Method and system to assess disease using dynamical analysis of biophysical signal

Abstract

To provide a method and a system to assess a disease by using a dynamical analysis of suitable biophysical signals.SOLUTION: An exemplified method and system characterize and identify biophysical signals, for example, non-linear dynamic characteristics such as photoplethysmographic and / or cardiac signals (for example, statistical and / or geometric property originated in Liapunov index (LE), correlated dimension, entropy (K2), or a Poincare map), and facilitate one or more dynamical analyses that can predict presence and / or localization of a disease or a disease state, or its index (including, for example, but not limited to, coronary artery disease, heart failure (including, but not limited to, elevated or abnormal left ventricular end-diastolic pressure disease) and pulmonary hypertension).SELECTED DRAWING: None

Description

[Technical field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This International PCT application claims priority to and the benefit of U.S. Provisional Patent Application No. 62 / 863,005, entitled "Method and System to Assess Disease Using Dynamical Analysis of Cardiac and Photoplethysmographic Signals," filed June 18, 2019, and U.S. Provisional Patent Application No. 62 / 862,991, entitled "Method and System to Assess Disease Using Dynamical Analysis of Biophysical Signals," filed June 18, 2019, each of which is incorporated by reference in its entirety.

[0002] The present disclosure generally relates to non-invasive methods and systems for characterizing one or more physiological systems and their associated functions, activities, and abnormalities. More specifically, in one aspect, the present disclosure relates to non-invasive methods that utilize plethysmography-related measurements, alone or in combination with other types of measurements of physiological phenomena and systems, to predict and / or detect the presence, absence, severity, and / or localization of, among other cardiovascular, pulmonary, and cardiopulmonary diseases, processes, or conditions. In another aspect, the present disclosure relates to non-invasive methods that utilize cardiac-related measurements therefor. In another aspect, the present disclosure relates to non-invasive methods that utilize both plethysmography-related and cardiac-related measurements therefor. [Background technology]

[0003] The term "biophysical signal" encompasses any physiological signal from which information may be obtained, as described in more detail below. Without wishing to be limiting, biophysical signals may be characterized, in part, by the form of energy such signals take (e.g., electrical, acoustic, chemical, thermal, magnetic, optical, etc.), by one or more physiological systems to which they may occur and / or be associated (e.g., circulatory / cardiovascular, neurological, respiratory, etc.), by associated organ system, by tissue type, by cell type, by cellular components such as organelles, etc. (including combinations thereof). Biophysical signals may be obtained passively or actively, or both.

[0004] Often, biophysical signals are acquired in conjunction with or through invasive or minimally invasive techniques (e.g., via catheters) and / or the use of radiation (e.g., nuclear imaging), exercise / stress (e.g., treadmill or nuclear stress tests) and / or administration of pharmacological and / or other agents (e.g., vasodilators, contrast agents). These various modalities may moderately or significantly increase the cost of acquiring such signals, as they may need to be administered in specialized environments, often via expensive equipment that often requires the patient to travel and even occasionally to stay overnight, e.g., in a hospital or hotel. Some of these modalities may increase the risk to the patient for side effects, such as, e.g., infections or allergic reactions. Some modalities expose the patient to doses of radiation that are undesirable. And, for example, in the case of exercise or treadmill, the tests may induce moderate or even severe adverse events (e.g., myocardial infarction) that would not have occurred otherwise. Furthermore, these various modalities typically increase the time required to confirm a patient's health status, disease, or condition, whose biophysical signals are being characterized, sometimes on the order of weeks or months, often for patients who have or are suffering from moderate or even severe health conditions. This leads to lost work productivity and higher overall health care costs for society. Such delays can also exact financial tolls on the patient (which may itself be detrimental to the patient's health), their family, friends, and other caregivers who attend to the patient's needs.

[0005] As such, it is desirable to derive information from biophysical signals that minimizes or even eliminates the need to use invasive and / or minimally invasive techniques, radiation, exercise / stress, and / or pharmacological and / or other agents, such that assessing (e.g., predicting and / or detecting) the presence, absence, severity, and (in some cases) localization of various diseases, lesions, or pathologies in mammalian or non-mammalian organisms may be accomplished more safely, at lower cost, and / or in less time than current methods and systems provide.

[0006] The methods and systems described herein address this need and may be used in a wide variety of environments - from hospitals to emergency rooms, laboratories, battlefields or remote settings, at the point of care with a patient's primary care physician or other caregiver, and even at home, for a wide variety of clinical and even research needs. Without being limiting, the following description provides exemplary methods and systems for such use in the context of cardiac or cardiovascular related disease states and conditions; particularly, pulmonary hypertension (PH) in its various forms, coronary artery disease (CAD) in its various forms, and heart failure in its various forms. Summary of the Invention [Means for solving the problem]

[0007] The illustrated methods and systems facilitate one or more kinetic analyses that can characterize and identify nonlinear dynamic properties (e.g., Lyapunov exponent (LE), correlation dimension, entropy (K2), or statistical and / or geometric properties derived from Poincaré maps) of biophysical signals, such as photoplethysmography signals and / or cardiac signals, and predict the presence and / or localization of a disease or pathology or indicator thereof (e.g., including but not limited to coronary artery disease, heart failure (including but not limited to abnormal left ventricular end-diastolic pressure disease), and pulmonary hypertension, among others).

[0008] In some embodiments, dynamical systems and nonlinear dynamical features are extracted, such as the entropy rate "K2", the correlation dimension of the fractal dimension "D2", the Lyapunov exponent ("LE"), mutual information (MI) and correlation (XC). In some embodiments, one or more features associated with the Poincaré map are extracted.

[0009] As used herein, a "cardiac signal" refers to one or more signals associated with the structure, function, and / or activity of the cardiovascular system, including the electrical / electrochemical conduction aspects of the signal, such as, for example, causing contraction of the cardiac muscle. Cardiac signals, in some embodiments, can include electrocardiographic signals, such as those obtained via, for example, an electrocardiogram (ECG) or other modalities.

[0010] As used herein, a "photoplethysmographic signal" refers to a signal waveform obtained from a light sensor, such as light having wavelengths in the red and infrared spectrum, that corresponds to measured changes in light absorption by oxygenated and deoxygenated hemoglobin. In some embodiments, a photoplethysmographic signal includes a raw signal obtained via a pulse oximeter or photoplethysmogram (PPG). In some embodiments, a photoplethysmographic signal is obtained from a custom or dedicated apparatus or circuitry (including off-the-shelf devices) configured to obtain such a signal waveform for purposes of diagnosing a disease or abnormal condition. Photoplethysmography signals typically include red photoplethysmography signals (e.g., electromagnetic signals in the visible light spectrum having most predominantly wavelengths between about 625 and 740 nanometers) and infrared photoplethysmography signals (e.g., electromagnetic signals extending up to about 1 mm from the nominal red end of the visible spectrum), although other spectra, such as near infrared, blue and green, may be used in different combinations depending on the type and / or mode of photoplethysmography-related measurement being used.

[0011] "Biophysical signals" include any physiological signal from which information can be obtained, including but not limited to cardiac, neurological, or photoplethysmographic signals. By way of example and not intended to be limiting, biophysical signals may be classified into types or categories that can include, for example, electrical (e.g., signals associated with specific cardiac and nervous systems that can be observed, identified, and / or quantified by techniques such as measurements of voltage / potential, impedance, resistance, conductance, current, etc. in various domains, such as time and / or frequency), magnetic, electromagnetic, optical (e.g., signals that can be observed, identified, and / or quantified by techniques such as reflectance, interferometry, spectroscopy, absorbance, transmission, visual observation, photoplethysmography, etc.), acoustic, chemical, mechanical (e.g., signals associated with flow, pressure, motion, vibration, displacement, strain), thermal, and electrochemical (e.g., signals that can be correlated to the presence of a specific analyte, such as glucose). Biophysical signals may in some cases be described in the context of physiological systems (e.g., respiratory system, circulatory system (cardiovascular, pulmonary), nervous system, lymphatic system, endocrine system, digestive system, excretory system, muscular system, skeletal system, renal / urinary / excretory system, immune system, integumentary / endocrine system, and reproductive system), organ systems (e.g., signals that may be specific to the heart and lungs because they work together), or in the context of tissues (e.g., muscle, fat, nerve, connective tissue, bone), cells, organelles, molecules (e.g., water, proteins, fats, sugars, gases, free radicals, inorganic ions, minerals, acids, and other compounds, elements, and their subatomic components). Unless otherwise stated, the term "obtaining a biophysical signal" generally refers to any passive or active means of obtaining a biophysical signal from a physiological system, such as a mammalian or non-mammalian organism. Passive and active biophysical signal acquisition generally refers to the observation of the natural or induced electric, magnetic, optical, and / or acoustic emittance of bodily tissues. Non-limiting examples of passive and active biophysical signal acquisition means include, for example, voltage / potential, current, magnetic, optical, acoustic, and other non-active methods of observing the natural emittance of bodily tissues, and in some cases, inducing such emittance.Non-limiting examples of passive and active biophysical signal acquisition means include, for example, ultrasound, radio waves, microwaves, infrared and / or visible light (e.g., for use in pulse oximetry or photoplethysmography), visible light, ultraviolet light, and other methods of actively interrogating body tissues that do not involve ionizing energy or radiation (e.g., x-rays). Active biophysical signal acquisition may include excitation-emission spectroscopy (e.g., including excitation-emission fluorescence). Active biophysical signal acquisition may also include transmitting ionizing energy or radiation (e.g., x-rays) (also referred to as "ionizing biophysical signals") to body tissues. Passive and active biophysical signal acquisition means may be performed in conjunction with invasive procedures (e.g., via surgery or invasive radiological intervention protocols) or non-invasively (e.g., via imaging).

[0012] The methods and systems described in various embodiments herein are not so limited and may be utilized in any context with another physiological system or systems of a living body, organs, tissues, cells, etc. By way of example only, two types of biophysical signals that may be useful in the context of the cardiovascular system include cardiac signals that may be obtained via conventional electrocardiogram (ECG / EKG) equipment, bipolar wideband biopotential (cardiac) signals that may be obtained from other equipment, such as those described herein, and signals that may be obtained by various plethysmography techniques, such as photoplethysmography.

[0013] In the context of the present disclosure, techniques for acquiring and analyzing biophysical signals are described for use in diagnosing the presence, absence, localization (where applicable), and / or severity of certain disease states or pathologies associated with or affecting the cardiovascular (or cardiac) system, including, inter alia, pulmonary hypertension (PH), coronary artery disease (CAD), and heart failure (e.g., left or right-sided heart failure).

[0014] Pulmonary hypertension, heart failure, and coronary artery disease are three diseases / conditions related to the cardiovascular or cardiac system. Pulmonary hypertension (PH) generally refers to high blood pressure in the arteries of the lungs and can include a wide range of conditions. PH typically has a complex, multifactorial etiology and an insidious clinical onset with variable severity. PH can progress to complications, such as right heart failure, but is often fatal. The World Health Organization (WHO) classifies PH into five groups or types. The first PH group classified by the WHO is pulmonary arterial hypertension (PAH). PAH is a chronic, currently incurable disease that, among other things, causes the walls of the arteries in the lungs to stiffen and become rigid. PAH requires, at a minimum, cardiac catheterization for diagnosis. PAH is characterized by vasculopathy of the pulmonary arteries and is defined as a mean pulmonary artery pressure of 25 mmHg or greater on cardiac catheterization. One form of pulmonary arterial hypertension is known as idiopathic pulmonary arterial hypertension, which is PAH that occurs without a clear cause. Among others, subcategories of PAH include hereditary PAH, drug and toxin-induced PAH, and PAH associated with other systemic diseases, such as connective tissue disease, HIV infection, portal hypertension, and congenital heart disease. PAH includes all causes that lead to structural narrowing of the pulmonary blood vessels. In PAH, progressive narrowing of the pulmonary arterial bed results from an imbalance of vasoactive mediators, including prostacyclin, nitric oxide, and endothelin-1. This leads to increased right ventricular afterload, right heart failure, and premature death. The second PH group classified by the WHO is pulmonary hypertension due to left heart disease. This group of disorders is generally characterized by problems on the left side of the heart. Such problems can lead to changes in the pulmonary arteries over time. Specific subgroups include left ventricular systolic dysfunction, left ventricular diastolic dysfunction, valvular disease, and finally, congenital cardiomyopathies and obstructions not due to valvular disease. Treatment of this second PH group tends to focus on the underlying problem (e.g., surgery to replace heart valves, various drug therapies, etc.). The third PH group, as classified by the WHO, is large and diverse, and is generally associated with pulmonary disease or hypoxia. Subgroups include chronic obstructive pulmonary disease, interstitial lung disease, sleep-disordered breathing, alveolar hypoventilation disorder, chronic high altitude exposure, and developmental lung disease.The fourth group of PH is classified by the WHO as chronic thromboembolic pulmonary hypertension, which occurs when a blood clot invades or forms in the lungs and blocks blood flow through the pulmonary arteries. The fifth group of PH is classified by the WHO as including a subgroup of rare disorders that lead to PH, such as hematological disorders, systemic disorders, such as sarcoidosis with pulmonary involvement, metabolic disorders, and other diseases. The mechanism of PH in this fifth group is poorly understood.

[0015] PH, in all its forms, can be difficult to diagnose in a routine examination because its most common symptoms (shortness of breath, fatigue, chest pain, edema, heart palpitations, dizziness) are associated with so many other conditions. Blood tests, chest x-rays, electrocardiograms and echocardiograms, pulmonary function tests, exercise stress tests, and nuclear scans are all used in a variety of ways to help doctors diagnose PH in its specific forms. As mentioned above, the "gold standard" for diagnosing PH, and especially PAH, is cardiac catheterization of the right side of the heart by directly measuring the pressure in the pulmonary artery. If PAH is suspected in a subject, one of several investigations may be performed to confirm the condition (e.g., electrocardiogram, chest x-ray, pulmonary function tests, among others). Right heart stress on an electrocardiogram and evidence of significant pulmonary artery or cardiac hypertrophy on a chest x-ray are typically seen. However, a normal electrocardiogram and chest x-ray do not necessarily exclude a diagnosis of PAH. Further tests may be required to confirm the diagnosis and determine the cause and severity. For example, blood tests, exercise tests, and overnight oximetry tests may be performed. In addition, imaging tests may also be performed. Examples of imaging tests include isotope perfusion lung scan, high-resolution computed tomography, computed tomography pulmonary angiography, and magnetic resonance pulmonary angiography. If these (and possibly other) non-invasive investigations support the diagnosis of PAH, right heart catheterization is typically required to confirm the diagnosis by directly measuring pulmonary pressure. It also allows for measurement of cardiac output and estimation of left atrial pressure using pulmonary artery wedge pressure. While non-invasive techniques exist to determine whether PAH may be present in a subject, these techniques cannot reliably confirm the diagnosis of PAH unless invasive right heart catheterization is performed. Aspects and embodiments of methods and systems for assessing PH are disclosed in commonly owned U.S. patent application Ser. No. 16 / 429,593, the entirety of which is hereby incorporated by reference.

[0016] Heart failure affects nearly 6 million people in the United States alone, with over 870,000 people diagnosed with heart failure each year. The term "heart failure" (sometimes referred to as congestive heart failure or CHF) generally refers to a chronic, progressive condition or process in which the heart muscle cannot pump enough blood to meet the body's needs because it becomes weak or stiff, or because there is a defect that prevents proper circulation. This can lead to, for example, blood and fluid backing up in the lungs, swelling, fatigue, dizziness, fainting, rapid heartbeat and / or arrhythmia, dry cough, nausea, and shortness of breath.

[0017] HF is a complex disorder encompassing a wide range of symptoms that can result from multiple diverse pathologies. This clinical syndrome can result from any structural or functional cardiac alteration that impairs the ability of the ventricles to fill or empty with blood. Patients typically fall into two distinct groups, grouped by left ventricular (LV) ejection fraction (LVEF): 1) HF with reduced LVEF (HFrEF [LVEF ≦40%]) and 2) HF with preserved LVEF (HFpEF [LVEF ≧50%]). While the defining characteristic of HFrEF is systolic dysfunction, in contrast, the defining characteristic of HFpEF is diastolic dysfunction, and both can occur to varying degrees within both HFrEF and HFpEF. Of the more than 6 million Americans with this diagnosis, there is an approximately equal distribution between these two categories. The two groups also have similar mortality rates at 5 years, with estimates ranging between 50-75%.

[0018] Common causes of heart failure are coronary artery disease (CAD), hypertension, cardiomyopathy, arrhythmias, kidney disease, heart defects, obesity, tobacco use, and diabetes. Diastolic heart failure (DHF), left or left-sided heart failure / disease (also referred to as left ventricular heart failure), right or right-sided heart failure / disease (also referred to as right ventricular heart failure), and systolic heart failure (SHF) are common types of heart failure.

[0019] Left-sided heart failure is further classified into two main types: systolic dysfunction (or heart failure with reduced ejection fraction or reduced left ventricular function) and diastolic dysfunction / dysfunction (or heart failure with preserved ejection fraction or preserved left ventricular function). Procedures and techniques commonly used to determine if a patient has left-sided heart failure include cardiac catheterization, x-rays, echocardiograms, electrocardiograms (EKGs), electrophysiological studies, radionuclide imaging, and various treadmill tests (peak VO 2 Ejection fraction (EF) is a measurement expressed as the percentage of blood volume that the ventricle (and left ventricle in cases of left-sided heart failure) pumps with each contraction, and is often obtained non-invasively via echocardiography. Normal left ventricular ejection fraction (LVEF) ranges from about 55% to about 70%.

[0020] When contractile dysfunction occurs, the left ventricle cannot contract forcefully enough to circulate blood normally throughout the body, thereby depriving the body of its normal supply of blood. As the left ventricle pumps harder to compensate, it becomes weaker and thinner. As a result, blood backs up into organs, causing fluid retention in the lungs and / or swelling in other parts of the body. Echocardiography, magnetic resonance imaging, and nuclear medicine scans (e.g., multi-gated acquisition) are techniques used to non-invasively measure the ejection fraction (EF), expressed as a percentage of the volume of blood pumped by the left ventricle relative to the filling capacity of the left ventricle, to aid in the diagnosis of contractile dysfunction. In particular, a left ventricular ejection fraction (LVEF) below 55% indicates that the heart's pumping ability is below normal, and in severe cases can be measured as less than about 35%. In general, a diagnosis of contractile dysfunction can be made or aided when these LVEF values ​​are below normal.

[0021] When diastolic heart failure occurs, the left ventricle becomes stiff or thickened and loses its ability to relax normally, which in turn causes the lower left ventricle of the heart to not fill with blood properly. This reduces the amount of blood pumped to the body. Over time, this causes blood to pool inside the left atrium and then in the lungs, leading to fluid retention and symptoms of heart failure. In this case, the LVEF value tends to remain within the normal range. As such, other tests, such as invasive catheterization, can be used to measure left ventricular end-diastolic pressure (LVEDP) to aid in the diagnosis of diastolic heart failure as well as other forms of heart failure with preserved EF. Typically, LVEDP is measured directly by placing a catheter in the left ventricle, or indirectly by placing a catheter in the pulmonary artery to measure pulmonary capillary wedge pressure. Such catheter techniques, by their nature, increase the risk of infection and other complications to the patient and tend to be expensive. As such, non-invasive methods and systems for determining or estimating LVEDP in diagnosing the presence or absence and / or severity of diastolic heart failure, as well as the myriad other forms of heart failure with preserved EF, are desirable. Also desirable are non-invasive methods and systems for diagnosing the presence or absence and / or severity of diastolic heart failure, as well as the myriad other forms of heart failure with preserved EF, without necessarily involving the determination or estimation of an abnormal LVEDP. Embodiments of the present disclosure address all of these needs.

[0022] Right-sided heart failure often occurs due to left-sided heart failure, when a weakened and / or stiffened left ventricle loses the strength to efficiently pump blood to the rest of the body. As a result, fluid is pushed back through the lungs, weakening the right side of the heart and causing right-sided heart failure. This backflow backs up in the veins, causing fluid swelling in the legs, ankles, digestive tract, and liver. In other cases, certain lung diseases, such as chronic obstructive pulmonary disease and pulmonary fibrosis, can cause right-sided heart failure even though the left side of the heart is functioning normally. Commonly used procedures and techniques to determine whether a patient has left-sided heart failure include blood tests, cardiac CT scans, cardiac catheterization, x-rays, coronary angiograms, echocardiograms, electrocardiograms (EKGs), myocardial biopsies, pulmonary function tests, and various forms of stress tests, such as treadmill tests.

[0023] Pulmonary hypertension is closely associated with heart failure. As mentioned above, PAH (first WHO PH group) can lead to increased right ventricular afterload, right heart failure, and premature death. PH due to left heart failure (second WHO PH group) is considered to be the most common cause of PH.

[0024] Ischemic heart disease (also known as cardiac ischemia or myocardial ischemia) and related pathologies or lesions can also be estimated or diagnosed using the techniques disclosed herein. Ischemic heart disease is a disease or group of diseases characterized by reduced blood supply to the heart muscle, usually due to coronary artery disease (CAD). CAD is closely related to and is the most common cause of heart failure. CAD typically occurs when the intima in the coronary arteries that supply blood to the myocardium, or heart muscle, develops atherosclerosis (hardening or stiffening of the intima and the accumulation of plaque therein, often accompanied by abnormal inflammation). Over time, CAD can also weaken the heart muscle, contributing to, for example, angina, myocardial infarction (cardiac arrest), heart failure, and arrhythmia. Arrhythmia is an abnormal heart rhythm that can include any change from the normal sequence of electrical conduction in the heart, which in some cases can lead to cardiac arrest. The evaluation of PH, heart failure, CAD, and other diseases and / or conditions can be complex, with many invasive techniques and tools being used to assess the presence and severity of the above-mentioned conditions. Moreover, the commonality among the symptoms of these diseases and / or conditions, as well as the fundamental relationship between the respiratory and cardiovascular systems - due to the fact that they work together to oxygenate the body's cells and tissues - points to complex physiological interrelationships that can be exploited to improve the detection and ultimate treatment of such diseases and / or conditions. In this context, conventional methods for evaluating these biophysical signals still pose significant challenges in providing medical practitioners with the tools to accurately detect / diagnose the presence or absence of such diseases and conditions.

[0025] For example, in electrocardiography - the field of cardiology that analyzes the electrical activity of the heart to obtain information about its structure and function - it has been observed that significant ischemic heart disease can alter the ventricular conduction properties of the myocardium in the perfusion bed downstream of the stenosis or occlusion of the coronary arteries, with lesions appearing in different parts of the heart and at different stages of severity, making accurate diagnosis difficult. Furthermore, while the electrical conduction characteristics of the myocardium can vary from person to person, other factors, such as measurement variability associated with the placement of the measurement probe, and parasitic losses associated with the probe and its related components, can also affect the biophysical signals captured during cardiac electrophysiology testing. Still further, when the conduction properties of the myocardium are captured as relatively long cardiac phase gradient signals, they can exhibit complex nonlinear variability that cannot be efficiently captured by traditional modeling techniques.

[0026] Indeed, the illustrated methods and systems facilitate one or more dynamic analyses that can characterize and identify nonlinear dynamic properties (e.g., Lyapunov exponent (LE), correlation dimension, entropy (K2), or statistical and / or geometric properties derived from Poincaré maps) of biophysical signals, such as photoplethysmography signals and / or cardiac signals, and predict the presence and / or localization of a disease or pathology or indicator thereof (e.g., including but not limited to, coronary artery disease, heart failure (including but not limited to abnormal left ventricular end-diastolic pressure disease), and pulmonary hypertension, among others).

[0027] In some embodiments, the dynamic feature comprises at least a determined correlation dimension of the acquired photoplethysmography signal (e.g., red photoplethysmography signal or infrared photoplethysmography signal). Notably, this assessed dynamic feature has been observed to be associated with abnormal left ventricular end-diastolic pressure (LVEDP) and may be used to predict the presence, absence, and / or severity of such pathologies in a clinical setting. As discussed above, LVEDP is considered a measure of ventricular performance, particularly left ventricular performance, and is often used to identify patients at increased risk of developing late clinical symptoms of heart failure (HF). Elevated LVEDP is commonly observed following myocardial infarction; however, it has been recognized to be an independent predictor of subsequent HF risk. In some embodiments, the dynamic feature comprises at least an assessed characteristic of a Poincaré map object derived from the waveforms of adjacent cardiac cycles. The assessed characteristic, in some embodiments, comprises a ratio of perimeter values ​​of the Poincaré map object (e.g., from infrared measurements). In some embodiments, the property evaluated includes a surface area of ​​the Poincaré map object.

[0028] In one aspect, a method for non-invasively assessing a disease or abnormal condition in a subject is disclosed, the method including: obtaining, by one or more processors (e.g., from a stored database or from a measurement system), a biophysical signal dataset (e.g., one or more photoplethysmographic signals or cardiac signals) of the subject; determining, by the one or more processors, one or more kinetic characteristics of the biophysical signal dataset; and determining, by the one or more processors, one or more estimates of the presence, absence, localization, and / or severity of the disease or condition based on the determined one or more kinetic characteristics.

[0029] In some embodiments, the presence, absence, and / or severity of a disease or condition may be assessed based on an assessment of left ventricular end-diastolic pressure (LVEDP), including elevated or abnormal LVEDP.

[0030] In some embodiments, the disease state or condition comprises significant coronary artery disease.

[0031] In some embodiments, the disease state or condition comprises pulmonary hypertension.

[0032] In some embodiments, the disease state or condition comprises pulmonary arterial hypertension (PAH).

[0033] In some embodiments, the disease state or condition comprises pulmonary hypertension due to left heart disease.

[0034] In some embodiments, the disease state or condition comprises a rare disorder that can lead to pulmonary hypertension.

[0035] In some embodiments, the disease state or condition comprises left ventricular heart failure or left-sided heart failure.

[0036] In some embodiments, the disease state or condition comprises right ventricular heart failure or right-sided heart failure.

[0037] In some embodiments, the disease state or condition comprises systolic heart failure (SHF).

[0038] In some embodiments, the disease state or condition comprises diastolic heart failure (DHF).

[0039] In some embodiments, the disease state or condition comprises ischemic heart disease.

[0040] In some embodiments, the disease state or condition comprises arrhythmia.

[0041] In some embodiments, the method further includes determining, by the one or more processors, one or more second estimates of the presence, absence, localization, and / or severity of two or more of the disease or condition.

[0042] In some embodiments, the kinetic property is selected from the group consisting of entropy value (K2), fractal dimension (D2), Lyapunov exponent, autocorrelation, automutual information, cross-correlation, and mutual information.

[0043] In some embodiments, the obtained biophysical signal dataset comprises one or more red photoplethysmography signals.

[0044] In some embodiments, the obtained biophysical signal dataset comprises one or more infrared photoplethysmography signals.

[0045] In some embodiments, the obtained biophysical signal dataset comprises one or more cardiac signals.

[0046] In some embodiments, the method further includes causing the one or more processors to generate a visualization of the estimate of the presence, absence, localization, and / or severity of the disease or condition, where the generated visualization is rendered and displayed on a display of a computing device (e.g., a computing workstation; a surgical, diagnostic, or instrumentation apparatus) and / or presented in a report (e.g., an electronic report).

[0047] In some embodiments, the method further includes determining, by the one or more processors, a histogram map of variance in periodicity in the biophysical signal dataset, where the histogram map is used in determining an estimate for the presence, absence, localization, and / or severity of the disease or condition.

[0048] In some embodiments, the method further includes determining, by the one or more processors, a Poincaré map of the obtained biophysical signal dataset; determining, by the one or more processors, an alpha shape object of the Poincaré map; and determining, by the one or more processors, one or more geometric properties of the alpha shape object, wherein the one or more determined geometric properties are used in determining an estimate for the presence, absence, localization, and / or severity of a disease or condition.

[0049] In some embodiments, the one or more determined geometric properties further include two or more properties selected from the following group: a density value of the alpha shaped object; a convex surface area value of the alpha shaped object; a perimeter value of the alpha shaped object; a porosity value of the alpha shaped object; and a void area value of the alpha shaped object.

[0050] In some embodiments, the one or more determined geometric properties further include two or more properties selected from the following group: a length of semi-axis "a" for the estimated maximum cluster ellipse of the Poincaré map; a length of semi-axis "b" for the estimated maximum cluster ellipse of the Poincaré map; a length of the longest axis of the estimated maximum cluster ellipse of the Poincaré map; a length of the shortest axis of the estimated maximum cluster ellipse of the Poincaré map; an estimated number of clusters in the Poincaré map; an estimated number n of kernel density modes in the histogram map; and an estimated Searles Bimodality Coefficient value from the histogram map.

[0051] In another aspect, a method for non-invasively assessing a disease or abnormal condition in a subject is disclosed, the method including: obtaining, by one or more processors (e.g., from a stored database or from a measurement system), a biophysical signal dataset (e.g., a photoplethysmography signal) of the subject; determining, by one or more processors, a Poincaré map of variance in the biophysical signal dataset; determining, by one or more processors, an alpha shape object of the Poincaré map; determining, by one or more processors, one or more geometric properties of the alpha shape object; and determining, by the one or more processors, an estimate for the presence, absence, localization, and / or severity of the disease or condition based on the determined one or more geometric properties, where the disease state includes the presence of coronary artery disease (e.g., significant coronary artery disease) or elevated / abnormal left ventricular end-diastolic pressure.

[0052] In some embodiments, the determined Poincaré map is generated by plotting photoplethysmography signal peaks from a first time x-1 to a second time x on a first axis and from a second time x to a third time x+1 on a second axis.

[0053] Indeed, in a Poincaré map, references to time are synonymous and thus can be used interchangeably with respect to data points in a given data set.

[0054] In another aspect, a system for non-invasively assessing a disease or abnormal condition in a subject is disclosed, the system comprising: a processor; and A memory having instructions stored thereon, where execution of the instructions by a processor causes the processor to: obtain (e.g., from a stored database or from a measurement system) a biophysical signal dataset (e.g., one or more photoplethysmographic signals or cardiac signals) of the subject; determine one or more kinetic characteristics of the biophysical signal dataset; and determine one or more estimates of the presence, absence, localization, and / or severity of a disease or condition based on the one or more kinetic characteristics.

[0055] In some embodiments, execution of the instructions by the processor further causes the processor to determine one or more second estimates of the presence, absence, localization, and / or severity of two or more of the disease or condition.

[0056] In some embodiments, the kinetic property is selected from the group consisting of entropy value (K2), fractal dimension (D2), Lyapunov exponent, autocorrelation, automutual information, cross-correlation, and mutual information.

[0057] In some embodiments, the obtained biophysical signal dataset comprises one or more red photoplethysmography signals.

[0058] In some embodiments, the obtained biophysical signal dataset comprises one or more infrared photoplethysmography signals.

[0059] In some embodiments, the obtained biophysical signal dataset comprises one or more cardiac signals.

[0060] In some embodiments, execution of the instructions by the processor further causes the processor to generate a visualization of an estimate of the presence, absence, localization, and / or severity of the disease or condition, where the generated visualization is rendered and displayed on a display of a computing device (e.g., a computing workstation; a surgical, diagnostic, or instrumentation apparatus) and / or presented in a report (e.g., an electronic report).

[0061] In some embodiments, execution of the instructions by the processor further causes the processor to determine a histogram map of variance in periodicity in the biophysical signal dataset, where the histogram map is used in determining an estimate for the presence, absence, localization, and / or severity of a disease or condition.

[0062] In some embodiments, execution of the instructions by the processor further causes the processor to determine a Poincaré map of the acquired biophysical signal dataset; determine an alpha shape object of the Poincaré map; and determine one or more geometric properties of the alpha shape object, wherein the one or more determined geometric properties are used in determining an estimate for the presence, absence, localization, and / or severity of a disease or condition.

[0063] In some embodiments, the one or more determined geometric properties further include two or more properties selected from the group of: a density value of the alpha shaped object; a convex surface area value of the alpha shaped object; a perimeter value of the alpha shaped object; a porosity value of the alpha shaped object; and a void area value of the alpha shaped object.

[0064] In some embodiments, the one or more determined geometric properties further include two or more properties selected from the group of: a length of semi-axis "a" for the estimated maximum cluster ellipse of the Poincaré map; a length of semi-axis "b" for the estimated maximum cluster ellipse of the Poincaré map; a length of the longest axis of the estimated maximum cluster ellipse of the Poincaré map; a length of the shortest axis of the estimated maximum cluster ellipse of the Poincaré map; an estimated number of clusters in the Poincaré map; an estimated number of kernel density modes in the histogram map; and an estimated Searles bimodality coefficient value from the histogram map.

[0065] In some embodiments, the system is further configured to obtain a biophysical signal dataset (e.g., a photoplethysmography signal) of the subject (e.g., from a stored database or from a measurement system); determine a Poincaré map of variance in the biophysical signal dataset; determine an alpha shape object of the Poincaré map; determine one or more geometric properties of the alpha shape object; and determine an estimate for the presence, absence, localization, and / or severity of a disease or condition based on the determined one or more geometric properties, where the disease state comprises the presence of coronary artery disease (e.g., significant coronary artery disease) or elevated / abnormal left ventricular end diastolic pressure.

[0066] In some embodiments, the determined Poincaré map is generated by plotting photoplethysmography signal peaks from a first time x-1 to a second time x on a first axis and from a second time x to a third time x+1 on a second axis.

[0067] In some embodiments, the system further includes a measurement system configured to acquire one or more photoplethysmography signals.

[0068] In some embodiments, the system further includes a measurement system configured to acquire one or more cardiac signals.

[0069] In some embodiments, the system further includes a first measurement system configured to acquire one or more photoplethysmography signals; and a second measurement system configured to acquire one or more cardiac signals.

[0070] In another aspect, a system is disclosed that includes a processor; and a memory having instructions stored therein, where execution of the instructions by the processor causes the processor to perform any of the above methods.

[0071] In another aspect, a computer-readable medium is disclosed having instructions stored therein, where execution of the instructions by a processor causes the processor to perform any of the above methods. The present invention provides, for example, the following items. (Item 1) 1. A method for non-invasively assessing a disease or abnormal condition in a subject, the method comprising: obtaining, by one or more processors, a biophysical signal dataset of interest; determining, by the one or more processors, one or more kinetic properties of the biophysical signal dataset; and determining, by the one or more processors, one or more estimates of the presence, absence, localization, and / or severity of a disease or condition based on the determined one or more kinetic characteristics. (Item 2) The method of claim 1, wherein the presence, absence, and / or severity of the disease or condition can be assessed based on an assessment of left ventricular end-diastolic pressure (LVEDP), including elevated or abnormal LVEDP. (Item 3) 2. The method of claim 1, wherein the disease state or condition comprises coronary artery disease. (Item 4) 2. The method of claim 1, wherein the disease state or condition comprises pulmonary hypertension. (Item 5) 2. The method of claim 1, wherein the disease state or condition comprises pulmonary arterial hypertension. (Item 6) 2. The method of claim 1, wherein the disease state or condition comprises pulmonary hypertension due to left heart disease. (Item 7) 2. The method of claim 1, wherein the disease state or condition comprises a disorder that can lead to pulmonary hypertension. (Item 8) 2. The method of claim 1, wherein the disease state or condition comprises left ventricular heart failure or left-sided heart failure. (Item 9) 2. The method of claim 1, wherein the disease state or condition comprises right ventricular heart failure or right-sided heart failure. (Item 10) 2. The method of claim 1, wherein the disease state or condition comprises systolic or diastolic heart failure. (Item 11) 2. The method of claim 1, wherein the disease state or condition comprises ischemic heart disease. (Item 12) 2. The method of claim 1, wherein the disease state or condition comprises arrhythmia. (Item 13) 13. The method of any one of items 1 to 12, further comprising determining, by the one or more processors, one or more second estimates of the presence, absence, localization, and / or severity of two or more of the diseases or conditions. (Item 14) 14. The method according to any one of items 1 to 13, wherein the dynamic property is selected from the group consisting of entropy value (K2), fractal dimension (D2), Lyapunov exponent, autocorrelation, automutual information, cross-correlation, and mutual information. (Item 15) 15. The method according to any one of items 1 to 14, wherein the obtained biophysical signal dataset comprises one or more red photoplethysmography signals. (Item 16) 15. The method according to any one of items 1 to 14, wherein the obtained biophysical signal dataset comprises one or more infrared photoplethysmography signals. (Item 17) 15. The method according to any one of items 1 to 14, wherein the obtained biophysical signal dataset comprises one or more cardiac signals. (Item 18) 18. The method of any one of items 1 to 17, further comprising causing the one or more processors to generate a visualization of the estimate of the presence, absence, localization, and / or severity of the disease or condition, wherein the generated visualization is rendered and displayed on a display of a computing device and / or presented in a report. (Item 19) 19. The method of any one of items 1 to 18, further comprising determining, by the one or more processors, a histogram map of variance in periodicity in the biophysical signal dataset, wherein the histogram map is used in the determination of the estimate of presence, absence, localization, and / or severity of the disease or pathology. (Item 20) determining, by the one or more processors, a Poincaré map of the obtained biophysical signal dataset; determining, by the one or more processors, an alpha shape object of the Poincaré map; and 20. The method of any one of items 1 to 19, further comprising determining, by the one or more processors, one or more geometric properties of the alpha shape object, wherein the one or more determined geometric properties are used in the determination of the estimate of presence, absence, localization, and / or severity of the disease or pathology. (Item 21) The one or more determined geometric characteristics include: a density value of said alpha shape object; a convex surface area value of said alpha shape object; A perimeter value of said alpha shape object; a porosity value of the alpha shape object; and 21. The method of claim 20, further comprising: providing two or more properties selected from the group consisting of: a) a gap area value of the alpha shape object; (Item 22) The one or more determined geometric characteristics include: the length of the semi-axis "a" for the estimated maximum cluster ellipse of said Poincaré map; the length of the semi-axis "b" for the estimated maximum cluster ellipse of said Poincaré map; the length of the longest axis of the estimated maximum cluster ellipse of said Poincaré map; the length of the shortest axis of the estimated maximum cluster ellipse of said Poincaré map; the number of evaluated clusters in the Poincaré map; The number of estimated kernel density modes in the histogram map; and 22. The method according to claim 20 or 21, further comprising two or more features selected from the group: a. Searles Bimodality Coefficient value assessed from the histogram map. (Item 23) 1. A method for non-invasively assessing a disease or abnormal condition in a subject, the method comprising: obtaining, by one or more processors, a biophysical signal dataset of interest; determining, by the one or more processors, a Poincaré map of variance in the biophysical signal dataset; determining, by the one or more processors, an alpha shape object of the Poincaré map; determining, by the one or more processors, one or more geometric properties of the alpha shape object; and determining, by the one or more processors, an estimate of the presence, absence, localization, and / or severity of a disease or condition based on the determined one or more geometric characteristics, wherein the disease state comprises the presence of coronary artery disease or elevated or abnormal left ventricular end diastolic pressure. (Item 24) 24. The method of claim 23, wherein the determined Poincaré map is generated by plotting photoplethysmography signal peaks from a first time x−1 to a second time x on a first axis and from the second time x to a third time x+1 on a second axis. (Item 25) A processor; and A system comprising: a memory having instructions stored therein, the execution of the instructions by the processor causing the processor to perform any of the methods of items 1-24. (Item 26) A computer-readable medium having instructions stored therein, the execution of the instructions by a processor causing the processor to perform any of the methods of items 1-24. (Item 27) 1. A system for non-invasively assessing a disease or abnormal condition in a subject, the system comprising: A processor; and A memory having instructions stored thereon, the execution of the instructions by the processor causing the processor to: Obtaining a biophysical signal dataset of interest; determining one or more kinetic properties of said biophysical signal dataset; and determining one or more estimates of the presence, absence, localization, and / or severity of a disease or condition based on the determined one or more kinetic characteristics. (Item 28) Execution of the instructions by the processor causes the processor to: 28. The system of claim 27, further configured to determine one or more second estimates of the presence, absence, localization, and / or severity of two or more of the diseases or conditions. (Item 29) 29. The system of claim 27 or 28, wherein the dynamical characteristic is selected from the group consisting of entropy value (K2), fractal dimension (D2), Lyapunov exponent, autocorrelation, automutual information, cross-correlation, and mutual information. (Item 30) 30. The system of any one of items 27 to 29, wherein the obtained biophysical signal dataset comprises one or more red photoplethysmography signals. (Item 31) 31. The system of any one of items 27 to 30, wherein the obtained biophysical signal dataset comprises one or more infrared photoplethysmography signals. (Item 32) 32. The system of any one of items 27 to 31, wherein the obtained biophysical signal dataset comprises one or more cardiac signals. (Item 33) Execution of the instructions by the processor causes the processor to: 33. The system of any one of items 27 to 32, further comprising causing generation of a visualization of the estimate of the presence, absence, localization, and / or severity of the disease or condition, the generated visualization being rendered and displayed on a display of a computing device and / or presented in a report. (Item 34) Execution of the instructions by the processor causes the processor to: 34. The system of any one of items 27 to 33, further comprising determining a histogram map of variance in periodicity in the biophysical signal dataset, wherein the histogram map is used in the determination of the estimate for presence, absence, localization, and / or severity of the disease or pathology. (Item 35) Execution of the instructions by the processor causes the processor to: determining a Poincaré map of the obtained biophysical signal dataset; determining an alpha shape object of the Poincare map; and 35. The system of any one of claims 27 to 34, further comprising determining one or more geometric properties of the alpha shape object, wherein the one or more determined geometric properties are used in the determination of the estimate for the presence, absence, localization, and / or severity of the disease or pathology. (Item 36) The one or more determined geometric characteristics include: a density value of said alpha shape object; a convex surface area value of said alpha shape object; A perimeter value of said alpha shape object; a porosity value of the alpha shape object; and 36. The system of claim 35, further comprising two or more properties selected from the group consisting of: a) a gap area value of the alpha shape object; (Item 37) The one or more determined geometric characteristics include: the length of the semi-axis "a" for the estimated maximum cluster ellipse of said Poincaré map; the length of the semi-axis "b" for the estimated maximum cluster ellipse of said Poincaré map; the length of the longest axis of the estimated maximum cluster ellipse of said Poincaré map; the length of the shortest axis of the estimated maximum cluster ellipse of said Poincaré map; the number of evaluated clusters in the Poincaré map; The number of estimated kernel density modes in the histogram map; and 37. The system of claim 35 or 36, further comprising two or more features selected from the group of: a. a Searles bimodality coefficient value evaluated from the histogram map. (Item 38) 1. A system for non-invasively assessing a disease or abnormal condition in a subject, the system comprising: A processor; and A memory having instructions stored thereon, the execution of the instructions by the processor causing the processor to: Obtaining a biophysical signal dataset of interest; determining a Poincaré map of variance in the biophysical signal dataset; determining an alpha shape object of the Poincaré map; determining one or more geometric characteristics of the alpha shape object; and and a memory that causes the system to determine an estimate of the presence, absence, localization, and / or severity of a disease or condition based on the determined one or more geometric characteristics, wherein the disease state comprises the presence of coronary artery disease or elevated or abnormal left ventricular end diastolic pressure. (Item 39) Item 39. The system of item 38, wherein the determined Poincaré map is generated by plotting photoplethysmography signal peaks from a first time x-1 to a second time x on a first axis and from the second time x to a third time x+1 on a second axis. (Item 40) 40. The system of any one of items 27 to 39, further comprising a measurement system configured to acquire one or more photoplethysmography signals. (Item 41) 41. The system of any one of items 27 to 40, further comprising a measurement system configured to acquire one or more cardiac signals. (Item 42) a first measurement system configured to acquire one or more photoplethysmography signals; and 40. The system of any one of items 27 to 39, further comprising a second measurement system configured to acquire one or more cardiac signals. [Brief description of the drawings]

[0072] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate the embodiments and, together with the description, serve to explain the principles of the methods and systems.

[0073] Embodiments of the invention will be better understood from the following detailed description when read in conjunction with the accompanying drawings. Such embodiments are for illustrative purposes only and depict novel and non-obvious aspects of the invention. The drawings include the following figures:

[0074] [Figure 1-1] FIG. 1 is a diagram of an exemplary system configured to non-invasively assess dynamic characteristics of a physiological system to predict and / or estimate the presence, absence, localization (if applicable), and / or severity of a disease or pathology, or indicators thereof, in such physiological system, according to an illustrative embodiment. [Figure 1-2] FIG. 1A is a diagram of another exemplary system configured to non-invasively evaluate dynamic characteristics of a photoplethysmography signal to predict and / or estimate the presence, absence, localization (if applicable), and / or severity of a disease or pathology, or indicators thereof, in a physiological system, in accordance with an illustrative embodiment. [Figure 1-3] FIG. 1B is a diagram of an exemplary system configured to non-invasively evaluate dynamic characteristics of cardiac signals to predict and / or estimate the presence, absence, localization (if applicable), and / or severity of a disease or pathology, or indicators thereof, in a physiological system, according to an illustrative embodiment. [Figure 2-1] 2A shows exemplary photoplethysmography signals (e.g., red and infrared photoplethysmography signals) as exemplary biophysical signals acquired via the measurement system of FIG 1 according to an illustrative embodiment. The signals are shown with baseline wander and high frequency noise removed. [Figure 2-2]FIG. 2B is a frequency domain representation of the acquired photoplethysmography signal of FIG. 2A with high frequency noise removed. [Figure 2-3] FIG. 2C is a frequency domain representation of the acquired photoplethysmography signal of FIG. 2A with high frequency noise removed. [Figure 2-4] FIG. 2D shows an exemplary sensor configuration for acquiring a photoplethysmography signal 104 in accordance with an illustrative embodiment. [Figure 2-5] FIG. 2E shows an exemplary sensor configuration for acquiring a photoplethysmography signal 104 in accordance with an illustrative embodiment. [Figure 2-6] FIG. 2F shows a three-dimensional phase space plot of the acquired photoplethysmography signal acquired via an infrared sensor. [Figure 2-7] FIG. 2G is a two-dimensional projection of the same data in FIG. 2F. [Figure 3-1] 3A shows an example cardiac signal (e.g., a biopotential signal) as an example biophysical signal acquired via the measurement system of FIG 1 according to an illustrative embodiment. The signal is shown with baseline wander and high frequency noise removed. [Figure 3-2] FIG. 3B is a diagram of a measurement system configured to acquire the cardiac signal of FIG. 3A according to an illustrative embodiment. [Figure 3-3] FIG. 3C shows an exemplary placement of the measurement system of FIG. 3B on a patient in a clinical environment, according to an illustrative embodiment. [Diagram 3-4] FIG. 3D is an illustration of an exemplary placement of surface electrodes of the measurement system of FIG. 3B on the chest and back of a patient to acquire the cardiac signal of FIG. 3A according to an illustrative embodiment. [Figure 4] FIG. 4 shows experimental results from a study showing the clinical predictive value of specific dynamic features extracted from photoplethysmography signals (red photoplethysmography signals and infrared photoplethysmography signals) in indicating the presence or absence, or indicative of, a disease or abnormal condition, according to an illustrative embodiment. [Figure 5-1] FIG. 5 shows experimental results from a study showing the clinical predictive value of specific dynamic features of extracted cardiac signals indicative of the presence or absence, or indicators of, a disease or abnormal condition, according to an illustrative embodiment. [Figure 5-2] FIG. 5 shows experimental results from a study showing the clinical predictive value of specific dynamic features of extracted cardiac signals indicative of the presence or absence, or indicators of, a disease or abnormal condition, according to an illustrative embodiment. [Figure 6] FIG. 6 illustrates a Lyapunov exponent feature extraction module in accordance with an illustrative embodiment. [Figure 7] FIG. 7 illustrates a fractal dimension feature extraction module in accordance with an illustrative embodiment. [Figure 8] FIG. 8 illustrates an entropy feature extraction module in accordance with an illustrative embodiment. [Figure 9] FIG. 9 illustrates a mutual information (MI) feature extraction module in accordance with an illustrative embodiment. [Figure 10] FIG. 10 illustrates a correlation feature extraction module in accordance with an illustrative embodiment. [Figure 11] FIG. 11 illustrates a Lyapunov exponent feature extraction module in accordance with an illustrative embodiment. [Figure 12] FIG. 12 illustrates a fractal dimension feature extraction module in accordance with an illustrative embodiment. [Figure 13] FIG. 13 illustrates an entropy feature extraction module in accordance with an illustrative embodiment. [Figure 14] FIG. 14 illustrates a mutual information (MI) feature extraction module in accordance with an illustrative embodiment. [Figure 15] FIG. 15 illustrates a correlation feature extraction module in accordance with an illustrative embodiment. [Figure 16]FIG. 16 shows experimental results from a study showing the clinical predictive value of certain dynamic features extracted from generated Poincaré maps of photoplethysmography signals (red photoplethysmography signals and / or infrared photoplethysmography signals) indicative of the presence or absence, or indications of, a disease or abnormal condition, in accordance with an illustrative embodiment. [Figure 17] FIG. 17 illustrates a Poincaré map statistical feature extraction module in accordance with an illustrative embodiment. [Figure 18-1] FIG. 18 illustrates a Poincaré map geometric feature extraction module in accordance with an illustrative embodiment. [Figure 18-2] FIG. 18A shows exemplary landmarks in an infrared photoplethysmography signal, according to an illustrative embodiment. [Figure 18-3] FIG. 18B shows an exemplary distribution of periodicity between the same landmarks from adjacent cycles in an infrared photoplethysmography signal, in accordance with an illustrative embodiment. [Figure 18-4] FIG. 18C shows an exemplary Poincaré map generated from the distribution of periodicities between lowest peak landmarks in an infrared photoplethysmography signal, in accordance with an illustrative embodiment. [Figure 19] FIG. 19 illustrates a cluster map geometric feature extraction module in accordance with an illustrative embodiment. [Figure 20] FIG. 20 illustrates an exemplary computing environment in which an exemplary embodiment of the analysis system may be implemented. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0075] Each and every feature described herein, and each and every combination of two or more such features, is included within the scope of the present invention, provided that the features included in such combinations are not mutually inconsistent.

[0076] While the present disclosure is directed to the beneficial evaluation of biophysical signals, e.g., raw or preprocessed photoplethysmographic signals, cardiac signals, etc., in the diagnosis and treatment of cardiac-related pathologies and conditions, such evaluation may be applied to the diagnosis and treatment of any pathology or condition in which a biophysical signal is contained in any relevant system of the living body, including surgical, minimally invasive, and / or pharmacological treatments. In the cardiac (or cardiovascular) context, the evaluation may be applied to the diagnosis and treatment of coronary artery disease (CAD) and diseases and / or conditions associated with elevated or abnormal left ventricular end-diastolic pressure (LVEDP). The evaluation may be applied to the diagnosis and treatment of any number of therapies, such as placing a stent in a coronary artery, performing an atherectomy, angioplasty, prescribing drug therapy, and / or prescribing exercise, nutrition, and other lifestyle changes, alone or in combination. Other cardiac-related lesions or conditions that may be diagnosed include, for example, arrhythmias, congestive heart failure, valvular insufficiency, pulmonary hypertension (e.g., pulmonary arterial hypertension, pulmonary hypertension due to left heart disease, pulmonary hypertension due to lung disease, pulmonary hypertension due to chronic thrombosis, and other diseases, such as pulmonary hypertension due to blood or other disorders), as well as other cardiac-related lesions, conditions, and / or diseases. In some embodiments, the evaluation may be applied to nerve-related lesions and conditions.Non-limiting examples of neurologically related diseases, pathologies, or conditions that may be diagnosed include, for example, epilepsy, schizophrenia, Parkinson's disease, Alzheimer's disease (and all other forms of dementia), autism spectrum (including Asperger's syndrome), attention deficit hyperactivity disorder, Huntington's disease, muscular dystrophy, depression, bipolar disorder, brain / spinal cord tumors (malignant and benign), movement disorders, cognitive disorders, speech disorders, various psychiatric diseases, brain / spinal cord / nerve injuries, chronic traumatic encephalopathy, cluster headaches, migraines, neurological disorders, and neurological disorders. disorders (its various forms including peripheral neuropathy), phantom limb / pain, chronic fatigue syndrome, acute and / or chronic pain (including low back pain, failed lumbar surgery syndrome, etc.), dyskinesia, anxiety disorders, conditions caused by infection or foreign body (e.g., Lyme disease, encephalitis, rabies), narcolepsy and other sleep disorders, post traumatic stress disorder, neurological conditions / effects associated with stroke, aneurysm, hemorrhagic injury, etc., tinnitus and other hearing related diseases / conditions, and vision related diseases / conditions.

[0077] Some references, which may include various patents, patent applications, and publications, are cited in the reference list and discussed in the disclosure provided herein. Citation and / or discussion of such references is provided merely to clarify the description of the disclosed technology and is not an admission that any such reference is "prior art" to any aspect of the disclosed technology described herein. For notational purposes, "[n]" corresponds to the nth reference in the list. For example,

[36] refers to the 36th reference in the list, i.e., F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, et al., "Scikit-learn: Machine learning in python," Journal of machine learning research 12, 2825-2830 (Oct 2011). All references cited and discussed herein are incorporated by reference in their entirety to the same extent as if each reference was individually incorporated by reference.

[0078] Exemplary System 1 is a diagram of an exemplary system 100 configured to non-invasively assess dynamic characteristics of a physiological system to predict and / or estimate (e.g., determine) the presence, absence, localization (if applicable), and / or severity of a disease or condition, or indicator thereof, in such physiological system, according to an illustrative embodiment. Indeed, as used herein, the term "prediction" refers to predicting a future event (e.g., the potential occurrence of a disease or condition), while the term "estimation" can refer to the quantification of some metric based on available information, for example, of the presence, absence, localization (if applicable), and / or severity of a disease or condition, or indicator thereof. The operations of prediction and estimation can be generally referred to as determination.

[0079] As used herein, a "physiological system" can refer to the cardiovascular, pulmonary, renal, and nervous systems, as well as other functional systems and subsystems of the body. In the context of the cardiovascular system, system 100 facilitates the investigation of the complex, nonlinear dynamic properties of the heart over many cardiac cycles.

[0080] In FIG. 1, a non-invasive measurement system 102 (shown as “measurement system” 102) acquires one or more biophysical signals 104 from a subject 108 via a measurement probe 106 and generates a biophysical signal dataset 110.

[0081] The acquired biophysical signals 104, in some embodiments, include one or more photoplethysmographic signals associated with measured changes in optical absorption of oxygenated and / or deoxygenated hemoglobin (e.g., as shown in FIG. 1A).

[0082] In other embodiments, the acquired biophysical signals 104 include one or more cardiac signals associated with biopotential measurements of the body (e.g., as shown in FIG. 1B). As used herein, the term "cardiac signal" refers to one or more signals associated with the structure, function, and / or activity of the cardiovascular system, including the electrical / electrochemical conduction aspects of the signal, such as causing contraction of the cardiac muscle. Cardiac signals, in some embodiments, may include electrocardiographic signals, such as those acquired via, e.g., an electrocardiogram (ECG) or other modalities.

[0083] 1, the non-invasive measurement system 102 is configured to transmit, for example, through a communication system and / or network or through a direct connection, the acquired biophysical signal dataset 110, or a dataset derived or processed therefrom, to a repository 112 (e.g., a storage area network) (not shown) that is accessible to the non-invasive biophysical signal evaluation system. The non-invasive biophysical signal evaluation system 114 (shown as analysis engine 114) is configured to analyze kinetic properties of the acquired biophysical signals 104.

[0084] In some embodiments, the analysis engine 114 includes a machine learning module 116 configured to evaluate a set of features determined from the acquired biophysical signals via one or more feature extraction modules (e.g., 118, 120) to determine features of clinical significance. Once features are extracted from the photoplethysmography or cardiac signals, any type of machine learning can then be used. Example embodiments of the machine learning module 116 are configured to perform, but are not limited to, decision trees, random forests, SVMs, neural networks, linear models, Gaussian processes, nearest neighbors, SVMs, naive Bayes. In some embodiments, the machine learning module 116 may perform as described, for example, in U.S. Patent Application No. 15 / 653,433, entitled "Discovering Novel Features to Use in Machine Learning Techniques, such as Machine Learning Techniques for Diagnosing Medical Conditions," and U.S. Patent Application No. 15 / 653,431, entitled "Discovering Genomes to Use in Machine Learning Techniques," each of which is incorporated herein by reference in its entirety. The photoplethysmography signal may be used in combination with other acquired photoplethysmography signals in a training or validation data set for the machine learning module 116 in evaluating a set of evaluated dynamic features. The photoplethysmography signal may have an associated label 122 for a given disease or abnormal condition. If determined to be clinically significant, the evaluated dynamic feature (e.g., from 118 or 120) may then be used as a predictor of, or an indicator of, a given disease or abnormal condition.

[0085] In some embodiments, the analysis engine 114 includes a pre-processing module configured, for example, to normalize and / or remove baseline wander from the acquired biophysical signals.

[0086] Photoplethysmography signal and acquisition system FIG. 1A is a diagram of an exemplary system 100 (shown as 100a) configured to non-invasively evaluate dynamic characteristics of an acquired photoplethysmography signal 104a to predict and / or estimate (e.g., determine) the presence, absence, localization (if applicable), and / or severity of a disease or pathology, or indicators thereof, in such a physiological system, according to an illustrative embodiment.

[0087] The photoplethysmographic signal may contain information related to the complex interactions between the cardiac and respiratory / pulmonary systems, hi some embodiments, the photoplethysmographic signal is obtained by a photoplethysmogram.

[0088] A photoplethysmogram is generally understood to include a non-invasive circulating biophysical signal related to the pulsatile volume of blood in tissue. A pulse oximeter produces a type of photoplethysmogram that can be used to detect changes in blood volume in the microvascular bed of tissue. A photoplethysmogram, in some embodiments, illuminates the skin and measures changes in light absorption using at least two different wavelengths of light. Pulse oximeters are commonly worn on the finger (although they can also be used on other parts of the body) in outpatient, inpatient, and trauma settings, and measure the partial oxygen saturation of hemoglobin in the blood ("SpO 2 Photoplethysmograms measure the amount of blood flow to the plethysmocyte (known as the plethysmogram "cardiac aspiration"). However, it is not common for the raw photoplethysmogram to be displayed or further analyzed. Aspects of the photoplethysmogram are described in Reisner et al., "Utility of the Photoplethysmogram in Circulatory Monitoring" Anesthesiology 5 2008, Vol. 108, 950-958, which is incorporated herein by reference in its entirety.

[0089] 1A, a non-invasive measurement system 102 (shown as "measurement system" 102a) is configured to acquire one or more photoplethysmographic signals 104 (shown as 104a) from an object 108 (e.g., at a patient's finger; shown as 108a) via a measurement probe 106 (shown as probes 106'a, 106'b) and produce a biophysical signal dataset 110 (shown as 110a). The acquired photoplethysmographic signal 104a is, in some embodiments, associated with a measured change in light absorption by oxygenated and / or deoxygenated hemoglobin.

[0090] In some embodiments, the measurement system 102a includes custom or dedicated equipment or circuitry (including off-the-shelf devices) configured to acquire such signal waveforms for the purpose of diagnosing a disease or abnormal condition. In other embodiments, the measurement system 102a includes a pulse oximeter or optical photoplethysmography device that can output the acquired raw signals for analysis. Indeed, in some embodiments, the acquired waveforms 104a are represented as "SpO 2 1A as "Oxygen Saturation Level." For the illustrated analysis application, however, only the waveform is processed and utilized.

[0091] 1A, the non-invasive measurement system 102a is configured to transmit, for example through a communication system and / or network or through a direct connection, the acquired photoplethysmographic signal dataset 110a, or a dataset derived or processed therefrom, to a repository 112 (e.g. a storage area network) accessible to the non-invasive biophysical signal evaluation system 114 (shown as analysis engine 114a) configured to analyze kinetic characteristics of the acquired photoplethysmographic signal.

[0092] FIG. 2A shows an example of a photoplethysmography signal 104a acquired via the measurement system 102 (e.g., 102a in FIG. 1A) of FIG. 1 according to an illustrative embodiment. Specifically, FIG. 2A shows a signal waveform 202 associated with the absorption level of the red spectrum of light (e.g., having a wavelength ranging from 660 nm) by deoxygenated hemoglobin from the patient's finger. FIG. 2A also shows a signal waveform 204 of the absorption level associated with the infrared spectrum of light (e.g., having a wavelength ranging from 940 nm) by oxygenated hemoglobin from the patient's finger. Other spectra may be acquired. Measurements may also be performed on other parts of the body. In FIG. 2A, the X-axis shows time (seconds) and the Y-axis shows the signal amplitude (millivolts (mv)).

[0093] Figures 2B and 2C are power spectral density graphs showing frequency domain representations of the acquired photoplethysmographic signal of Figure 2A. In Figures 2B and 2C, the X-axis shows frequency (Hertz) and the Y-axis shows the logarithmic power of the signal.

[0094] In some embodiments, red and infrared channel light absorption data is recorded at a rate of 500 samples / second. Other sampling rates may be used. The photoplethysmography signal may be acquired simultaneously with the cardiac signal for each subject. In some embodiments, the acquisition between the two modalities has a jitter of less than about 10 microseconds (μs). The jitter between channel cardiac signals may be approximately 10 femtoseconds (fs), although other jitter may be acceptable.

[0095] 2D shows an exemplary sensor configuration for acquiring a photoplethysmography signal 104a according to an illustrative embodiment. In FIG. 2D, the system includes a light source (e.g., red and infrared LEDs) and a phototransistor (e.g., red and infrared detectors); the phototransistor is positioned distal to the light source.

[0096] Figure 2E shows another exemplary sensor configuration for acquiring a photoplethysmography signal 104a according to another illustrative embodiment. In Figure 2D, the system also includes a light source (e.g., red and infrared LEDs) and a phototransistor (e.g., red and infrared detectors); however, the phototransistor is positioned proximal to the light source to measure reflectance.

[0097] The photoplethysmography signal 104a may be considered as a measurement of the state of a dynamic system in the body, similar to the cardiac signal. The behavior of the dynamic system may be influenced by the action of the cardiac and respiratory systems. It is hypothesized that any abnormality (due to disease or abnormal conditions) may be manifested in the dynamics of the photoplethysmography signal 104a through certain interaction mechanisms.

[0098] In some embodiments, the acquired photoplethysmography signal 104a is downsampled to 250 Hz. Other frequency ranges may be used. In some embodiments, the acquired photoplethysmography signal 104a is processed to remove baseline wander and filter for noise and main frequencies.

[0099] The acquired photoplethysmography signal 104a may be embedded in a certain higher dimensional space (e.g., phase space embedding) to reconstruct the manifold (phase space) created by the underlying dynamical system. A three-dimensional visualization and its two-dimensional projection are shown in Fig. 2F and Fig. 2G (e.g., for a red photoplethysmography signal 202). Specifically, Fig. 2F shows a three-dimensional phase space plot of the acquired photoplethysmography signal 204 acquired via an infrared sensor. The axes are transformed voltage values ​​(i.e., the units on the vertical axis are still mV, but are normalized and baseline wander is removed to have a mean value of about zero). The embedding is defined in Equation 2. The colors are chosen to show coherent structures within this geometrical object. The dynamical features of the photoplethysmography-related measurements are calculated based on the embedding represented by the diagram. Fig. 2G shows the two-dimensional projection of the same.

[0100] Cardiac Signal and Acquisition System FIG. 1B is a diagram of an exemplary system 100 (shown as 100b) configured to non-invasively assess dynamic characteristics of a physiological system using acquired cardiac signals 104b to predict and / or estimate (e.g., determine) the presence, absence, localization (if applicable), and / or severity of a disease or pathology, or indicators thereof, in such physiological system, according to an illustrative embodiment.

[0101] In FIG. 1B, a non-invasive measurement system 102 (shown as "measurement system" 102b) acquires one or more cardiac signals 104 (shown as 104b) from a subject 108 (e.g., at the patient's chest and back; shown as 108b) via measurement probes 106 (shown as probes 106a-106f) and produces a biophysical signal dataset 110 (shown as 110b).

[0102] In some embodiments, the measurement system 102b is configured to acquire a biopotential biophysical signal, which may be based on the body's biopotential via a bipotential sensing circuit.

[0103] In the cardiac and / or electrocardiographic context, the measurement system 102b is configured to capture cardiac-related biopotential or electrophysiological signals of a mammalian subject (such as a human) as a biopotential cardiac signal dataset. In some embodiments, the measurement system 102b is configured to acquire broadband cardiac phase gradient signals as biopotential, current, impedance, magnetic, ultrasonic or acoustic signals, etc. The term "broadband" with reference to the acquired signals and corresponding datasets refers to signals having a frequency range substantially greater than the Nyquist sampling rate of the highest dominant frequency of the physiological system of interest. For cardiac signals, which typically have dominant frequency components between about 0.5 Hz and about 80 Hz, wideband cardiac phase gradient signals or wideband cardiac biophysical signals contain cardiac frequency information at frequencies selected from the group consisting of between about 0.1 Hz and 1 KHz, between about 0.1 Hz and about 2 KHz, between about 0.1 Hz and about 3 KHz, between about 0.1 Hz and about 4 KHz, between about 0.1 Hz and about 5 KHz, between about 0.1 Hz and about 6 KHz, between about 0.1 Hz and about 7 KHz, between about 0.1 Hz and about 8 KHz, between about 0.1 Hz and about 9 KHz, between about 0.1 Hz and about 10 KHz and above (e.g., 0.1 Hz to 50 KHz or 0.1 Hz to 500 KHz). In addition to capturing the dominant frequency components, wideband capture also facilitates capture of other frequencies of interest. Examples of such frequencies of interest can include, among others, a QRS frequency profile (which can have a frequency range up to 250 Hz). The term "phase gradient" with reference to an acquired signal and corresponding data set refers to signals acquired at different locations on the body to observe phase information for a series of different events / functions of a physiological system of interest. Following signal acquisition, the term "phase gradient" refers to non-distorting signal processing and preservation of phase information through the use of pre-processing hardware, software, and techniques (e.g., phase linear filters and signal processing operators and / or algorithms).

[0104] In some embodiments, the cardiac signal dataset 110b includes wideband biopotential signals acquired via a phase space recorder, for example, as described in U.S. Patent Publication No. 2017 / 0119272, entitled "Method and Apparatus for Wide-Band Phase Gradient Signal Acquisition," which is incorporated herein by reference in its entirety. In some embodiments, the cardiac signal dataset includes bipolar wideband biopotential signals acquired via a phase space recorder, for example, as described in U.S. Patent Publication No. 2018 / 0249960, entitled "Method and Apparatus for Wide-Band Phase Gradient Signal Acquisition," which is incorporated herein by reference in its entirety. In other embodiments, the cardiac signal dataset 110b includes one or more biopotential signals acquired from a conventional electrocardiogram (ECG / EKG) device (e.g., Holter device, 12-lead ECG, etc.).

[0105] The phase space recorder described in 2017 / 0119272 is, in some embodiments, configured to simultaneously acquire the photoplethysmography signal 104a together with the cardiac signal 104b. Thus, in some embodiments, the measurement system 102b is configured to acquire two types of biophysical signals.

[0106] FIG. 3A shows an exemplary cardiac signal (e.g., a biopotential signal) as an exemplary biophysical signal acquired via the measurement system of FIG. 1 according to an illustrative embodiment. The signal is shown with baseline wander and high frequency noise removed. In some embodiments, the cardiac signal 104b is acquired using a phase space recorder device, for example, as described in 2017 / 0119272. The signal 104b includes bipolar biopotential measurements acquired across three channels to provide three signals 302, 304, 306 (also referred to as channel "x", channel "y", and channel "z"). In FIG. 3A, the X-axis shows time (seconds) and the Y-axis shows signal amplitude (millivolts (mv)).

[0107] 3B is a diagram of a phase space recorder device, such as that described in U.S. Patent Publication No. 2017 / 0119272, configured to acquire a cardiac signal 104b, which is further configured to also acquire a photoplethysmography signal 104a.

[0108] 1B, the non-invasive measurement system 102b is configured to transmit, for example, through a communication system and / or network or through a direct connection, the acquired cardiac signal dataset 110b, or a dataset derived or processed therefrom, to a repository 112 (e.g., a storage area network) accessible to a non-invasive biophysical signal evaluation system 114 (shown as analysis engine 114) configured to analyze dynamic characteristics of the acquired photoplethysmographic signals.

[0109] In a neurological context, the measurement system 102 is configured to capture neurologically relevant biopotential or electrophysiological signals of a mammalian subject (such as a human) as a neurological biophysical signal dataset. In some embodiments, the measurement system 102 is configured to acquire wideband neurological phase gradient signals, such as biopotential signals, current signals, impedance signals, magnetic signals, ultrasound or acoustic signals, optical signals, etc. An example of a measurement system 102 is described in U.S. Patent Publication No. 2017 / 0119272 and in U.S. Patent Publication No. 2018 / 0249960, each of which is incorporated herein by reference in its entirety.

[0110] In some embodiments, the measurement system 102 is configured to capture the wideband biopotential biophysical phase gradient signal as an unfiltered mammalian electrophysiological signal so that the spectral content of the signal is unchanged. Indeed, in such embodiments, the wideband biopotential biophysical phase gradient signal is captured, converted, and even analyzed without being filtered (e.g., via hardware circuits and / or digital signal processing techniques, etc.) (e.g., prior to digitization) that may otherwise affect the phase linearity of the biophysical signal of interest. In some embodiments, the wideband biopotential biophysical phase gradient signal is captured at microvolt or sub-microvolt resolution that is, below, or significantly below the noise floor of conventional electrocardiogram, electroencephalogram, and other biophysical signal acquisition instruments. In some embodiments, the wideband biopotential biophysical signals are sampled simultaneously and have a temporal skew or "lag" of less than about 1 microsecond, and in other embodiments, a temporal skew or lag of about 10 femtoseconds or less. Of note, the illustrated embodiment minimizes nonlinear distortions (e.g., those that may be introduced via certain filters) in the acquired broadband phase gradient signal and does not affect the information therein.

[0111] FIG. 3C shows an exemplary placement of the measurement system of FIG. 3B on a patient in a clinical environment, according to an illustrative embodiment. FIG. 3D is a diagram of an exemplary placement of surface electrodes 106a-106g on a patient to acquire the cardiac signal of FIG. 3A, according to an illustrative embodiment. Specifically, FIG. 3D shows an exemplary placement of surface electrodes 106a-106g on the chest and back of a patient to acquire a biopotential signal associated with a wideband cardiac phase gradient signal, according to an illustrative embodiment. In the left pane of FIG. 3D, the surface electrodes 106a-106g are shown placed on the chest and back of a patient. In the right pane of FIG. 3D, a side view of the placement of the surface electrodes 106a-106g is shown.

[0112] In the exemplary configuration shown in FIG. 3D, surface electrodes 106a-106g are positioned on the patient's skin at: i) a first location proximal to the right anterior axillary line corresponding to the fifth intercostal space; ii) a second location proximal to the left anterior axillary line corresponding to the fifth intercostal space; iii) a third location proximal to the left sternal border corresponding to the first intercostal space; iv) a fourth location proximal to the left sternal border under the sternum and lateral to the patient's xiphoid process; v) a fifth location proximal to the left sternal border corresponding to the third intercostal space; vi) a sixth location directly opposite the fifth location and proximal to the patient's back to the left of the patient's spine; and viii) a seventh location proximal to the right upper abdomen along the left axillary line corresponding to the second intercostal space. A common lead (designated as "CMM") is also shown. The locations of the individual surface electrodes may vary in other embodiments of the disclosure as other electrode configurations are useful.

[0113] 1 , the non-invasive measurement system 102 is configured with circuitry and computing hardware, software, firmware, middleware, etc. to acquire cardiac and / or photoplethysmographic signals and generate a biophysical signal dataset 110. In other embodiments, the non-invasive measurement system 102 includes a first device (not shown) for acquiring cardiac signals and a second device (not shown) for acquiring photoplethysmographic signals.

[0114] Referring to FIG. 1, the dynamics feature extraction module 118, in some embodiments, is configured to evaluate one or more non-linear dynamics properties (e.g., including but not limited to, Lyapunov exponent (LE), entropy (K2), and other statistical and geometric characterization properties of the photoplethysmography signal 104).

[0115] The Lyapunov exponent is a comprehensive measure that characterizes the strength of exponential divergence

[30] . For chaotic systems, the maximum Lyapunov exponent is a positive number indicating that the system has less memory of the past. For a given dynamical system, the larger the value of the Lyapunov exponent, the shorter the time horizon over which the past information can be used to predict the future. Entropy (KS) (or Kolmogorov-Sinai entropy K2 [31, 32]) represents the rate of change of entropy with time. Fractal dimension (D2) characterizes the topological properties of an attractor in phase space and can be used to reveal more about the dynamics when combining the geometric information of the attractor (fractality) and how the dynamics evolve on it

[33] .

[0116] Nonlinear dynamics and chaos theory can be used systematically to explain the complexity of linear systems and provide tools for quantitatively analyzing their behavior

[19] . Linear systems can generate exponentially growing / decaying responses, or periodically oscillating responses, or combinations thereof, where irregular patterns in the responses can be attributed to irregularities or randomness in the inputs to these systems. Linear systems are a simplification of reality; most dynamical systems, whether natural or manmade, are inherently nonlinear and can produce complex and irregular behaviors without any source of randomness. These behaviors are often referred to as deterministic chaos. Nonlinear dynamics and chaos tools have been used to explain a variety of complex biological and physiological phenomena [20, 21, 22, 23]; for example, to classify atrial fibrillation

[24] and characterize heart rate variability

[25] , each of which is incorporated herein by reference in its entirety.

[0117] In some embodiments, the system 100 includes a healthcare provider portal for displaying scores or various outputs of the analytics engine 114 in predicting and / or estimating the presence, absence, severity, and / or localization (if applicable) of a disease or abnormal condition or indicator thereof, e.g., in a report. The physician or clinician portal, in some embodiments, is configured to access and retrieve reports from a repository (e.g., a storage area network). The physician or clinician portal and / or repository may comply with various privacy laws and regulations, such as the Health Insurance Portability and Accountability Act of 1996 (HIPAA). Further description of an exemplary healthcare provider portal is provided in U.S. Pat. No. 10,292,596, entitled "Method and System for Visualization of Heart Tissue at Risk," which is incorporated herein by reference in its entirety. In certain embodiments, the portal is configured for presentation of patient medical information to healthcare professionals, while in other embodiments, the healthcare provider portal may be accessible to patients, researchers, academics, and / or other portal users.

[0118] Referring to FIG. 1, in some embodiments, the analysis engine 114 includes a Poincaré feature extraction module 120 configured to evaluate geometric and topographical properties of a Poincaré map object generated from the photoplethysmography signal 104.

[0119] Experimental results of dynamic analysis of photoplethysmographic signals 4 shows experimental results from a study showing that dynamic features extracted from photoplethysmography signals (red and infrared photoplethysmography signals) have clinical predictive value in the assessment of a disease or abnormal condition or indicator thereof, according to an illustrative embodiment. Although the dataset describes that the prediction / inference is for a particular population set (e.g., based on gender) and disease or condition or indicator thereof, the experimental results are simply stratified according to these criteria in the presented analysis. Indeed, the experimental results as well as the methods and systems discussed herein provide a basis for diagnosing the presence or absence and / or severity and / or localization of a disease or condition, such as heart failure (HF) in general, even when ejection fraction (EF) is preserved, without necessarily correlating it to LVEDP levels. In other words, the instant systems and methods may be used to non-invasively diagnose or determine the presence or absence and / or severity of various forms of heart failure (HF), as well as other diseases and / or conditions without determining / estimating LVEDP. It is generally understood that LVEDP may be indicative of disease, but is not itself considered a disease state or condition.

[0120] In this study, a series of dynamic features of the photoplethysmographic signal were evaluated, including those related to correlation and mutual information, Lyapunov exponents, and fractal dimension and entropy. Correlation may include autocorrelation (e.g., autocorrelation lag) and cross-correlation to capture linear interactions. Mutual information may be used to find non-linear dependencies. Lyapunov exponents may be used to measure the level of chaos. Fractal dimension may also be referred to as "D2". Entropy may be used to assess the rate at which information is generated on a fractal; also referred to as "K2".

[0121] In this study, candidate features were evaluated using t-tests, mutual information, or AUC. T-tests were performed against the null hypotheses of normal LVEDP and negative coronary artery disease. A t-test is a statistical test that can determine whether there is a difference between two sample means from two populations with unknown variances. The output of a t-test is a p-value, where a small p-value (typically ≦0.05) indicates strong evidence against the null hypothesis. This study used random sampling with replacement (bootstrapping) to generate a test set.

[0122] A mutual information procedure was performed to assess the dependency of elevated or abnormal LVEDP or significant coronary artery disease on a particular set of features. Mutual information refers to a dimensionless quantity that is a measure of the interdependence between two random variables. MI was standardized by the number of bins, and high and low MI were defined as:

number

[0123] A receiver operating characteristic curve (ROC curve) is a graphical plot that illustrates the diagnostic ability of a binary classifier system as the discrimination threshold is varied. ROC curves are constructed by plotting the true positive rate (TPR) against the false positive rate (FPR) at various threshold settings. The area under the curve ROC (AUC-ROC) further takes into account the cost of inaccurate settings. ROC and AUC-ROC values ​​are significant when they are greater than 0.50.

[0124] Table 1 provides a description of each of the evaluated kinetic extraction parameters in FIG. [Table 1-1] [Table 1-2]

[0125] Figure 4 shows that the fractal dimension "D2" of the photoplethysmography signal has potential clinical relevance in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease, as well as diseases or pathologies associated with elevated or abnormal LVEDP. Criteria for the presence of CAD are defined as having a stenosis of greater than 70% by angiography or a fraction-flow of less than 0.80 by flowwire.

[0126] Specifically, Figure 4 shows that the fractal dimension "D2" (denoted as "SpD2L") of the infrared photoplethysmography signal has a t-test p-value of 0.000000434 in predicting / estimating elevated or abnormal LVEDP (which may indicate the presence, absence, and / or severity of a disease and / or pathology). A small p-value (typically < 0.05) indicates strong evidence against the null hypothesis (i.e., no presence of elevated or abnormal LVEDP). FIG. 4 further illustrates that the fractal dimension ("D2") of the red photoplethysmography signal (denoted as "SpD2U") has a t-test p-value of 0.00000382 in predicting / estimating elevated or abnormal LVED (which may indicate the presence, absence, and / or severity of a disease or condition), and a t-test p-value of 0.02 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. FIG. 4 further illustrates that the fractal dimension "D2" of the red photoplethysmography signal (denoted as "SpD2U") has a t-test p-value of 0.02 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. A small p-value (typically ≦0.05) indicates strong evidence against the null hypothesis (i.e., elevated or abnormal LVEDP or no presence of coronary artery disease).

[0127] Further, FIG. 4 shows that the mutual information of the acquired photoplethysmography signals has potential clinical relevance in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. Specifically, FIG. 4 shows that the minimum self-mutual information lag of the infrared photoplethysmography signal (denoted as "SpAMILmin") and the minimum self-mutual information lag of the red photoplethysmography signal (denoted as "SpAMIUmin") have mutual information values ​​of 1.288 and 1.016, respectively, in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. The time / index lag is calculated via the self-mutual information of the signal with respect to the signal shifted with respect to itself to yield the minimum mutual information value. A mutual information value greater than 1.0 has statistical significance.

[0128] Further, Figure 4 shows that the entropy "K2" value of the acquired photoplethysmography signal has potential clinical relevance in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease and / or disease or condition associated with elevated or abnormal LVEDP. Specifically, Figure 4 shows that the entropy ("K2") of the red photoplethysmography signal (denoted as "SpK2U") and the entropy ("K2") of the infrared photoplethysmography signal (denoted as "SpK2L") have t-test p-values ​​of 0.041 and 0.046, respectively, to predict / estimate the presence, absence, localization (if applicable), and / or severity of coronary artery disease and / or disease or condition associated with elevated or abnormal LVEDP in a particular population based on gender. A small p-value (typically ≦0.05) indicates strong evidence against the null hypothesis (i.e., no significant coronary artery disease is present).A small p-value (typically ≦0.05) indicates strong evidence against the null hypothesis (i.e., no CAD is present).

[0129] Experimental results of dynamic analysis of cardiac signals 5 shows experimental results from a study showing that dynamic features extracted from cardiac signals have clinical predictive value in the assessment of a disease or elevated or abnormal condition or indicator thereof, according to an illustrative embodiment. As described above, the dataset describes the prediction / inference for a specific population set (e.g., based on gender) and disease or pathology or indicator thereof (e.g., LVEDP or CAD), but the experimental results are simply stratified according to these criteria in the presented analysis. In fact, the experimental results as well as the methods and systems discussed herein provide a basis for diagnosing the presence or absence and / or severity and / or localization (if applicable) of a disease or pathology or indicator thereof, such as heart failure (HF) in general, even when ejection fraction (EF) is preserved, without necessarily correlating it to LVEDP levels. In other words, the instant systems and methods may be used to non-invasively diagnose or determine the presence or absence and / or severity and / or localization (if applicable) of various forms of heart failure (HF), as well as other diseases and / or conditions without determining / estimating LVEDP.

[0130] In this study, a series of dynamic features of cardiac signals were evaluated, including those related to correlation and mutual information, Lyapunov exponents, as well as fractal dimension and entropy. Correlation may include autocorrelation (e.g., autocorrelation lag) and cross-correlation to capture linear interactions. Mutual information may be used to find nonlinear dependencies. Lyapunov exponents may be used to measure the level of chaos. Fractal dimension may also be referred to as "D2". Entropy may be used to evaluate the rate at which information is generated on a fractal; it is also referred to as "K2".

[0131] In this study, candidate features were evaluated using t-tests, mutual information, or AUC. T-tests were performed against the null hypotheses of normal LVEDP and negative coronary artery disease. A t-test is a statistical test that can determine whether there is a difference between two sample means from two populations with unknown variances. The output of a t-test is a dimensionless quantity known as a p-value. A small p-value (typically ≦0.05) indicates strong evidence against the null hypothesis. This study used random sampling with replacement (bootstrapping) to generate a test set.

[0132] Mutual information techniques were performed to assess any dependence of elevated or abnormal LVEDP or the finding of significant coronary artery disease on a particular set of features. The term "mutual information" refers to an information-theoretic measure of interdependence between two random variables. MI was standardized by the number of bins, and high and low MI were defined as:

number

[0133] Table 2 provides a description of each of the evaluated kinetic extraction parameters in FIG. [Table 2]

[0134] 5 shows that the Lyapunov exponent of the acquired cardiac signal has potential clinical relevance in predicting / estimating elevated or abnormal LVEDP, which may indicate the presence, absence, and / or severity of a disease and / or pathology. Specifically, the Lyapunov exponent value of channel "y" ("LEY") is shown to have a mutual information value of 1.2 in predicting / estimating elevated or abnormal LVEDP, which may indicate the presence, absence, and / or severity of a disease and / or pathology. A mutual information value greater than 1.0 has significance.

[0135] FIG. 5 also shows that the fractal dimension "D2" of the acquired cardiac signal has potential clinical relevance in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. Specifically, FIG. 5 shows that the fractal dimension "D2" of channel "x" (denoted as "D2X") has an AUC of 0.53 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. Furthermore, FIG. 5 shows that the fractal dimension "D2" of channel "y" (denoted as "D2Y") has an AUC of 0.52 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease; t-test p-value of 0.002. AUC values ​​greater than 0.5 have significance, and p-values ​​less than 0.05 have significance.

[0136] FIG. 5 also shows that the entropy "K2" of the acquired cardiac signal has potential clinical relevance in predicting / estimating elevated or abnormal LVEDP, which may indicate the presence, absence, localization (if applicable), and / or severity of disease and / or pathology. Specifically, FIG. 5 shows that the entropy "K2" of channel "x" (denoted as "K2X") has a mutual information value of 1.03 and an AUC value of 0.56 in predicting / estimating elevated or abnormal LVEDP, which may indicate the presence, absence, and / or severity of disease and / or pathology. Furthermore, FIG. 5 also shows that the entropy "K2" of channel "x" (denoted as "K2X") has a mutual information value of 1.32; a t-test p-value of 0.0002; and an AUC of 0.53 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. FIG. 5 further illustrates that the entropy "K2" channel "y" (denoted as "K2Y") has a t-test p-value of 0.0002; a mutual information value of 1.05; and an AUC of 0.53 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. FIG. 5 further illustrates that the entropy "K2" channel "z" (denoted as "K2Z") has a t-test p-value of 0.03; a mutual information value of 1.07; and an AUC value of 0.52 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. AUC values ​​greater than 0.5 have significance; p values ​​less than 0.05 have significance; and mutual information values ​​greater than 1.0 have significance.

[0137] 5 also shows that the autocorrelation of the acquired cardiac signal has potential clinical relevance in predicting / estimating elevated or abnormal LVEDP (which may indicate the presence, absence, localization (if applicable), and / or severity of disease and / or pathology) and the presence, absence, localization (if applicable), and / or severity of coronary artery disease. Specifically, FIG. 5 shows that the calculated minimum automutual information lag (shown as "AMIYmin") of channel "y", i.e., the time / index lag that should be shifted between the calculated mutual information of the signal and itself to result in the minimum mutual information, has a t-test p-value of 0.02 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. Further, Figure 5 shows that the minimum automutual information lag (denoted as "AMIZmin") of channel "z" has a t-test p-value of 0.03 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. A p-value of less than 0.05 has significance.

[0138] FIG. 5 also shows that autocorrelation of cardiac signals has potential clinical relevance in predicting / estimating elevated or abnormal LVEDP (which may indicate the presence, absence, localization (if applicable), and / or severity of disease and / or pathology). Specifically, FIG. 5 shows that the first zero crossing of the autocorrelation of channel "x" (shown as "ACFXZ1") has a mutual information value of 1.05 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. Furthermore, FIG. 5 also shows that the first zero crossing of the autocorrelation of channel "y" ("ACFYZ1") and the autocorrelation of channel "z" ("ACFZZ1") have t-test p-values ​​of 0.0001 and 0.04, respectively, in predicting / estimating elevated or abnormal LVEDP (which may indicate the presence, absence, and / or severity of disease and / or pathology). 5 further illustrates that the second zero crossing of the autocorrelation of channel "x" ("ACFXZ2") has a t-test p-value of 0.03 and an AUC value of 0.51 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. Further, FIG. 5 illustrates that the second zero crossing of the autocorrelation of channel "y" ("ACFYZ2") has a t-test p-value of 0.001 in predicting / estimating elevated or abnormal LVEDP (which may indicate the presence, absence, and / or severity of disease and / or pathology), and an AUC value of 0.51 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. Further, Figure 5 shows that the second zero crossing of the autocorrelation of channel "z" ("ACFZZ2") has a t-test p-value of 0.002 in predicting / estimating elevated or abnormal LVEDP (which may indicate the presence, absence, and / or severity of a disease and / or pathology). AUC values ​​greater than 0.5 have significance; p-values ​​less than 0.05 have significance; and mutual information values ​​greater than 1.0 have significance.

[0139] 5 also shows that cross-correlation between different channels of cardiac signals has potential clinical relevance in predicting / estimating elevated or abnormal LVEDP, which may indicate the presence, absence, localization (if applicable), and / or severity of disease and / or pathology. Specifically, FIG. 5 shows that the maximum value of cross-correlation between channel "y" and channel "z" of the acquired cardiac signals (shown as "XCFYZMax") has a mutual information value of 1.03 in predicting / estimating elevated or abnormal LVEDP, which may indicate the presence, absence, and / or severity of disease and / or pathology, and a mutual information value of 1.13 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. FIG. 5 further illustrates that the maximum value of the cross-correlation between channel "x" and channel "y" of the acquired cardiac signals (shown as "XCFXYMax") has a t-test p-value of 0.0004 in predicting / estimating elevated or abnormal LVEDP (which may indicate the presence, absence, and / or severity of disease and / or pathology). FIG. 5 further illustrates that the maximum value of the cross-correlation between channel "x" and channel "z" of the acquired cardiac signals (shown as "XCFXZMax") has a t-test p-value of 0.04 in predicting / estimating elevated or abnormal LVEDP (which may indicate the presence, absence, and / or severity of disease and / or pathology), and a mutual information value of 1.03 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. A p-value less than 0.05 has significance, and a mutual information value greater than 1.0 has significance.

[0140] FIG. 5 also shows that the cross-correlation (zero or no lag) between channel "x" and channel "z" of the acquired cardiac signal (denoted as "XCFXZ1") has a t-test p-value of 0.002; a mutual information value of 1.59; and an AUC value of 0.54 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. FIG. 5 also shows that the first zero crossing of the cross-correlation between channel "x" and channel "z" of the acquired cardiac signal ("XCFXZZ1") has a t-test p-value of 0.0005; a mutual information value of 1.16; and an AUC value of 0.56 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. FIG. 5 further illustrates that the second zero crossing of the cross-correlation between channel "y" and channel "z" of the acquired cardiac signal (shown as "XCFYZZ2") has a t-test p-value of 0.004 in predicting / estimating an elevated or abnormal LVEDP (which may indicate the presence, absence, and / or severity of a disease and / or pathology). FIG. 5 further illustrates that the delay / lag between channels "y" and "z" (shown as "XCFYZDelay") in the cross-correlation between channels "y" and "z" has a t-test p-value of 0.04 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. AUC values ​​greater than 0.5 have significance; p-values ​​less than 0.05 have significance; mutual information values ​​greater than 1.0 have significance.

[0141] Exemplary Methods of Operation 6-10 and 11-15 each illustrate an exemplary dynamic trait analysis module 118 of FIG. 1 (and FIGS. 1A and 1B) in accordance with an illustrative embodiment. The outputs of the modules in FIGS. 6-10 and 11-15 are merely illustrative. Embodiments may be practiced using some or all of the outputs shown. In some embodiments, additional outputs are generated.

[0142] Unlike systems with mathematical models (equations), the dynamics of the cardiovascular system are represented as a number of measurements and NDS features are extracted from the measured signals rather than through explicit governing equations. The measurements can be seen as a projection of the true state of the system; for this reason, it is essential to perform measurements that contain the most information about the true system. If the true state of the system is x 1 (t),...x n (t), the measurement s(t) may be expressed as

number

[0143] The embedding theorem states that in NDS the components or states of a system usually conjugate or interact with each other, so that exactly one measurement should contain information about all these effects, and a topological equivalent that is representative of the true system can be constructed from a single measurement.

[0144] One effective approach is the method of lazy embedding, which constructs a vector space of size m as follows:

number

[0145] There are two important parameters, the m-dimension of the phase space and the delay τ. The dimension should be chosen high enough so that the reconstructed manifold is sufficiently expanded to represent the original dynamics. The delay should not be too small (temporal correlations can become a dominant effect) and not too large; a suitable value should result in a sufficiently expanded manifold. These values ​​may be fine-tuned for each application, here cardiovascular signals.

[0146] In this test, m=24 and tau=40 (ms), corresponding to 10 index points in a 250 Hz signal. These values ​​were obtained using convergence analysis. In some embodiments, NDS techniques can be applied to characterize the system in phase space.

[0147] Lyapunov index characteristics Figures 6 and 11 each illustrate a Lyapunov exponent feature extraction module 600. In Figure 6, module 600 (shown as 600a) is configured to determine a maximum Lyapunov exponent determined from a photoplethysmography signal (e.g., a red photoplethysmography signal and / or an infrared photoplethysmography signal). In Figure 11, module 600 (shown as 1100b) is configured to determine a maximum Lyapunov exponent determined from a cardiac signal (e.g., channel "x" of a PSR device, channel "y" of a PSR device, and / or channel "z" of a PSR device).

[0148] The Lyapunov exponent is the exponential growth rate of a small initial perturbation. Essentially, it describes how fast two close orbits diverge.

number

[0149] As shown in Figure 6, module 600 may output the maximum Lyapunov exponent value determined from each respective photoplethysmography signal (e.g., of the red photoplethysmography signal and / or of the infrared photoplethysmography signal). In Figure 11, module 1100b may output the maximum Lyapunov exponent value determined from each respective cardiac signal (e.g., from acquisition channel "x" of the PSR device, acquisition channel "y" of the PSR device, and / or acquisition channel "z" of the PSR device).

[0150] Table 3 shows exemplary input arguments to the LE feature extraction module 600 (eg, 600a, 1100b). [Table 3]

[0151] Fractal Dimension Characteristics Figures 7 and 12 each illustrate a fractal dimension feature extraction module 700. In Figure 7, module 700 (shown as 700a) is configured to determine a fractal dimension value for a photoplethysmography signal (e.g., a red photoplethysmography signal and an infrared photoplethysmography signal), including, for example, the fractal dimension ("D2") of the red photoplethysmography signal and the infrared photoplethysmography signal as described in connection with Figure 4. In Figure 12, module 700 (shown as 1200b) is configured to determine a fractal dimension "D2" determined from a cardiac signal (e.g., from channel "x" of the PSR device, channel "y" of the PSR device, and / or channel "z" of the PSR device).

[0152] Fractals are geometric objects with self-similar structures, meaning that the same overall pattern can be observed by magnifying it at various scales. One other aspect of fractal structure is their non-integer dimension. For example, the famous Lorenz attractor has a correlation dimension of 2.05, which is larger than a two-dimensional manifold, but smaller than a three-dimensional volume. To find the fractal dimension, more data is required for LE. Still, finding the exact fractal dimension from measured data is computationally intensive. To alleviate this problem, a lower bound to the fractal dimension can be calculated by the correlation dimension (D2).

[0153] The probability that a trajectory of data in phase space (PS) is found within a sphere U(ε) of radius ε can be expressed as Equation 4:

number

[0154] In the equation, μ(s) is the probability density function. Next, we define the generalized correlation integral of order q as Equation 5.

number

[0155] The integral in Equation 5 can be expanded to the following form in Equation 6:

number

[0156] According to Equation 6, the function Θ is the Heaviside function acting on two points of the trajectory s and s'. It is observed that the correlation sum varies according to the following power law:

number

[0157] From Equation 7, the correlation dimension of order q can be obtained by Equation 8 as follows:

number

[0158] In the formula, q=2, and using this, D 2 This calculation can also be useful for estimating the rate of change of entropy.

[0159] As shown in Figure 7, module 700a may output a fractional dimension "D2" determined from each respective photoplethysmography signal (e.g., of the red photoplethysmography signal and / or of the infrared photoplethysmography signal). In Figure 12, module 1200b may output a fractal dimension "D2" determined from each respective cardiac signal (e.g., from acquisition channel "x" of the PSR device, acquisition channel "y" of the PSR device, and / or acquisition channel "z" of the PSR device).

[0160] Table 4 shows exemplary input arguments to the fractal dimension feature extraction module 700 (eg, 700a, 1200b). [Table 4-1] [Table 4-2]

[0161] Linear scaling regions may be calculated for D2 and K2. Entropy curves for various embedding dimensions m may also be calculated.

[0162] Entropy traits Figures 8 and 13 each show an entropy feature extraction module 800. In Figure 8, module 800 (shown as 800a) is configured to determine an entropy value for a photoplethysmography signal (e.g., a red photoplethysmography signal and / or an infrared photoplethysmography signal). In Figure 13, module 800 (shown as 1300b) is configured to determine an entropy value for a cardiac signal (e.g., from channel "x" of the PSR device, channel "y" of the PSR device, and / or channel "z" of the PSR device).

[0163] Entropy can be understood as a measure of uncertainty, or equivalently, information. If the probability of an event occurring is high, the uncertainty is small and the amount of information is high, and vice versa. Shannon entropy is defined as Equation 9:

number

[0164] Equation 9 defines entropy as the sum over all possible states. For chaotic systems, this quantity increases because there are infinitely many states. Hence, the rate of change of entropy over an attractor is a more robust and informative measure of uncertainty. The rate of change of entropy is known as the Kolmogorov-Sinai entropy, according to Equation 10.

number

[0165] Equation 10 is the average rate of change of entropy using block probabilities. That is, if we divide the data in phase space into m blocks, the probability that point 1 is i 1 Inside, point 2 is i 2 Describe the joint probability that θ is in θ. Calculating this quantity can be very computationally expensive; instead, we bound the lower limit k 2We may calculate the order-q Renyi entropy as Equation 11.

number

[0166] It can be shown that the entropy rate (K2) can be calculated according to Equation 12 as follows:

number

number

[0167] K 2 The entropy rate can be a good approximation to a lower bound on K.

[0168] As shown in Figure 8, module 800a may output a maximum entropy value "K2" determined from each respective photoplethysmography signal (e.g., of the red photoplethysmography signal and / or of the infrared photoplethysmography signal). In Figure 13, module 1300b may output a maximum entropy value "K2" determined from each respective cardiac signal (e.g., from acquisition channel "x" of the PSR device, acquisition channel "y" of the PSR device, and / or acquisition channel "z" of the PSR device).

[0169] Table 5 shows exemplary input parameters for the entropy feature extraction module 800 (e.g., 800a, 1300b). The parameters are appropriate for a 250 Hz signal. [Table 5]

[0170] An Nref value of 2000 or 3000 may be used; however, other values ​​may be used to reduce computational cost.

[0171] mutual information Figures 9 and 13 each show a mutual information (MI) feature extraction module 900. In Figure 9, module 900 (shown as 900a) is configured to determine self mutual information at lags from the photoplethysmography signals (e.g., a red photoplethysmography signal and an infrared photoplethysmography signal). In Figure 13, module 900 (shown as 1300b) is configured to determine self mutual information at lags from the heart (e.g., from channel "x" of the PSR device, channel "y" of the PSR device, and / or channel "z" of the PSR device).

[0172] Mutual information captures the nonlinear dependency between two signals or trajectories in PS in a probabilistic sense. Roughly speaking, MI quantifies the question: knowing that a trajectory is in state i, what is the probability that another trajectory is in state j?

number

[0173] The self-mutual information of X can be obtained by replacing the signal Y in Equation 14.1 with a lagged version of X (i.e., X(t+τ)). The AMI is thus a function of the lag τ. We use as the feature the lag at which the AMI reaches its minimum.

[0174] Formally, the self mutual information at lag τ can be defined by Equation 14.2.

number

[0175] In some embodiments, the mutual information is calculated by partitioning the phase space (PS) and calculating the joint probability distribution. In some embodiments, the ratio

number

[0176] An input parameter, in some embodiments, is the number of bins. The value used in this study is 128. Other numbers of bins may also be used.

[0177] As shown in FIG. 9, module 900a may output the self mutual information from each respective photoplethysmography signal (eg, of the red photoplethysmography signal and / or of the infrared photoplethysmography signal).

[0178] In FIG. 13, module 1300b may output self mutual information determined from each respective cardiac signal (e.g., from acquisition channel "x" of the PSR device, acquisition channel "y" of the PSR device, and / or acquisition channel "z" of the PSR device).

[0179] Cross-correlation Figures 10 and 14 each show a correlation feature extraction module 1000. In Figure 10, module 1000 (shown as 1000a) is configured to determine auto- and cross-correlations at zero crossings between acquired red and infrared photoplethysmography signals. In Figure 14, module 1000 (shown as 1400b) is configured to determine auto- and cross-correlations at zero crossings between acquired cardiac signals (e.g., between channels "x" and "y", between channels "x" and "z", and between channels "y" and "z").

[0180] Nonlinear dependencies were quantified through mutual information. Linear interactions between two random variables or signals can be identified using cross-correlation. The cross-correlation function is defined as follows:

number

[0181] As shown in Figures 10 and 15, in some embodiments the first and second zero crossings, the maximum correlation, the delay at this maximum and the value at τ=0 are extracted as features.

[0182] Consideration Systems whose behavior or state evolves in time are called dynamical systems (DS); these systems can be deterministic or stochastic. In the former case, the behavior of the system is governed by deterministic rules and there is no randomness in the system, but random-like responses can be observed; in the latter case, however, the system evolves as a stochastic process where randomness is the driving mechanism.

[0183] Deterministic dynamical systems can exhibit behavior that appears to be completely random, even though there is no randomness in the system. This type of response is called chaos and is a hallmark of nonlinear deterministic dynamical systems. The nonlinearities in these systems couple with the component responses in complex ways, resulting in random-like behavior. These types of dynamics can be identified and characterized by using mathematical techniques of nonlinear dynamical systems.

[0184] As used herein, when referring to a nonlinear dynamical system, it is intended that it be deterministic.

[0185] One important feature of the chaotic behavior of NDSs is their sensitive dependence on the initial conditions; a small difference in the starting conditions grows exponentially fast, leading to two completely different behaviors in a relatively short time. This growth rate can be quantified using the Lyapunov exponent (LE). Given a long enough time, the trajectory of the motion of the chaotic system fills a bounded region of phase space (for dissipative systems); the geometry that follows is highly complex and has fractal properties. This object is also referred to as an attractor. To examine this geometric aspect of chaos, fractal mathematics is used, and the fractal dimension is one such technique. Entropy is a measure that combines both the dynamical and geometric aspects of chaos and captures this phenomenon from a probabilistic perspective. These and other techniques are introduced in the following sections.

[0186] The cardiovascular system, with its sophisticated conduction and mechanical subsystems, may be considered as an NDS; chaos in physiological function allows the system to respond better to exogenous conditions. When the internal characteristics of the DS change, for example due to certain parameter changes, its behavior may diverge, thereby producing responses with different characteristics. In the context of the cardiovascular system, this translates into different NDS trait values ​​(e.g., LE) as the heart moves from a normal to a pathological state.

[0187] A feature of a dynamic system often requires that the measurement signal is long enough so that it is well represented in phase space. In reality, however, it would not be possible to acquire a cardiovascular signal for such a long time. As a result, the extracted features should not be considered as accurate. In some embodiments, the signal is downsampled to 250 Hz. A higher sampling rate may be used, but would be subject to higher computational requirements and a significant portion of it would be noise. In some embodiments, the signal is filtered for baseline wander and for noise and main frequencies.

[0188] Poincaré map feature extraction As shown in FIG. 1, in some embodiments, the system 100 includes a Poincaré feature extraction module 120 configured to evaluate geometric and topographical properties of a Poincaré map object generated from the photoplethysmography signal 104.

[0189] In some embodiments, the analysis includes extracting statistical and geometric features of the generated Poincaré map.

[0190] FIG. 16 shows experimental results from a study showing the clinical predictive value of certain kinetic features extracted from generated Poincaré maps of photoplethysmography signals (red and / or infrared photoplethysmography signals) indicative of a disease or abnormal condition, or indicator thereof, according to an illustrative embodiment. As described above, the dataset describes the prediction / inference for a particular population set (e.g., based on gender) and disease or condition, or indicator thereof, but the experimental results are simply stratified according to these criteria in the presented analysis. Indeed, the experimental results as well as the methods and systems discussed herein provide a basis for diagnosing the presence or absence and / or severity and / or localization (if applicable) of a disease or condition, such as heart failure (HF) in general, even when ejection fraction (EF) is preserved, without necessarily correlating it to LVEDP levels. In other words, the instant systems and methods may be used to non-invasively diagnose or determine the presence or absence and / or severity and / or localization (if applicable) of various forms of heart failure (HF), as well as other diseases and / or conditions without determining / estimating LVEDP.

[0191] In this study, a first type of Poincaré map of the photoplethysmography signal 104 between predefined landmarks (e.g., peaks, crossovers) in the red photoplethysmography signal and the infrared photoplethysmography signal was evaluated, and a second type of Poincaré map of the photoplethysmography signal 104 between predefined landmarks (e.g., peaks, crossovers) in the same red photoplethysmography signal and the same infrared photoplethysmography signal was evaluated.

[0192] From the Poincaré maps, tests assessed statistical properties including the mean, median, mode, standard deviation, skewness, and kurtosis. Tests also assessed geometric properties including: ellipse fitting based on points containing three standard deviations of the data; major and minor axes and orientation.

[0193] Table 6 provides a description of each of the evaluated kinetic extraction parameters of FIG. 16. In the table, the photoplethysmography signal is referred to as the "PPG signal." Indeed, as described above, in Poincaré maps, references to time are synonymous and thus may be used interchangeably with respect to data points in a given data set. Furthermore, references to successive times or data points may refer to instantaneous data points or time increments as well as data points or time increments of a fixed increment. [Table 6-1] [Table 6-2]

[0194] FIG. 16 shows that various geometric features extracted from the Poincaré plot (also referred to as a Poincaré map) have potential clinical relevance in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease and / or diseases or pathologies associated with elevated or abnormal LVEDP.

[0195] 16, for example, shows that the density (e.g., surface area normalized by the number of data points) of the generated alpha shape (shown as "alphaShapePoincareOutput.alphaShapeDensity") of the Poincare map of the photoplethysmography signal has an AUC value of 0.538 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. An AUC value greater than 0.5 has significance.

[0196] Further, Figure 16 shows that the surface area of ​​the convex hull surrounding the alpha shape generated from the Poincare map (shown as "alphaShapePoincareOutput.convexSurfaceArea") has an AUC value of 0.533 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. An AUC value greater than 0.5 has significance.

[0197] Further, Figure 16 shows that the perimeter of the alpha shape generated from the Poincare map of the photoplethysmography signal (shown as "alphaShapePoincareOutput.perim") has a t-test p-value of 0.044; a mutual information value of 1.295; and an AUC value of 0.523 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. An AUC value greater than 0.5 has significance; a p-value less than 0.05 has significance, and a mutual information greater than 0.5 has significance.

[0198] Further, FIG. 16 shows that the ratio of the perimeter of an alpha shape over its surface area (shown as "alphaShapePoincareOutput.perimSurfaceAreaRatio") has a t-test p-value of 0.00001; a mutual information value of 1.841; and an AUC value of 0.566 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. Furthermore, the same feature has a t-test p-value of 0.011 in predicting / estimating elevated or abnormal LVEDP (which may indicate the presence, absence, and / or severity of disease and / or pathology). An AUC value greater than 0.5 has significance; a p-value less than 0.05 has significance; and a mutual information greater than 0.5 has significance.

[0199] Further, Figure 16 shows that the porosity of the generated alpha shape (shown as "alphaShapePoincareOutput.porosity") of the Poincare map of the photoplethysmography signal has a t-test p-value of 0.0035 and an AUC value of 0.509 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. An AUC value greater than 0.5 has significance; a p-value less than 0.05 has significance.

[0200] Further, Figure 16 shows that the surface area of ​​the Poincare map of the photoplethysmography signal (shown as "alphaShapePoincareOutput.surfaceArea") has an AUC value of 0.549 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. An AUC value greater than 0.5 has significance.

[0201] Further, Figure 16 shows that the void area (e.g., the difference in the surface area of ​​the convex hull and the alpha shape) of the Poincare map of the photoplethysmography signal (shown as "alphaShapePoincareOutput.voidArea") has an AUC value of 0.505 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. An AUC value greater than 0.5 has significance.

[0202] 16 also shows that the standard deviation of the time difference between adjacent PPG peaks has an AUC value of 0.506 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. An AUC value greater than 0.5 has significance.

[0203] FIG. 16 also shows that parameters associated with the fitted ellipses in the clusters of the Poincaré map have potential clinical relevance in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. Specifically, FIG. 16 shows that the minor axis (radius) of the x-axis of the non-tilted ellipse encompassing the largest cluster in the Poincaré map (shown as "largestClusterEllipse.a") has an AUC value of 0.502 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. AUC values ​​greater than 0.5 have significance.

[0204] Further, Figure 16 shows that the minor y-axis (radius) of the non-tilted ellipse encompassing the largest cluster in the Poincaré map (shown as "largestClusterEllipse.b") has an AUC value of 0.502 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. An AUC value greater than 0.5 has significance.

[0205] Further, Figure 16 shows that the size of the major axis of the ellipse encompassing the largest cluster in the Poincaré map (shown as "largestClusterEllipse.long_axis") has a mutual information value of 1.37 and an AUC value of 0.508 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. An AUC value greater than 0.5 has significance; a mutual information value greater than 1.0 has significance.

[0206] 16 further shows that the size of the short axis of the ellipse encompassing the largest cluster in the Poincaré map (shown as "largestClusterEllipse.short_axis") has a mutual information value of 1.086 and an AUC value of 0.527 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. An AUC value greater than 0.5 has significance; a mutual information value greater than 1.0 has significance.

[0207] 16 further shows that the center on the x-axis of the non-tilted ellipse encompassing the largest cluster in the Poincaré map (shown as "largestClusterEllipse.X0") has a mutual information value of 1.04 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. Mutual information values ​​greater than 1.0 have significance.

[0208] 16 also shows that the number of major modes in a kernel density quantification of a histogram of the time differences between adjacent PPG peaks (shown as "numberOfKernelDensityModes") has a test p-value of 0.049 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease. A p-value of less than 0.05 has significance.

[0209] 16 also shows that the number of clusters (shown as "numClusters") in the Poincaré map detected by the DBSCAN clustering algorithm has a t-test p-value of 0.013 in predicting / estimating elevated or abnormal LVEDP (which may indicate the presence, absence, and / or severity of a disease and / or pathology). A p-value of less than 0.05 has significance.

[0210] FIG. 16 also shows that quantification of the bimodality of the distribution using skewness and kurtosis (shown as "sarleBiomodalityCoef") has a t-test p-value of 0.045 in predicting / estimating the presence, absence, localization (if applicable), and / or severity of coronary artery disease, and a mutual information value of 1.234 in predicting / estimating elevated or abnormal LVEDP (which may indicate the presence, absence, and / or severity of disease and / or pathology). A p-value less than 0.05 has significance; a mutual information value greater than 1.0 has significance.

[0211] 17-19 each illustrate an example Poincaré map feature analysis module 120 of FIG. 1 in accordance with an illustrative embodiment. The outputs of the modules in FIGS. 17-19 are merely illustrative. Embodiments may be practiced using some or all of the outputs shown. In some embodiments, additional outputs are generated.

[0212] 17 shows a Poincaré map statistical feature extraction module 1700. Module 1700, in some embodiments, is configured to determine the mean, mode, median, standard deviation, skewness, and kurtosis of the periodicity between landmarks in the same photoplethysmography signal, or between landmarks in a red photoplethysmography signal and an infrared photoplethysmography signal.

[0213] 18 illustrates a Poincaré map geometric feature extraction module 1800. Module 1800 is configured to determine geometric features from the generated alpha shape of a Poincaré map object. In some embodiments, the Poincaré map and its corresponding object may be generated from periodicity between landmarks in the red photoplethysmography signal and the infrared photoplethysmography signal. In some embodiments, the Poincaré map and its corresponding object may be generated from periodicity between landmarks in the same photoplethysmography signal (e.g., the infrared photoplethysmography signal and / or the red photoplethysmography signal).

[0214] FIG. 18A shows exemplary landmarks (lowest peaks) in an infrared photoplethysmography signal. In FIG. 18A, the X-axis shows time (seconds) and the Y-axis shows signal amplitude (millivolts (mv)). FIG. 18B shows an exemplary distribution of the variance of amplitude values ​​between adjacent cycles in an infrared photoplethysmography signal in a histogram. In FIG. 18B, the X-axis of the histogram shows signal amplitude (mV) and the Y-axis shows frequency / count. FIG. 18C shows an exemplary Poincaré map generated from the amplitude values ​​of the infrared photoplethysmography signal at times x and x-1 in the x-axis and times x and x+1 in the y-axis. That is, each evaluation parameter (e.g., signal amplitude) at a given time / data point is proportional to the amplitude of the next time / data point (e.g., [x i ,x i+1 ] vs [x i ,x i-1 ]) in a Poincaré map. The Poincaré map thus facilitates analysis of the variation of a given parameter (e.g., the variation in the lowest peak landmark) between cycles in an acquired data set. Similar analyses may be applied to any of the parameters and features discussed herein.

[0215] From the Poincaré map, the system generates an alpha shape, and then extracts the geometric features of the resulting alpha shape.

[0216] 18, in some embodiments, a Poincaré map geometric feature extraction module 1800 is configured to extract density values ​​from the alpha shapes of the Poincaré map. In some embodiments, the density is determined by module 1800 as a surface area normalized by the number of data points.

[0217] 18, in some embodiments, a Poincaré map geometric feature extraction module 1800 is configured to extract convex surface area values ​​from the alpha shape of the Poincaré map. In some embodiments, the convex surface area is determined by module 1800 as the surface area of ​​a convex hull generated to encompass the alpha shape of the Poincaré map.

[0218] According to FIG. 18, in some embodiments, a Poincaré map geometric feature extraction module 1800 is configured to extract a perimeter value from an alpha shape of a Poincaré map.

[0219] 18, in some embodiments, a Poincaré map geometric feature extraction module 1800 is configured to extract perimeter and surface area values ​​from the alpha shapes of the Poincaré map. A ratio based on the perimeter and surface area may be generated by module 1300.

[0220] According to FIG. 18, in some embodiments, a Poincaré map geometric feature extraction module 1800 is configured to extract porosity values ​​from the alpha shapes of the Poincaré map.

[0221] According to FIG. 18, in some embodiments, a Poincaré map geometric feature extraction module 1800 is configured to extract surface area from the alpha shape of the Poincaré map.

[0222] 18, in some embodiments, a Poincaré map geometric feature extraction module 1800 is configured to extract void area from the alpha shape of the Poincaré map. In some embodiments, the module 1800 determines the void area as the difference in the surface areas of the convex hull and the alpha shape.

[0223] According to FIG. 19, in some embodiments the Poincaré map geometric feature extraction module 1900 is configured to extract the standard deviation of the time differences between adjacent peaks in the photoplethysmography signal.

[0224] In accordance with FIG. 19, a cluster map geometric feature extraction module 1900 is configured to also determine geometric features from the determined clusters of the Poincaré map objects.

[0225] As shown in FIG. 19, in some embodiments, the module 1900 is configured to determine the minor axis (radius) of the x-axis of a non-tilted ellipse that encompasses the largest cluster in the Poincaré map. In some embodiments, the module 1900 is configured to determine the minor axis (radius) of the y-axis of a non-tilted ellipse that encompasses the largest cluster in the Poincaré map. In some embodiments, the module 1900 is configured to determine the size of the major axis of an ellipse that encompasses the largest cluster in the Poincaré map. In some embodiments, the module 1900 is configured to determine the size of the minor axis of an ellipse that encompasses the largest cluster in the Poincaré map. In some embodiments, the module 1900 is configured to determine the center in the x-axis of a non-tilted ellipse that encompasses the largest cluster in the Poincaré map. In some embodiments, the module 1900 is configured to determine the number of principal modes in a kernel density quantification of a histogram of time differences between adjacent PPG peaks. In some embodiments, the module 1900 is configured to determine the number of clusters in the Poincaré map detected by a DBSCAN clustering algorithm.

[0226] In some embodiments, the module 1900 is configured to use skewness and kurtosis to determine a quantification of the bimodality of the distribution.

[0227] Module 1900 may generate, for example, one, some, or all of the parameters discussed above for use in subsequent analysis and / or diagnosis of a disease state or condition.

[0228] According to FIG. 16, these parameters are shown to have a certain statistical relevance, dependency, or clinical value in assessing elevated or abnormal LVEDP and coronary artery disease.

[0229] Coronary Artery Disease - Learning Algorithm Development Test The "Coronary Artery Disease - Learning Algorithm Development" (CADLAD) trial will trial acquired photoplethysmography and cardiac signals to support the development and testing of machine learning algorithms.

[0230] In this study, paired clinical data is used to guide the design and development of the pre-processing, feature extraction, and machine learning stages of development. That is, the collected clinical trial data is divided into the following cohorts: training cohort, validation cohort, and verification cohort. In this study, each acquired data set is first pre-processed to clean and standardize the data. Following the pre-processing process, a set of features is extracted from the signal, where each set of features is paired with a representation of the true condition, such as a binary classification of the presence or absence of significant CAD or a scored classification of the presence or absence of significant CAD in a given coronary artery.

[0231] An evaluation system (e.g., 114, 114a, 114b) automatically and iteratively explores combinations of features in various permutations, in some embodiments, with the goal of finding those combinations that can successfully match feature-based predictions. A validation set is used as a comparison to avoid overfitting the answer to the training data. Once candidate predictors are developed, they are then manually applied to the validation data set to evaluate the performance of the predictor against data that has never been used to generate the predictor. Provided the data set is large enough, the performance of the selected predictor on the validation set will be close to the performance of the predictor on new data.

[0232] Provider Portal With reference to FIG. 1 (as well as FIGS. 1A and 1B), the system 100 (e.g., 100a, 100b), in some embodiments, includes a healthcare provider portal for presenting an assessment of a disease state or condition (e.g., associated with elevated or abnormal LVEDP and / or coronary artery disease) in a report. In some embodiments, the report is configured as an angiography equivalent report. The physician or clinician portal, in some embodiments, is configured to access and retrieve the report from a repository (e.g., a storage area network). The physician or clinician portal and / or repository may be HIPAA compliant. An exemplary healthcare provider portal is provided in U.S. Patent No. 15 / 712,104, entitled "Method and System for Visualization of Heart Tissue at Risk," which is incorporated herein by reference in its entirety. In certain embodiments, the portal is configured for presentation of a patient's medical information to a healthcare professional, while in other embodiments, the healthcare provider portal may be accessible to patients, researchers, academics, and / or other portal users. This portal can be used in a wide variety of environments - from hospitals to emergency rooms, laboratories, battlefields or remote settings, at the point of care with a patient's primary care physician or other caregiver, and even at home, for a wide variety of clinical and even research needs.

[0233] Machine-Based Classifiers Machine learning techniques predict outcomes based on a set of input data. For example, machine learning techniques are used to recognize patterns and images, supplement medical diagnoses, and the like. Machine learning techniques rely on a set of features, each of which represents some measurable aspect of the observed data, generated using a training set of data (i.e., a data set of observations, each of which has a known predicted outcome), to generate and train one or more predictive models. For example, observed signals (e.g., heart rate signals from a large number of subjects) may be analyzed to collect frequencies, averages, and other statistical information about these signals. Machine learning techniques may use these features to generate and train models related to one or more disease states, such as some forms of cardiovascular disease (CVD), including coronary artery disease (CAD), and then apply the models to data sources with unknown outcomes, such as undiagnosed patients or future patterns. Traditionally, in the context of cardiovascular disease, these features are manually selected from conventional electrocardiograms and combined by data scientists working with domain experts.

[0234] Examples of machine learning embodiments include, but are not limited to, decision trees, random forests, SVMs, neural networks, linear models, Gaussian processes, nearest neighbor methods, SVMs, and naive Bayes. In some embodiments, machine learning may be performed as described, for example, in U.S. patent application Ser. No. 15 / 653,433, entitled "Discovering Novel Features to Use in Machine Learning Techniques, such as Machine Learning Techniques for Diagnosing Medical Conditions," and U.S. patent application Ser. No. 15 / 653,431, entitled "Discovering Genomes to Use in Machine Learning Techniques," each of which is incorporated herein by reference in its entirety.

[0235] Exemplary Computing Device FIG. 20 illustrates an exemplary computing environment in which exemplary embodiments of analysis system 114 and aspects thereof may be implemented.

[0236] The computing device environment is just one example of a suitable computing environment and is not intended to suggest any limitation as to the scope of use or functionality.

[0237] Numerous other general purpose or special purpose computing device environments or configurations may be used. Examples of well-known computing devices, environments, and / or configurations that may be suitable for use include, but are not limited to, personal computers, server computers, handheld or laptop devices, mobile phones, wearable devices, multiprocessor systems, microprocessor-based systems, networked personal computers (PCs), minicomputers, mainframe computers, embedded systems, distributed computing environments that include any of the above systems or devices, and the like.

[0238] Computer-executable instructions executed by a computer, such as program modules, may be used. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Distributed computing environments may also be used where tasks are performed by remote processing devices that are linked through a communications network or other data transmission medium. In a distributed computing environment, program modules and other data may be located in both local and remote computer storage media (including memory storage devices).

[0239] 20, an exemplary system for performing aspects described herein includes a computing device, such as computing device 2000. In its most basic configuration, computing device 2000 typically includes at least one processing unit 2002 and memory 2004. Depending on the exact configuration and type of computing device, memory 2004 may be volatile (e.g., random access memory (RAM)), non-volatile (e.g., read only memory (ROM), flash memory, etc.), or some combination of the two. This most basic configuration is illustrated in FIG. 20 by dashed line 2006.

[0240] Computing device 2000 may have additional features / functionality. For example, computing device 2000 may include additional storage (removable and / or non-removable) including, but not limited to, magnetic or optical disks or tape. Such additional storage is illustrated in FIG. 20 by removable storage 2008 and non-removable storage 2010.

[0241] The computing device 2000 typically includes a variety of computer-readable media, which can be any available media that can be accessed by the device 2000, including both volatile and nonvolatile media, removable and non-removable media.

[0242] Computer storage media includes any method or technology for storage of information, such as volatile and nonvolatile, removable and non-removable media implemented in computer readable instructions, data structures, program modules or other data. Memory 2004, removable storage 2008, and non-removable storage 2010 are all examples of computer storage media. Computer storage media include, but are not limited to, RAM, ROM, Electrically Erasable Program Read Only Memory (EEPROM), Flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage devices or other magnetic storage devices, or any other medium that can be used to store the desired information and that can be accessed by computing device 2000. Any such computer storage media may be part of computing device 2000.

[0243] The computing device 2000 may include communications connections 2012 that allow the device to communicate with other devices. The computing device 2000 may also have input devices 2014, such as a keyboard, mouse, pen, voice input device, touch input device, etc., either alone or in combination. Output devices 2016, such as a display, speakers, printer, vibrating mechanism, etc., either alone or in combination, may also be included. All these devices are well known in the art and need not be discussed at length here.

[0244] It should be understood that the various techniques described herein may be implemented in connection with hardware or software components, or, where appropriate, a combination of both. Illustrative types of hardware components that may be used include field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), and the like. The methods and apparatus of the presently disclosed subject matter, or certain aspects or portions thereof, may take the form of program code (i.e., instructions) embodied in a tangible medium, such as a floppy disk, CD-ROM, hard drive, or any other machine-readable storage medium, which, when the program code is loaded into and executed by a machine, such as a computer, causes the machine to become an apparatus for practicing the presently disclosed subject matter.

[0245] Although an exemplary implementation may refer to utilizing aspects of the presently disclosed subject matter in the context of one or more stand-alone computer systems, the present subject matter is not so limited, but rather may be implemented in the context of any computing environment, such as a networked or distributed computing environment. Additionally, aspects of the presently disclosed subject matter may be implemented in or across multiple processing chips or devices, and storage may similarly be provided across multiple devices. Such devices may include, for example, personal computers, network servers, handheld devices, and wearable devices.

[0246] Although the subject matter has been described in language specific to structural features and / or methodological acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the particular features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

[0247] Further examples of the illustrated methods and systems and processes that may be used are described in U.S. Patent No. 9,289,150, entitled "Non-invasive Method and System for Characterizing Cardiovascular Systems"; U.S. Patent No. 9,655,536, entitled "Non-invasive Method and System for Characterizing Cardiovascular Systems"; U.S. Patent No. 9,968,275, entitled "Non-invasive Method and System for Characterizing Cardiovascular Systems"; U.S. Patent No. 8,923,958, entitled "System and Method for Evaluating an Electrophysiological Signal"; U.S. Patent No. 9,408,543, entitled "Non-invasive Method and System for Characterizing Cardiovascular Systems and All-Cause Mortality and Sudden Cardiac Death Risk"; U.S. Patent No. 9,955,883 entitled "Noninvasive Electrocardiographic Method for Estimating Mammalian Cardiac Chamber Size and Mechanical Function"; U.S. Patent No. 9,737,229 entitled "Noninvasive Electrocardiographic Method for Estimating Mammalian Cardiac Chamber Size and Mechanical Function";U.S. Patent No. 10,039,468 entitled "Noninvasive Electrocardiographic Method for Estimating Mammalian Cardiac Chamber Size and Mechanical Function"; U.S. Patent No. 9,597,021 entitled "Noninvasive Method for Estimating Glucose, Glycosylated Hemoglobin and Other Blood Constituents"; U.S. Patent No. 9,968,265 entitled "Method and System for Characterizing Cardiovascular Systems From Single Channel Data"; U.S. Patent No. 9,910,964 entitled "Methods and Systems Using Mathematical Analysis and Machine Learning to Diagnose Disease"; U.S. Patent Publication No. 2017 / 0119272 entitled "Method and Apparatus for Wide-Band Phase Gradient Signal Acquisition"; PCT Publication No. WO2017 / 033164, entitled "Non-invasive Method and System for Measuring Myocardial Ischemia, Stenosis Identification, Localization and Fractional Flow Reserve Estimation"; U.S. Patent Publication No. 2018 / 0000371, entitled "Non-invasive Method and System for Measuring Myocardial Ischemia, Stenosis Identification, Localization and Fractional Flow Reserve Estimation";PCT Publication No. WO2017 / 221221 entitled "Non-invasive Method and System for Measuring Myocardial Ischemia, Stenosis Identification, Localization and Fractional Flow Reserve Estimation"; U.S. Patent No. 10,292,596 entitled "Method and System for Visualization of Heart Tissue at Risk"; U.S. Patent Application No. 16 / 402,616 entitled "Method and System for Visualization of Heart Tissue at Risk"; U.S. Patent Publication No. 2018 / 0249960 entitled "Method and System for Wide-band Phase Gradient Signal Acquisition"; U.S. Patent Application No. 16 / 232,801 entitled "Method and System to Assess Disease Using Phase Space Volumetric Objects"; PCT Publication No. IB / 2018 / 060708 entitled "Methods and Systems of De-Noising Magnetic-Field Based Sensor Data of Electrophysiological Signals"; U.S. Patent Publication No. US2019 / 0117164 entitled "Method and System to Assess Disease Using Phase Space Tomography and Machine Learning"; U.S. Patent Application No. 16 / 232,586 entitled "Method and System to Assess Disease Using Phase Space Tomography and Machine Learning";PCT Application No. PCT / IB2018 / 060709 entitled "Method and System to Assess Disease Using Phase Space Tomography and Machine Learning"; U.S. Patent Application No. 16 / 445,158 entitled "Methods and Systems to Quantify and Remove Asynchronous Noise in Biophysical Signals"; U.S. Patent Application No. 16 / 725,402 entitled "Method and System to Assess Disease Using Phase Space Tomography and Machine Learning"; U.S. Patent Application No. 16 / 429,593 entitled "Method and System to Assess Pulmonary Hypertension Using Phase Space Tomography and Machine Learning"; U.S. Patent Application No. 16 / 725,416 entitled "Method and System for Automated Quantification of Signal Quality"; U.S. patent application Ser. No. 16 / 725,430, entitled "Discovering Novel Features to Use in Machine Learning Techniques, Such as Machine Learning Techniques for Diagnosing Medical Conditions"; U.S. patent application Ser. No. 15 / 653,433, entitled "Discovering Novel Features to Use in Machine Learning Techniques, Such as Machine Learning Techniques for Diagnosing Medical Conditions"; and U.S. patent application Ser. No. 15 / 653,431, entitled "Discovering Genomes to Use in Machine Learning Techniques," each of which is incorporated by reference herein in its entirety.

[0248] Unless expressly stated otherwise, it is in no way intended that any method set forth herein be construed as requiring that its steps be performed in a particular order. Thus, unless a method claim actually recites an order to be followed by its steps or is otherwise specifically stated in the claim or description that the steps are limited to a particular order, no order is intended to be inferred at any point. This applies to any possible non-expressive basis for interpretation, including questions of logic regarding the arrangement of steps or flow of operations; plain meaning derived from grammatical construction or punctuation; or the number or type of embodiments described herein.

[0249] While the methods and systems have been described in connection with specific embodiments and examples, it is not intended that the scope be limited to the specific embodiments illustrated, as the embodiments herein are intended in all respects to be illustrative rather than restrictive.

[0250] The methods, systems, and processes described herein are used to generate stenosis and FFR output for use in procedures, such as placement of vascular stents within a blood vessel, such as an artery, of a living (e.g., human) subject, as well as in conjunction with other interventional and surgical systems or processes. In one embodiment, the methods, systems, and processes described herein can be configured to use the FFR / stenosis output to determine and / or modify the number of stents to be placed in a living (e.g., human) subject during operation, including, among other things, their optimal location for placement within a given vessel.

[0251] Examples of other biophysical signals that may be analyzed in whole or in part using the exemplary methods and systems include, but are not limited to, electrocardiogram (ECG) datasets, electroencephalogram (EEG) datasets, gamma-synchronous signal datasets; respiratory function signal datasets; pulse oximetry signal datasets; perfusion data signal datasets; quasi-periodic biological signal datasets; fetal ECG datasets; blood pressure signals; cardiac magnetic field datasets, and heart rate signal datasets.

[0252] Exemplary analyses can be used in the diagnosis and treatment of cardiac-related and / or neural-related pathologies and pathologies, and such evaluations can be applied to the diagnosis and treatment (including surgical, minimally invasive, and / or pharmaceutical treatments) of any pathology or pathology in which a biophysical signal is contained in any relevant system of the living body. One example in the cardiac context is the diagnosis of CAD and its treatment by any number of therapies, alone or in combination, such as placing a stent in a coronary artery, performing an atherectomy, angioplasty, prescribing drug therapy, and / or prescribing exercise, nutrition, and other lifestyle changes. Other cardiac-related pathologies or pathologies that may be diagnosed include, for example, arrhythmias, congestive heart failure, valvular insufficiency, pulmonary hypertension (e.g., pulmonary arterial hypertension, pulmonary hypertension due to left heart disease, pulmonary hypertension due to lung disease, pulmonary hypertension due to chronic thrombosis, and other diseases, such as pulmonary hypertension due to blood or other disorders), as well as other cardiac-related pathologies, pathologies, and / or diseases. Non-limiting examples of neurologically related diseases, pathologies, or conditions that may be diagnosed include, for example, epilepsy, schizophrenia, Parkinson's disease, Alzheimer's disease (and all other forms of dementia), autism spectrum (including Asperger's syndrome), attention deficit hyperactivity disorder, Huntington's disease, muscular dystrophy, depression, bipolar disorder, brain / spinal cord tumors (malignant and benign), movement disorders, cognitive disorders, speech disorders, various psychiatric diseases, brain / spinal cord / nerve injuries, chronic traumatic encephalopathy, cluster headaches, migraines, neurological disorders, and neurological disorders. disorders (its various forms including peripheral neuropathy), phantom limb / pain, chronic fatigue syndrome, acute and / or chronic pain (including low back pain, failed lumbar surgery syndrome, etc.), dyskinesia, anxiety disorders, conditions caused by infection or foreign body (e.g., Lyme disease, encephalitis, rabies), narcolepsy and other sleep disorders, post traumatic stress disorder, neurological conditions / effects associated with stroke, aneurysm, hemorrhagic injury, etc., tinnitus and other hearing related diseases / conditions, and vision related diseases / conditions.

[0253] The patents, applications, and publications listed below, and throughout this document, are hereby incorporated by reference in their entirety. List of References [1] I. Kononenko, “Machine learning for medical diagnosis: history, state of the art and perspective,” Artificial Intelligence in medicine 23 (1) 89-109 (2001). [2] B. A. Mobley, E. Schechter, W. E. Moore, P. A. McKee, J. E. Eichner, “Predictions of coronary artery stenosis by artificial neural network,” Artificial Intelligence in Medicine 18 (3) 187-203 (2000). [3] V. L. Patel, E. H. Shortliffe, M. Stefanelli, P. Szolovits, M. R. Berthold, R. Bellazzi, A. Abu-Hanna, “The coming of age of artificial intelligence in medicine,” Artificial intelligence in medicine 46 (1) 5-17 (2009). [4] V. Jahmunah, S. L. Oh, V. Rajinikanth, E. J. Ciaccio, K. H. Cheong, U. R. Acharya, et al., “Automated detection of schizophrenia using nonlinear signal processing methods,” Artificial Intelligence in Medicine, Vol. 100, 101698 (September 2019). [5] A. M. Tai, A. Albuquerque, N. E. Carmona, M. Subramanieapillai, D. S. Cha, M. Sheko, Y. Lee, R. Mansur, R. S. McIntyre, “Machine learning and big data: Implications for disease modeling and therapeutic discovery in psychiatry,” Artificial Intelligence in Medicine 101704 (2019). [6] G. K. Hansson, “Inflammation, atherosclerosis, and coronary artery disease,” New England Journal of Medicine 352 (16) 1685-1695 (2005). [7] W. G. Members, D. Lloyd-Jones, R. J. Adams, T. M. Brown, M. Carnethon, S. Dai, G. De Simone, T. B. Ferguson, E. Ford, K. Furie, et al., “Executive summary: heart disease and stroke statistics2010 update: a report from the American heart association,” Circulation 121 (7) 948-954 (2010). [8] G. A. Mensah, D. W. Brown, “An overview of cardiovascular disease burden in the united states,” Health affairs 26 (1) 38-48 (2007). [9] Y. N. Reddy, A. El-Sabbagh, R. A. Nishimura, “Comparing pulmonary arterial wedge pressure and left ventricular end diastolic pressure for assessment of left-sided filling pressures,” JAMA cardiology 3 (6) 453-454 (2018).

[10] M. J. Kern, T. Christopher, “Hemodynamic rounds series II: the LVEDP,” Catheterization and cardiovascular diagnosis 44 (1) 70-74 (1998).

[11] J.-H. Park, T. H. Marwick, “Use and limitations of e / e’ to assess left ventricular filling pressure by echocardiography,” Journal of cardiovascular ultrasound 19 (4) 169-173 (2011).

[12] S. R. Ommen, R. A. Nishimura, C. P. Appleton, F. Miller, J. K. Oh, M. M. Redfield, A. Tajik, “Clinical utility of doppler echocardiography and tissue doppler imaging in the estimation of left ventricular filling pressures: a comparative simultaneous doppler-catheterization study,” Circulation 102 (15) 1788-1794 (2000).

[13] J. Allen, “Photoplethysmography and its application in clinical physiological measurement,” Physiological measurement 28 (3) R1 (2007).

[14] S. D. Fihn, J. M. Gardin, J. Abrams, K. Berra, J. C. Blankenship, A. P. Dallas, P. S. Douglas, J. M. Foody, T. C. Gerber, A. L. Hinderliter, et al., “2012 accf / aha / acp / aats / pcna / scai / sts guideline for the diagnosis and management of patients with stable ischemic heart disease.,” Journal of the American College of Cardiology 60 (24) 2564-2603 (2012).

[15] G. N. Levine, E. R. Bates, J. C. Blankenship, S. R. Bailey, J. A. Bittl, B. Cercek, C. E. Chambers, S. G. Ellis, R. A. Guyton, S. M. Hollenberg, et al., “2011 accf / aha / scai guideline for percutaneous coronary intervention: executive summary.,” Journal of the American College of Cardiology 58 (24) 2550-2583 (2011).

[16] L. M. Mielniczuk, G. A. Lamas, G. C. Flaker, G. Mitchell, S. C. Smith, B. J. Gersh, S. D. Solomon, L. A. Moy´e, J. L. Rouleau, J. D. Rutherford, et al., “Left ventricular end-diastolic pressure and risk of subsequent heart failure in patients following an acute myocardial infarction,” Congestive Heart Failure 13 (4) 209-214 (2007).

[17] J. J. Russo, N. Aleksova, I. Pitcher, E. Couture, S. Parlow, M. Faraz, S. Visintini, T. Simard, P. Di Santo, R. Mathew, et al., “Left ventricular unloading during extracorporeal membrane oxygenation in patients with cardiogenic shock,” Journal of the American College of Cardiology 73 (6) 654-662 (2019).

[18] R. Salem, A. Denault, P. Couture, S. Belisle, A. Fortier, M.-C. Guertin, M. Carrier, R. Martineau, “Left ventricular end-diastolic pressure is a predictor of mortality in cardiac surgery independently of left ventricular ejection fraction,” BJA: British Journal of Anaesthesia 97 (3) 292-297 (2006).

[19] S. H. Strogatz, “Nonlinear dynamics and chaos: with applications to physics, biology, chemistry, and engineering,” CRC Press, (2018).

[20] A. L. Goldberger, D. R. Rigney, B. J. West, “Chaos and fractals in human physiology,” Scientific American 262 (2) 42-49 (1990).

[21] A. L. Goldberger, “Nonlinear dynamics, fractals and chaos: applications to cardiac electrophysiology,” Annals of biomedical engineering 18 (2) 195-198 (1990).

[22] L. Glass, A. Beuter, D. Larocque, “Time delays, oscillations, and chaos in physiological control systems,” Mathematical Biosciences 90 (1-2) 111-125 (1988).

[23] L. Glass, “Synchronization and rhythmic processes in physiology,” Nature 410 (6825) 277 (2001).

[24] M. I. Owis, A. H. Abou-Zied, A.-B. Youssef, Y. M. Kadah, “Study of features based on nonlinear dynamical modeling in ecg arrhythmia detection and classification,” IEEE transactions on Biomedical Engineering 49 (7) 733-736 (2002).

[25] A. Voss, S. Schulz, R. Schroeder, M. Baumert, P. Caminal, “Methods derived from nonlinear dynamics for analysing heart rate variability, Philosophical Transactions of the Royal Society A: Mathematical,” Physical and Engineering Sciences 367 (1887) 277-296 (2008).

[26] L. Glass, P. Hunter, A. McCulloch, “Theory of heart: biomechanics, biophysics, and nonlinear dynamics of cardiac function,” Springer Science & Business Media, (2012).

[27] P. Billingsley, “Ergodic theory and information,” Vol. 1, Wiley New York, 1965.

[28] T. Sauer, J. A. Yorke, M. Casdagli, “Embedology,” Journal of statistical Physics 65 (3-4) 579-616 (1991).

[29] A. Chatterjee, “An introduction to the proper orthogonal decomposition,” Current science 808-817 (2000).

[30] A. Wolf, J. B. Swift, H. L. Swinney, J. A. Vastano, “Determining Lyapunov exponents from a time series,” Physica D: Nonlinear Phenomena 16 (3) 285-317 (1985).

[31] A. N. Kolmogorov, “Entropy per unit time as a metric invariant of automorphisms,” Doklady of Russian Academy of Sciences, Vol. 124, pp. 754-755 (1959).

[32] P. Grassberger, I. Procaccia, “Estimation of the kolmogorov entropy from a chaotic signal,” Physical review A 28 (4) 2591 (1983).

[33] J. Theiler, “Efficient algorithm for estimating the correlation dimension from a set of discrete points,” Physical review A 36 (9) 4456 (1987).

[34] A. Pikovsky, J. Kurths, M. Rosenblum, J. Kurths, “Synchronization: a universal concept in nonlinear sciences,” Vol. 12, Cambridge university press (2003).

[35] D. Dubin, “Rapid interpretation of EKG’s: an interactive course,” Cover Publishing Company (2000).

[36] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, et al., “Scikit-learn: Machine learning in python,” Journal of machine learning research 12, 2825-2830 (Oct 2011).

[37] T. Chen, C. Guestrin, “Xgboost: A scalable tree boosting system,” Proceedings of the 22nd acm-sigkdd international conference on knowledge discovery and data mining, ACM, pp. 785-794 (2016).

[38] H. Zou, T. Hastie, “Regularization and variable selection via the elastic net,” Journal of the royal statistical society: series B (statistical methodology) 67 (2) 301-320 (2005).

Claims

[Claim 1] The invention described in this specification.

Images