system is operated in the continuous or the ambulatory (ABMP) modes.

Blood pressure thresholds: There are different studies which are relevant to the WCH and WCE. According to these studies, there are various thresholds of blood pressure that determine the WCH and the WCE.

For example, the WCH is determined when the measured blood pressure is the following: the SBP is at least about 140 mmHg and/or the DBP is at least about 90 in office settings, while at in other settings (e.g., at home) the measured blood pressure is the following: the SBP is less than about 135 mmHg and/or the DBP is less than about 85.

Foe another example, the WCE is determined when the measured blood pressure in office settings in higher than the measured blood pressure in other setting (e.g., at home) in the following measures: the SBP is higher by at least about 20 mmHg, and the DBP is higher by at least about 10 mmHg.

Registration of the location of measurement: When the system of the present invention performs a measurement, it is highly important to register the location in which the measurement is taken, for the WCH and WCE diagnosis algorithm. Therefore, as part of the operation of the system, the location of the operation is registered. The measurement location may be classified to office setting and to other settings, and the algorithm may use this classification for the diagnosis of WCH and WCE.

Registration of the identity of person who performs the measurement: In some embodiments of the invention, when a measurement is performed , the personal and professional identity of the person performing the measurement is registered. For example, when a doctor performs the measurement, the system is operated in office settings (e.g., doctor's office). Contrary, if the measurement is performed by the person himself, this means that the system is operated in other settings (e.g., home settings).

According to some embodiments, the algorithm of the second storage is further adapted to register the settings in which the system is operated. The settings are selected from a group consisting of: the location measurement, the kind of person who performs the measurement, such that the settings are classified to two classes: office settings and other settings. Furthermore, the system is adapted to diagnose WCH and WCE in the patient according to said diagnosis protocol and said settings.

According to some embodiments of the invention, the system may be used to detect when the WCH and/or WCE do not influence on the measured blood pressure, or at least reduced. This can be done by the algorithm of the second storage which can detect the time in which the blood pressure is reduced to a predetermined level in which the sittings in which the system is operated do not influence.

According to some embodiments, the system of the present invention is adapted to differentiate between patients with WCH and/or WCE ad patients with sustained or normalized hypertension with a precision of at least about 90%.

According to some embodiment, the algorithm of the second storage may perform statistical analysis as part of its operation to detect the WCH and the WCE in the patient.

According to some embodiments, the determination of the blood pressure in different settings may be performed by calculation of mean blood pressure (e.g., mean SBP, mean DBP, etc.) in a predetermined time and in a specific location. Moreover, according to some embodiments, the level of the mean blood pressure may comprise two levels: an upper level and a lower level of the mean blood pressure. The analysis of the algorithm of the second storage may be performed with respect to these two levels.

According to some embodiment, the system of the present invention may differentiate patients with sustained or normalized hypertension and patients with WCH, when the blood pressure levels are defined as following: a measurement which is performed by the person himself in which the SBP is < 140 mmHg and/or the DBP is < 90 mmHg, and a measurement which is performed by the doctor in which the SBP is > 160 mmHg and/or the DBP is > 95 mmHg.

According to some embodiment of the present invention, the algorithm of the second storage is adapted to diagnose WCH and WCE by comparing the measured blood pressure of a patient during said office settings (e.g., for about 15 minutes), and the blood pressure of said patient before/after said visit (e.g., for about 15 minutes).

According to other embodiments of the invention, the diagnosis of the WCH and the WCE can be performed via other known in the art diagnosis protocols, and is not limited to the diagnosis protocol disclosed by the present invention.

"Real" blood pressure measurement by the system of the present invention:

According to another embodiment of the present invention, the present invention is adapted to measure blood pressure of a patient with elimination of the WCH and the WCE. According to this embodiment, the second storage, which is in communication with the computing means containing programmed executable instructions (algorithm) adapted to diagnose the WCH and WCE in said patient according to a diagnosis protocol, and to provide a "real" blood pressure measurement which is not biased by said WCH and WCE by eliminating the profile of the WCH and the WCE from the estimated blood pressure measurement of the patient. The measurement of blood pressure and the diagnosis of said WCH and WCE of this embodiment of the present invention are performed via the disclosed above embodiments of the present invention.

Following the estimation of the patient's blood pressure (e.g., SBP, DBP, MBP), and a determination of the WCH and/or the WCE in said patient, the programmed executable instructions (algorithm) of the second storage may estimate and characterize the profile of said WCH and said WCE. The profile of said WCH and said WCE in said patient is characterized by a time-dependent amplitude of the difference between a blood pressure of said patient in office settings and a blood pressure of said patient in other settings.

When a patient with WCE and WCH is located in an office setting, and his blood pressure is estimated and measured is these settings, this measured blood pressure is not the "real" blood pressure of the patient, but a biased one. This biasing factor should be eliminated from the blood pressure measurement in order to provide a "real" blood pressure which is not influenced by said WCH and said WCE. This biasing factor is the profile of said WCH and said WCE.

According to one object of the present invention, the profile of said WCH and WCE is estimated by the diagnosis protocol which comprises the information regarding the blood pressure signal of said patient in different settings. For example, this diagnosis protocol has a record of a patient's blood pressure in office setting (a first signal) and a record of a patient's blood pressure in other setting (a second signal), both of them are characterized by the same length in time. By subtracting the second signal from the first signal, and optionally performing additional signal processing (e.g., interpolation), said profile of said WCH and WCE is estimated.

According to one object of the present invention, the profile of said WCH and WCE is estimated by other conventional techniques which can characterize the profile of said WCH and WCE, and eliminate them from the measured blood pressure, and thereby provides a "real" blood pressure.

According to some embodiments, the profile of said WCH and WCE is stored in the database defined by the present invention.

According to some embodiments, the person that activates the system of the present invention (e.g., a doctor, a nurse, etc.) may receive two kinds of blood pressure measurement signals simultaneously: an estimated blood pressure by the system of the present invention, a "real" blood pressure in case of a WCH and WCE in a patient.

According to other embodiments of the present invention, the person that activates the system of the present invention (e.g., a doctor, a nurse, etc.) may activate and deactivate in any time the algorithm that provides the "real" blood pressure. In case of activated algorithm, a "real" blood pressure is provided, and in case of deactivated algorithm, a blood pressure measurement is provided. Support vector machines (SVMs) are a set of related supervised learning methods used for classification and regression. In simple words, given a set of training examples, each marked as belonging to one of two categories, an SVM training algorithm builds a model that predicts whether a new example falls into one category or the other. Intuitively, an SVM model is a representation of the examples as points in space, mapped so that the examples of the separate categories are divided by a clear gap that is as wide as possible. New examples are then mapped into that same space and predicted to belong to a category based on which side of the gap they fall on.

More formally, a support vector machine constructs a hyperplane or set of hyperplanes in a high or infinite dimensional space, which can be used for classification, regression or other tasks. Intuitively, a good separation is achieved by the hyperplane that has the largest distance to the nearest training datapoints of any class (so-called functional margin), since in general the larger the margin the lower the generalization error of the classifier.

According to other embodiments of the present invention the classification is performed via a Support Vector Machine (SVM) algorithm, instead of the "random forests" algorithm. Therefore, all the methods of calculation and data classification as described above might be performed via the SVM algorithm. Moreover, for each application of the "random forests" algorithm, according to said other embodiments, the operations might be performed via the SVM algorithm instead.

Claims

A non-invasive system for measuring blood pressure of a patient with elimination of white coat hypertension (WCH) and white coat effect (WCE), said system consisting of:

a. a blood pressure module consisting of a plethysmograph for measuring changes in a tissue volume in a predetermined location of the patient, and generating an electrical signal associated with said changes in the tissue volume;

b. a calculation device with a processor, said calculation device is in communication with the blood pressure module;

c. a first storage in communication with the calculation device containing programmed executable instructions configured to receive the electrical signal and to process the same by performing at least one operation selected from: (i) calculation of a set of measurement parameters from the electrical signal based on at least one auto-regressive moving average (ARMA) model; (ii) generation of a fixed length data vector consisting of the set of measurement parameters and clinical parameters of the patient; (iii) storage in a communicable database the data vector and other data vectors; and, (iv) performing a regression based on a "Random Forest" algorithm by using the data vector and the database, such that the blood pressure of the patient is calculated; and, d. a second storage in communication with said calculation device containing programmed executable instructions adapted to diagnose the WCH and the WCE in the patient and to characterize the profile of the WCH and the WCE in the patient according to a diagnosis protocol; wherein the programmed executable instructions of said second storage are further adapted to provide a "real" blood pressure measurement which is not biased by the WCH and WCE by eliminating the profile of the WCH and the WCE from the estimated blood pressure measurement of the patient.

The system of claim 1, wherein the profile of the WCH and the WCE in the patient is characterized by a time-dependent amplitude of the difference between a blood pressure of the patient in office settings and a blood pressure of the patient in other settings.

3. The system of claim 1, wherein the blood pressure module is selected from a group consisting of: a photoplethysmograph (PPG), a pulse oximeter, an acoustic plethysmograph, a mechanical plethysmograph, or any combination thereof.

4. The system of claim 1, wherein said system does not require calibration by means of an additional blood measurement technique.

5. The system of claim 1, wherein the at least one auto-regressive moving average (ARMA) model is a Teager-Kaiser operator.

6. The system of claim 1, wherein the clinical parameters of the patient are selected from a group consisting of: sex, age, weight, height, food consumption, time of day, BMI, weight divided by age, weight divided by Heart Rate (HR), height divided by HR, HR divided by age, height divided by age, age divided by the BMI, HR divided by body mass index, or any combination thereof.

7. The system of claim 1, wherein the first storage is further adapted for performing error reduction of the blood pressure calculated by means of the "Random Forests" algorithm.

8. The system of claim 1, wherein the calculation device is selected from a group consisting of: a DSP system, FPGA, microcontroller, or any combination thereof.

9. The system of claim 1, wherein the second storage is further adapted to detect when the WCH and the WCE are reduced.

10. The system of claim 1, wherein the blood pressure of the patient is selected from a group consisting of: a systolic blood pressure (SBP), a diastolic blood pressure (DBP), a mean arterial pressure (MAP), or any combination thereof.

11. The system of claim 1, wherein the programmed executable instructions of the second storage are adapted to differentiate between a patient with WCH and WCE, and a patient with sustained or normalized hypertension with a precision of at least approximately 90%.

12. The system of claim 1, wherein the diagnosis protocol is adapted to locate a decrease in the blood pressure of the patient in other settings, after a predetermined series of readings and over a predetermined period of time, and to compare said decrease to a predetermined value of blood pressure measured in office settings, said predetermined value is associated with WCE.

13. The system of claim 12, wherein the predetermined value is selected from a group consisting of: systolic blood pressure (SBP) is approximately 20 mmHg, diastolic blood pressure (DBP) is approximately 10 mmHg, or any combination thereof.

14. The system of claim 1, wherein the diagnosis protocol is adapted to determine that the measured blood pressure after a predetermined series of readings and over a predetermined period of time is substantially above an elevated blood pressure level in office settings and is substantially below a normal blood pressure level in other settings, such that said patient is diagnosed with WCH.

15. The system of claim 14, wherein the elevated blood pressure level is selected from a group consisting of: systolic blood pressure (SBP) is approximately 140 mmHg, diastolic blood pressure (DBP) is approximately 90 mmHg, or any combination thereof; said normal blood pressure level is selected from a group consisting of: systolic blood pressure (SBP) is approximately 135 mmHg, diastolic blood pressure (DBP) is approximately 85 mmHg, or any combination thereof.

16. The system of claim 1, wherein the mode of operation of said system is selected from: ambulatory, continuous, discrete, or any combination thereof.

17. The system of claim 1, wherein the system is adapted to be operated in a location selected from a group consisting of: in the doctor's office, at home, at work, a hospital, or any combination thereof.

18. The system of claim 1, wherein the second storage further adapted to perform a statistical analysis to detect the WCH and the WCE in the patient.

The system of claim 1, wherein the first storage and the second storage are integrated.

The system of claim 1, wherein the second storage is further adapted to register the settings in which said system is operated, the settings selected from a group consisting of: the location measurement, the kind of person who performs the measurement, such that the settings are classified in two classes: office settings and other settings; further wherein the system is adapted to diagnose the WCH and the WCE in the patient according to said diagnosis protocol and said settings.

A method for measuring blood pressure of a patient with elimination of white coat hypertension (WCH) and white coat effect (WCE), said method consisting of the steps of:

a. obtaining a non-invasive system for diagnosing a WCH and WCE and in a patient, said system consisting of: (i) a blood pressure module consisting of a plethysmograph; (ii) a calculation device with a processor, said calculation device is in communication with the blood pressure module; (iii) a first storage in communication with said calculation device containing programmed executable instructions configured to receive the electrical signal and to process the same; and, (iv) a second storage in communication with the calculation device containing programmed executable instructions adapted to diagnose the WCH and the WCE in the patient and to characterize the profile of the WCH and the WCE in the patient according to a diagnosis protocol; b. measuring changes in a tissue volume in a predetermined location of the patient, and generating an electrical signal associated with said changes in the tissue volume by means of the blood pressure module; c. calculating a set of measurement parameters from the electrical signal, wherein said set of measurement parameters is based on at least one auto-regressive moving average (ARMA) model;

d. obtaining a set of clinical parameters of the patient; e. generating a fixed length data vector consisting of the set of measurement parameters and clinical parameters of the patient;

f. storing the data vector in a communicable database, said database further comprising other data vectors;

5 g. performing a regression based on a "Random Forest" algorithm by using the data vector and the database, and thereby calculating the blood pressure of the patient;

h. diagnosing the WCH and the WCE in the patient according to a diagnostic protocol by means of the second storage; and,

10 i. eliminating the profile of the WCH and the WCE from the estimated blood pressure measurement of the patient, thereby providing a "real" blood pressure measurement which is not biased by the WCH and WCE.

22. The method of claim 21, further comprising the step of characterizing the 15 profile by calculating the time-dependent amplitude of the difference between the blood pressure of the patient in office settings and the blood pressure of the patient in other settings.

23. The method of claim 21, further comprising the step of selecting the blood pressure module from a group consisting of: a photoplethysmograph (PPG),

20 a pulse oximeter, an acoustic plethysmograph, a mechanical plethysmograph, or any combination thereof.

24. The method of claim 21, wherein said method does not require an additional step of calibrating the system by means of an additional blood measurement technique.

25 25. The method of claim 21, wherein the at least one auto-regressive moving average (ARMA) model is a Teager-Kaiser operator.

26. The method of claim 21, further comprising the step of selecting the clinical parameters of the patient from a group consisting of: sex, age, weight, height, food consumption, time of day, BMI, weight divided by age, weight 30 divided by Heart Rate (HR), height divided by HR, HR divided by age, height divided by age, age divided by the BMI, HR divided by body mass index, or any combination thereof.

27. The method of claim 21, wherein the method further comprising a step of performing error reduction of the blood pressure calculated by means of the

5 "Random Forests" algorithm by the first storage.

28. The method of claim 21, further comprising the step of selecting the calculation device from a group consisting of: a DSP system, FPGA, microcontroller, or any combination thereof.

29. The method of claim 21, further comprising a step of detecting when the 10 WCH and the WCE is reduced by the second storage.

30. The method of claim 21, further comprising the step of selecting the blood pressure of the patient from a group consisting of: a systolic blood pressure (SBP), a diastolic blood pressure (DBP), a mean arterial pressure (MAP), or any combination thereof.

15 31. The method of claim 21, wherein the step of differentiating patients with sustained or normalized hypertension and patients with WCH and WCE is performed with a precision of at least 90%.

32. The method of claim 21, further comprising a step of locating a decrease in the blood pressure of the patient after a predetermined series of readings

20 and over a predetermined period of time according to the diagnostic protocol, and comparing said decrease to a predetermined value, said predetermined value being associated with WCE.

33. The method of claim 32, further comprising a step of selecting the predetermined value from a group consisting of: systolic blood pressure

25 (SBP) is approximately 20 mmHg, diastolic blood pressure (DBP) is approximately 10 mmHg, or any combination thereof.

34. The method of claim 21, further comprising a step of determining that the measured blood pressure after a predetermined series of readings and over a predetermined period of time is above a predetermined level of blood

30 pressure according to the diagnostic protocol, and thereby diagnosing the patient with WCH.

35. The method of claim 34, further comprising the step of selecting the predetermined level from a group consisting of: systolic blood pressure (SBP) is approximately 140 mmHg, diastolic blood pressure (DBP) is approximately 90 mmHg, or any combination thereof. 36. The method of claim 21, further comprising the step of selecting the mode of operation of the system is selected from a group consisting of: ambulatory, continuous, discrete, or any combination thereof.

37. The method of claim 21, further comprising the step of selecting the location of operation of the system from: the doctor's office, at home, at work, a hospital, or any combination thereof.

38. The method of claim 21, further comprising step of performing statistical analysis to detect the WCH in the patient by the second storage.

39. The method of claim 21, further comprising the step of registering the settings in which the system is operated, said settings being selected from a group consisting of: the location measurement, the kind of person who performs the measurement, and thereby classifying the settings in two classes: office settings and other settings, and diagnosing the WCH and the WCE in the patient according to said diagnosis protocol and said settings.

40. The method of claim 21, wherein the profile of the WCH and the WCE in the patient is characterized by a time-dependent amplitude of the difference between a blood pressure of the patient in office settings and a blood pressure of the patient in other settings.

41. A non-invasive system for diagnosing white coat hypertension (WCH) and white coat effect (WCE) in a patient, the system consisting of: a. a blood pressure module consisting of a plethysmograph for measuring changes in a tissue volume in a predetermined location of the patient, and generating an electrical signal associated with said changes in the tissue volume; b. a calculation device with a processor, said calculation device is in communication with the blood pressure module; and, c. a first storage in communication with the calculation device containing programmed executable instructions configured to receive the electrical signal and to process the same by performing at least one operation selected from: (i) calculation of a set of measurement parameters from the electrical signal based on at least one auto-regressive moving average (ARMA) model; (ii) generation of a fixed length data vector consisting of the set of measurement parameters and clinical parameters of the patient; (iii) storage in a communicable database the data vector and other data vectors; and, (iv) performing a regression based on a "Random Forest" algorithm by using the data vector and the database, such that the blood pressure of the patient is calculated;

wherein the system further consists of a second storage in communication with said calculation device containing programmed executable instructions adapted to diagnose the WCH and the WCE in the patient according to a diagnosis protocol, and to differentiate patients with sustained or normalized hypertension and patients with WCH and WCE.

The system of claim 41, wherein the blood pressure module is selected from a group consisting of: a photoplethysmograph (PPG), a pulse oximeter, an acoustic plethysmograph, a mechanical plethysmograph, or any combination thereof.

The system of claim 41, wherein said system does not require calibration by means of an additional blood measurement technique.

The system of claim 41, wherein the at least one auto-regressive moving average (ARMA) model is performed by means of a Teager-Kaiser operator.

The system of claim 41, wherein the clinical parameters of the patient are selected from a group consisting of: sex, age, weight, height, food consumption, time of day, BMI, weight divided by age, weight divided by Heart Rate (HR), height divided by HR, HR divided by age, height divided by age, age divided by the BMI, HR divided by body mass index, or any combination thereof.

The system of claim 41, wherein the first storage is further adapted for performing error reduction of the blood pressure calculated by means of the "Random Forests" algorithm.

47. The system of claim 41, wherein the calculation device is selected from a group consisting of: a DSP system, FPGA, microcontroller, or any combination thereof.

48. The system of claim 41, wherein the second storage is further adapted to detect when the WCH and the WCE are reduced.

49. The system of claim 41, wherein the blood pressure of the patient is selected from a group consisting of: a systolic blood pressure (SBP), a diastolic blood pressure (DBP), a mean arterial pressure (MAP), or any combination thereof.

50. The system of claim 41, wherein the programmed executable instructions of the second storage adapted to differentiate between a patient with WCH and WCE, and a patient with sustained or normalized hypertension with a precision of at least approximately 90%.

51. The system of claim 41, wherein the diagnosis protocol is adapted to locate a decrease in the blood pressure of the patient in other settings, after a predetermined series of readings and over a predetermined period of time, and to compare the decrease to a predetermined value of blood pressure measured in office settings, the predetermined value is associated with WCE.

52. The system of claim 51, wherein the predetermined value is selected from a group consisting of: systolic blood pressure (SBP) is approximately 20 mmHg, diastolic blood pressure (DBP) is approximately 10 mmHg, or any combination thereof.

53. The system of claim 41, wherein the diagnosis protocol is adapted to determine the measured blood pressure after a predetermined series of readings and over a predetermined period of time is substantially above an elevated blood pressure level in office settings and is substantially below a normal blood pressure level in other settings, such that the patient is diagnosed with WCH.

54. The system of claim 53, wherein the elevated blood pressure level is selected from a group consisting of: systolic blood pressure (SBP) is approximately 140 mmHg, diastolic blood pressure (DBP) is approximately 90 mmHg, or any combination thereof; the elevated blood pressure level is

5 selected from a group consisting of: systolic blood pressure (SBP) is approximately 135 mmHg, diastolic blood pressure (DBP) is approximately 85 mmHg, or any combination thereof.

55. The system of claim 41, wherein the mode of operation of said system is selected from: ambulatory, continuous, discrete, or any combination thereof.

10 56. The system of claim 41, wherein said system is adapted to be operated in a location selected from a group consisting of: in the doctor's office, at home, at work, a hospital, or any combination thereof.

57. The system of claim 41, wherein the second storage further adapted to perform a statistical analysis to detect the WCH and the WCE in the patient.

15 58. The system of claim 41, wherein the first storage and the second storage are integrated.

59. The system of claim 41, wherein the second storage is further adapted to register the settings in which said system is operated, said settings being selected from: the location measurement, the kind of person who performs

20 the measurement, such that the settings are classified in two classes: office settings and other settings; further wherein said system is adapted to diagnose the WCH and the WCE in the patient according to said diagnosis protocol and said settings.

60. A method for diagnosing white coat hypertension (WCH) and white Coat 25 Effect (WCE) in a patient, said method consists of:

j. obtaining a non-invasive system for diagnosing a WCH and WCE and in a patient, said system consisting of: (i) a blood pressure module consisting of a plethysmograph; (ii) a calculation device with a processor, the calculation device is in communication with the blood 30 pressure module; (iii) a first storage in communication with the calculation device containing programmed executable instructions configured to receive said electrical signal and to process the same; and, (iv) a second storage in communication with said calculation device containing programmed executable instructions adapted to diagnose WCE and WCH in the patient according to a diagnosis protocol;

k. measuring changes in a tissue volume in a predetermined location of the patient, and generating an electrical signal related to said changes in the tissue volume by means of the blood pressure module;

I. calculating of a set of measurement parameters from said electrical signal based on at least one auto-regressive moving average (ARMA) model;

m. obtaining a set of clinical parameters of the patient;

n. generating a fixed length data vector consisting of the set of measurement parameters and clinical parameters of the patient;

o. storing the data vector in a communicable database, said database further comprising other data vectors;

p. performing a regression based on a "Random Forest" algorithm by using the data vector and said database, and thereby calculating the blood pressure of the patient;

q. diagnosing the WCH and the WCE in the patient according to a diagnostic protocol by said second storage; and,

r. differentiating patients with sustained or normalized hypertension and patients with WCH and WCE.

The method of claim 60, further comprising the step of selecting said blood pressure module from a group consisting of: a photoplethysmograph (PPG), a pulse oximeter, an acoustic plethysmograph, a mechanical plethysmograph, or any combination thereof.

The method of claim 60, wherein said method does not require an additional step of calibrating the system by means of an additional blood measurement technique.

The method of claim 60, wherein said at least one auto-regressive moving average (ARMA) model is performed by means of a Teager-Kaiser operator.

64. The method of claim 60, further comprising the step of selecting the clinical parameters of the patient from a group consisting of: sex, age, weight, height, food consumption, time of day, BMI, weight divided by age, weight

5 divided by Heart Rate (HR), height divided by HR, HR divided by age, height divided by age, age divided by the BMI, HR divided by body mass index, or any combination thereof.

65. The method of claim 60, wherein said method further comprises a step of performing an error reduction of the blood pressure calculated by means of

10 the "Random Forests" algorithm by the first storage.

66. The method of claim 60, further comprising step of selecting the calculation device from a group consisting of: a DSP system, FPGA, microcontroller, or any combination thereof.

67. The method of claim 60, further comprising a step of detecting when the 15 WCH and the WCE is reduced by means of the second storage.

68. The method of claim 60, further comprising a step of selecting the blood pressure of the patient from a group consisting of: a systolic blood pressure (SBP), a diastolic blood pressure (DBP), a mean arterial pressure (MAP), or any combination thereof.

20 69. The method of claim 60, wherein the step of differentiating patients with sustained or normalized hypertension and patients with WCH and WCE is performed with a precision of at least a 90%.

70. The method of claim 60, further comprising a step of locating a decrease in the blood pressure of the patient after a predetermined series of readings

25 and over a predetermined period of time according to the diagnostic protocol, and comparing said decrease to a predetermined value, said predetermined value being associated with WCE.

71. The method of claim 70, further comprising a step of selecting the predetermined value from a group consisting of: systolic blood pressure

30 (SBP) is approximately 20 mmHg, diastolic blood pressure (DBP) is approximately 10 mmHg, or any combination thereof.

72. The method of claim 60, further comprising a step of determining that the measured blood pressure after a predetermined series of readings and over a predetermined period of time is above a predetermined level of blood pressure according to the diagnostic protocol, and thereby diagnosing the

5 patient with WCH.

73. The method of claim 72, further comprising a step of selecting the predetermined level from a group consisting of: systolic blood pressure (SBP) is approximately 140 mmHg, diastolic blood pressure (DBP) is approximately 90 mmHg, or any combination thereof.

10 74. The method of claim 60, further comprising step of selecting the mode of operation of the system is selected from a group consisting of: ambulatory, continuous, discrete, or any combination thereof.

75. The method of claim 60, further comprising a step of selecting the location of operation of the system from: the doctor's office, at home, at work, a

15 hospital, or any combination thereof.

76. The method of claim 60, further comprising a step of performing statistical analysis to detect the WCH in the patient by means of the second storage.

77. The method of claim 60, further comprising the step of registering the settings in which the system is operated, said settings selected from a group

20 consisting of: the location measurement, the kind of person who performs the measurement, and thereby classifying the settings in two classes: office settings and other settings, and diagnosing the WCH and the WCE in the patient according to said diagnosis protocol and said settings.

78. A non-invasive system for measuring blood pressure of a patient with 25 elimination of white coat hypertension (WCH) and white coat effect (WCE), said system comprising:

a. a plesthymograph based blood pressure system for estimation of said patient's blood pressure; and,

b. a second storage in communication with said calculation device 30 containing programmed executable instructions adapted to: (i) diagnosing the WCH and the WCE in the patient; (ii) characterizing the profile of the WCH and the WCE in the patient according to a diagnosis protocol; and, (iii) to providing a "real" blood pressure measurement which is not biased by the WCH and WCE by eliminating the profile of the WCH and the WCE from the estimated blood pressure measurement of the patient;

wherein the estimation of the patient's blood pressure is performed by means of a "Random Forest" algorithm which is adapted to receive a fixed length data vector consisting of a set of measurement parameters and clinical parameters, said measurement parameters are based on at least one auto- regressive moving average (ARMA) model of the signals received from the PPG, the clinical parameters are received from the patient.

j. obtaining a plesthymograph based blood pressure system for calculating the patient's blood pressure;

k. estimating the blood pressure of the patient by means of said system;

I. diagnosing the WCH and the WCE in the patient according to a diagnostic protocol by a second storage located within the system; and, m. eliminating the profile of the WCH and the WCE from the estimated blood pressure measurement of the patient, thereby providing a "real" blood pressure measurement which is not biased by the WCH and WCE.

wherein the step of estimation of the blood pressure of the patient is performed by means of a "Random Forest" algorithm which is adapted to receive a fixed length data vector consisting of a set of measurement parameters and clinical parameters, said measurement parameters are based on at least one auto-regressive moving average (ARMA) model of the signals received from the PPG, the clinical parameters are received from the patient. A non-invasive system for diagnosing white coat hypertension (WCH) and white coat effect (WCE) in a patient, said system comprising:

a. a plesthymograph based blood pressure system for estimation of the patient's blood pressure; and,

b. a storage in communication with said blood pressure system containing programmed executable instructions adapted to diagnose the WCH and the WCE in the patient according to a diagnosis protocol;

A non-invasive system for diagnosing white coat hypertension (WCH) and white coat effect (WCE) in a patient, said system consisting of:

a. a PPG based blood pressure system for determining the patient's blood pressure, said estimation of the patient's blood pressure being performed by means of a SVM algorithm adapted to receive a fixed length data vector consisting of a set of measurement parameters and clinical parameters, the measurement parameters are based on at least one auto-regressive moving average (ARMA) model of the signals received from the PPG, the clinical parameters are received from the patient; and

wherein the non-invasive system for diagnosing white coat hypertension (WCH) and white coat effect (WCE) in a patient system does not require calibration by means of an additional blood measurement technique. A non-invasive system for measuring blood pressure of a patient with elimination of white coat hypertension (WCH) and white coat effect (WCE), said system consisting of:

b. a calculation device with a processor, said calculation device being in communication with the blood pressure module;

c. a first storage in communication with the calculation device containing programmed executable instructions configured to receive the electrical signal and to process the same by performing at least one operation selected from: (i) calculation of a set of measurement parameters from the electrical signal based on at least one auto-regressive moving average (ARMA) model; (ii) generation of a fixed length data vector consisting of the set of measurement parameters and clinical parameters of the patient; (iii) storage in a communicable database the data vector and other data vectors; and, (iv) performing a regression based on a SVM algorithm by using the data vector and the database, such that the blood pressure of the patient is estimated; and,

d. a second storage in communication with said calculation device containing programmed executable instructions adapted to diagnose the WCH and the WCE in the patient and to characterize the profile of the WCH and the WCE in the patient according to a diagnosis protocol; wherein the programmed executable instructions of said second storage are further adapted to provide a "real" blood pressure measurement which is not biased by the WCH and WCE by eliminating the profile of the WCH and the WCE from the estimated blood pressure measurement of the patient.

The system of claim 81, wherein the profile of the WCH and the WCE in the patient is characterized by a time-dependent amplitude of the difference between a blood pressure of the patient in office settings and a blood pressure of the patient in other settings.

84. The system of claim 81, wherein the blood pressure module is selected from a group consisting of: a photoplethysmograph (PPG), a pulse oximeter, an acoustic plethysmograph, a mechanical plethysmograph, or any

5 combination thereof.

85. The system of claim 81, wherein said system does not require calibration by means of an additional blood measurement technique.

86. The system of claim 81, wherein the at least one auto-regressive moving average (ARMA) model is performed by means of a Teager-Kaiser operator.

10 87. The system of claim 81, wherein the clinical parameters of the patient are selected from a group consisting of: sex, age, weight, height, food consumption, time of day, BMI, weight divided by age, weight divided by Heart Rate (HR), height divided by HR, HR divided by age, height divided by age, age divided by the BMI, HR divided by body mass index, or any

15 combination thereof.

88. The system of claim 81, wherein the first storage is further adapted to performi an error reduction of the blood pressure calculated by means of the SVM algorithm.

89. The system of claim 81, wherein the calculation device is selected from a 20 group consisting of: a DSP system, FPGA, microcontroller, or any combination thereof.

90. The system of claim 81, wherein the second storage is further adapted to detect when the WCH and the WCE are reduced.

91. The system of claim 81, wherein the blood pressure of the patient is 25 selected from a group consisting of: a systolic blood pressure (SBP), a diastolic blood pressure (DBP), a mean arterial pressure (MAP), or any combination thereof.

92. The system of claim 81, wherein the programmed executable instructions of the second storage adapted to differentiate between a patient with WCH and

30 WCE, and a patient with sustained or normalized hypertension with a precision of at least approximately 90%.

93. The system of claim 81, wherein the diagnosis protocol is adapted to locate a decrease in the blood pressure of the patient in other settings, after a predetermined series of readings and over a predetermined period of time,

5 and to compare said decrease to a predetermined value of blood pressure measured in office settings, the predetermined value being associated with WCE.

94. The system of claim 93, wherein said predetermined value is selected from a group consisting of: systolic blood pressure (SBP) is approximately 20

10 mmHg, diastolic blood pressure (DBP) is approximately 10 mmHg, or any combination thereof.

95. The system of claim 81, wherein the diagnosis protocol is adapted to determine that the measured blood pressure after a predetermined series of readings and over a predetermined period of time is substantially above an

15 elevated blood pressure level in office settings and is substantially below a normal blood pressure level in other settings, such that said patient is diagnosed with WCH.

96. The system of claim 95, wherein the elevated blood pressure level is selected from a group consisting of: systolic blood pressure (SBP) is

20 approximately 140 mmHg, diastolic blood pressure (DBP) is approximately

90 mmHg, or any combination thereof; said normal blood pressure level is selected from a group consisting of: systolic blood pressure (SBP) is approximately 135 mmHg, diastolic blood pressure (DBP) is approximately 85 mmHg, or any combination thereof.

25 97. The system of claim 81, wherein the mode of operation of said system is selected from: ambulatory, continuous, discrete, or any combination thereof.

98. The system of claim 81, wherein the system is adapted to be operated in a location selected from a group consisting of: in the doctor's office, at home, at work, a hospital, or any combination thereof.

30 99. The system of claim 81, wherein the second storage is further adapted to perform a statistical analysis to detect the WCH and the WCE in the patient.

100. The system of claim 81, wherein the first storage and the second storage are integrated.

101. The system of claim 81, wherein the second storage is further adapted to register the settings in which said system is operated, the settings selected

5 from a group consisting of: the location measurement, the kind of person who performs the measurement, such that the settings are classified in two classes: office settings and other settings; further wherein the system is adapted to diagnose the WCH and the WCE in the patient according to said diagnosis protocol and said settings.

10 102. A method for measuring blood pressure of a patient with elimination of white coat hypertension (WCH) and white coat effect (WCE), said method comprising steps of:

a. obtaining a non-invasive system for diagnosing a WCH and WCE and in a patient, said system consisting of: (i) a blood pressure module

15 consisting of a plethysmograph; (ii) a calculation device with a processor, said calculation device is in communication with the blood pressure module; (iii) a first storage in communication with said calculation device containing programmed executable instructions configured to receive the electrical signal and to process the same; and,

20 (iv) a second storage in communication with the calculation device containing programmed executable instructions adapted to diagnose the WCH and the WCE in the patient and to characterize the profile of the WCH and the WCE in the patient according to a diagnosis protocol; b. measuring changes in a tissue volume in a predetermined location of 25 the patient, and generating an electrical signal associated with said changes in the tissue volume by means of the blood pressure module; c. calculating a set of measurement parameters from said electrical signal, wherein the set of measurement parameters is based on at least one auto-regressive moving average (ARMA) model;

30 d. obtaining a set of clinical parameters of the patient;

e. generating a fixed length data vector consisting of the set of measurement parameters and clinical parameters of the patient;

f. storing the data vector in a communicable database, the database further comprising other data vectors;

g. performing a regression, wherein the classification is based on a SVM algorithm by using the data vector and the database, and thereby estimating the blood pressure of the patient;

i. eliminating the profile of the WCH and the WCE from the estimated blood pressure measurement of the patient, thereby providing a "real" blood pressure measurement which is not biased by the WCH and WCE.

103. The method of claim 102, further comprising a step of characterizing the profile by calculating the time-dependent amplitude of the difference between a blood pressure of the patient in office settings and a blood pressure of the patient in other settings.

104. The method of claim 102, further comprising step of selecting the blood pressure module from a group consisting of: a photoplethysmograph (PPG), a pulse oximeter, an acoustic plethysmograph, a mechanical plethysmograph, or any combination thereof.

105. The method of claim 102, wherein said method does not require an additional step of calibrating the system by means of an additional blood measurement technique.

106. The method of claim 102, wherein the at least one auto-regressive moving average (ARMA) model is performed by means of a Teager-Kaiser operator.

107. The method of claim 102, further comprising step of selecting the clinical parameters of the patient from a group consisting of: sex, age, weight, height, food consumption, time of day, BMI, weight divided by age, weight divided by Heart Rate (HR), height divided by HR, HR divided by age, height divided by age, age divided by the BMI, HR divided by body mass index, or any combination thereof.

108. The method of claim 102, wherein the method further comprises a step of performing an error reduction of the blood pressure estimated by means of the SVM algorithm by the first storage.

5 109. The method of claim 102, further comprising step of selecting the calculation device from a group consisting of: a DSP system, FPGA, microcontroller, or any combination thereof.

110. The method of claim 102, further comprising a step of detecting when the WCH and the WCE are reduced by means of the second storage.

10 111. The method of claim 102, further comprising step of selecting the blood pressure of the patient from a group consisting of: a systolic blood pressure (SBP), a diastolic blood pressure (DBP), a mean arterial pressure (MAP), or any combination thereof.

112. The method of claim 102, wherein the step of differentiating patients with 15 sustained or normalized hypertension and patients with WCH and WCE is performed with a precision of at least a 90%.

113. The method of claim 102, further comprising a step of locating a decrease in the blood pressure of the patient after a predetermined series of readings and over a predetermined period of time according to the diagnostic protocol,

20 and comparing said decrease to a predetermined value, said predetermined value being associated with WCE.

114. The method of claim 113, further comprising a step of selecting the predetermined value from a group consisting of: systolic blood pressure (SBP) is approximately 20 mmHg, diastolic blood pressure (DBP) is

25 approximately 10 mmHg, or any combination thereof.

115. The method of claim 102, further comprising a step of determining that the measured blood pressure after a predetermined series of readings and over a predetermined period of time is above a predetermined level of blood pressure according to the diagnostic protocol, and thereby diagnosing the

30 patient with WCH.

116. The method of claim 115, further comprising the step of selecting the predetermined level from a group consisting of: systolic blood pressure (SBP) is approximately 140 mmHg, diastolic blood pressure (DBP) is approximately 90 mmHg, or any combination thereof.

5 117. The method of claim 102, further comprising the step of selecting the mode of operation of the system from a group consisting of: ambulatory, continuous, discrete, or any combination thereof.

118. The method of claim 102, further comprising the step of selecting the location of operation of the system from a group consisting of: the doctor's0 office, at home, at work, a hospital, or any combination thereof.

119. The method of claim 102, further comprising the step of performing statistical analysis to detect the WCH in the patient by the second storage.

120. The method of claim 102, further comprising the step of registering the settings in which the system is operated, the settings selected from a group5 consisting of: the location measurement, the kind of person who performs the measurement, and thereby classifying the settings in two classes: office settings and other settings, and diagnosing the WCH and the WCE in the patient according to said diagnosis protocol and said settings.

121. The method of claim 102, wherein the profile of the WCH and the WCE in0 the patient is characterized by a time-dependent amplitude of the difference between a blood pressure of the patient in office settings and a blood pressure of the patient in other settings.

122. A non-invasive system for diagnosing white coat hypertension (WCH) and white coat effect (WCE) in a patient, said system comprising: 5 a. a blood pressure module comprising a plethysmograph for measuring changes in a tissue volume in a predetermined location of the patient, and generating an electrical signal associated with said changes in the tissue volume; b. a calculation device with a processor, said calculation device being in0 communication with the blood pressure module; and, c. a first storage in communication with the calculation device containing programmed executable instructions configured to receive the electrical signal and to process the same by performing at least one operation selected from: (i) calculation of a set of measurement parameters from 5 the electrical signal based on at least one auto-regressive moving average (ARMA) model; (ii) generation of a fixed length data vector consisting of the set of measurement parameters and clinical parameters of the patient; (iii) storing in a communicable database the data vector and other data vectors; and, (iv) performing a regression 10 based on a SVM algorithm by using the data vector and the database, such that the blood pressure of the patient is estimated;

wherein the system further comprises a second storage in communication with said calculation device containing programmed executable instructions adapted to diagnose the WCH and the WCE in the patient according to a 15 diagnosis protocol, and to differentiate patients with sustained or normalized hypertension and patients with WCH and WCE.

123. The system of claim 122, wherein the blood pressure module is selected from a group consisting of: a photoplethysmograph (PPG), a pulse oximeter, an acoustic plethysmograph, a mechanical plethysmograph, or any

20 combination thereof.

124. The system of claim 122, wherein said system does not require calibration by means of an additional blood measurement technique.

125. The system of claim 122, wherein the at least one auto-regressive moving average (ARMA) model is performed by means of a Teager-Kaiser operator.

25 126. The system of claim 122, wherein the clinical parameters of the patient are selected from a group consisting of: sex, age, weight, height, food consumption, time of day, BMI, weight divided by age, weight divided by Heart Rate (HR), height divided by HR, HR divided by age, height divided by age, age divided by the BMI, HR divided by body mass index, or any

30 combination thereof.

127. The system of claim 122, wherein the first storage is further adapted for performing an error reduction of the blood pressure estimated by means of the SVM algorithm.

128. The system of claim 122, wherein the calculation device is selected from a group consisting of: a DSP system, FPGA, microcontroller, or any combination thereof.

129. The system of claim 122, wherein the second storage is further adapted to detect when the WCH and the WCE are reduced.

130. The system of claim 122, wherein the blood pressure of the patient is selected from a group consisting of: a systolic blood pressure (SBP), a diastolic blood pressure (DBP), a mean arterial pressure (MAP), or any combination thereof.

131. The system of claim 122, wherein the programmed executable instructions of the second storage are adapted to differentiate between a patient with WCH and WCE, and a patient with sustained or normalized hypertension with a precision of at least approximately 90%.

132. The system of claim 122, wherein the diagnosis protocol is adapted to locate a decrease in the blood pressure of the patient in other settings, after a predetermined series of readings and over a predetermined period of time, and to compare said decrease to a predetermined value of blood pressure measured in office settings, the predetermined value is associated with WCE.

133. The system of claim 132, wherein the predetermined value is selected from a group consisting of: systolic blood pressure (SBP) is approximately 20 mmHg, diastolic blood pressure (DBP) is approximately 10 mmHg, or any combination thereof.

134. The system of claim 122, wherein the diagnosis protocol is adapted to determine that the measured blood pressure after a predetermined series of readings and over a predetermined period of time is substantially above an elevated blood pressure level in office settings and is substantially below a normal blood pressure level in other settings, such that said patient is diagnosed with WCH.

135. The system of claim 133, wherein the elevated blood pressure level is selected from a group consisting of: systolic blood pressure (SBP) is approximately 140 mmHg, diastolic blood pressure (DBP) is approximately 90 mmHg, or any combination thereof; said normal blood pressure level is

136. The system of claim 122, wherein the mode of operation of said system is selected from: ambulatory, continuous, discrete, or any combination thereof.

10 137. The system of claim 122, wherein the system is adapted to be operated in a location selected from a group consisting of: in the doctor's office, at home, at work, a hospital, or any combination thereof.

138. The system of claim 122, wherein the second storage further adapted to perform a statistical analysis to detect the WCH and the WCE in the patient.

15 139. The system of claim 122, wherein the first storage and the second storage are integrated.

140. The system of claim 122, wherein the second storage is further adapted to register the settings in which said system is operated, the settings selected from a group consisting of: the location measurement, the kind of person

20 who performs the measurement, such that the settings are classified to two classes: office settings and other settings; further wherein the system is adapted to diagnose the WCH and the WCE in the patient according to said diagnosis protocol and said settings.

141. A method for diagnosing white coat hypertension (WCH) and white Coat 25 Effect (WCE) in a patient, said method comprising steps of:

a. obtaining a non-invasive system for diagnosing WCH and WCE and in a patient, said system comprising: (i) a blood pressure module consisting of a plethysmograph; (ii) a calculation device with a processor, said calculation device is in communication with the blood 30 pressure module; (iii) a first storage in communication with said calculation device containing programmed executable instructions configured to receive the electrical signal and to process the same; and, (iv) a second storage in communication with the calculation device containing programmed executable instructions adapted to detect the WCH in the patient according to a diagnosis protocol;

5 b. measuring changes in a tissue volume in a predetermined location of the patient, and generating an electrical signal associated with said changes in the tissue volume by means of the blood pressure module; c. calculating of a set of measurement parameters from the electrical signal based on at least one auto-regressive moving average (ARMA)

10 model;

d. obtaining a set of clinical parameters of the patient;

f. storing the data vector in a communicable database, said database 15 further comprising other data vectors;

g. performing a regression based on a SVM algorithm by using the data vector and the database, and thereby calculating the blood pressure of the patient;

h. diagnosing the WCH and the WCE in the patient according to a 20 diagnostic protocol by means of the second storage; and,

142. The method of claim 141, further comprising the step of selecting the blood pressure module from a group consisting of: a photoplethysmograph (PPG),

25 a pulse oximeter, an acoustic plethysmograph, a mechanical plethysmograph, or any combination thereof.

143. The method of claim 141, wherein said method does not require an additional step of calibrating the system by means of an additional blood measurement technique.

30 144. The method of claim 141, wherein the at least one auto-regressive moving average (ARMA) model is performed by means of a Teager-Kaiser operator.

145. The method of claim 141, further comprising the step of selecting the clinical parameters of the patient from a group consisting of: sex, age, weight, height, food consumption, time of day, BMI, weight divided by age,

5 weight divided by Heart Rate (HR), height divided by HR, HR divided by age, height divided by age, age divided by the BMI, HR divided by body mass index, or any combination thereof.

146. The method of claim 141, wherein the method further comprises a step of performing error reduction of the blood pressure calculated by means of the

10 SVM algorithm by the first storage.

147. The method of claim 141, further comprising the step of selecting the calculation device from a group consisting of: a DSP system, FPGA, microcontroller, or any combination thereof.

148. The method of claim 141, further comprising a step of detecting when the 15 WCH and the WCE is reduced by the second storage.

149. The method of claim 141, further comprising the step of selecting the blood pressure of the patient from a group consisting of: a systolic blood pressure (SBP), a diastolic blood pressure (DBP), a mean arterial pressure (MAP), or any combination thereof.

20 150. The method of claim 141, wherein the step of differentiating patients with sustained or normalized hypertension and patients with WCH and WCE is performed with a precision of at least a 90%.

151. The method of claim 141, further comprising a step of locating a decrease in the blood pressure of the patient after a predetermined series of readings

25 and over a predetermined period of time according to the diagnostic protocol, and comparing the decrease with a predetermined value, said predetermined value is associated with WCE.

152. The method of claim 151, further comprising a step of selecting the predetermined value from a group consisting of: systolic blood pressure

153. The method of claim 141, further comprising a step of determining that the measured blood pressure after a predetermined series of readings and over a predetermined period of time is above a predetermined level of blood pressure according to the diagnostic protocol, and thereby diagnosing the

5 patient with WCH.

154. The method of claim 153, further comprising the step of selecting the predetermined level from a group consisting of: systolic blood pressure (SBP) is approximately 140 mmHg, diastolic blood pressure (DBP) is approximately 90 mmHg, or any combination thereof.

10 155. The method of claim 141, further comprising the step of selecting the mode of operation of the system is selected from a group consisting of: ambulatory, continuous, discrete, or any combination thereof.

156. The method of claim 141, further comprising the step of selecting the location of operation of the system from a group consisting of: the doctor's

15 office, at home, at work, a hospital, or any combination thereof.

157. The method of claim 141, further comprising the step of performing statistical analysis to detect the WCH in the patient by means of the second storage.

158. The method of claim 141, further comprising the step of registering the 20 settings in which the system is operated, said settings selected from a group consisting of: the location measurement, the kind of person who performs the measurement, and thereby classifying the settings in two classes: office settings and other settings, and diagnosing the WCH and the WCE in the patient according to said diagnosis protocol and said settings.

25 159. A non-invasive system for measuring blood pressure of a patient with elimination of white coat hypertension (WCH) and white coat effect (WCE), said system comprising:

e. a plesthymograph based blood pressure system for estimation of the patient's blood pressure; and,

30 f. a second storage in communication with said calculation device containing programmed executable instructions adapted to: (i) diagnose the WCH and the WCE in the patient; (ii) characterize the profile of the WCH and the WCE in the patient according to a diagnosis protocol; and, (iii) to provide a "real" blood pressure measurement which is not biased by the WCH and WCE by eliminating the profile of the WCH and the 5 WCE from the estimated blood pressure measurement of the patient; wherein the estimation of the patient's blood pressure is performed by means of a SVM algorithm which is adapted to receive a fixed length data vector comprising a set of measurement parameters and clinical parameters, said measurement parameters are based on at least one auto-regressive moving 10 average (ARMA) model of the signals received from the PPG, the clinical parameters are received from the patient.

160. A method for measuring blood pressure of a patient with elimination of white coat hypertension (WCH) and white coat effect (WCE), said method comprising steps of:

15 3. obtaining a plesthymograph based blood pressure system for estimation of the patient's blood pressure;

4. estimating the blood pressure of the patient by means of said system;

5. diagnosing the WCH and the WCE in the patient according to a diagnostic protocol by a second storage located within the system; and,

20 6. eliminating the profile of the WCH and the WCE from the estimated blood pressure measurement of the patient, thereby providing a "real" blood pressure measurement which is not biased by the WCH and WCE.

wherein the step of estimation of the blood pressure of the patient is 25 performed by means of a SVM algorithm which is adapted to receive a fixed length data vector consisting of a set of measurement parameters and clinical parameters, said measurement parameters are based on at least one auto-regressive moving average (ARMA) model of the signals received from the PPG, the clinical parameters are received from the patient.

30 161. A non-invasive system for diagnosing white coat hypertension (WCH) and white coat effect (WCE) in a patient, said system comprising: a. a plesthymograph based blood pressure system for estimation of the patient's blood pressure; and,

wherein the estimation of the patient's blood pressure is performed by means of a SVM algorithm which is adapted to receive a fixed length data vector consisting of a set of measurement parameters and clinical parameters, said measurement parameters are based on at least one auto-regressive moving average (ARMA) model of the signals received from the PPG, the clinical parameters are received from the patient.

162. A non-invasive system for diagnosing white coat hypertension (WCH) and white coat effect (WCE) in a patient, said system comprising:

a. a PPG based blood pressure system for determining the patient's blood pressure, said determination being performed by means of a SVM algorithm adapted to receive a fixed length data vector consisting of a set of measurement parameters and clinical parameters, the measurement parameters are based on at least one auto-regressive moving average (ARMA) model of the signals received from the PPG, the clinical parameters are received from the patient; and

wherein the non-invasive system for diagnosing white coat hypertension (WCH) and white coat effect (WCE) in a patient system does not require calibration by means of an additional blood measurement technique.