Methods and systems for assessing disease using dynamic analysis of biophysical signals

Abstract

The illustrative methods and systems facilitate one or more dynamic analyses that can characterize and identify nonlinear dynamic properties (e.g., Lyapunov exponents (LE), correlation dimension, entropy (K2), or statistical and / or geometric properties derived from Poincare maps, etc.) of biophysical signals (e.g., photoplethysmography signals and / or cardiac signals) to predict the presence and / or location of a disease or condition, or an indicator of one of them, including but not limited to, for example, coronary artery disease, heart failure (including but not limited to abnormal left ventricular end-diastolic pressure), and pulmonary hypertension.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This International PCT Application claims priority to and the benefit of U.S. Provisional Patent Application No. 62 / 863,005, filed on June 18, 2019, entitled “Method and System to Assess Disease Using Dynamical Analysis of Cardiac and Photoplethysmographic Signals,” and U.S. Provisional Patent Application No. 62 / 862,991, filed on June 18, 2019, entitled “Method and System to Assess Disease Using Dynamical Analysis of Biophysical Signals,” each of which is incorporated herein by reference in its entirety. Technical Field

[0003] 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 location of cardiovascular, pulmonary, and cardiopulmonary diseases, evolution, or conditions, etc. In another aspect, the present disclosure relates to non-invasive methods that utilize cardiac-related measurements to predict and / or detect the presence, absence, severity, and / or location of cardiovascular, pulmonary, and cardiopulmonary diseases, evolution, or conditions, etc. In another aspect, the present disclosure relates to non-invasive methods that utilize both plethysmography and cardiac-related measurements to predict and / or detect the presence, absence, severity, and / or location of cardiovascular, pulmonary, and cardiopulmonary diseases, evolution, or conditions, etc. Background Art

[0004] As described in more detail below, the term "biophysical signal" includes any physiological signal from which information can be obtained. Without wishing to be limited, a biophysical signal is characterized in part by the energy form the signal takes (e.g., electrical, acoustic, chemical, thermal, magnetic, optical, etc.), one or more physiological systems (e.g., circulatory / cardiovascular, neural, respiratory, etc.) that are the source of the signal and / or are associated with the signal, the relevant organ system, tissue type, cell type, cellular components such as organelles, etc., including combinations thereof. Biophysical signals can be acquired passively or actively, or both.

[0005] Typically, biophysical signals are collected in association with or through invasive or minimally invasive techniques (e.g., by catheterization) and / or the use of radiation (e.g., nuclear imaging), exercise / stress (e.g., treadmill or nuclear stress testing), and / or the administration of pharmacological and / or other agents (e.g., vasodilators, contrast agents). These various approaches may moderately or even significantly increase the cost of collecting such signals because they may require administration in specialized environments, often using expensive equipment that requires the patient to travel to use, and sometimes even requiring, for example, an overnight stay in a hospital or hotel. Some of these approaches increase the patient's risk of side effects, such as infection or allergic reactions. Some approaches expose the patient to undesirable doses of radiation. And in the case of, for example, exercise or treadmill testing, moderate or even severe adverse events (e.g., myocardial infarction) that would not otherwise have occurred may be induced. Furthermore, these various approaches typically increase the time required to determine the health, disease, or condition of the patient whose biophysical signals are being characterized, often requiring weeks or months for patients who already have or are at risk of moderate or even severe health conditions. This can lead to decreased productivity and increased overall healthcare costs for society. Such delays can also cause emotional trauma to patients (which itself can be detrimental to their health), their families, friends, and other caregivers who cater to the patients' needs.

[0006] Thus, it is desirable to obtain information from biophysical signals that minimizes or even eliminates the need to use invasive and / or minimally invasive techniques, radiation, exercise / stress, and / or the use of pharmacological and / or other agents so that the assessment (e.g., prediction and / or detection) of the presence, severity, and (in some cases) location of various diseases, pathologies, or conditions in mammalian or non-mammalian organisms can be accomplished more safely, at a lower cost, and / or in a shorter time than current methods and systems.

[0007] The methods and systems described herein address this need and can be used for a variety of clinical and even research needs in a variety of settings—from the hospital to the emergency room, laboratory, battlefield, or remote settings, at the point of care with the patient's primary care physician or other caregiver, or even at home. Without limitation, the following description provides example methods and systems for use in the context of cardiac or cardiovascular-related disease states and conditions, particularly various forms of pulmonary hypertension (PH), various forms of coronary artery disease (CAD), and various forms of heart failure. Summary of the Invention

[0008] The illustrative 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 a Poincare map, etc.) of biophysical signals (e.g., photoplethysmography signals and / or cardiac signals) to predict the presence and / or location of a disease or condition, or an indicator of one of the above-mentioned diseases or conditions, including but not limited to, for example, coronary artery disease, heart failure (including but not limited to abnormal left ventricular end-diastolic pressure), and pulmonary hypertension.

[0009] In some embodiments, dynamical system and nonlinear dynamic features are extracted, such as entropy rate "K2", correlation dimension "D2" of fractal dimension, Lyapunov exponent ("LE"), mutual information (MI) and correlation (XC). In some embodiments, one or more features associated with the Poincare map are extracted.

[0010] As used herein, "cardiac signal" refers to one or more signals related to the structure, function, and / or activity of the cardiovascular system, including the electrical / electrochemical conduction aspects of such signals, which, for example, cause myocardial contraction. In some embodiments, the cardiac signal may include electrocardiographic signals, such as those acquired by electrocardiography (ECG), or signals of other modalities.

[0011] As used herein, "photoplethysmography" refers to a signal waveform acquired from an optical sensor that corresponds to measured changes in the absorption of light by oxygenated and deoxygenated hemoglobin, such as light having wavelengths in the red and infrared spectrums. In some embodiments, the photoplethysmography signal comprises a raw signal acquired by a pulse oximeter or photoplethysmography (PPG). In some embodiments, the photoplethysmography signal is acquired from custom or dedicated equipment or circuitry (including off-the-shelf devices) configured to acquire such signal waveforms for use in diagnosing a disease or abnormal condition. The photoplethysmography signal typically includes a red photoplethysmography signal (e.g., electromagnetic signals in the visible light spectrum primarily having wavelengths of approximately 625 to 740 nanometers) and an infrared photoplethysmography signal (e.g., electromagnetic signals extending from the nominal red edge of the visible light spectrum up to approximately 1 mm), although different combinations of other light spectrums (e.g., near infrared, blue, and green) may be used, depending on the type and / or mode of measurement employed in conjunction with the photoplethysmography.

[0012] "Biophysical signals" are not limited to cardiac signals, neurological signals, or photoplethysmography signals, but encompass any physiological signal from which information can be obtained. Without limitation to the examples, biophysical signals can be divided into types or categories that may include, for example, electrical signals (e.g., certain cardiac and nervous system related signals that can be observed, identified, and / or quantified by techniques such as measuring voltage / potential, impedance, resistivity, conductivity, current, etc., in various domains such as time and / or frequency), magnetic signals, electromagnetic signals, optical signals (e.g., signals that can be observed, identified, and / or quantified by techniques such as reflection, interference, spectroscopy, absorbance, transmittance, visual observation, photoplethysmography, etc.), acoustic signals, chemical signals, mechanical signals (e.g., signals related to fluid flow, pressure, motion, vibration, displacement, strain), thermal signals, and electrochemical signals (e.g., signals that can be associated with the presence of certain analytes such as glucose). In some cases, biophysical signals may be described in the context of physiological systems (e.g., respiratory, circulatory (cardiovascular, pulmonary), neural, lymphatic, endocrine, digestive, excretory, muscular, skeletal, renal / urinary / excretory, immune, epidermal / exocrine, and reproductive) or organ systems (e.g., signals that may be unique to the heart and lungs when they work together), or may be described in the context of tissues (e.g., muscle, fat, nerves, connective tissue, bone), cells, organelles, molecules (e.g., water, proteins, fats, carbohydrates, gases, free radicals, inorganic ions, minerals, acids and other compounds, elements and their subatomic components). Unless otherwise specified, the term "biophysical signal acquisition" generally refers to any passive or active means of acquiring biophysical signals from a physiological system (e.g., a mammalian or non-mammalian organism). Passive and active biophysical signal acquisition generally refers to the observation of natural or induced electrical, magnetic, optical, and / or acoustic emissivity of body tissue. Non-limiting examples of passive and active biophysical signal acquisition means include, for example, observing the natural radiation of body tissue in the form of voltage / potential, current, magnetism, light, sound, and other non-active means, and in some cases, inducing such radiation. 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 pulse oximetry or photoplethysmography), visible light, ultraviolet light, and other active means of interrogating body tissue that do not involve ionizing energy or radiation (e.g., X-rays). Active biophysical signal acquisition may involve excitation-emission spectroscopy (including, for example, excitation-emission fluorescence). Active biophysical signal acquisition may also involve transmitting ionizing energy or radiation (e.g., X-rays) (also referred to as "ionizing biophysical signals") to body tissue.Passive and active biophysical signal acquisition approaches can be performed in conjunction with invasive procedures (eg, through surgery or invasive radiological intervention protocols) or can be performed non-invasively (eg, through imaging).

[0013] The methods and systems described in various embodiments herein are not limited thereto and may be used in any context of another physiological system or a living body's system, organ, tissue, cell, etc. By way of example only, two types of biophysical signals that may be used in a cardiovascular context include cardiac signals that may be acquired by conventional electrocardiogram (ECG / EKG) equipment, bipolar broadband biopotential (cardiac) signals that may be acquired from other devices (such as those described herein), and signals that may be acquired by various volumetric descriptive techniques such as photoplethysmography.

[0014] In the context of the present disclosure, techniques are described for acquiring and analyzing biophysical signals, particularly for diagnosing the presence, location (if applicable), and / or severity of certain disease states or conditions in, associated with, or affecting the cardiovascular (or cardiac) system, including, for example, pulmonary hypertension (PH), coronary artery disease (CAD), and heart failure (e.g., left-sided or right-sided heart failure).

[0015] 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 encompass a range of conditions. PH often has a complex and multifactorial etiology and has an insidious clinical onset of varying severity. PH may develop complications such as right heart failure and, in many cases, is fatal. The World Health Organization (WHO) classifies PH into five groups or types. The first PH group in the WHO classification is pulmonary arterial hypertension (PAH). PAH is a chronic disease with no current cure that, among other things, causes tightening and hardening of the pulmonary artery walls. PAH requires at least cardiac catheterization for diagnosis. PAH is characterized by pulmonary artery vasculopathy, defined during cardiac catheterization as a mean pulmonary artery pressure of 25 mmHg or higher. One form of pulmonary hypertension is called idiopathic pulmonary hypertension—PAH that occurs without a clear cause. Subtypes 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 encompasses all causes that lead to narrowing of the pulmonary vascular structures. In PAH, the gradual narrowing of the pulmonary artery bed is due to an imbalance in vasoactive mediators, including prostacyclin, nitric oxide, and endothelin-1. This can lead to increased right ventricular afterload, right heart failure, and premature death. The second group of PH, according to the WHO classification, is pulmonary hypertension due to left-sided heart disease. This group of conditions is typically characterized by problems on the left side of the heart. Over time, these problems lead to changes in the pulmonary arteries. Specific subgroups include left ventricular systolic dysfunction, left ventricular diastolic dysfunction, valvular disease, and congenital cardiomyopathy and obstruction due to non-valvular disease. Treatment of group II PH often focuses on the underlying problem (e.g., surgery to replace the heart valve, various medications, etc.). The third group of PH, according to the WHO classification, is large and diverse and is often related to lung disease or hypoxia. Subgroups include chronic obstructive pulmonary disease, interstitial lung disease, sleep apnea, alveolar hypoventilation, chronic high-altitude exposure, and developmental lung disease. The fourth group of PH is classified by the WHO as chronic thromboembolic pulmonary hypertension, which is caused when a blood clot enters or forms in the lungs, blocking the flow of blood through the pulmonary arteries. The fifth group of PH is classified by the WHO as a subgroup that includes rare diseases that cause PH, such as blood system diseases, systemic diseases (such as sarcoidosis involving the lungs), metabolic disorders, and other diseases. The mechanisms of PH in this fifth group are poorly understood.

[0016] All forms of PH can be difficult to diagnose during a routine physical exam because the most common symptoms of PH (shortness of breath, fatigue, chest pain, edema, palpitations, dizziness) are associated with many other conditions. Blood tests, chest X-rays, electrocardiograms and echocardiograms, pulmonary function tests, exercise tolerance tests, and nuclear scans are all widely used to help physicians diagnose specific forms of PH. As mentioned above, the "gold standard" for diagnosing PH, especially PAH, is cardiac catheterization of the right side of the heart by directly measuring the pressure in the pulmonary artery. If a subject is suspected of having PAH, one of several investigations may be performed to confirm the condition, such as an electrocardiogram, chest x-ray, and pulmonary function tests. It is common to see evidence of right heart strain on the electrocardiogram and significant evidence of enlarged pulmonary arteries or heart on the chest x-ray. However, a normal electrocardiogram and chest x-ray cannot rule out the diagnosis of PAH. Further testing may be needed to confirm the diagnosis and determine the cause and severity. For example, blood tests, exercise testing, and overnight oximetry testing may be performed. In addition, imaging tests may also be performed. Examples of imaging tests include isotope perfusion lung scanning, high-resolution computed tomography, computed tomography pulmonary angiography, and magnetic resonance pulmonary angiography. If these (and possibly other) non-invasive tests support a diagnosis of PAH, right heart catheterization is typically required to confirm the diagnosis by directly measuring pulmonary pressures. It also allows for measurement of cardiac output and estimation of left atrial pressure using pulmonary artery wedge pressure. Although non-invasive techniques exist to determine whether PAH is present in a subject, these techniques cannot reliably confirm a 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 entire contents of which are incorporated herein by reference.

[0017] Heart failure affects nearly 6 million people in the United States alone, with more than 870,000 diagnosed each year. The term "heart failure" (sometimes called congestive heart failure or CHF) generally refers to a chronic, progressive condition or progression in which the heart muscle cannot pump enough blood to meet the body's needs because the heart muscle has become weak or stiff, or because there are defects that prevent normal circulation. This can lead to symptoms such as blood and fluid backing up into the lungs, swelling, fatigue, dizziness, fainting, a fast and / or irregular heartbeat, a dry cough, nausea, and shortness of breath.

[0018] HF is a complex disease encompassing a wide range of symptoms that may result from a variety of different pathologies. The clinical syndrome can result from any structural or functional alteration in the heart that impairs the filling or ejection capacity of the ventricles. Patients are typically categorized into two distinct groups based on left ventricular (LV) ejection fraction (LVEF): 1) HF with reduced LVEF (HFrEF [LVEF ≤ 40%]) and 2) HF with preserved LVEF (HFpEF [LVEF ≥ 50%]). Although the defining characteristics of HFrEF are systolic dysfunction and relative diastolic dysfunction, both can occur to varying degrees in HFrEF and HFpEF. Among the more than 6 million Americans diagnosed, there is a roughly even distribution between the two categories. Furthermore, the 5-year mortality rate is similar in both groups, with estimates ranging from 50% to 75%.

[0019] Common causes of heart failure are coronary artery disease (CAD), hypertension, cardiomyopathy, arrhythmias, kidney disease, heart defects, obesity, tobacco use, and diabetes. Common types of heart failure include diastolic heart failure (DHF), left or left-sided heart failure / disease (also known as left ventricular heart failure), right or right-sided heart failure / disease (also known as right ventricular heart failure), and systolic heart failure (SHF).

[0020] Left-sided heart failure is further divided into two main types: systolic failure (or heart failure with reduced ejection fraction or reduced left ventricular function) and diastolic failure / dysfunction (or heart failure with preserved ejection fraction or preserved left ventricular function). Procedures and techniques commonly used to determine whether a patient has left-sided heart failure include cardiac catheterization, X-rays, echocardiograms, electrocardiograms (EKGs), electrophysiology studies, radionucleotide imaging, and various treadmill tests, including those that measure peak VO2. The ejection fraction (EF) is a measurement expressed as a percentage of the amount of blood pumped out by the ventricle (the left ventricle in the case of left-sided heart failure) with each contraction, which is most often obtained noninvasively via echocardiography. A normal left ventricular ejection fraction (LVEF) ranges from about 55% to about 70%.

[0021] When systolic failure occurs, the left ventricle is unable to contract forcefully enough to keep blood circulating throughout the body, preventing it from supplying the body with blood properly. As the left ventricle pumps harder to compensate, it becomes weaker and thinner. As a result, blood flows backward into the organs, leading to fluid accumulation 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), which is expressed as a percentage of the volume of blood pumped out by the left ventricle relative to its filling volume, to help diagnose systolic failure. In particular, left ventricular ejection fraction (LVEF) values ​​below 55% indicate that the heart's ability to pump blood is lower than normal and can be measured below about 35% in severe cases. Generally, when these LVEF values ​​are lower than normal, a diagnosis of systolic failure can be made or can help diagnose systolic failure.

[0022] When diastolic heart failure occurs, the left ventricle becomes stiff or thickened, losing its ability to relax normally. This, in turn, means the heart's lower left chamber cannot properly fill with blood. This reduces the amount of blood pumped to the body. Over time, this can cause blood to accumulate in the left atrium and then in the lungs, leading to fluid congestion and heart failure symptoms. In these cases, LVEF values ​​tend to remain within a normal range. Therefore, other tests, such as invasive catheterization, can be used to measure left ventricular end-diastolic pressure (LVEDP) to help diagnose diastolic heart failure and other forms of heart failure with preserved EF. Typically, LVEDP is measured directly by placing a catheter in the left ventricle or indirectly by measuring pulmonary capillary wedge pressure by placing a catheter in the pulmonary artery. Such catheterization techniques, by their nature, increase the risk of infection and other complications for patients and are often expensive. Therefore, non-invasive methods and systems for determining or estimating LVEDP when diagnosing the presence and / or severity of diastolic heart failure and countless other forms of heart failure with preserved EF are desirable. Furthermore, non-invasive methods and systems for diagnosing the presence and / or severity of diastolic heart failure, as well as myriad other forms of heart failure with preserved EF, that do not necessarily include determination or estimation of abnormal LVEDP are desirable. Embodiments of the present disclosure address all of these needs.

[0023] Right-sided heart failure often occurs as a result of left-sided heart failure, when a weakened and / or stiff left ventricle loses its ability to pump blood effectively to the rest of the body. As a result, fluid is forced back up through the lungs, weakening the right side of the heart and leading to right-sided heart failure. This backflow backs up in the veins, causing fluid to swell in the legs, ankles, gastrointestinal tract, and liver. In other cases, certain lung diseases (such as chronic obstructive pulmonary disease and pulmonary fibrosis) can lead to right-sided heart failure even if the left side of the heart is functioning normally. Procedures and techniques commonly used to determine whether a patient has left-sided heart failure include blood tests, heart CT scans, cardiac catheterization, X-rays, coronary angiography, echocardiograms, electrocardiograms (EKGs), myocardial biopsies, pulmonary function studies, and various forms of stress testing, such as treadmill tests.

[0024] Pulmonary hypertension is closely related to heart failure. As mentioned above, PAH (first WHO PH group) can lead to increased right ventricular afterload, right heart failure, and premature death. PH caused by left heart failure (second WHO PH group) is considered the most common cause of PH.

[0025] Ischemic heart disease (also known as cardiac ischemia or myocardial ischemia) and related conditions or pathologies can also be estimated or diagnosed using the technology disclosed herein. Ischemic heart disease is a disease or a group of diseases characterized by a decrease in blood supply to the myocardium, usually caused by coronary artery disease (CAD). CAD is closely related to heart failure and is its most common cause. CAD typically occurs when atherosclerosis (hardening or stiffening of the inner wall and accumulation of plaque therein, usually with abnormal inflammation) occurs in the inner walls of the coronary arteries that supply blood to the myocardium or heart muscle. Over time, CAD can also weaken the heart muscle and lead to, for example, angina, myocardial infarction (cardiac arrest), heart failure, and arrhythmias. Arrhythmia is an abnormal heart rhythm that may include any change in the normal sequence of cardiac electrical conduction, 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, and many invasive techniques and tools are used to assess the presence and severity of the above-mentioned conditions. Furthermore, the commonality among the symptoms of these diseases and / or conditions, as well as the fundamental connection between the respiratory and cardiovascular systems—as they work together to supply oxygen to the body's cells and tissues—represents a complex physiological interconnectedness that can be exploited to improve the detection and ultimately treatment of such diseases and / or conditions. Traditional methods of evaluating these biophysical signals in this setting remain significant challenges in providing healthcare providers with the tools to accurately detect / diagnose the presence or absence of such diseases and conditions.

[0026] For example, in electrocardiography—the field of cardiology in which the electrical activity of the heart is analyzed 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 coronary artery narrowing or occlusion, with the pathology manifesting at different locations in the heart and at varying stages of severity, making accurate diagnosis challenging. Furthermore, the conductive properties of the myocardium can vary from person to person, and other factors such as measurement variability associated with the placement of measurement probes and parasitic losses associated with such probes and their associated components can also affect the biophysical signals captured during cardiac electrophysiological examinations. Furthermore, when the conductive properties of the myocardium are captured as relatively long cardiac phase gradient signals, they can exhibit complex nonlinear variability that cannot be effectively captured by traditional modeling techniques.

[0027] In practice, the exemplified methods and systems facilitate one or more dynamic analyses that can characterize and identify nonlinear dynamic properties (e.g., Lyapunov exponents (LE), correlation dimensions, entropy (K2), or statistical and / or geometric properties derived from Poincare maps) of biophysical signals (e.g., photoplethysmography signals and / or cardiac signals) to predict the presence and / or location of a disease or condition, or an indicator of one of the above-mentioned diseases or conditions, including but not limited to coronary artery disease, heart failure (including but not limited to abnormal left ventricular end-diastolic pressure) and pulmonary hypertension, etc.

[0028] In some embodiments, the dynamic features include at least a determined relevant dimension of the acquired photoplethysmography signal (e.g., a red photoplethysmography signal or an infrared photoplethysmography signal). Notably, it has been observed that such assessed dynamic features are associated with abnormalities in left ventricular end-diastolic pressure (LVEDP) and can be used to predict the presence and / or severity of such conditions in a clinical setting. As described above, LVEDP is considered a measure of ventricular function, particularly left ventricular function, which is often used to identify patients at increased risk of developing late clinical symptoms of heart failure (HF). Elevated LVEDP has been observed to be common after myocardial infarction; however, it has been considered an independent predictor of subsequent HF risk. In some embodiments, the dynamic features include at least an assessed attribute of a Poincare map object derived from waveforms of adjacent cardiac cycles. In some embodiments, the assessed attribute includes a ratio of circumference values ​​of the Poincare map object (e.g., from infrared measurements). In some embodiments, the assessed attribute includes a surface area of ​​the Poincare map object.

[0029] In one aspect, a method for non-invasively assessing a disease state or abnormal condition of a subject is disclosed, the method comprising: 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 photoplethysmography signals or cardiac signals) of the subject; determining, by the one or more processors, one or more dynamic characteristics of the biophysical signal dataset; and determining, by the one or more processors, one or more estimates of the presence, location, and / or severity of a disease or condition based on the determined one or more dynamic characteristics.

[0030] In some embodiments, the presence and / or severity of a disease or condition can be assessed based on an assessment of left ventricular end-diastolic pressure (LVEDP), including an elevated or abnormal LVEDP.

[0031] In some embodiments, the disease state or condition comprises significant coronary artery disease.

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

[0033] In some embodiments, the disease state or condition comprises pulmonary hypertension (PAH).

[0034] In some embodiments, the disease state or condition comprises pulmonary hypertension due to left heart disease.

[0035] In some embodiments, the disease state or condition comprises a rare disease that can lead to pulmonary hypertension.

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

[0037] In some embodiments, the disease state or condition comprises right ventricular heart failure or right-sided heart failure.

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

[0039] In some embodiments, the disease state or condition comprises diastolic heart failure (DHF).

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

[0041] In some embodiments, the disease state or condition comprises a cardiac arrhythmia.

[0042] In some embodiments, the method further comprises determining, by the one or more processors, one or more second estimates of the presence, location, and / or severity of two or more of the diseases or conditions.

[0043] In some embodiments, the dynamic characteristic is selected from the group consisting of: entropy value (K2), fractal dimension (D2), Lyapunov exponent, autocorrelation, auto-mutual information, cross-correlation, and mutual information.

[0044] In some embodiments, the acquired biophysical signal dataset includes one or more red photoplethysmography signals.

[0045] In some embodiments, the acquired biophysical signal dataset includes one or more infrared photoplethysmography signals.

[0046] In some embodiments, the acquired biophysical signal dataset includes one or more cardiac signals.

[0047] In some embodiments, the method further includes: generating, by the one or more processors, a visualization of an estimate of the presence, location, and / or severity of a disease or condition, wherein the generated visualization is rendered and displayed on a display of a computing device (e.g., a computing workstation, a surgical device, a diagnostic device, or an instrument device) and / or presented in a report (e.g., an electronic report).

[0048] In some embodiments, the method further comprises determining, by the one or more processors, a histogram of periodic variations in the biophysical signal dataset, wherein the histogram is used to determine an estimate of the presence, location, and / or severity of the disease or condition.

[0049] In some embodiments, the method further comprises: determining, by the one or more processors, a Poincare map of the obtained biophysical signal data set; determining, by the one or more processors, an alpha shape object of the Poincare map; and determining, by the one or more processors, one or more geometric properties of the alpha shape object, wherein the determined one or more geometric properties are used to determine an estimate of the presence, location, and / or severity of the disease or condition.

[0050] In some embodiments, the one or more determined geometric characteristics also include two or more characteristics selected from the group consisting of: a density value of the alpha shape object; a convex surface area value of the alpha shape object; a perimeter value of the alpha shape object; a porosity value of the alpha shape object; and a blank area value of the alpha shape object.

[0051] In some embodiments, the one or more determined geometric characteristics also include two or more characteristics selected from the group consisting of: the semi-axis length "a" of the estimated maximum cluster ellipse of the Poincare mapping; the semi-axis length "b" of the estimated maximum cluster ellipse of the Poincare mapping; the length of the longest axis of the estimated maximum cluster ellipse of the Poincare mapping; the length of the shortest axis of the estimated maximum cluster ellipse of the Poincare mapping; the number of clusters evaluated in the Poincare mapping; the evaluated number of kernel density modes in the histogram; and the Sarles bimodality coefficient value evaluated based on the histogram.

[0052] In one aspect, a method for non-invasively assessing a disease state or abnormal condition in a subject is disclosed, the method comprising: 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 the one or more processors, a Poincare map of the variance in the biophysical signal dataset; determining, by the one or more processors, an alpha-shaped object of the Poincare map; determining, by the one or more processors, one or more geometric properties of the alpha-shaped object; and determining, by the one or more processors, an estimate of the presence, location, and / or severity of a disease or condition based on the determined one or more geometric properties, wherein the disease state comprises the presence of coronary artery disease (e.g., significant coronary artery disease) or elevated or abnormal left ventricular end-diastolic pressure.

[0053] In some embodiments, the determined Poincare map is generated by plotting photoplethysmography signal peaks on a first axis at a first time x-1 to a second time x and on a second axis at the second time x to a third time x+1.

[0054] In fact, in the Poincare map, references to time are synonymous and can therefore be used interchangeably with respect to a data point in a given dataset.

[0055] On the other hand, a system for non-invasively assessing a disease state or abnormal condition of a subject is disclosed, the system comprising: a processor; and a memory having instructions stored thereon, wherein execution of the instructions by the 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 photoplethysmography signals or cardiac signals) of the subject; determine one or more dynamic characteristics of the biophysical signal dataset; and determine one or more estimates of the presence, location, and / or severity of a disease or condition based on the determined one or more dynamic characteristics.

[0056] In some embodiments, execution of the instructions by the processor further causes the processor to: determine one or more second estimates of the presence, location, and / or severity of two or more of the diseases or conditions.

[0057] In some embodiments, the dynamic characteristic is selected from the group consisting of: entropy value (K2), fractal dimension (D2), Lyapunov exponent, autocorrelation, auto-mutual information, cross-correlation, and mutual information.

[0058] In some embodiments, the acquired biophysical signal dataset includes one or more red photoplethysmography signals.

[0059] In some embodiments, the acquired biophysical signal dataset includes one or more infrared photoplethysmography signals.

[0060] In some embodiments, the acquired biophysical signal dataset includes one or more cardiac signals.

[0061] In some embodiments, execution of the instructions by the processor further causes the processor to: generate a visualization of an estimate of the presence, location, and / or severity of the disease or condition, wherein the generated visualization is rendered and displayed on a display of a computing device (e.g., a computing workstation, a surgical device, a diagnostic device, or an instrument device) and / or presented in a report (e.g., an electronic report).

[0062] In some embodiments, execution of the instructions by the processor further causes the processor to: determine a histogram of periodic variations in the biophysical signal dataset, wherein the histogram is used to determine an estimate of the presence, location, and / or severity of the disease or condition.

[0063] In some embodiments, execution of the instructions by the processor further causes the processor to: determine a Poincare map of the obtained biophysical signal dataset; determine an alpha shape object of the Poincare map; and determine one or more geometric properties of the alpha shape object, wherein the determined one or more geometric properties are used to determine an estimate of the presence, location, and / or severity of the disease or condition.

[0064] In some embodiments, the one or more determined geometric characteristics also include two or more characteristics selected from the group consisting of: a density value of the alpha shape object; a convex surface area value of the alpha shape object; a perimeter value of the alpha shape object; a porosity value of the alpha shape object; and a blank area value of the alpha shape object.

[0065] In some embodiments, the one or more determined geometric characteristics also include two or more characteristics selected from the group consisting of: the semi-axis length "a" of the estimated maximum cluster ellipse of the Poincare mapping; the semi-axis length "b" of the estimated maximum cluster ellipse of the Poincare mapping; the length of the longest axis of the estimated maximum cluster ellipse of the Poincare mapping; the length of the shortest axis of the estimated maximum cluster ellipse of the Poincare mapping; the number of clusters evaluated in the Poincare mapping; the evaluated number of kernel density modes in the histogram; and the value of the Sarles bimodality coefficient evaluated based on the histogram.

[0066] In some embodiments, the system is further configured to obtain (e.g., from a stored database or from a measurement system) a biophysical signal dataset (e.g., a photoplethysmography signal) of the subject; determine a Poincare map of the variance in the biophysical signal dataset; determine an alpha-shaped object of the Poincare map; determine one or more geometric properties of the alpha-shaped object; and determine an estimate of the presence, location, and / or severity of a disease or condition based on the determined one or more geometric properties, wherein the disease state includes the presence of coronary artery disease (e.g., significant coronary artery disease) or elevated or abnormal left ventricular end-diastolic pressure.

[0067] In some embodiments, the determined Poincare map is generated by plotting photoplethysmography signal peaks on a first axis at a first time x-1 to a second time x and on a second axis at the second time x to a third time x+1.

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

[0069] In some embodiments, the system further comprises: a measurement system configured to acquire one or more cardiac signals.

[0070] In some embodiments, the system further comprises: 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.

[0071] In another aspect, a system is disclosed, comprising: a processor; and a memory having instructions stored therein, wherein execution of the instructions by the processor causes the processor to perform the method described above.

[0072] In another aspect, a computer-readable medium storing instructions is disclosed, wherein execution of the instructions by a processor causes the processor to perform the method described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments and, together with the description, serve to explain the principles of the method and system.

[0074] Embodiments of the present invention may be better understood from the following detailed description when read in conjunction with the accompanying drawings. Such embodiments, which are provided for illustrative purposes only, illustrate novel and non-obvious aspects of the present invention. The accompanying drawings include the following figures:

[0075] Figure 1 is a schematic diagram of an example system configured to non-invasively assess dynamic characteristics of a physiological system to predict and / or estimate the presence, location (if applicable), and / or severity of a disease or condition in such physiological system, or an indicator of one of the above diseases or conditions, according to an exemplary embodiment.

[0076] Figure 1A is a schematic diagram of another example system configured to non-invasively evaluate dynamic characteristics of a photoplethysmography signal to predict and / or estimate the presence, location (if applicable), and / or severity of a disease or condition in a physiological system or an indicator of one of the above diseases or conditions in accordance with an exemplary embodiment.

[0077] Figure 1B is a schematic diagram of an example system configured to non-invasively evaluate dynamic characteristics of cardiac signals to predict and / or estimate the presence, location (if applicable), and / or severity of a disease or condition in a physiological system, or an indicator of one of the above diseases or conditions, according to an exemplary embodiment.

[0078] Figure 2A Example photoplethysmography signals (eg, red photoplethysmography signals and infrared photoplethysmography signals) are shown as examples of Figure 1 Example biophysical signals acquired by a measurement system. The signals are shown with baseline drift and high-frequency noise removed.

[0079] Figure 2B and 2C Removes high-frequency noise Figure 2A Frequency domain representation of the acquired photoplethysmography signal.

[0080] Figure 2D and 2E 1 and 2 respectively illustrate example sensor configurations for acquiring the photoplethysmography signal 104 according to an exemplary embodiment.

[0081] Figure 2F A three-dimensional phase space plot of the acquired photoplethysmography signal acquired via an infrared sensor is shown.

[0082] Figure 2G Shown Figure 2F A two-dimensional projection of the same data.

[0083] Figure 3A An example cardiac signal (eg, a biopotential signal) is shown as a pulsed signal transmitted via a pulsed signal source according to an exemplary embodiment. Figure 1 Example biophysical signals acquired by a measurement system. The signals are shown with baseline drift and high-frequency noise removed.

[0084] Figure 3B is configured to collect Figure 3A Diagram of the cardiac signal measurement system.

[0085] Figure 3C According to an exemplary embodiment, Figure 3B Example placement of a measurement system on a patient in a clinical setting.

[0086] Figure 3D According to an exemplary embodiment, Figure 3B The surface electrodes of the measurement system are placed on the patient's chest and back to collect Figure 3A An exemplary arrangement diagram of a cardiac signal.

[0087] Figure 4 Experimental results from a study according to an exemplary embodiment are shown, which indicate the clinical predictive value of specific dynamic features extracted from photoplethysmography signals (red photoplethysmography signals and infrared photoplethysmography signals), which indicate the presence or absence of a disease or abnormal condition or an indicator of one of the above-mentioned diseases or conditions.

[0088] Figure 5 Experimental results from a study according to an exemplary embodiment are shown that indicate the clinical predictive value of specific dynamic features extracted from cardiac signals that indicate the presence or absence of a disease or abnormal condition or an indicator of one of the aforementioned diseases or conditions.

[0089] Figure 6 and 11 Lipuyanov exponent feature extraction modules according to exemplary embodiments are respectively shown.

[0090] Figure 7 and 12 The fractal dimension feature extraction modules according to exemplary embodiments are respectively shown.

[0091] Figure 8 and 13 Entropy feature extraction modules according to exemplary embodiments are respectively shown.

[0092] Figure 9 and14 Mutual information (MI) feature extraction modules according to exemplary embodiments are respectively shown.

[0093] Figure 10 and 15 Correlation feature extraction modules according to exemplary embodiments are respectively shown.

[0094] Figure 16 Experimental results from a study according to an exemplary embodiment are shown, which indicate the clinical predictive value of certain dynamic features extracted from the produced Poincare maps of photoplethysmography signals (red photoplethysmography signals and infrared photoplethysmography signals), which clinical predictive value indicates the presence or absence of a disease or abnormal condition or an indicator of one of the above-mentioned diseases or conditions.

[0095] Figure 17 A Poincare map statistical feature extraction module according to an exemplary embodiment is shown.

[0096] Figure 18 A Poincare map geometric feature extraction module according to an exemplary embodiment is shown.

[0097] Figure 18A Exemplary landmarks in an infrared photoplethysmography signal are shown in accordance with an exemplary embodiment.

[0098] Figure 18B An example distribution of periodicity between identical landmarks from adjacent cycles in an infrared photoplethysmography signal is shown in accordance with an exemplary embodiment.

[0099] Figure 18C An example Poincare map generated from a periodic distribution between lowest-peak landmarks in an infrared photoplethysmography signal is shown in accordance with an exemplary embodiment.

[0100] Figure 19 A cluster graph geometric feature extraction module according to an exemplary embodiment is shown.

[0101] Figure 20 An example computing environment is shown in which an example embodiment of the analysis system may be implemented. DETAILED DESCRIPTION

[0102] Each and every feature described herein and each combination of two or more of these features is included within the scope of the present invention, provided that the features included in this combination are not mutually inconsistent.

[0103] While the present disclosure relates to the beneficial evaluation of biophysical signals (e.g., raw or pre-processed photoplethysmography signals, cardiac signals, etc.) in the diagnosis and treatment of cardiac-related pathologies and conditions, such evaluations may also be applied to the diagnosis and treatment (including surgical, minimally invasive, and / or drug therapy) of any pathology or condition of any relevant system of a living being in which the biophysical signals are involved. In a cardiac (or cardiovascular) setting, 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 (alone or in combination), such as placement of stents in coronary arteries, performing atherectomy, angioplasty, prescribing drug therapy, and / or prescribing exercise, nutritional and other lifestyle changes, and the like. Other cardiac-related pathologies or conditions that can be diagnosed include, for example, arrhythmias, congestive heart failure, valvular failure, pulmonary hypertension (e.g., pulmonary hypertension, pulmonary hypertension caused by left heart disease, pulmonary hypertension caused by lung disease, pulmonary hypertension caused by chronic thrombosis, and pulmonary hypertension caused by other diseases (e.g., blood or other disorders), and other cardiac-related pathologies, conditions, and / or diseases. In some embodiments, the assessment can be applied to neurological-related pathologies and conditions. Non-limiting examples of neurological-related diseases, pathologies or conditions that may be diagnosable include, for example, epilepsy, schizophrenia, Parkinson's disease, Alzheimer's disease (and all other forms of dementia), autism spectrum disorders (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, language disorders, various psychiatric disorders, brain / spinal cord / nerve injuries, chronic traumatic encephalopathy, cluster headaches, migraines, neuropathies (various forms, including peripheral neuropathy), phantom limb / pain, chronic fatigue syndrome, acute and / or chronic pain (including back pain, failed back surgery syndrome, etc.), movement dysfunction, anxiety disorders, conditions caused by infections or exogenous factors (such as 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.

[0104] 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 are provided solely to illustrate the description of the disclosed technology, and it should not be considered that any such reference is "prior art" for any aspect of the disclosed technology described herein. In terms of notation, "[n]" corresponds to the nth reference in the list. For example,

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

[0105] Example System

[0106] Figure 1 is a schematic diagram of an example system 100 configured to non-invasively assess dynamic characteristics of a physiological system to predict and / or estimate (e.g., determine) the presence, location (if applicable), and / or severity of a disease or condition in such physiological system, or an indicator of one of the disease or condition. In practice, as used herein, the term "predict" refers to forewarning of a future event (e.g., the potential development of a disease or condition), while the term "estimate" may refer to quantification of some metric based on available information, e.g., the presence, location (if applicable), and / or severity of a disease or condition, or an indicator of one of the disease or condition. The operations of predicting and estimating may generally be referred to as determining.

[0107] As used herein, "physiological system" may refer to the cardiovascular system, pulmonary system, renal system, nervous system, and other functional systems and subsystems of the body. In the context of the cardiovascular system, system 100 facilitates studying the complex, nonlinear dynamics of the heart over many cardiac cycles.

[0108] exist Figure 1 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 to generate a biophysical signal dataset 110 .

[0109] In some embodiments, the acquired biophysical signals 104 include one or more photoplethysmography signals (e.g., Figure 1A shown).

[0110] In other embodiments, the acquired biophysical signals 104 include one or more cardiac signals associated with biopotential measurements of the body (e.g., Figure 1B As used herein, "cardiac signal" refers to one or more signals related to the structure, function, and / or activity of the cardiovascular system, including the electrical / electrochemical conduction aspects of such signals, which, for example, cause myocardial contraction. In some embodiments, the cardiac signal may include an electrocardiogram (ECG) signal, such as those acquired by an electrocardiogram (ECG), or other modality.

[0111] Still refer to Figure 1 The non-invasive measurement system 102 is configured to transmit the acquired biophysical signal dataset 110 or a dataset derived therefrom or processed therefrom to a repository 112 (e.g., a storage area network) (not shown), such as via a communication system and / or network, or via a direct connection, which is accessible to the non-invasive biophysical signal evaluation system. The non-invasive biophysical signal evaluation system 114 (shown as an analysis engine 114) is configured to analyze the dynamic characteristics of the acquired biophysical signal 104.

[0112] In some embodiments, the analysis engine 114 includes a machine learning module 116 that is configured to evaluate a set of features determined from the collected biophysical signals by one or more feature extraction modules (e.g., 118, 120) to determine clinically significant features. Once features are extracted from the photoplethysmography signal or the cardiac signal, any type of machine learning can be used. Examples of embodiments of the machine learning module 116 are configured to implement decision trees, random forests, SVMs, neural networks, linear models, Gaussian processes, nearest neighbors, SVMs, naive Bayes, but are not limited thereto. In some embodiments, the machine learning module 116 can be implemented as described in the following U.S. patent applications: 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,” U.S. patent application Ser. No. 15 / 653,431, entitled “Discovering Genomes to Use in Machine Learning Techniques,” the entire contents of which are incorporated herein by reference. The photoplethysmographic signal can be combined with other acquired photoplethysmographic signals for use in a training dataset or validation dataset when evaluating a set of evaluated dynamic features by the machine learning module 116. The photoplethysmographic signal has an associated signature 122 for a given disease state or abnormal condition. If the evaluated dynamic feature (e.g., from 118 or 120) is determined to be clinically significant, it can then be used as a predictor of a given disease state or abnormal condition or an indicator of one of the diseases or conditions.

[0113] In some embodiments, the analysis engine 114 includes a pre-processing module, eg, configured to remove baseline drift from the acquired biophysical signals and / or normalize them.

[0114] Photoplethysmography signal and acquisition system

[0115] Figure 1A is a schematic diagram of an example system 100 (shown as 100a) configured to non-invasively evaluate dynamic characteristics of acquired photoplethysmography signals 104a to predict and / or estimate (e.g., determine) the presence, location (if applicable), and / or severity of a disease or condition in such a physiological system, or an indicator of one of the aforementioned diseases or conditions, in accordance with an exemplary embodiment.

[0116] The photoplethysmographic signal may include information about the complex interactions between the heart and the respiratory / pulmonary system.In some embodiments, the photoplethysmographic signal is acquired via photoplethysmography.

[0117] A photoplethysmogram is generally understood to include non-invasive circulatory biophysical signals related to the pulsating blood volume in a tissue. A pulse oximeter generates a type of photoplethysmogram that can be used to detect changes in blood volume in the microvascular bed of a tissue. In some embodiments, a photoplethysmogram illuminates the skin and measures changes in light absorption using at least two different wavelengths of light. In outpatient, inpatient, and trauma settings, pulse oximeters are typically worn on a finger (although they can be used on other parts of the body) to measure the oxygen saturation fraction of hemoglobin in the blood (called "SpO2"). However, raw photoplethysmograms are rarely displayed or further analyzed. Various aspects of photoplethysmography are described in "Utility of the Photoplethysmogram in Circulatory Monitoring" by Reisner et al., Journal of Anesthesiology, Vol. 108, pp. 950-958, May 2008, the entire contents of which are incorporated herein by reference.

[0118] exist Figure 1A In the present invention, a non-invasive measurement system 102 (shown as "measurement system" 102a) is configured to acquire one or more photoplethysmography signals 104 (shown as 104a) from a subject 108 (e.g., at a patient's finger; shown as 108a) via a measurement probe 106 (shown as probes 106'a, 106'b) to generate a biophysical signal dataset 110 (shown as 110a). In some embodiments, the acquired photoplethysmography signals 104a are associated with changes in the measured optical absorption of oxygenated and / or deoxygenated hemoglobin.

[0119] In some embodiments, the measurement system 102a includes a custom or dedicated device or circuit (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 signal for analysis. Indeed, in some embodiments, the acquired waveform 104a can be analyzed to calculate Figure 1A The oxygen saturation level of the blood is shown as an “SpO2 reading.” However, for the example analysis application, only the waveform is processed and utilized.

[0120] Still refer to Figure 1AThe non-invasive measurement system 102a is configured to transmit the acquired photoplethysmography signal dataset 110a, or a dataset derived therefrom or processed therefrom, to a repository 112 (e.g., a storage area network), for example, via a communication system and / or network, or via a direct connection, which is accessible to a non-invasive biophysical signal evaluation system. The non-invasive biophysical signal evaluation system 114 (shown as an analysis engine 114a) is configured to analyze the dynamic characteristics of the acquired photoplethysmography signal.

[0121] Figure 2A According to an exemplary embodiment, Figure 1 The measurement system 102 (e.g. Figure 1A Specifically, Figure 2A A signal waveform 202 is shown that correlates to the absorption level of the red spectrum (eg, having wavelengths spanning 660 nm) by deoxyhemoglobin from a patient's finger. Figure 2A Also shown is a signal waveform 204 of the absorption level of the infrared spectrum (e.g., having wavelengths spanning 940 nm) associated with oxygenated hemoglobin from the patient's finger. Other spectra can be acquired. Additionally, measurements can be made at other locations on the body. Figure 2A In the example, the x-axis shows time in seconds and the y-axis shows signal amplitude in millivolts (mV).

[0122] Figure 2B and 2C It shows Figure 2A The power spectrum density diagram of the frequency domain representation of the acquired photoplethysmography signal. Figure 2B and 2C In the graph, the x-axis represents frequency (in Hz) and the y-axis represents the logarithmic power of the signal.

[0123] In some embodiments, light absorption data for the red and infrared channels is recorded at a rate of 500 samples per second. Other sampling rates may be used. The photoplethysmography signal may be acquired simultaneously with each subject's cardiac signal. In some embodiments, the acquisition between the two modalities has a jitter of less than about 10 microseconds (μs). The jitter between cardiac signal channels is about 10 femtoseconds (fs), but other jitter may be tolerated.

[0124] Figure 2D An example sensor configuration for acquiring a photoplethysmography signal 104a is shown in FIG. Figure 2D In the embodiment, the system further comprises a light source (eg, a red LED and an infrared LED) and a phototransistor (eg, a red detector and an infrared detector); the phototransistor is disposed away from the light source.

[0125] Figure 2E Another example sensor configuration for acquiring a photoplethysmography signal 104a according to another exemplary embodiment is shown. Figure 2D In the embodiment, the system further includes a light source (eg, a red LED and an infrared LED) and a phototransistor (eg, a red detector and an infrared detector); however, the phototransistor is disposed close to the light source to measure reflectivity.

[0126] Photoplethysmography signal 104a can be considered a measurement of the state of a dynamic system in the body, similar to a cardiac signal. The behavior of a dynamic system may be affected by the actions of the heart and respiratory system. It is assumed that any distortion (due to disease or abnormal conditions) may manifest itself in the dynamics of photoplethysmography signal 104a through some interaction mechanism.

[0127] 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 drift and filter out noise and mains frequency.

[0128] The acquired photoplethysmography signal 104a can be embedded in some higher dimensional space (e.g., phase space embedding) to reconstruct the manifold (phase space) created by the underlying dynamic system. The three-dimensional visualization and its two-dimensional projection are shown in Figure 2F and 2G (e.g., for the red photoplethysmography signal 202). Specifically, Figure 2F A three-dimensional phase space plot of a photoplethysmographic signal 204 acquired via an infrared sensor is shown. The axes are converted voltage values ​​(i.e., the units on the vertical axis are still mV, but normalized to have a mean value of approximately zero with baseline drift removed). The embedding is defined in Equation 2. The colors are selected to illustrate the coherent structure within this geometric object. Dynamic characteristics of the photoplethysmographic measurement are calculated based on the embedding represented in the graph. Figure 2G A two-dimensional projection of the same photoplethysmography signal is shown.

[0129] Cardiac signal and acquisition system

[0130] Figure 1Bis a schematic diagram of an example system 100 (shown as 100b) according to an exemplary embodiment, which is configured to use acquired cardiac signals 104b to non-invasively assess dynamic characteristics of a physiological system to predict and / or estimate (e.g., determine) the presence, location (if applicable), and / or severity of a disease or condition in the physiological system or an indicator indicative of one of the above-mentioned diseases or conditions.

[0131] exist Figure 1B In the present invention, 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., in the chest and back regions of a patient; shown as 108b) via measurement probes 106 (shown as probes 106a-106f) to generate a biophysical signal dataset 110 (shown as 110b).

[0132] In some embodiments, the measurement system 102 b is configured to acquire a biophysical signal that may be based on a biopotential of the body as a biopotential biophysical signal through a dual potential sensing circuit.

[0133] In a cardiac and / or electrocardiographic context, the measurement system 102b is configured to capture cardiac-related biopotential signals or electrophysiological signals of a mammalian subject (e.g., 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 signals, current signals, impedance signals, magnetic signals, ultrasound or acoustic signals, etc. The term "broadband" with respect to the acquired signals and their corresponding datasets refers to signals whose frequency range is significantly greater than the Nyquist sampling rate of the highest dominant frequency of the physiological system of interest. For a cardiac signal typically having a primary frequency component between about 0.5 Hz and about 80 Hz, the broadband cardiac phase gradient signal or broadband cardiac biophysical signal includes cardiac frequency information of a frequency selected from the group consisting of: a range between about 0.1 Hz and about 1 kHz, a range between about 0.1 Hz and about 2 kHz, a range between about 0.1 Hz and about 3 kHz, a range between about 0.1 Hz and about 4 kHz, a range between about 0.1 Hz and about 5 kHz, a range between about 0.1 Hz and about 6 kHz, a range between about 0.1 Hz and about 7 kHz, a range between about 0.1 Hz and about 8 kHz, a range between about 0.1 Hz and about 9 kHz, a range between about 0.1 Hz and about 10 kHz, and a range between about 0.1 Hz and greater than 10 kHz (e.g., a range between 0.1 Hz and 50 kHz or a range between 0.1 Hz and 500 kHz). In addition to capturing the primary frequency components, broadband acquisition also helps capture other frequencies of interest. Examples of such frequencies of interest may include QRS frequency distribution diagrams (which may have frequencies up to 250 Hz), etc. The term "phase gradient" in relation to acquired signals and corresponding data sets refers to signals acquired at different vantage points on the body to observe phase information of a set of different events / functions of the physiological system of interest. After signal acquisition, the term "phase gradient" refers to the preservation of phase information through the use of non-distorting signal processing and pre-processing hardware, software, and techniques (e.g., phase linear filters and signal processing operators and / or algorithms).

[0134] In some embodiments, the cardiac signal dataset 110b includes broadband biopotential signals, which are acquired, for example, via a phase space recorder described in U.S. patent application publication number 2017 / 0119272, entitled “Method and Apparatus for Wide-Band Phase Gradient Signal Acquisition,” the entire contents of which are incorporated herein by reference. In some embodiments, the cardiac signal dataset 110b includes bipolar broadband biopotential signals, which are acquired, for example, via a phase space recorder described in U.S. patent application publication number 2018 / 0249960, entitled “Method and Apparatus for Wide-Band Phase Gradient Signal Acquisition,” the entire contents of which are incorporated herein by reference. In other embodiments, the cardiac signal dataset 110b includes one or more biopotential signals acquired from a conventional electrocardiogram (ECG / EKG) device (e.g., a Holter device, a 12-lead ECG, etc.).

[0135] In some embodiments, a phase space recorder as described in U.S. Patent Application Publication No. 2017 / 0119272 is configured to simultaneously acquire the photoplethysmography signal 104a and the cardiac signal 104b. Thus, in some embodiments, the measurement system 102b is configured to acquire two types of biophysical signals.

[0136] Figure 3A An example cardiac signal (e.g., a biopotential signal) is shown as a Figure 1 17 / 0119272). Figure 3A In the example, the x-axis shows time in seconds and the y-axis shows signal amplitude in millivolts (mV).

[0137] Figure 3B 2 is a diagram of a phase space recorder device configured to acquire a cardiac signal 104b, such as described in U.S. Patent Application Publication No. 2017 / 0119272. The phase space recorder device is further configured to also acquire a photoplethysmography signal 104a.

[0138] Still refer to Figure 1B The non-invasive measurement system 102b is configured to transmit the acquired cardiac signal dataset 110b, or a dataset derived therefrom or processed therefrom, to a repository 112 (e.g., a storage area network), for example, via a communication system and / or network, or via a direct connection, which is accessible to a non-invasive biophysical signal evaluation system. The non-invasive biophysical signal evaluation system 114 (shown as an analysis engine 114) is configured to analyze the dynamic characteristics of the acquired photoplethysmography signal.

[0139] In a neurological setting, the measurement system 102 is configured to capture neurologically relevant biopotentials or electrophysiological signals of a mammalian subject (e.g., a human) as a neurological biophysical signal dataset. In some embodiments, the measurement system 102 is configured to acquire broadband neural phase gradient signals as biopotential signals, current signals, impedance signals, magnetic signals, ultrasound or acoustic signals, optical signals, etc. Examples of the measurement system 102 are described in U.S. patent application publications Nos. 2017 / 0119272 and 2018 / 0249960, each of which is incorporated herein by reference in its entirety.

[0140] In some embodiments, the measurement system 102 is configured to capture broadband biopotential biophysical phase gradient signals as unfiltered mammalian electrophysiological signals such that the spectral components of the signals are not altered. In fact, in such embodiments, the broadband biopotential biophysical phase gradient signals are captured, converted, and even analyzed without filtering (such as by hardware circuitry and / or digital signal processing techniques, etc.) (e.g., prior to digitization) that would otherwise affect the phase linearity of the biophysical signal of interest. In some embodiments, the broadband biopotential biophysical phase gradient signals are captured with a microvolt or sub-microvolt resolution that is at, below, or significantly below the noise floor of conventional electrocardiogram, electroencephalogram, and other biophysical signal acquisition instruments. In some embodiments, the broadband biopotential biophysical signals are sampled simultaneously (with a time deviation or "lag" of less than about 1 microsecond and in other embodiments, with a time deviation or lag of no more than about 10 femtoseconds). Notably, the exemplified system minimizes nonlinear distortion (e.g., such distortion that may be introduced by certain filters) in the acquired broadband phase gradient signals so as not to affect the information therein.

[0141] Figure 3C According to an exemplary embodiment, Figure 3B Example placement of a measurement system on a patient in a clinical setting. Figure 3D is an example placement of surface electrodes 106a-106g on a patient to collect Figure 3A Specifically, Figure 3D An example placement of surface electrodes 106a-106g on the chest and back of a patient is shown to acquire biopotential signals associated with broadband cardiac phase gradient signals in accordance with an exemplary embodiment. Figure 3D In the left pane of FIG, surface electrodes 106a-106g are shown placed on the chest and back areas of the patient. Figure 3D In the right pane, a side view of the placement of the surface electrodes 106a-106g is shown.

[0142] exist Figure 3D In the example configuration shown, the surface electrodes 106a-106g are positioned on the patient's skin at i) a first location near the right anterior axillary line corresponding to the 5th intercostal space; ii) a second location near the left anterior axillary line corresponding to the 5th intercostal space; iii) a third location near the left sternal border corresponding to the 1st intercostal space; iv) a fourth location near the left sternal border below the sternum and lateral to the patient's xiphoid process; v) a fifth location near the left sternal border corresponding to the 3rd intercostal space; vi) a sixth location near the patient's back, directly opposite the fifth location, on the left side of the patient's spine; and viii) a seventh location near the right upper quadrant, corresponding to the 2nd intercostal space along the left axillary line. A common lead (shown as "CMM") is also shown. In other embodiments of the present disclosure, the positions of the individual surface electrodes may vary, as other electrode configurations may be useful.

[0143] refer to Figure 1 The non-invasive measurement system 102 is configured with circuitry and computing hardware, software, firmware, middleware, etc. to acquire cardiac signals and / or photoplethysmography signals to 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 includes a second device (not shown) for acquiring photoplethysmography signals.

[0144] refer to Figure 1 In some embodiments, the dynamic feature extraction module 118 is configured to evaluate one or more nonlinear dynamic characteristics, including, for example, but not limited to, the Lyapunov exponent (LE), entropy (K2), and other statistical and geometric characterization characteristics of the photoplethysmography signal 104.

[0145] The Lyapunov exponent is a global measure of the strength of the exponential divergence

[30] . For chaotic systems, the maximum Lyapunov exponent is a positive number, which indicates that the system has little memory of the past. For a given dynamic system, as the value of the Lyapunov exponent increases, the time range of past information that can be used to predict the future becomes shorter. Entropy (KS) (or Kolmogorov-Sinai entropy K2 [31,32]) represents the rate of change of entropy over time. The fractal dimension (D2) characterizes the topological properties of attractors in phase space, which can be used to combine the geometric information (fractals) of the attractor to reveal more information about the dynamics and how the dynamics evolve within it

[33] .

[0146] Nonlinear dynamics and chaos theory can be systematically used to explain the complexity of linear systems and provide tools for quantitatively analyzing their behavior

[19] . Linear systems can generate responses that are exponentially growing / decaying or periodic oscillations, or a combination thereof, where any irregular patterns in the responses can be attributed to the irregularity or randomness of the inputs to these systems. Linear systems are simplifications of reality, and most dynamic systems, whether natural or artificial, are inherently nonlinear and will produce complex irregular behaviors even in the absence of any random source. 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.

[0147] In some embodiments, system 100 includes a healthcare provider portal to display, for example, in a report, a score or various outputs of the analysis engine 114 when predicting and / or estimating the presence or absence of a disease or abnormal condition, severity and / or positioning (if applicable), or indicating an indicator of one of the above-mentioned diseases or conditions. In some embodiments, the physician or clinician portal is configured to access and retrieve reports from a repository (e.g., a storage area network). The physician or clinician portal and / or repository can comply with various privacy laws and regulations, such as the U.S. Health Insurance Portability and Accountability Act (HIPAA) of 1996. A further description of the example healthcare provider portal is provided in U.S. Patent No. 10,292,596, entitled "Method and System for Visualization of Heart Tissue at Risk," which is incorporated herein by reference in its entirety. Although in certain embodiments, the portal is configured to present patient medical information to healthcare professionals, in other embodiments, the healthcare provider portal can be accessed by patients, researchers, scholars, and / or other portal users.

[0148] refer to Figure 1 In some embodiments, the analysis engine 114 includes a Poincare feature extraction module 120 configured to evaluate geometric and topological properties of a Poincare map object generated from the photoplethysmography signal 104 .

[0149] Experimental results of dynamic analysis of photoplethysmography signals

[0150] Figure 4 Experimental results from a study, according to exemplary embodiments, are presented, demonstrating the clinical predictive value of dynamic features extracted from photoplethysmography signals (red and infrared photoplethysmography signals) in the assessment of a disease or abnormal condition, or an indicator of one of the aforementioned diseases or conditions. Although the dataset indicates that predictions / estimations are made for certain demographic groups (e.g., based on gender) and diseases or conditions, or indicators of one of the aforementioned diseases or conditions, the experimental results are stratified solely by these criteria in the provided analysis. Indeed, the experimental results, methods, and systems discussed herein essentially provide a basis for diagnosing the presence, absence, severity, and / or location of a disease or condition, such as heart failure (HF), even when ejection fraction (EF) is retained and not necessarily associated with LVEDP level. In other words, the present systems and methods can be used to non-invasively diagnose or determine the presence, absence, and / or severity of various forms of heart failure (HF) and other diseases and / or conditions without determining or estimating LVEDP. It is generally recognized that LVEDP may be an indicator of disease, but is not itself considered a disease state or condition.

[0151] In this study, a set of dynamic features of photoplethysmography signals were evaluated, including those related to correlation and mutual information, Lyapunov exponents, fractal dimension, and entropy. Correlations can include autocorrelation (e.g., autocorrelation lag) and cross-correlation to capture linear interactions. Mutual information can be used to discover nonlinear dependencies. Lyapunov exponents can be used to measure the degree of chaos. Fractal dimension is also known as "D2." Entropy can be used to assess the rate at which information is generated on a fractal; it is also known as "K2."

[0152] In the study, candidate features were evaluated using t-tests, mutual information, or AUC. A t-test was performed for the null hypothesis of normal LVEDP and the null hypothesis of negative coronary artery disease. The t-test is a statistical test that determines whether there is a difference between the means of two samples from two populations with unknown variances. The output of the t-test is a p-value, where a small p-value (usually ≤0.05) indicates strong evidence against the null hypothesis. The study used random sampling with replacement (bootstrapping) to generate the test set.

[0153] Mutual information is performed to assess the dependence of elevated or abnormal LVEDP or significant coronary artery disease on a set of features. Mutual information is a dimensionless quantity that measures the mutual dependence between two random variables. MI is normalized by the number of bins, and high MI and low MI are calculated as The selected features have high values ​​greater than 1.0 and low values ​​greater than 1.0.

[0154] The receiver operating characteristic curve or ROC curve is a graph showing the diagnostic ability of a binary classifier system when its discrimination threshold is varied. The ROC curve is created by plotting the true positive rate (TPR) versus the false positive rate (FPR) at various threshold settings. The area under the curve ROC (AUC-ROC) further takes into account the cost of incorrect settings. ROC and AUC-ROC values ​​are significant when they are greater than 0.50.

[0155] Table 1 provides the Figure 4 Description of the dynamically extracted parameters for each evaluation.

[0156] Table 1

[0157]

[0158] Figure 4 The potential clinical relevance of the fractal dimension "D2" of the photoplethysmography signal in predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease and / or diseases or conditions associated with elevated or abnormal LVEDP is shown. The criteria for the presence of CAD were defined as an angiographic stenosis greater than 70% or a streamlined flow fraction less than 0.80.

[0159] Specifically, Figure 4 The fractal dimension "D2" (shown as "SpD2L") of the infrared photoplethysmography signal is shown to have a t-test p-value of 0.000000434 in predicting / estimating elevated or abnormal LVEDP (which may indicate the presence or absence and / or severity of a disease and / or condition). Small p-values ​​(typically ≤ 0.05) indicate strong evidence against the null hypothesis (i.e., the absence of elevated or abnormal LVEDP). In addition, Figure 4 The fractal dimension ("D2") of the red photoplethysmography signal (shown as "SpD2U") was shown to have 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, location (if applicable), and / or severity of coronary artery disease. In addition, Figure 4Also shown is a t-test p-value of 0.02 for the fractal dimension "D2" of the red photoplethysmography signal (shown as "SpD2U") in predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. Small p-values ​​(typically ≤ 0.05) indicate strong evidence against the null hypothesis (i.e., the absence of elevated or abnormal LVEDP or coronary artery disease).

[0160] also, Figure 4 The mutual information of the acquired photoplethysmography signals is shown to have potential clinical relevance in predicting / estimating the presence, location (if applicable) and / or severity of coronary artery disease. Figure 4 The minimum automatic mutual information lag for infrared photoplethysmography signals (shown as "SpAMILmin") and red photoplethysmography signals (shown as "SpAMILmin") are shown to have mutual information values ​​of 1.288 and 1.016, respectively, when predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. The time / index lag is calculated via the automatic mutual information of the signals (for signals offset relative to themselves) to produce the minimum mutual information value. Mutual information values ​​greater than 1.0 are statistically significant.

[0161] also, Figure 4 The entropy "K2" value of the acquired photoplethysmography signal is shown to have potential clinical relevance in predicting / estimating the presence, location (if applicable) and / or severity of coronary artery disease and / or diseases or conditions associated with elevated or abnormal LVEDP. Specifically, Figure 4 The entropy ("K2") of the red photoplethysmography signal (shown as "SpK2U") and the entropy ("K2") of the infrared photoplethysmography signal (shown as "SpK2L") for predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease and / or diseases or conditions associated with elevated or abnormal LVEDP in a specific population based on sex are shown with t-test p-values ​​of 0.041 and 0.046, respectively. Small p-values ​​(typically ≤ 0.05) indicate strong evidence against the null hypothesis (i.e., the absence of significant coronary artery disease). Small p-values ​​(typically ≤ 0.05) indicate strong evidence against the null hypothesis (i.e., the absence of CAD).

[0162] Experimental results of dynamic analysis of cardiac signals

[0163] Figure 5Experimental results from a study according to an exemplary embodiment are shown that indicate the clinical predictive value of dynamic features extracted from cardiac signals in the assessment of a disease or elevated or abnormal condition or an indicator thereof. As described above, although the dataset indicates that the predictions / estimates are for certain population groups (e.g., based on gender) and indicators of a disease or condition or one of them (e.g., LVEDP or CAD), the experimental results are stratified only by these criteria in the provided analysis. In fact, the experimental results and methods and systems discussed herein provide a basis for diagnosing the presence, absence, severity, and / or location (if applicable) of a disease or condition (e.g., heart failure (HF)) or an indicator of one of the above diseases or conditions, even when the ejection fraction (EF) is retained and it is not necessarily necessary to correlate it with the LVEDP level. In other words, the present system and method can be used to non-invasively diagnose or determine the presence, absence, severity, and / or location (if applicable) of various forms of heart failure (HF) and other diseases and / or conditions without determining and estimating LVEDP.

[0164] In this study, a set of dynamic features of cardiac signals were evaluated, including those related to correlation and mutual information, Lyapunov exponents, fractal dimension, and entropy. Correlation can include autocorrelation (e.g., autocorrelation lag) and cross-correlation to capture linear interactions. Mutual information can be used to discover nonlinear dependencies. Lyapunov exponents can be used to measure the degree of chaos. Fractal dimension is also known as "D2." Entropy can be used to assess the rate at which information is generated on a fractal; it is also known as "K2."

[0165] In the study, candidate features were evaluated using t-tests, mutual information, or AUC. A t-test was performed for the null hypothesis of normal LVEDP and the null hypothesis of negative coronary artery disease. The t-test is a statistical test that determines whether there is a difference between the means of two samples from two populations with unknown variances. The output of the t-test is a dimensionless quantity known as the p-value. A small p-value (usually ≤ 0.05) indicates strong evidence against the null hypothesis. The study used random sampling with replacement (bootstrapping) to generate the test set.

[0166] Mutual information is used to assess any dependence of the finding of elevated or abnormal LVEDP or significant coronary artery disease on some set of features. The term "mutual information" is an information-theoretic measure of the mutual dependence between two random variables. MI is normalized by the number of bins, and high MI and low MI are calculated as The selected features have high values ​​greater than 1.0 and low values ​​greater than 1.0.

[0167] Table 2 provides the Figure 5 Description of the dynamically extracted parameters for each evaluation.

[0168] Table 2

[0169]

[0170]

[0171] Figure 5 The Lyapunov exponents of acquired cardiac signals are shown to have potential clinical relevance in predicting / estimating elevated or abnormal LVEDP (which may indicate the presence, absence, and / or severity of a disease and / or condition). Specifically, the Lyapunov exponent value ("LEY") for channel "y" 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 condition). Mutual information values ​​greater than 1.0 are considered significant.

[0172] also, Figure 5 The fractal dimension "D2" of the acquired cardiac signal is shown to have potential clinical relevance in predicting / estimating the presence, location (if applicable) and / or severity of coronary artery disease. Specifically, Figure 5 The fractal dimension "D2" of channel "x" (shown as "D2X") is shown to have an AUC of 0.53 in predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. In addition, Figure 5 The fractal dimension "D2" of channel "y" (shown as "D2Y") shows an AUC of 0.52 and a t-test p-value of 0.002 for predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. An AUC value greater than 0.5 is considered significant, and a p-value less than 0.05 is considered significant.

[0173] also, Figure 5 The entropy "K2" of the acquired cardiac signal is shown to have potential clinical relevance in predicting / estimating elevated or abnormal LVEDP (which may indicate the presence, location (if applicable), and / or severity of a disease and / or symptom). Specifically, Figure 5 It is shown that the entropy "K2" of channel "x" (shown 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 or absence and / or severity of a disease and / or symptom). In addition, Figure 5 It is also shown that the entropy "K2" of channel "x" (shown 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, location (if applicable), and / or severity of coronary artery disease. In addition, Figure 5It is shown that the entropy "K2" of channel "y" (shown 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, location (if applicable), and / or severity of coronary artery disease. In addition, Figure 5 The entropy "K2" (shown as "K2Z") of channel "z" is shown to have 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, location (if applicable), and / or severity of coronary artery disease. An AUC value greater than 0.5 is considered significant; a p-value less than 0.05 is considered significant; and a mutual information value greater than 1.0 is considered significant.

[0174] also, Figure 5 The autocorrelation of acquired cardiac signals is shown to have potential clinical relevance in predicting / estimating elevated or abnormal LVEDP (which may indicate the presence, location (if applicable), and / or severity of a disease and / or condition), and in predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. Specifically, Figure 5 It is shown that the calculated minimum automatic mutual information lag (shown as "AMIYmin") for channel "y" - that is, the time / index lag offset between the calculated mutual information of the signal and itself to produce the minimum mutual information - has a t-test p-value of 0.02 in predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. In addition, Figure 5 The minimum automatic mutual information lag (shown as "AMIZmin") for channel "z" is shown to have a t-test p-value of 0.03 in predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. A p-value of less than 0.05 is considered significant.

[0175] also, Figure 5 The autocorrelations of cardiac signals are shown to have potential clinical relevance in predicting / estimating elevated or abnormal LVEDP, which may indicate the presence, location (if applicable), and / or severity of a disease and / or symptom. Specifically, Figure 5 The first zero crossing of the autocorrelation of channel "x" (shown as "ACFXZ1") is shown to have a mutual information value of 1.05 in predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. In addition, Figure 5 It is also shown that the first zero crossing of the autocorrelation of channel "y" ("ACFYZ1") and the first zero crossing of 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 or absence and / or severity of disease and / or symptoms). In addition, Figure 5The second zero crossing of the autocorrelation of channel "x" ("ACFXZ2") is shown to have a t-test p-value of 0.03 and an AUC value of 0.51 in predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. In addition, Figure 5 The second zero crossing of the autocorrelation of channel "y" ("ACFYZ2") is shown to have a t-test p-value of 0.001 in predicting / estimating elevated or abnormal LVEDP (which may indicate the presence and / or severity of disease and / or symptoms) and an AUC value of 0.51 in predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. In addition, Figure 5 The t-test p-value for the second zero crossing of the autocorrelation for channel "z" ("ACFZZ2") is shown to be 0.002 in predicting / estimating elevated or abnormal LVEDP (which may indicate the presence and / or severity of disease and / or symptoms). An AUC value greater than 0.5 is considered significant; a p-value less than 0.05 is considered significant; and a mutual information value greater than 1.0 is considered significant.

[0176] also, Figure 5 The cross-correlations between different channels of the cardiac signal are shown to be of potential clinical relevance in predicting / estimating elevated or abnormal LVEDP, which may indicate the presence, location (if applicable), and / or severity of a disease and / or symptom. Specifically, Figure 5 The maximum value of the cross-correlation between channel "y" and channel "z" of the acquired cardiac signal (shown as "XCFYZMax") is shown to have a mutual information value of 1.03 in predicting / estimating an elevated or abnormal LVEDP (which may indicate the presence, absence, and / or severity of a disease and / or condition) and a mutual information value of 1.13 in predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. In addition, Figure 5 It is shown that the maximum value of the cross-correlation between channel "x" and channel "y" of the acquired cardiac signal (shown as "XCFXYMax") has a t-test p-value of 0.0004 in predicting and / or estimating elevated or abnormal LVEDP (which may indicate the presence, absence and / or severity of a disease and / or condition). In addition, Figure 5 The maximum value of the cross-correlation between channel "x" and channel "z" of the acquired cardiac signal (shown as "XCFXZMax") has a t-test p-value of 0.04 for predicting / estimating elevated or abnormal LVEDP (which may indicate the presence, absence, and / or severity of a disease and / or condition) and a mutual information value of 1.03 for predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. A p-value of less than 0.05 is considered significant, and a mutual information value of greater than 1.0 is considered significant.

[0177] also, Figure 5 The cross-correlation between channel "x" and channel "z" of the acquired cardiac signal (shown as "XCFXZ1") (zero lag or no lag) in predicting / estimating the presence, absence, location (if applicable) and / or severity of coronary artery disease has a t-test p-value of 0.002, a mutual information value of 1.59, and an AUC value of 0.54. In addition, Figure 5 The first zero crossing ("XCFXZZ1") of the cross-correlation between channel "x" and channel "z" of the acquired cardiac signal is shown to have 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, location (if applicable), and / or severity of coronary artery disease. In addition, Figure 5 The second zero crossing (shown as "XCFYZZ2") of the cross-correlation between channel "y" and channel "z" of the acquired cardiac signal is shown to have a t-test p-value of 0.004 in predicting / estimating elevated or abnormal LVEDP (which may indicate the presence, absence and / or severity of a disease and / or symptom). In addition, Figure 5 A t-test p-value of 0.04 was shown for the delay / lag between channels "y" and "z" (shown as "XCFYZDelay") in the cross-correlation between channels "y" and "z" in predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. An AUC value greater than 0.5 was considered significant, a p-value less than 0.05 was considered significant, and a mutual information value greater than 1.0 was considered significant.

[0178] How to use the example

[0179] Figure 6-10 and 11-15 respectively show the Figure 1 (as well as Figure 1A and 1B )'s example dynamic feature analysis module 118. Figure 6-10 The outputs of the modules in 11-15 are merely exemplary. Embodiments may be implemented with some or all of the outputs shown. In some embodiments, additional outputs are generated.

[0180] Unlike systems that have mathematical models (equations), the dynamics of the cardiovascular system are represented as a set of measurements, and the NDS characteristics are extracted from the measured signals rather than through explicit governing equations. The measurements can be considered as projections of the true state of the system; therefore, it is important to perform measurements that contain the most information about the true system. If the true state of the system is x1(t),…x n (t), then the measurement s(t) can be expressed as

[0181] s=g(x1,…,x n) (Equation 1)

[0182] where g(…) is the projection function. The task now is to reconstruct the real system or a mathematically equivalent approximation from s(t). This can be achieved by using delayed embedding phase space reconstruction. A further description can be found in "Embedology" by Sauer et al. (Jour. Of Statistical Physics, Vol. 65:3-4, pp. 579-616 (November 1991)).

[0183] The embedding theorem states that since in an NDS, the system's constituent components or states are often coupled or interacting with each other, a single measurement should contain information about all of these effects. Furthermore, a topologically equivalent representation of a real system can be constructed from a single measurement.

[0184] An effective method is the delayed embedding method. In this method, a vector space of size m is constructed as follows:

[0185]

[0186] Two important parameters are the phase space dimension m 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 be neither too small, where temporal correlations will dominate, nor too large; appropriate values ​​should produce a well-expanded manifold. These values ​​can be fine-tuned for each application, in this case cardiovascular signals.

[0187] In the study, m=24 and tau=40 (ms) correspond to 10 index points in the 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.

[0188] Lyapunov exponent characteristics

[0189] Figure 6 and 11 Both show the Lyapunov exponent feature extraction module 600. Figure 6 In the embodiment, module 600 (shown as 600a) is configured to determine a maximum Lyapunov exponent determined from a photoplethysmography signal (eg, a red photoplethysmography signal and / or an infrared photoplethysmography signal). Figure 11 , module 600 (shown as 1100b) is configured to determine a maximum Lyapunov exponent determined based on a cardiac signal (e.g., a cardiac signal from channel "x" of a PSR device, channel "y" of a PSR device, and / or channel "z" of a PSR device).

[0190] The Lyapunov exponent is an exponential growth rate with a small initial perturbation. Basically, it represents how quickly two nearby trajectories diverge:

[0191]

[0192] where λ is the LE and δ(t) is the evolution of the initial perturbation δ0. In some embodiments, λ is calculated as the average of many points over a finite time.

[0193] like Figure 6 As shown, module 600 may output a maximum Lyapunov exponent value determined based on each corresponding photoplethysmography signal (eg, a red photoplethysmography signal and / or an infrared photoplethysmography signal). Figure 11 , module 1100b can output the maximum Lyapunov exponent determined based on each corresponding cardiac signal (e.g., the cardiac signal from acquisition channel "x" of the PSR device, acquisition channel "y" of the PSR device, and / or acquisition channel "z" of the PSR device).

[0194] Table 3 shows example input parameters for the LE feature extraction module 600 (eg, 600a, 1100b).

[0195] Table 3

[0196]

[0197]

[0198] Fractal dimension characteristics

[0199] Figure 7 and 12 Both show the fractal dimension feature extraction module 700. Figure 7 In the embodiment, module 700 (shown as 700a) is configured to determine a fractal dimension value of a photoplethysmography signal (eg, a red photoplethysmography signal and an infrared photoplethysmography signal), including, for example, information about Figure 4 The fractal dimension ("D2") of the red photoplethysmography signal and the infrared photoplethysmography signal is described. Figure 12 , module 700 (shown as 1200b) is configured to determine a fractal dimension “D2” determined based on a cardiac signal (e.g., a cardiac signal from channel “x” of a PSR device, channel “y” of a PSR device, and / or channel “z” of a PSR device).

[0200] Fractals are geometric objects with self-similar structures, meaning that the same overall pattern is observed when magnified at different scales. Another aspect of fractal structures is their non-integer dimensionality. For example, the famous Lorenz attractor has a correlation dimension of 2.05, which is larger than a 2-manifold but smaller than a 3-dimensional volume. To find the fractal dimension, more data is needed than for LE. Even so, finding the exact fractal dimension from measured data is computationally intensive. To alleviate this problem, a lower bound on the fractal dimension can be calculated using the correlation dimension (D2).

[0201] The probability that a data trajectory in phase space (PS) falls within a sphere U(∈) with radius ∈ can be expressed as Equation 4:

[0202] p ∈ (s)=∫ U(∈) dμ(s) (Equation 1)

[0203] In the equation, μ(s) is the probability density function. The generalized correlation integral of order q is then defined as Equation 5.

[0204] C q (∈)=∫ s p ∈ (s) q-1 dμ(s) (Equation 5) The integral of Equation 5 can be expanded into the following form in Equation 6.

[0205] C q (∈)=∫ s dμ(s)[∫ s′ Θ(∈-|ss′|)dμ(s′)] q-1 (Equation 6)

[0206] According to Formula 6, the function Θ is a Heviside function that acts on two points of the trajectory s and s'. It is observed that the correlation sum varies according to the following power law.

[0207]

[0208] According to Equation 7, the correlation dimension of order q can be obtained as follows according to Equation 8.

[0209]

[0210] Here, q = 2 and is used to calculate D2. These calculations can also be used to estimate the rate of change of entropy.

[0211] like Figure 7As shown, module 700a can output a fractal dimension "D2" determined based on each corresponding photoplethysmography signal (e.g., the fractal dimension "D2" of the red photoplethysmography signal and / or the infrared photoplethysmography signal). Figure 12 , module 1200b may output a fractal dimension “D2” determined based on each corresponding cardiac signal (e.g., a cardiac signal from acquisition channel “x” of the PSR device, acquisition channel “y” of the PSR device, and / or acquisition channel “z” of the PSR device).

[0212] Table 4 shows example input parameters for the fractal dimension feature extraction module 700 (eg, 700a, 1200b).

[0213] Table 4

[0214]

[0215] The linear scaling regions can be calculated for D2 and K2. In addition, entropy curves for various embedding dimensions can be calculated.

[0216] Entropy characteristics

[0217] Figure 8 and 13 The entropy feature extraction module 800 is shown. Figure 8 In the embodiment of the present invention, module 800 (shown as 800a) is configured to determine an entropy value of a photoplethysmography signal (eg, a red photoplethysmography signal and / or an infrared photoplethysmography signal). Figure 13 , module 800 (shown as 1300b) is configured to determine an entropy value of a cardiac signal (e.g., a cardiac signal from channel "x" of a PSR device, channel "y" of a PSR device, and / or channel "z" of a PSR device).

[0218] Entropy can be understood as a measure of uncertainty or, equivalently, information. If the probability of an event occurring is high, the uncertainty is low and the information is high, and vice versa. Shannon entropy is defined according to Equation 9.

[0219] H S =-∑ i p i log(p i ) (Equation 9)

[0220] According to Equation 9, entropy is defined as the sum of all possible states. For chaotic systems, this number increases due to the infinite number of states. Therefore, the rate of change of entropy at an attractor is a more robust and informative measure of uncertainty. According to Equation 10, the rate of change of entropy is called the Kolmogorov-Sinai entropy.

[0221]

[0222] Equation 10 shows the average rate of change of entropy using block probabilities. That is, if the data in phase space is divided into m blocks, the probability represents the joint probability of point 1 being in i1 and point 2 being in i2, and so on. Calculating this quantity can be very computationally intensive; however, a lower bound k2 can be calculated. The q-order Renyi entropy is defined according to Equation 11.

[0223]

[0224] It can be shown that the entropy rate (K2) can be calculated according to Equation 12 as follows.

[0225]

[0226] in,

[0227] lim m→∞,∈→0 K 2,m (∈)≈K2 (Equation 13)

[0228] The K2 entropy rate can be a good approximation to the lower limit of K.

[0229] like Figure 8 As shown, module 800a can output a maximum entropy value "K2" determined based on each corresponding photoplethysmography signal (e.g., a red photoplethysmography signal and / or an infrared photoplethysmography signal). Figure 13 , module 1300b can output the maximum entropy value "K2" determined based on each corresponding cardiac signal (for example, the cardiac signal from the acquisition channel "x" of the PSR device, the acquisition channel "y" of the PSR device and / or the acquisition channel of the PSR device "z").

[0230] Table 5 shows example input parameters for the entropy feature extraction module 800 (eg, 800a, 1300b). These parameters are applicable to a 250 Hz signal.

[0231] Table 5

[0232] M min 23 M max 26 Hysteresis For 250Hz downsampled signals, 1(indx); typically 4ms Nref 3000 N min 100 Search Algorithms Kd Radius Array logspace(log10(0.12),log10(0.55),20);

[0233] Although Nref values ​​of 2000 or 3000 may be used; other values ​​may be used to reduce computational cost.

[0234] Mutual Information

[0235] Figure 9 and 13 Both show the mutual information (MI) feature extraction module 900. Figure 9In the embodiment, module 900 (shown as 900a) is configured to determine the lagged auto mutual information based on the photoplethysmography signals (eg, the red photoplethysmography signal and the infrared photoplethysmography signal). Figure 13 , module 900 (shown as 1300b) is configured to determine lagged auto-mutual information based on the cardiac signal (e.g., the cardiac signal from channel "x" of the PSR device, channel "y" of the PSR device, and / or channel "z" of the PSR device).

[0236] Mutual information captures the nonlinear dependency between two signals or trajectories in PS in a probabilistic sense. Roughly speaking, MI quantifies the following question: given that one trajectory is in state i, what is the probability that the other trajectory is in state j.

[0237]

[0238] The automatic mutual information of X can be obtained by replacing the signal Y in Equation 14.1 with a lagged version of X, namely X(t+τ). Therefore, the AMI will become a function of the lag τ. The delay at which the AMI reaches its minimum is used as a feature.

[0239] Formally, the auto mutual information at lag τ can be defined according to Equation 14.2.

[0240]

[0241] 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 was calculated as the normalized MI.

[0242] In some embodiments, the input parameter is the number of bins. The value used in the study was 128. Other numbers of bins can be used.

[0243] like Figure 9 As shown, module 900a can output automatic mutual information based on each corresponding photoplethysmography signal (eg, automatic mutual information of a red photoplethysmography signal and / or an infrared photoplethysmography signal).

[0244] exist Figure 13 , module 1300b may output automatic mutual information determined based on each corresponding cardiac signal (e.g., cardiac signals from acquisition channel "x" of the PSR device, acquisition channel "y" of the PSR device, and / or acquisition channel "z" of the PSR device).

[0245] Cross-correlation

[0246] Figure 10 and14 The correlation feature extraction module 1000 is shown. Figure 10 In FIG. 1 , module 1000 (shown as 1000a) is configured to determine the autocorrelation and cross-correlation at zero crossings between the acquired red photoplethysmography signal and the infrared photoplethysmography signal. Figure 14 , module 1000 (shown as 1400b) is configured to determine the autocorrelation and cross-correlation at zero crossings between the acquired cardiac signals (e.g., between channel “x” and channel “y”, between channel “x” and channel “z”, and between channel “y” and channel “z”).

[0247] Nonlinear dependencies are quantified by mutual information. Linear interactions between two random variables or signals can be identified by using cross-correlation. The cross-correlation function is defined as:

[0248]

[0249] like Figure 10 and 15 As shown, in some embodiments, the first and second zero crossings, the maximum correlation, the delay at the maximum, and the value at τ=0 are extracted as features.

[0250] discuss

[0251] Systems whose behavior or state evolves over time are called dynamical systems (DS); these systems can be either deterministic or stochastic. In the former case, the system's behavior is governed by deterministic rules and there is no randomness in the system, although random-like responses may be observed; however, in the latter case, the system evolves as a stochastic process, where randomness is the driving mechanism.

[0252] Deterministic dynamic systems can exhibit seemingly completely random behavior, even when there is no randomness in the system. This type of response, known as chaos, is characteristic of nonlinear deterministic dynamic systems. The nonlinearities in these systems couple the responses of the components involved in complex ways, resulting in seemingly random behavior. These types of dynamics can be identified and characterized using mathematical techniques for nonlinear dynamic systems.

[0253] As used herein, when referring to a nonlinear dynamic system, a deterministic dynamic system is meant.

[0254] A key characteristic of the chaotic behavior of NDS is its sensitive dependence on initial conditions; small differences in the starting state will grow exponentially rapidly, leading to two completely different behaviors within a relatively short period of time. This growth rate can be quantified using the Lyapunov exponent (LE). Given sufficiently long time periods, the trajectory of the chaotic system fills a bounded region of phase space (for dissipative systems); the resulting geometry is highly complex and exhibits fractal properties. This object is also called an attractor. To study the geometric aspects of chaos, fractal mathematics is used; fractal dimension is one such technique. Entropy is a measure that combines the dynamical and geometric aspects of chaos and adopts a probabilistic view of the phenomenon. These and other techniques are introduced in the following sections.

[0255] The cardiovascular system, with its complex conduction and mechanical subsystems, can be considered an NDS; the chaotic nature of its physiological functions enables the system to better respond to external conditions. When the internal characteristics of a DS change, for example due to changes in certain parameters, its behavior can undergo bifurcations, resulting in responses with different characteristics. In the context of the cardiovascular system, this translates into different NDS characteristic values ​​(such as LE) when the heart transitions from a normal to a pathological state.

[0256] Dynamic system characterization often requires that the measured signal be long enough to create a good representation in phase space. However, in practice, cardiovascular signals may not be acquired for long periods of time. Therefore, the extracted features should not be considered precise. In some embodiments, the signal is downsampled to 250 Hz. Higher sampling rates can be used, but are subject to higher computational requirements and a significant portion of the signal will be noise. In some embodiments, the signal is baseline-drifted and filtered for noise and power supply frequencies.

[0257] Poincare map feature extraction

[0258] like Figure 1 As shown, in some embodiments, the system 100 includes a Poincare feature extraction module 120 configured to evaluate geometric and topological properties of a Poincare map object generated from the photoplethysmography signal 104 .

[0259] In some embodiments, the analysis includes extracting statistical and geometric features of the generated Poincare map.

[0260] Figure 16Experimental results from a study, according to an exemplary embodiment, are shown that indicate the clinical predictive value of certain dynamic features extracted from generated Poincare maps of photoplethysmography signals (red photoplethysmography signals and infrared photoplethysmography signals) for the presence or absence of a disease or abnormal condition, or an indicator of one of the aforementioned diseases or conditions. As described above, while the dataset indicates predictions / estimates for certain population groups (e.g., based on gender) and diseases or conditions, or indicators of one of the aforementioned diseases or conditions, the experimental results are stratified only by 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 and / or severity and / or location (if applicable) of a disease or condition, such as heart failure (HF) in general, even when ejection fraction (EF) is preserved and does not necessarily have to be correlated with LVEDP levels. In other words, the present systems and methods can be used to non-invasively diagnose or determine the presence, absence, severity and / or location (if applicable) of various forms of heart failure (HF) and other diseases and / or symptoms without LVEDP measurement / estimation.

[0261] In this study, a first type of Poincare map of the photoplethysmography signal 104 between predefined landmarks (e.g., peaks, intersections) in the red photoplethysmography signal and the infrared photoplethysmography signal was evaluated. Additionally, a second type of Poincare map of the photoplethysmography signal 104 between predefined landmarks (e.g., peaks, intersections) in the same red photoplethysmography signal and the same infrared photoplethysmography signal was evaluated.

[0262] Based on the Poincare map, the study evaluated statistical properties including mean, median, mode, standard deviation, skewness, and kurtosis. Geometric properties were also evaluated, including: ellipse fits based on points within three standard deviations of the data; major and minor diameters, and orientation.

[0263] Table 6 provides the Figure 16 A description of the dynamic extraction parameters for each evaluation is provided. In the table, the photoplethysmography signal is referred to as the "PPG signal." In practice, as mentioned above, in the Poincare map, references to time are synonymous and can therefore be used interchangeably for data points in a given dataset. Furthermore, references to continuous time or data points can refer to both immediate data points or time increments as well as data points or time increments at a fixed increment.

[0264] Table 6

[0265]

[0266]

[0267] Figure 16 Various geometric features extracted from Poincare diagrams (also known as Poincare maps) are shown to have potential clinical relevance in predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease and / or diseases and / or conditions associated with elevated or abnormal LVEDP.

[0268] For example, Figure 16 The density of the alpha shape (e.g., surface area normalized by the number of data points) generated from the Poincare map of the photoplethysmography signal (displayed as "alphaShapePoincareOutput.alphaShapeDensity") showed an AUC value of 0.538 for predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. AUC values ​​greater than 0.5 are considered significant.

[0269] also, Figure 16 The surface area of ​​the convex hull of the alpha shape generated from the Poincare map (shown as "alphaShapePoincareOutput.convexSurfaceArea") is shown to have an AUC value of 0.533 in predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. AUC values ​​greater than 0.5 are considered significant.

[0270] also, Figure 16 The perimeter of the alpha shape generated from the Poincare map of the photoplethysmography signal (shown as "alphaShapePoincareOutput.perim") shows 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, location (if applicable), and / or severity of coronary artery disease. An AUC value greater than 0.5 is considered significant; a p-value less than 0.05 is considered significant, and a mutual information value greater than 0.5 is considered significant.

[0271] also, Figure 16The ratio of the perimeter of the alpha shape to its surface area (shown as "alphaShapePoincaréOutput.perimSurfaceAreaRatio") demonstrated a t-test p-value of 0.00001, a mutual information value of 1.841, and an AUC value of 0.566 for predicting the presence, location (if applicable), and severity of coronary artery disease. Furthermore, the same feature demonstrated a t-test p-value of 0.011 for predicting elevated or abnormal LVEDP (which may indicate the presence and / or severity of a disease and / or condition). An AUC value greater than 0.5 was considered significant; a p-value less than 0.05 was considered significant; and a mutual information value greater than 0.5 was considered significant.

[0272] also, Figure 16 The alpha-shaped porosity (shown as "alphaShapePoincaréOutput.porosity") generated from the Poincare map of the photoplethysmography signal has a t-test p-value of 0.0035 and an AUC value of 0.509 for predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. An AUC value greater than 0.5 is considered significant; a p-value less than 0.05 is considered significant.

[0273] also, Figure 16 The surface area of ​​the Poincare map of the photoplethysmography signal (shown as "alphaShapePoincareOutput.surfaceArea") shows an AUC value of 0.549 in predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. An AUC value greater than 0.5 is considered significant.

[0274] also, Figure 16 The void area of ​​the Poincare map of the photoplethysmography signal (displayed as "alphaShapePoincareOutput.voidArea") (e.g., the difference between the surface areas of the convex hull and the alpha shape) has an AUC value of 0.505 in predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. An AUC value greater than 0.5 is considered significant.

[0275] also, Figure 16 The AUC value for the standard deviation of the time differences between adjacent PPG peaks in predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease is 0.506. An AUC value greater than 0.5 is considered significant.

[0276] also, Figure 16The parameters associated with the fitted ellipses in the clusters of the Poincare map are shown to have potential clinical relevance in predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. Specifically, Figure 16 The area under the curve (AUC) of the x-axis (radius) of the non-tilted ellipse containing the largest cluster in the Poincare map (shown as "largestClusterEllipse.a") is 0.502 for predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. An AUC value greater than 0.5 is considered significant.

[0277] also, Figure 16 The area under the curve (AUC) of the y-axis (radius) of the non-tilted ellipse containing the largest cluster in the Poincare map (designated "largestClusterEllipse.b") for predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease is 0.502. An AUC value greater than 0.5 is considered significant.

[0278] also, Figure 16 The long axis size of the ellipse containing the largest cluster in the Poincare map (shown as "largestClusterEllipse.long_axis") has a mutual information value of 1.37 and an area under the curve (AUC) of 0.508 for predicting the presence, location (if applicable), and / or severity of coronary artery disease. An AUC value greater than 0.5 is considered significant, and a mutual information value greater than 1.0 is considered significant.

[0279] also, Figure 16 The short axis size of the ellipse containing the largest cluster in the Poincare map (shown as "largestClusterEllipse.short_axis") has a mutual information value of 1.086 and an area under the curve (AUC) of 0.527 for predicting the presence, location (if applicable), and / or severity of coronary artery disease. An AUC value greater than 0.5 is considered significant, and a mutual information value greater than 1.0 is considered significant.

[0280] also, Figure 16 The x-axis center of the non-tilted ellipse containing the largest cluster in the Poincare map (shown as "largestClusterEllipse.X0") is shown to have a mutual information value of 1.04 in predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. Mutual information values ​​greater than 1.0 are considered significant.

[0281] also, Figure 16A t-test p-value of 0.049 was obtained for the number of major modes in the kernel density quantification of the time difference between adjacent PPG peaks (displayed as "numberOfKernelDensityModes") in predicting / estimating the presence, location (if applicable), and / or severity of coronary artery disease. A p-value of less than 0.05 was considered significant.

[0282] also, Figure 16 The t-test p-value for the number of clusters in the Poincare map detected by the DBSCAN clustering algorithm (shown as "numClusters") in predicting / estimating elevated or abnormal LVEDP (which may indicate the presence, absence, and / or severity of a disease and / or condition) was 0.013. A p-value of less than 0.05 was considered significant.

[0283] also, Figure 16 The quantification of the bimodality of the distribution using skewness and kurtosis (shown as "SarleBiomodalityCoef") showed a t-test p-value of 0.045 in predicting / estimating the presence, location (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 and / or severity of a disease and / or condition). A p-value less than 0.05 was considered significant; a mutual information value greater than 1.0 was considered significant.

[0284] Figure 17-19 Each shows an exemplary embodiment according to Figure 1 An example Poincare map feature analysis module 120 is provided. Figure 17-19 The outputs of the modules are merely exemplary. Embodiments may be implemented with some or all of the outputs shown. In some embodiments, additional outputs are generated.

[0285] Figure 17 Shown is a Poincare map statistical feature extraction module 1700. In some embodiments, the module 1700 is configured to determine the mean, mode, median, standard deviation, skewness, and kurtosis of periodicity between landmarks in the same photoplethysmography signal or between landmarks in a red photoplethysmography signal and an infrared photoplethysmography signal.

[0286] Figure 18A Poincare map geometric feature extraction module 1800 is shown. Module 1800 is configured to determine geometric features from the generated alpha shape of a Poincare map object. In some embodiments, the Poincare map and its corresponding object can be generated based on periodicity between landmarks in a red photoplethysmography signal and an infrared-red photoplethysmography signal. In some embodiments, the Poincare map and its corresponding object can be generated based on periodicity between landmarks in the same photoplethysmography signal (e.g., an infrared photoplethysmography signal and / or a red photoplethysmography signal).

[0287] Figure 18A An example landmark (lowest peak) in an infrared photoplethysmography signal is shown. Figure 18A In the graph, the x-axis represents time in seconds and the y-axis represents signal amplitude in millivolts (mv). Figure 18B An example distribution of the variance of amplitude values ​​between adjacent cycles in an infrared photoplethysmography signal is shown as a histogram. Figure 18B In the histogram, the x-axis represents the signal amplitude (in mV) and the y-axis represents the frequency / count. Figure 18C An example Poincare map generated from the amplitude values ​​of the infrared photoplethysmography signal at times x and x-1 on the x-axis and at times x and x+1 on the y-axis is shown. That is, each evaluation parameter (e.g., signal amplitude) at a given time / data point is shown relative to the next time / data point (e.g., [x i ,x i+1 ] relative to [x i ,x i-1 ]) is located in the Poincare map. Therefore, the Poincare map helps to analyze the variability of a given parameter (e.g., the variability of the lowest peak landmark) between cycles in the collected data set. Similar analysis can be applied to any parameter and feature discussed here.

[0288] According to the Poincare map, the system generates an alpha shape, from which geometric features of the obtained alpha shape are extracted.

[0289] according to Figure 18 In some embodiments, the Poincare map geometric feature extraction module 1800 is configured to extract density values ​​from the alpha shape of the Poincare map. In some embodiments, the module 1800 determines density as the surface area normalized by the number of data points.

[0290] according to Figure 18In some embodiments, the Poincare map geometric feature extraction module 1800 is configured to extract convex surface area values ​​from the alpha shape of the Poincare map. In some embodiments, the module 1800 determines the convex surface area as the surface area of ​​the convex hull generated to contain the alpha shape of the Poincare map.

[0291] according to Figure 18 In some embodiments, the Poincare map geometric feature extraction module 1800 is configured to extract perimeter values ​​from the alpha shape of the Poincare map.

[0292] according to Figure 18 In some embodiments, the Poincare map geometric feature extraction module 1800 is configured to extract perimeter values ​​and surface area values ​​from the alpha shape of the Poincare map. The module 1300 may generate a ratio based on the perimeter value and the surface area.

[0293] according to Figure 18 In some embodiments, the Poincare map geometric feature extraction module 1800 is configured to extract the porosity value from the alpha shape of the Poincare map.

[0294] according to Figure 18 In some embodiments, the Poincare map geometric feature extraction module 1800 is configured to extract the surface area from the alpha shape of the Poincare map.

[0295] according to Figure 18 In some embodiments, the Poincare map geometric feature extraction module 1800 is configured to extract the gap area from the alpha shape of the Poincare map. In some embodiments, the module 1800 determines the gap area as the difference between the surface areas of the convex hull and the alpha shape.

[0296] according to Figure 19 In some embodiments, the Poincare map geometric feature extraction module 1900 is configured to extract the standard deviation of the time difference between adjacent peaks in the photoplethysmography signal.

[0297] exist Figure 19 In the embodiment of the present invention, the cluster graph geometric feature extraction module 1900 is configured to further determine geometric features from the determined clusters of Poincare map objects.

[0298] like Figure 19As shown, in some embodiments, module 1900 is configured to determine the sub-axis (radius) of the x-axis of the non-tilted ellipse containing the largest cluster in the Poincare map. In some embodiments, module 1900 is configured to determine the sub-axis (radius) of the y-axis of the non-tilted ellipse containing the largest cluster in the Poincare map. In some embodiments, module 1900 is configured to determine the size of the major axis of the ellipse containing the largest cluster in the Poincare map. In some embodiments, module 1900 is configured to determine the size of the minor axis of the ellipse containing the largest cluster in the Poincare map. In some embodiments, module 1900 is configured to determine the center of the x-axis of the non-tilted ellipse containing the largest cluster in the Poincare map. In some embodiments, module 1900 is configured to determine the number of major modes in the kernel density quantification of the histogram of time differences between adjacent PPG peaks. In some embodiments, module 1900 is configured to determine the number of clusters in the Poincare map detected by the DBSCAN clustering algorithm.

[0299] In some embodiments, module 1900 is configured to use skewness and kurtosis to determine a quantification of the bimodality of a distribution.

[0300] Module 1900 may generate one, some, or all of the above parameters, for example, for subsequent analysis and / or for diagnosis of a disease state or condition.

[0301] according to Figure 16 , which showed that these parameters have some statistical correlation, dependence, or clinical value in the assessment of elevated or abnormal LVEDP and coronary artery disease.

[0302] Coronary Artery Disease - Learning Algorithm Development Research

[0303] The Coronary Artery Disease - Learning Algorithm Development (CADLAD) study, which acquired photoplethysmography signals along with cardiac signals to support the development and testing of machine learning algorithms, has not yet been conducted.

[0304] In this study, paired clinical data was used to guide the design and development of the preprocessing, feature extraction, and machine learning phases of the development process. Specifically, the collected clinical study data was divided into multiple cohorts: a training cohort, a validation cohort, and a verification cohort. Each acquired dataset was first preprocessed to clean and normalize the data. Following the preprocessing process, a set of features was extracted from the signal, where each set of features was paired with a representation of a true condition (e.g., a binary classification of the presence or absence of significant CAD or a scored classification of the presence of significant CAD in a given coronary artery).

[0305] In some embodiments, the evaluation system (e.g., 114, 114a, 114b) automatically and iteratively explores feature combinations in various functional permutations with the goal of finding those combinations that successfully match feature-based predictions. To avoid overfitting the solution to the training data, a validation set is used as a comparator. Once candidate predictors are developed, they are manually applied to a validation dataset to evaluate predictor performance against data that was not used to generate the predictor. If the dataset is large enough, the performance of the selected predictor on the validation set will approach the performance of the predictor on new data.

[0306] Healthcare Provider Portal

[0307] refer to Figure 1 (as well as Figure 1A and 1B ), in some embodiments, system 100 (e.g., 100a, 100b) includes a healthcare provider portal to display an assessment of a disease state or symptom (e.g., associated with elevated or abnormal LVEDP and / or coronary artery disease) in a report. In some embodiments, the report is constructed as an angiography equivalent report. In some embodiments, the physician or clinician portal is configured to access and retrieve the report from a repository (e.g., a storage area network). The physician or clinician portal and / or the repository can be HIPAA compliant. An example healthcare provider portal is provided in U.S. patent application Ser. No. 15 / 712,104, entitled “Method and System for Visualization of Heart Tissue at Risk,” which is incorporated herein by reference in its entirety. While in some embodiments, the portal is configured to present patient medical information to healthcare professionals, in other embodiments, the healthcare provider portal can be accessed by patients, researchers, academics, and / or other portal users. The portal can be used to meet a variety of clinical and even research needs in a variety of settings—from hospitals to emergency rooms, laboratories, battlefields, or remote environments, at the point of care with the patient's primary care physician or other caregivers, or even at home.

[0308] Machine-based classifiers

[0309] Machine learning techniques predict outcomes based on input data sets. For example, machine learning techniques are used to identify patterns and images, supplement medical diagnoses, and more. Machine learning techniques rely on a set of features generated using a training data set (i.e., a data set of observations where the outcome to be predicted is known in each observation), where each feature represents some measurable aspect of the observed data, to generate and adjust one or more predictive models. For example, observed signals (e.g., heartbeat signals from multiple subjects) can be analyzed to collect frequency, average, and other statistical information about these signals. Machine learning techniques can use these features to generate and adjust a model that associates these features with one or more conditions, such as certain forms of cardiovascular disease (CVD), including coronary artery disease (CVD), and then apply the model to a data source where the outcomes are unknown (e.g., undiagnosed patients or future patterns, etc.). Traditionally, in the context of cardiovascular disease, these features are manually selected from traditional electrocardiograms and combined by data scientists in collaboration with domain experts.

[0310] Examples of machine learning embodiments include, but are not limited to, decision trees, random forests, SVMs, neural networks, linear models, Gaussian processes, nearest neighbors, SVMs, and naive Bayes. In some embodiments, machine learning can be implemented, for example, as described 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,” the entire contents of which are incorporated herein by reference.

[0311] Sample computing environment

[0312] Figure 20 An example computing environment is shown in which example embodiments of the analysis system 114 and aspects thereof may be implemented.

[0313] The computing device environment is only one example of a suitable computing environment and is not intended to suggest any limitation as to scope of use or functionality.

[0314] 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, network personal computers (PCs), minicomputers, mainframe computers, embedded systems, and distributed computing environments that include any of the foregoing.

[0315] Computer-executable instructions executed by a computer, such as program modules, can be used. Generally, program modules include routines, programs, objects, components, data structures, etc., which perform specific tasks or implement specific abstract data types. A distributed computing environment can be used when tasks are performed by remote processing devices connected through a communication 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).

[0316] Reference Figure 20 , an example system for implementing 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 specific configuration and type of computing device, memory 2004 may be volatile (such as random access memory (RAM)), non-volatile (such as read-only memory (ROM), flash memory, etc.), or some combination of the two. This most basic configuration is as follows Figure 20 Indicated by the dotted line 2006.

[0317] The computing device 2000 may have additional features / functionality. For example, the computing device 2000 may include additional storage devices (removable and / or non-removable), including but not limited to magnetic or optical disks or tapes. Such additional storage devices may be stored in the computer system. Figure 20 Shown are removable storage 2008 and non-removable storage 2010 .

[0318] The computing device 2000 typically includes a variety of computer-readable media. Computer-readable media can be any available media that can be accessed by the device 2000, including both volatile and nonvolatile media, removable and non-removable media.

[0319] Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Memory 2004, removable storage device 2008, and non-removable storage device 2010 are all examples of computer storage media. Computer storage media include, but are not limited to, RAM, ROM, electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and that can be accessed by the computing device 2000. Any such computer storage media can be part of the computing device 2000.

[0320] The computing device 2000 may include communication 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, a mouse, a pen, a voice input device, a touch input device, etc. (alone or in combination). Output devices 2016 (such as a display, a speaker, a printer, a vibration mechanism, etc.) may also be included, alone or in combination. All of these devices are well known in the art and need not be discussed in detail here.

[0321] It should be understood that the various techniques described herein may be associated with hardware components or software components, or, where appropriate, implemented by a combination of both. Example 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 chips (SOCs), complex programmable logic devices (CPLDs), etc. 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, wherein, when the program code is loaded into and executed by a machine (such as a computer), the machine becomes an apparatus for practicing the presently disclosed subject matter.

[0322] Although example implementations may refer to using the presently disclosed subject matter in the context of one or more standalone computer systems, the subject matter is not limited thereto and may be implemented in any computing environment, such as a network or distributed computing environment. Furthermore, various aspects of the presently disclosed subject matter may be implemented in or across multiple processing chips or devices, and storage may similarly be implemented across multiple devices. For example, these devices may include personal computers, network servers, handheld devices, and wearable devices.

[0323] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

[0324] Other examples of processes that can be used with the example methods and systems are described in the following: 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 “Non-invasive Method and System for Characterizing Cardiovascular Systems and All-Cause Mortality and Sudden Cardiac Death Risk”; 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 Application Publication No. 2017 / 0119272, entitled “Method and Apparatus for Wide-Band Phase Gradient Signal Acquisition”; PCT Publication No. WO2017 / 033164, entitled “Method and Apparatus for Wide-Band Phase Gradient Signal Acquisition” Acquisition”; U.S. Patent Application Publication No. 2018 / 0000371, entitled “Non-invasive Method and System for Measuring Myocardial Ischemia, Stenosis Identification, Localization and Fractional Flow Reserve Estimation”; International Application 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 Application Publication No. 2018 / 0249960, entitled “Method and System for Wideband Phase Gradient Signal Acquisition”; U.S. Patent Application No. 16 / 232,801, entitled “Method and System to Assess Disease Using Phase Space Volumetric Objects”; International PCT Application No. IB / 2018 / 060708, entitled “Method and System to Assess Disease Using Phase Space Volumetric Objects”; U.S. Patent Application Publication No. US2019 / 0117164, entitled “Methods and Systems of De-Noising Magnetic-Field Based Sensor Data of Electrophysiological Signals”; U.S. Patent Application No. 16 / 232,586, entitled “Method and System to Assess Disease Using Phase Space Volumetric Objects” U.S. patent application entitled “Method and System to Assess Disease Using Phase Space Tomography and Machine Learning”; International application PCT application number PCT / IB2018 / 060709, entitled “Method and System to Assess Disease Using Phase Space Tomography and Machine Learning”; U.S. patent application number 16 / 445,158, entitled “Methods and Systems to Quantify and Remove Asynchronous Noise in Biophysical Signals”; U.S. patent application number 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 “Methods and Systems 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 No. 16 / 725,430, entitled “Method and System to Configure and Use Neural Network To Assess Medical Disease”; 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.

[0325] Unless otherwise expressly stated, it is not intended that any method described herein be construed as requiring that its steps be performed in a specific order. Therefore, if a method claim does not actually recite the order in which its steps are to be followed, or if the steps are not otherwise specifically stated in the claims or specification to be limited to a particular order, then in no way should that order be inferred. This applies to any possible non-express basis for interpretation, including: logical issues regarding the arrangement of steps or operational flow; plain meaning derived from grammatical organization or punctuation; or the number or type of embodiments described in the specification.

[0326] Although the methods and systems have been described in conjunction with certain embodiments and specific examples, it is not intended to limit the scope to the particular embodiments set forth, as the embodiments herein are intended in all respects to be illustrative rather than restrictive.

[0327] The methods, systems, and processes described herein can be used to generate stenosis and FFR outputs for use with procedures such as placing a vascular stent within a blood vessel, such as an artery, of a living (e.g., human) subject, and 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 outputs to determine and / or modify the number of stents to be placed in a living (e.g., human) subject during surgery, including their optimal deployment location within a given blood vessel, among other things.

[0328] Examples of other biophysical signals that may be analyzed in whole or in part using the example methods and systems include, but are not limited to, electrocardiogram (ECG) datasets, electroencephalogram (EEG) datasets, gamma synchronization signal datasets, respiratory function signal datasets, pulse oximetry signal datasets, perfusion data signal datasets, quasi-periodic biosignal datasets, fetal ECG datasets, blood pressure signals, cardiac magnetic field datasets, and heart rate signal datasets.

[0329] Example analyses can be used for the diagnosis and treatment of cardiac-related pathologies and conditions and / or nervous system-related pathologies and conditions, and such assessments can be applied to the diagnosis and treatment (including surgical, minimally invasive and / or drug treatments) of any pathology or condition of any relevant system of a living being in which the biophysical signals are related. An example in the cardiac area is the diagnosis of CAD and its treatment (alone or in combination) by various therapies, such as placement of stents in the coronary arteries, atherectomy, angioplasty, prescription of drug therapy, and / or exercise prescription, nutritional and other lifestyle changes, etc. Other cardiac-related pathologies or conditions that can be diagnosed include, for example, arrhythmias, congestive heart failure, valvular failure, pulmonary hypertension (e.g., pulmonary arterial hypertension, pulmonary hypertension caused by left heart disease, pulmonary hypertension caused by lung disease, pulmonary hypertension caused by chronic thrombosis and pulmonary hypertension caused by other diseases (such as blood or other diseases)), and other cardiac-related pathologies, conditions and / or diseases. Non-limiting examples of diagnosable neurological-related diseases, pathologies or conditions include, for example, epilepsy, schizophrenia, Parkinson's disease, Alzheimer's disease (and all other forms of dementia), autism spectrum disorders (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, language disorders, various mental illnesses, brain / spinal cord / nerve injuries, chronic traumatic encephalopathy, cluster headaches, migraines, neuropathies (various forms, including peripheral neuropathy), phantom limb / pain, chronic fatigue syndrome, acute and / or chronic pain (including back pain, failed back surgery syndrome, etc.), movement dysfunction, anxiety disorders, conditions caused by infections or exogenous factors (such as 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.

[0330] The following patents, applications, and publications listed below and throughout this document are hereby incorporated by reference in their entirety.

[0331] References

[0332] [1] I. Kononenko, “Machine learning for medical diagnosis: history, current status and prospects”, Artificial Intelligence in Medicine, 23(1):89–109 (2001).

[0333] [2] BA Mobley, E. Schechter, WE Moore, PAM McCee, JE Eichner, “Prediction of coronary artery stenosis by artificial neural networks,” Artificial Intelligence in Medicine, 18(3) 187–203 (2000).

[0334] [3] V.L. Patel, E.H. Shortliffe, M.Stefanelli, P.Szolovits, M.R. Berthold, R.Bellazzi, A.Abu-Hanna, “The advent of artificial intelligence in medicine”, Artificial Intelligence in Medicine, 46(1)5-17 (2009).

[0335] [4] V. Jahmunah, S. L. Oh, V. Rajinikanth, E. J. Ciaccio, K. H. Cheong, U. R. Acharya, et al., “Automatic detection of schizophrenia using nonlinear signal processing methods,” Artificial Intelligence in Medicine, vol. 100, 101698 (September 2019).

[0336] [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: impact on disease modeling and treatment discovery in psychiatry,” Artificial Intelligence in Medicine, 101704 (2019).

[0337] [6] GK Hansson, “Inflammation, atherosclerosis, and coronary artery disease,” New England Journal of Medicine, 352(16):1685–1695 (2005).

[0338] [7] WG Members, D. Lloyd-Jones, RJ 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 statistics 2010 update: a report from the American Heart Association,” Circulation, 121(7) 948–954 (2010).

[0339] [8] G.A. Mensah, D.W. Brown, “Overview of the burden of cardiovascular disease in the United States,” Health Affairs, 26(1):38-48 (2007).

[0340] [9] Y.N. Reddy, A. El-Sabbagh, R.A. Shimura, “Comparison of pulmonary artery wedge pressure and left ventricular end-diastolic pressure for assessment of left-sided filling pressures,” JAMA Cardiology, 3(6) 453–454 (2018).

[0341]

[10] MJ Kern, T. Christopher, “Hemodynamic Examination Series II: LVEDP,” Catheterization and Cardiovascular Diagnosis, 44(1) 70–74 (1998).

[0342]

[11] J.-H. Park, T.H. Marwick, “Uses and limitations of e / e' for the assessment of left ventricular filling pressures by echocardiography,” Journal of Cardiovascular Ultrasound, 19(4) 169–173 (2011).

[0343]

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

[0344]

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

[0345]

[14] SD Fihn, JM Gardin, J. Abrams, K. Berra, JC Blankship, 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 guidelines for the diagnosis and management of patients with stable ischemic heart disease,” Journal of the American College of Cardiology, 60(24): 2564–2603 (2012).

[0346]

[15] GN Levine, ER Baates, JC Blankship, SR Bailey, JA Bittl, B. Cercek, CE Chambers, SG Ellis, RA Guyton, SM Hollenberg, et al., “2011 ACCF / AHA / SCAI guidelines for percutaneous coronary intervention: executive summary,” Journal of the American College of Cardiology, 58(24): 2550–2583 (2011).

[0347]

[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 the risk of subsequent heart failure in patients after acute myocardial infarction,” Congestive Heart Failure, 13(4): 209–214 (2007).

[0348]

[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).

[0349]

[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 independent of left ventricular ejection fraction,” BJA: British Journal of Anaesthesia, 97(3) 292–297 (2006).

[0350]

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

[0351]

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

[0352]

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

[0353]

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

[0354]

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

[0355]

[24] M. I. Owis, A. H. Bou-Zied, A.-B. Youssef, Y. M. Kadah, “Feature study based on nonlinear dynamics modeling for electrocardiogram arrhythmia detection and classification,” IEEE Transactions on Biomedical Engineering, 49(7)733–736 (2002).

[0356]

[25] A. Voss, S. Schulz, R. Schroeder, M. Baumert, P. Caminal, “A method based on the derivation of nonlinear dynamics for the analysis of heart rate variability, Philosophical Transactions of the Royal Society A: Mathematical,” Physical and Engineering Sciences, 367(1887) 277–296 (2008).

[0357]

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

[0358]

[27] P. Billingsley, Ergodic Theory and Information, vol. 1, Wiley, New York, 1965.

[0359]

[28] T. Sauer, J. A. Worke, and M. Casdagli, “Embeddings,” Journal of Statistical Physics, 65(3-4): 579–616 (1991).

[0360]

[29] A. Chatterjee, “Introduction to eigenorthogonal decomposition,” Current Science, 808–817 (2000).

[0361]

[30] A. Wolf, J. B. Swift, H. L. Winney, J. A. Vastano, “Determination of Lyapunov exponents from time series”, Physics D: Nonlinear Phenomena, 16(3) 285–317 (1985).

[0362]

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

[0363]

[32] P. Grassberger, I. Procaccia, “Estimating K-entropy from chaotic signals”, Physical Review, A 28(4)2591 (1983).

[0364]

[33] J. Theiler, “An efficient algorithm for estimating the correlation dimension from a set of discrete points,” Physical Review, A36(9)4456 (1987).

[0365]

[34] A. Pikovsky, J. Kurths, M. Rosenblum, J. Kurths, Synchrony: A universal concept in nonlinear science, vol. 12, Cambridge University Press (2003).

[0366]

[35] D. Dubin, “Rapid Interpretation of the Electrocardiogram: An Interactive Course,” Cover Publishing Company (2000).

[0367]

[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 (October 2011).

[0368]

[37] T. Chen and C. Guestrin, “Xgboost: A scalable tree boosting system,” in Proceedings of the 22nd ACM-SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM, pp. 785–794 (2016).

[0369]

[38] H. Zou, T. Hastie, “Regularization and variable selection via elastic nets,” Journal of the Royal Statistical Society: Series B (Statistical Methods), 67(2) 301–320 (2005).

Claims

1. A method for non-invasively assessing a disease state or abnormal condition in a subject, the method comprising: obtaining, by one or more processors, a biophysical signal dataset of the subject, wherein the biophysical signal dataset is associated with at least a photoplethysmography signal and a cardiac signal; determining, by the one or more processors, a Poincare map of one or more dynamic characteristic features derived from a machine learning model and the obtained biophysical signal dataset, wherein the one or more dynamic characteristic features are associated with the photoplethysmography signal and the cardiac signal; as well as determining, by the one or more processors, an alpha shape object of the Poincare map; determining, by the one or more processors, one or more geometric characteristics of the alpha shape object; One or more estimates of the presence, location, and / or severity of a disease or condition are determined by the one or more processors based on the determined one or more dynamic characteristic features and the one or more determined geometric characteristics of the alpha-shaped object.

2. The method of claim 1, wherein the presence and / or severity of the disease or condition is assessed based on an assessment of left ventricular end-diastolic pressure, including elevated or abnormal left ventricular end-diastolic pressure.

3. The method of claim 1, wherein the disease state or condition comprises coronary artery disease.

4. The method of claim 1, wherein the disease state or condition comprises pulmonary hypertension.

5. The method of claim 1, wherein the disease state or condition comprises pulmonary hypertension.

6. The method of claim 1, wherein the disease state or condition comprises pulmonary hypertension due to left heart disease.

7. The method of claim 1, wherein the disease state or condition comprises a disorder capable of leading to pulmonary hypertension.

8. The method of claim 1, wherein the disease state or condition comprises left ventricular heart failure or left-sided heart failure.

9. The method of claim 1, wherein the disease state or condition comprises right ventricular heart failure or right-sided heart failure.

10. The method of claim 1, wherein the disease state or condition comprises systolic heart failure or diastolic heart failure.

11. The method of claim 1 , wherein the disease state or condition comprises ischemic heart disease.

12. The method of claim 1, wherein the disease state or condition comprises a cardiac arrhythmia.

13. The method according to any one of claims 1 to 12, further comprising: One or more second estimates of the presence, location, and / or severity of two or more of the diseases or conditions are determined by the one or more processors.

14. The method according to any one of claims 1 to 13, wherein: The dynamic characteristic feature is selected from the group consisting of: entropy value (K2), fractal dimension (D2), Lyapunov exponent, autocorrelation, auto mutual information, cross-correlation, and mutual information.

15. The method according to any one of claims 1 to 14, wherein The obtained biophysical signal dataset includes one or more red photoplethysmography signals.

16. The method according to any one of claims 1 to 14, wherein The obtained biophysical signal dataset includes one or more infrared photoplethysmography signals.

17. The method according to any one of claims 1 to 14, wherein The obtained biophysical signal dataset includes one or more cardiac signals.

18. The method according to any one of claims 1 to 17, further comprising: Generating, by the one or more processors, a visualization of an estimate of the presence, location, and / or severity of a disease or condition, wherein the generated visualization is rendered and displayed on a display of the computing device and / or presented in a report.

19. The method according to any one of claims 1 to 18, further comprising: A histogram of periodic variations in the biophysical signal dataset is determined by the one or more processors, wherein the histogram is used to determine an estimate of the presence, location, and / or severity of the disease or condition.

20. The method according to claim 1, wherein The one or more determined geometric characteristics further comprise two or more characteristics selected from the group consisting of: the density value of the alpha shape object; The convex surface area value of the alpha shape object; The perimeter value of the alpha shape object; the porosity value of the alpha shape object; and The blank area value of the alpha shape object.

21. The method according to claim 19, wherein The one or more determined geometric characteristics further comprise two or more characteristics selected from the group consisting of: the semi-axis length "a" of the largest cluster ellipse evaluated for the Poincare map; the semi-axis length "b" of the largest cluster ellipse evaluated for the Poincare map; the length of the longest axis of the largest cluster ellipse evaluated by the Poincare map; The length of the shortest axis of the largest cluster ellipse evaluated by the Poincare map; the number of clusters evaluated in the Poincare map; an estimated number of kernel density modes in the histogram; and Sarles' coefficient of bimodality value assessed from the histogram.

22. The method according to claim 1, wherein The determined Poincare map is generated by plotting photoplethysmography signal peaks on a first axis at a first time x-1 to a second time x and on a second axis at the second time x to a third time x+1.

23. A system comprising: processor; as well as A memory having instructions stored therein, wherein execution of the instructions by the processor causes the processor to perform the method according to any one of claims 1-22.

24. A computer-readable medium storing instructions, wherein execution of the instructions by a processor causes the processor to perform the method according to any one of claims 1 to 22.

25. A system for non-invasively assessing a disease state or abnormal condition in a subject, the system comprising: processor; and a memory having stored thereon instructions, wherein execution of the instructions by the processor causes the processor to: obtaining a biophysical signal dataset of a subject, wherein the biophysical signal dataset is associated with at least a photoplethysmography signal and a cardiac signal; determining one or more dynamic characteristic features derived from a machine learning model and a Poincare map of the biophysical signal dataset, wherein the one or more dynamic characteristic features are based on a set of features associated with the photoplethysmography signal and the cardiac signal; and determine the alpha shape object of the Poincare map; determining one or more geometric properties of the alpha shape object; One or more estimates of the presence, location, and / or severity of a disease or condition are determined based on the determined one or more dynamic characteristic features and the one or more determined geometric characteristics of the alpha-shaped object.

26. The system of claim 25, wherein: Execution of the instructions by the processor causes the processor to: One or more second estimates of the presence, location, and / or severity of two or more of the diseases or conditions are determined.

27. The system according to claim 25 or 26, wherein: The dynamic characteristic feature is selected from the group consisting of: entropy value (K2), fractal dimension (D2), Lyapunov exponent, autocorrelation, auto mutual information, cross-correlation, and mutual information.

28. The system according to any one of claims 25 to 27, wherein: The obtained biophysical signal dataset includes one or more red photoplethysmography signals.

29. The system according to any one of claims 25 to 28, wherein: The obtained biophysical signal dataset includes one or more infrared photoplethysmography signals.

30. The system according to any one of claims 25 to 29, wherein: The obtained biophysical signal dataset includes one or more cardiac signals.

31. The system according to any one of claims 25 to 30, wherein: Execution of the instructions by the processor causes the processor to: A visualization is caused to be generated for an estimate of the presence, location, 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.

32. The system of any one of claims 25-31, wherein execution of the instructions by the processor causes the processor to: A histogram of periodic variations in the biophysical signal dataset is determined, wherein the histogram is used to determine an estimate of the presence, location, and / or severity of the disease or condition.

33. The system of claim 25, wherein: The one or more determined geometric characteristics further comprise two or more characteristics selected from the group consisting of: the density value of the alpha shape object; The convex surface area value of the alpha shape object; The perimeter value of the alpha shape object; the porosity value of the alpha shape object; and The blank area value of the alpha shape object.

34. The system of claim 32, wherein: The one or more determined geometric characteristics further comprise two or more characteristics selected from the group consisting of: the semi-axis length "a" of the largest cluster ellipse evaluated for the Poincare map; the semi-axis length "b" of the largest cluster ellipse evaluated for the Poincare map; the length of the longest axis of the largest cluster ellipse evaluated by the Poincare map; The length of the shortest axis of the largest cluster ellipse evaluated by the Poincare map; the number of clusters evaluated in the Poincare map; an estimated number of kernel density modes in the histogram; and Sarles' coefficient of bimodality value assessed from the histogram.

35. The system of claim 25 or 26, further comprising: A measurement system is configured to acquire one or more photoplethysmography signals.

36. The system of claim 25 or 26, further comprising: A measurement system is configured to acquire one or more cardiac signals.

37. The system of claim 25 or 26, further comprising: a first measurement system configured to acquire one or more photoplethysmography signals; as well as The second measurement system is configured to acquire one or more cardiac signals.

38. A system for non-invasively assessing a disease state or abnormal condition in a subject, the system comprising: processor; as well as a memory having stored thereon instructions, wherein execution of the instructions by the processor causes the processor to: obtaining a biophysical signal dataset of a subject, wherein the biophysical signal dataset is associated with at least a photoplethysmography signal and a cardiac signal; determining one or more dynamic characteristic features using a machine learning model; determining a Poincare map of variance in the biophysical signal dataset; determining an alpha shape object of the Poincare map; determining one or more geometric properties of the alpha shape object; as well as An estimate of the presence, location, and / or severity of a disease or condition is determined based on the determined one or more geometric characteristics and the one or more dynamic characteristic features, wherein the disease state includes the presence of coronary artery disease or elevated or abnormal left ventricular end-diastolic pressure.

39. The system of claim 38, wherein: The determined Poincare map is generated by plotting photoplethysmography signal peaks on a first axis at a first time x-1 to a second time x and on a second axis at the second time x to a third time x+1.

40. The system of any one of claims 38-39, further comprising: A measurement system is configured to acquire one or more photoplethysmography signals.

41. The system of any one of claims 38-39, further comprising: A measurement system is configured to acquire one or more cardiac signals.

42. The system of any one of claims 38-39, further comprising: a first measurement system configured to acquire one or more photoplethysmography signals; as well as The second measurement system is configured to acquire one or more cardiac signals.

Images