Multi-sensor MEMS system and machine learning analysis method for hypertrophic cardiomyopathy estimation

Through non-invasive biophysical sensor systems and machine learning analysis technology, the problem of early diagnosis of HCM in the existing technology is solved, and rapid, economical and safe assessments are achieved in multiple environments, improving diagnostic accuracy.

CN118922128APending Publication Date: 2024-11-08ANALYTICS FOR LIFE
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202380028578.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2022-01-23
Filing Date
2023-01-23
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The prior art is difficult to diagnose and efficiently evaluate hypertrophic cardiomyopathy (HCM), and the traditional methods are costly, long and inconvenient to use in non-hospital settings.

Method used

Using a non-invasive biophysical sensor system, including a MEMS accelerometer and a photoplethysmography sensor, the electrocardiogram, vibration schema, photovoltaic graph and cardiac sound schema are analyzed through machine learning to estimate the presence, absence and severity of HCM.

Benefits of technology

It realizes rapid, economical and safe evaluation of HCM in various environments, reducing diagnostic costs and time, and improving diagnostic accuracy and feasibility.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118922128A_ABST
    Figure CN118922128A_ABST
Patent Text Reader

Abstract

An exemplary method is disclosed that can be used to diagnose hypertrophic cardiomyopathy (HCM) using a biophysical sensor system, the biophysical sensor system is configured to non-invasively simultaneously acquire electrocardiogram signals, vibrogram signals, photoplethysmogram signals, and / or heart sound signals (collectively referred to herein as biophysical signals) from at least a chest region of a subject. The acquired biophysical signals may be evaluated to assess one or more conditions or indices of hypertrophic cardiomyopathy, and simultaneously assess indices of other cardiac diseases, conditions, or any one.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] Related Applications

[0002] This PCT international patent application claims priority to and the benefit of U.S. Provisional Patent Application No. 63 / 302,109, filed on January 23, 2022, and entitled “MEMS-SENSOR SYSTEM AND MACHINE-LEARNED ANALYSIS METHOD FOR HYPERTROPHIC CARDIOMYOPATHY ESTIMATION,” the entire contents of which are hereby incorporated herein by reference. Background Art

[0003] Hypertrophic cardiomyopathy (HCM) is a disease, usually of autosomal dominant origin, that causes the muscle cells (cardiomyocytes) in the heart wall to enlarge and cause one or more areas of the heart wall to become abnormally thick (hypertrophy). It may lead to diastolic and / or systolic dysfunction, clinically manifesting as heart failure or heart valve disease. Although approximately 100,000 people in the United States are diagnosed with HCM, it is estimated that more than 500,000 people in the United States may have this condition

[16] . HCM causes sudden cardiac death in approximately 1% of the affected population each year. Its symptoms include, for example, chest pain, fainting (syncope), palpitations, and shortness of breath. Current diagnostic options for HCM include genetic testing, echocardiography, electrocardiography (ECG / EKG), and cardiac magnetic resonance imaging (MRI). Some of these tests can be costly and often require specialized equipment in a dedicated room at a hospital or clinical center and performed by experienced technicians. They are usually scheduled individually within a few days or weeks of the initial visit to a healthcare provider.

[0004] There is a great deal of interest in early diagnosis and treatment of HCM, for example, reducing or preventing further expansion of cardiomyocytes to a hypertrophic state. Such early diagnosis and / or treatment may improve the health and overall outcomes of patients suffering from this condition. Early diagnosis and treatment of HCM may save lives and healthcare costs because more expensive interventions and treatments may be avoided or mitigated.

[0005] It would also be beneficial to be able to systematically screen or assess the presence, absence, and / or severity of HCM (regardless of the stage of the disease) using non-invasive techniques, without the use of radiation, drugs, and / or stress, and in a faster and more cost-effective manner than currently available methods, thereby allowing the assessment (e.g., prediction and / or detection) of the presence, absence, severity, and (in some cases) localization of various diseases, pathologies, or conditions in mammalian or non-mammalian organisms to be accomplished more safely, at a lower cost, and / or in a shorter time than currently available methods and systems.

[0006] 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 hospitals to emergency rooms, laboratories, battlefields, remote environments, the patient's primary care physician or other caregiver's point of care, and even the home. Summary of the invention

[0007] An exemplary method is disclosed that can be used to diagnose hypertrophic cardiomyopathy (HCM) using a biophysical sensor system (e.g., a multi-sensor system) configured to non-invasively and simultaneously acquire electrocardiogram signals, shock tracing signals, photoplethysmograms, and / or phonocardiogram signals, etc. (collectively referred to herein as biophysical signals) from a subject. One or more of these signals can be collected from the chest region of the patient. The acquired biophysical signals can be evaluated to evaluate one or more conditions or indicators of hypertrophic cardiomyopathy and simultaneously evaluate indicators of other diseases, conditions, or either. The biophysical sensor system can include a MEMS-based accelerometer, transducer, or sensor to acquire shock tracing signals and / or phonocardiogram signals and other related signals, such as ballistocardiogram signals. The biophysical sensor system can include a surface electrode-based acquisition circuit or module to directly acquire electrocardiogram signals or cardiac signals. The biophysical sensor system can include a photoplethysmographic sensor or module to directly acquire photoplethysmographic signals or other hemodynamic signals. The biophysical sensor system can use wired or wireless communication, or can be an independent or integrated sensor. The biophysical sensor system is operably connected and operates as part of a clinical evaluation system, which includes an analysis system, the analysis system including an analysis engine, the analysis engine configured to perform machine learning-based analysis to provide one or more estimated indicators related to the presence, absence and / or severity of hypertrophic cardiomyopathy or a condition (as described herein), which may not otherwise be detected or understood to the same extent. In some embodiments, the clinical evaluation system may include an additional analysis engine configured to perform additional machine learning-based analysis to assess other physiological states of the patient, including the presence or absence of other diseases, medical conditions, or indications of any of the following diseases and conditions: (i) heart failure (e.g., left-sided or right-sided heart failure; heart failure with preserved ejection fraction (HFpEF), heart failure with reduced ejection fraction (HFrEF)), (ii) coronary artery disease (CAD), (iii) various forms of pulmonary hypertension (PH), including but not limited to pulmonary arterial hypertension (PAH), (iv) abnormal left ventricular ejection fraction (LVEF), and various other diseases or conditions. Examples of indications of certain forms of disease that may be assessed include the presence of elevated or abnormal left ventricular end-diastolic pressure (LVEDP) as an indication of heart failure, or elevated or abnormal mean pulmonary artery pressure (mPAP) as an indication of pulmonary hypertension.

[0008] In one aspect, a method for non-invasively estimating the presence, absence, and / or severity of hypertrophic cardiomyopathy in a mammalian subject is disclosed, the method comprising: obtaining, by one or more processors, one or more biophysical signals of a patient from one or more sensors; determining, by the one or more processors, one or more values ​​associated with one or more features and / or machine learning-based analysis using at least a portion of the one or more signals; and determining, by the one or more processors, an estimate of the presence, absence, and / or severity of hypertrophic cardiomyopathy using multiple values ​​associated with multiple features or machine learning-based analysis, wherein an estimate of the presence, absence, and / or severity of hypertrophic cardiomyopathy (e.g., an HCM score) is output for diagnosis of hypertrophic cardiomyopathy and / or guiding treatment of hypertrophic cardiomyopathy.

[0009] On the other hand, a method for non-invasively estimating the presence, absence and / or severity of hypertrophic cardiomyopathy in a mammalian subject is disclosed, the method comprising: obtaining, by one or more processors, one or more seismocardiographic signals (SCG signals) and / or phonocardiographic signals (PCG signals) from a multi-sensor device placed on or worn on a patient; determining, by the one or more processors, a plurality of values ​​associated with a plurality of features or a machine learning-based analysis using at least a portion of the one or more seismocardiographic signals and / or phonocardiographic signals; and determining, by the one or more processors, an estimate of the presence, absence and / or severity of hypertrophic cardiomyopathy using the plurality of values ​​associated with the plurality of features or the machine learning-based analysis, wherein an estimate of the presence, absence and / or severity of hypertrophic cardiomyopathy (e.g., an HCM score) is output for use in diagnosing hypertrophic cardiomyopathy or guiding treatment of hypertrophic cardiomyopathy.

[0010] In another aspect, a method for non-invasively estimating the presence, absence, and / or severity of hypertrophic cardiomyopathy in a mammalian subject is disclosed, the method comprising: obtaining, by one or more processors, a first biophysical signal dataset (PPG signal) associated with a first photoplethysmographic signal and a second photoplethysmographic signal, wherein the first biophysical dataset has been acquired over a plurality of cardiac cycles of the subject; obtaining, by the one or more processors, a second biophysical signal dataset (cardiac signal) associated with a cardiac signal, wherein the second biophysical dataset has been acquired simultaneously with the first biophysical signal dataset over the plurality of cardiac cycles; determining, by the one or more processors, a plurality of values ​​associated with a plurality of features or a machine learning-based analysis using at least a portion of the first biophysical signal and the second biophysical signal; and determining, by the one or more processors, an estimate of the presence, absence, and / or severity of hypertrophic cardiomyopathy using the plurality of values ​​associated with the plurality of features or the machine learning-based analysis, wherein the estimate of the presence, absence, and / or severity of hypertrophic cardiomyopathy (e.g., an HCM score) is output for diagnosis of hypertrophic cardiomyopathy or for guiding treatment of hypertrophic cardiomyopathy.

[0011] In some embodiments, multiple features or machine learning-based analyses are configured to quantify deviations of the VD wave trajectory from a three-dimensionally modeled VD wave trajectory (eg, to assess high frequency and low amplitude patterns in the VD trajectory).

[0012] In some embodiments, multiple features or machine learning-based analyses are configured to quantify beat-to-beat variations in the cardiac signal.

[0013] In some embodiments, the plurality of features or machine learning based analysis is configured to quantify the variability of registered landmarks in cardiac, PPG and / or SCG signals via Poincare analysis and histogram analysis.

[0014] In some embodiments, multiple features or machine learning-based analyses are configured to quantify dynamic properties of cardiac, PPG, and / or SCG signals (e.g., Lyapunov exponents, correlation dimension, entropy, mutual information, correlation, and / or nonlinear filtering).

[0015] In some embodiments, multiple features or machine learning-based analyses are configured to quantify properties of cardiac, PPG, and / or SCG signals (e.g., waveform amplitude, duration, heart rate, morphology; properties of PPG, VPG, APG signals, e.g., peak amplitude, peak-to-peak distance, point-to-point angles, and various ratios).

[0016] In some embodiments, multiple features or machine learning based analyses are configured to quantify the dominant frequency components of cardiac, PPG and / or SCG signals using wavelet analysis.

[0017] In some embodiments, multiple features or machine learning based analyses are configured to quantify the power spectrum and frequency content of cardiac, PPG and / or SCG signals using power spectrum and coherence (cross spectrum analysis) analysis.

[0018] In some embodiments, multiple features or machine learning-based analyses are configured to quantify properties of the cardiac, PPG, and / or SCG signals on loop regions (e.g., atrial depolarization, ventricular depolarization, and ventricular repolarization) in 3D phase space, their projections, and loop vectors.

[0019] In some embodiments, multiple features or machine learning-based analyses are configured to approximate a respiratory waveform using (i) PPG and cardiac signals or (ii) SCG signals to assess (1) heart rate variability, (2) respiratory rate, (3) a difference feature representing the distance between respiratory and modulation signals, and (4) squared coherence representing the correlation between modulation and respiratory rate signals, wherein the approximated respiratory waveform is used for HCM assessment by generating a depicted inspiratory portion and expiratory portion of the SCG signal for analysis.

[0020] In some embodiments, multiple features or machine learning-based analyses are configured to quantify physiological aspects of cardiac and / or SCG signals.

[0021] In some embodiments, multiple features or machine learning-based analyses are configured to quantify characteristic changes in cardiac, SCG, and / or PCG signals associated with inspiration versus expiration versus Valsalva maneuvers to identify HCM patients.

[0022] In some embodiments, multiple features or machine learning-based analyses are configured to quantify characteristic changes in cardiac, SCG, and / or PCG signals associated with inspiration versus expiration versus Valsalva maneuvers to identify a subset of HCM patients with obstructive HCM (HOCM).

[0023] In some embodiments, multiple features or machine learning-based analyses are configured to approximate left ventricular ejection time (LVET) using one or more SCG and / or PCG signals.

[0024] In some embodiments, multiple features or machine learning-based analyses are configured to quantify propagation characteristics (e.g., wave speed, trajectory, orbital frequency, planarity) of a ventricular depolarization (VD) wave and / or a ventricular repolarization (VR) wave in three-dimensional space.

[0025] In some embodiments, multiple features or machine learning-based analyses are evaluated at (i) an inspiratory region of one or more epicardiographic signals and / or phonocardiographic signals and / or (ii) an expiratory region of one or more epicardiographic signals and / or phonocardiographic signals.

[0026] In another aspect, a device (e.g., an SCG / PCG measurement device) is disclosed, comprising: a sensor body configured to be worn externally or placed on a chest region of a subject to acquire biophysical signals from the chest region, including signals of the heart; and two or more MEMS-based biophysical sensors (e.g., accelerometers: single-axis or multi-axis), comprising a first MEMS-based sensor and a second MEMS-based sensor, wherein the two or more MEMS-based sensors are located within the sensor body and connected to electrodes configured to be placed on the subject, wherein the first MEMS-based sensor and the second MEMS-based sensor generate a first biophysical signal and a second biophysical signal during operation to be provided to an analysis system, the analysis system being configured to evaluate multiple features or machine learning-based analysis to generate an estimate of the presence, absence, and / or severity of hypertrophic cardiomyopathy (e.g., an HCM score) (e.g., for diagnosing hypertrophic cardiomyopathy or guiding treatment of hypertrophic cardiomyopathy).

[0027] In another aspect, a device (e.g., an SCG / PCG measurement device) is disclosed, comprising: a sensor body configured to be worn externally or placed on a chest region of a subject to acquire biophysical signals from the chest region (including the heart); and two or more MEMS-based accelerometers (single-axis or multi-axis), including a first MEMS-based accelerometer and a second MEMS-based accelerometer, wherein the two or more MEMS-based accelerometers are located within the sensor body and connected to electrodes configured to be placed on the subject, wherein the first MEMS-based accelerometer and the second MEMS-based accelerometer generate a first shock tracing signal and a second shock tracing signal during operation to provide to an analysis system, the analysis system being configured to evaluate multiple features or machine learning-based analysis to generate an estimate of the presence, absence, and / or severity of hypertrophic cardiomyopathy (e.g., an HCM score) (e.g., for diagnosing hypertrophic cardiomyopathy or guiding treatment of hypertrophic cardiomyopathy).

[0028] In some embodiments, the device further comprises a plurality of surface electrodes configured to be placed on a surface of a chest region of the subject to provide a plurality of cardiac signals of the subject's heart, wherein the plurality of cardiac signals are provided to an analysis system to evaluate a plurality of features or a machine learning-based analysis to generate an estimate of the presence, absence and / or severity of hypertrophic cardiomyopathy.

[0029] In some embodiments, the device further comprises a plurality of photoplethysmographic sensors configured to be placed on the subject to provide one or more photoplethysmographic signals, wherein the one or more photoplethysmographic signals are provided to an analysis system to evaluate a plurality of features or a machine learning-based analysis to generate an estimate of the presence, absence, and / or severity of hypertrophic cardiomyopathy.

[0030] In some embodiments, the first MEMS-based accelerometer is configured to be placed near the apex region of the heart.

[0031] In some embodiments, the second MEMS-based accelerometer is configured to be placed near the base region of the heart.

[0032] In another aspect, a system is disclosed, the system comprising any of the above-described apparatus and an analysis system, wherein the analysis system is implemented in a cloud-based processing and network infrastructure.

[0033] In another aspect, a system (e.g., a cloud platform or a local computing platform) is disclosed, the system comprising one or more processors and one or more memories, the one or more memories respectively storing instructions, wherein the one or more processors execute the instructions so that the one or more processors perform any of the above methods.

[0034] In another aspect, a non-transitory computer-readable medium is disclosed, comprising instructions stored thereon, wherein execution of the instructions by one or more processors causes the one or more processors to perform any of the above methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] 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 methods and systems.

[0036] Embodiments of the present invention may be better understood by reading the following detailed description in conjunction with the accompanying drawings. These embodiments are for illustrative purposes only and depict novel and non-obvious aspects of the present invention. The accompanying drawings include the following figures:

[0037] Figure 1 is a schematic diagram of a clinical evaluation system configured to non-invasively and simultaneously acquire electrocardiographic, vibrographic, photoplethysmographic, and / or phonocardiographic signals and evaluate the acquired biophysical signals in a machine learning-based analysis to generate one or more estimated indices associated with the presence, absence, and / or severity of hypertrophic cardiomyopathy.

[0038] Figure 2Diagrams showing example HCM physiological effects and example machine learning-based analysis.

[0039] Figure 3 A graph depicts example biophysical signals acquired for use in evaluating hypertrophic cardiomyopathy in accordance with an illustrative embodiment.

[0040] Figure 4A A diagram of an example SCG / PCG measurement apparatus is shown in accordance with an illustrative embodiment.

[0041] Figure 4B A diagram is shown of another example SCG / PCG measurement apparatus in accordance with an illustrative embodiment.

[0042] Figure 4C A diagram showing yet another example SCG / PCG measurement apparatus in accordance with an illustrative embodiment.

[0043] Figure 4D is a diagram of an example measurement system configured as a wearable MEMS sensor device in accordance with an illustrative embodiment.

[0044] Figure 4E A wearable chest sensor device configured as a wearable chest sensor device according to an illustrative embodiment is shown. Figure 4D Image of an example fabricated wearable MEMS sensor device.

[0045] Figure 5A A schematic diagram of an example clinical evaluation system according to an illustrative embodiment is shown, the system being configured to use machine learning-based analysis (as well as other analyses) to generate one or more indicators associated with a patient's physiological state, including, for example, the presence, absence, and / or severity of HCM, other conditions or indications, and / or the severity of any of them.

[0046] Figure 5B According to an illustrative embodiment, Figure 5A Schematic diagram of the operation of an example clinical evaluation system.

[0047] Figures 6A-6H Experimental results of various developed ML features for determining physiological effects of HCM in accordance with illustrative embodiments are shown. DETAILED DESCRIPTION

[0048] Every feature described herein and every combination of two or more such features is included within the scope of the present invention, provided that the features included in such combination are not mutually inconsistent.

[0049] definition

[0050] As used herein, the terms "subject" and "patient" are generally used interchangeably to refer to those who have been subjected to the analysis performed by the exemplary systems and methods.

[0051] As used herein, the term "biophysical signal" includes, but is not limited to, one or more cardiac signals, neural signals, episiograph signals, ballistocardiogram signals, and / or photoplethysmographic signals, phonocardiogram signals, and / or episiocardiogram signals, but it also more broadly encompasses any physiological signal from which information can be obtained. Without limitation to the examples, biophysical signals can be classified into a variety of types or categories, including, 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 in various domains such as time and / or frequency (e.g., biopotential), impedance, resistivity, conductivity, current, etc.), magnetic signals, electromagnetic signals, optical signals (e.g., signals that can be observed, identified, and / or quantified by techniques such as reflectance, interferometry, 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 (e.g., 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, integumentary / exocrine, and reproductive), one or more organ systems (e.g., signals that may be unique to the heart and lungs working together), or 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 observing natural or induced electrical, magnetic, optical, and / or acoustic emissions from body tissues. Non-limiting examples of passive and active biophysical signal acquisition means include, for example, voltage / potential, current, magnetism, light, sound, and other non-active means for observing natural emissions from body tissues and, in some cases, inducing such emissions. 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 methods of actively interrogating body tissues 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 the transmission of ionizing energy or radiation (e.g., X-rays) to body tissues (also referred to as "ionizing biophysical signals").Passive and active biophysical signal acquisition approaches can be combined with invasive procedures (e.g., through surgery or invasive radiological interventions) or performed non-invasively (e.g., through imaging, ablation, cardiac contraction modulation (e.g., through pacemakers), catheterization, etc.).

[0052] The term "cardiac signal" as used herein refers to one or more signals (including electrical / electrochemical conduction aspects of the signal) directly or indirectly associated with the structure, function and / or activity of the cardiovascular system, such as causing myocardial contraction. In some embodiments, the cardiac signal may include a biopotential signal or an electrocardiogram signal, such as a signal acquired by an electrocardiogram (ECG), a cardiac and photoplethysmographic waveform, or a signal capture or recording instrument described later herein or otherwise. In some embodiments, the cardiac signal is acquired as an orthogonal voltage gradient (OVG) signal.

[0053] As used herein, the term "photoplethysmographic signal" refers to one or more signals or waveforms acquired from an optical sensor that correspond to measured changes in light absorption by oxyhemoglobin and deoxyhemoglobin, such as light having wavelengths in the red and infrared spectra. In some embodiments, the photoplethysmographic signal comprises a raw signal acquired by a pulse oximeter or photoplethysmogram (PPG). In some embodiments, the photoplethysmographic signal is acquired from an off-the-shelf, custom, and / or dedicated device or circuit configured to acquire such signal waveforms for use in monitoring health and / or diagnosing a disease or abnormal condition. The photoplethysmographic signal typically includes a red photoplethysmographic signal (e.g., an electromagnetic signal having a wavelength of about 625 to 740 nanometers most predominantly in the visible light spectrum) and an infrared photoplethysmographic signal (e.g., an electromagnetic signal extending from the nominal red edge of the visible light spectrum to about 1 mm), but other light spectra, such as near infrared, blue, and green, may be used in different combinations depending on the type and / or mode of PPG employed.

[0054] As used herein, the term "ballistocardiographic signal" refers to a signal or group of signals that generally reflect the flow of blood through the body, which can be observed by vibration, sound, movement, or orientation, such as using an accelerometer, such as an accelerometer or transducer based on an electromechanical system (MEMS). In other embodiments, the ballistocardiographic signal can be acquired by an external device, such as a bed or surface-based device that measures phenomena such as changes in body weight as blood moves back and forth in a longitudinal direction between the head and feet. In such an embodiment, the amount of blood at each location may change dynamically and be reflected in the weight measured at each location on the bed and the rate of change of that weight.

[0055] As used herein, the term "seismocardiographic signal" refers to a signal or set of signals that generally reflects recorded body vibrations, sounds, or orientations recorded by a sensor (e.g., a MEMS sensor mounted or positioned near the heart, such as a MEMS accelerometer). The term "seismocardiographic signal" may be used interchangeably with the term "seismocardiographic signal."

[0056] As used herein, the term "phonocardiogram signal" refers to a signal or set of signals generally reflecting recorded body sounds, vibrations, and acoustic radiation recorded by a sensor, such as a microphone or accelerometer mounted or positioned near the heart or around the chest of a subject. The term "phonocardiogram signal" may be used interchangeably with the term "phonocardiographic signal".

[0057] Example System

[0058] Figure 1 1 is a schematic diagram of a clinical evaluation system 100 configured to non-invasively and simultaneously acquire electrocardiogram (ECG) signals, one or more shockcardiography (SCG) signals, (PPG) photoplethysmography, and / or phonocardiography (PCG) signals, and evaluate the acquired biophysical signals in a machine learning-based analysis to generate one or more estimated indices associated with the presence, absence, and / or severity of hypertrophic cardiomyopathy. The system 100 includes a measurement system 102 and an analysis system 104 on a network 106. Figure 1 In the example shown, the analysis system 104 is implemented in a cloud-based infrastructure. The analysis system 104 includes (i) a data storage 108 for receiving one or more data files 114 associated with the measurements performed by the measurement system 102, and (ii) an analysis engine, including an analysis feature analysis module 110 (shown as "features" 110) and a machine learning classifier module 112, for evaluating the one or more data files 114 in a machine learning-based analysis. The output 116 of the analysis system 104 can be provided as a report to the patient, such as through a healthcare portal, or as an output to a wearable device, or as an output to a medical device for treatment of an indication of a disease, condition, or either. A healthcare provider, such as a physician, can review the report and interpret it to provide a disease diagnosis or develop a treatment plan.

[0059] Machine learning-based analysis refers to analysis or features that include or are derived from machine learning or artificial intelligence analysis. In some embodiments, the machine learning-based analysis includes evaluating features from a feature library to down-select or train using clinical data to obtain features that are statistically significant in estimating indicators related to the presence, absence and / or severity of hypertrophic cardiomyopathy, such as through ElasticNet machine learning classifier models [9], RandomForestClassifier machine learning classifier models

[10] , and extreme gradient boosting (XGB) classifier models

[11] . An example of a training system for configuring an analysis system (e.g., for elevated LVEDP estimation) is described in U.S. Provisional Application No. 63 / 235,960, filed on August 23, 2021, entitled "METHODAND SYSTEM TO ASSESS HEART FAILURE", which is hereby incorporated by reference in its entirety. Another example of a training system that can be used to configure an analysis engine is described in

[19] , which is hereby incorporated by reference in its entirety.

[0060] HCM physiological effects and indicators

[0061] Figure 2 Figures showing example HCM physiological effects and example machine learning-based analyses. Hypertrophic cardiomyopathy (HCM) is a genetic disorder characterized by left ventricular hypertrophy that is unexplained by secondary causes, with a nondilated left ventricle and typically preserved or increased ejection fraction. It is often asymmetric, with the most severe hypertrophy involving the basal ventricular septum. Approximately one-third of patients present with left ventricular outflow tract obstruction at rest, while an additional third may be induced

[21] . Pathological hallmarks of the disease include cardiomyocyte hypertrophy and disorganization, interstitial and replacement fibrosis, small vessel abnormalities, and cardiomyocyte electrical remodeling, all of which may underlie ventricular arrhythmias. Hypertrophy is also frequently associated with left ventricular diastolic dysfunction

[22] . In addition, a higher prevalence of sinus node dysfunction (66%) and His-Purkinje (HV) conduction abnormalities (30%) has been observed in HCM patients with electrophysiological abnormalities

[23] . The most commonly induced supraventricular arrhythmias may be atrial reentrant tachycardia and atrial fibrillation (10% and 11% of patients, respectively).

[0062] In HCM patients, the heart wall (e.g., 202a, 202b) increases in size, mass, and stiffness (or loss of compliance) due to cardiomyocyte enlargement (hypertrophy). HCM hearts can exhibit different topological structures. In some cases, the thickening may be asymmetric, for example, involving only the septum (202a) between the left and right ventricles, or the circumferential thickness of the left ventricular wall (202b) may increase concentrically.

[0063] Dilation effect (202'). When the septal wall (204) (shown as ventricular septum 204) dilates, it encroaches on the left ventricular outflow tract (see 206); it can create a physiological condition similar to aortic valve obstruction, blocking blood from flowing out of the left ventricle (208) and into the aorta (201). This obstruction or blood flow restriction (203') has been observed as turbulent flow through the narrowed left ventricular outflow tract (LVOT), causing a "murmur" (obstructive murmur) or sound and vibration, similar to all the physiological effects of aortic stenosis (narrowing of the left ventricular outlet of the heart).

[0064] In addition to this flow or obstruction blockage (203'), the intrusion of the septal wall (204) into the left ventricular cavity (208) may also affect the function of the mitral valve (210), resulting in mitral regurgitation (a condition in which the mitral valve, which consists of two leaflets and is located between the left atrium (212) and the left ventricle (208) of the heart, fails to close tightly, causing blood to flow back in the left atrium (212)) (205'). Due to this systolic anterior motion (SAM) of the mitral valve (210), the anterior mitral leaflet may be pulled toward (214) the septum, resulting in mitral valve (210a) insufficiency. Leakage (205') at the mitral valve (e.g., 210a) may lead to cardiac enlargement and clinical manifestations of heart failure, which may also occur with aortic stenosis. Mitral regurgitation (205') and associated leaks across the mitral valve typically result in turbulent flow, a heart murmur ("mitral regurgitation murmur"), and vibrations.

[0065] Altered tissue stiffness (207'). Because the ventricular muscle (202b) is thicker, it is also stiffer and more integral, and the physiology may be similar to heart failure with preserved ejection fraction (HFpEF), where the heart can contract perfectly but cannot relax appropriately. HfpEF is characterized by abnormal diastolic function, with increased left ventricular wall stiffness (202b) leading to reduced left ventricular relaxation during diastole, resulting in increased pressures and / or impaired filling. In other cases, patients with HCM have impaired diastolic function and decreased systolic function. All of these effects (loss of cardiac tissue compliance (207'), obstruction / obstructed flow (203'), valve leakage (205')), impaired systolic and / or diastolic function, and may lead to pulmonary congestion, resulting in shortness of breath and syncope (temporary loss of consciousness, often associated with insufficient cerebral blood flow), among other symptoms.

[0066] Reduced left ventricular relaxation during diastole is essentially a difficulty filling (209') of the left ventricle (208) (rather than difficulty contracting the ventricle). This can be modeled or thought of as a muscle-constrained heart whose ability to relax sufficiently to allow blood to flow in is impaired, and thus can result in increased left atrial pressure (representing pulmonary venous pressure), increased left ventricular pressure (LVP) (pressure within the left ventricle), and increased diastolic pressure (pressure exerted by the blood on the arterial walls when the heart relaxes between heartbeats). In order to achieve adequate filling, the heart can increase pulmonary venous pressure (211'), which can lead to effects such as congestion (fluid in the lungs) and shortness of breath. The effect of the heart muscle being able to contract adequately but not being able to relax adequately to fill for the next heartbeat can also cause the body to compensate by increasing arterial and venous blood pressure; this can also lead to shortness of breath and other conditions.

[0067] All of these effects (loss of cardiac tissue compliance, obstruction / impeded flow, valve leakage, loss of cardiac tissue compliance) affect the voltage distribution and pattern of the heart compared to a normal heart. Due to changes in cardiac geometry (asymmetry or symmetry), cardiac operation changes over time and is indicated by changes in left ventricular ejection time (LVET) (213'). LVET measures the period of blood flow across the aortic valve and has a normal value of 0.35 ± 0.08 seconds.

[0068] Furthermore, all of these effects (loss of cardiac tissue compliance, obstruction / flow obstruction, valvular leaks) affect commonly observable components of the heart. For example, the frequency components of the heart (e.g., those observed by power spectral density or wavelet frequency components, etc.) may vary with respiratory rate. During inspiration, the heart fills more than during expiration because the transthoracic pressure during inspiration can increase the ventricular filling pressure. The transthoracic pressure can be thought of as the combination of the hemodynamic pressure and the negative pressure within the thoracic cavity during inspiration.

[0069] Additionally, there may be observable phase elements in the sound due to loss of cardiac tissue compliance, obstruction / flow obstruction, and valvular leaks. During deep inspiration, the heart can fill more with less left ventricular outflow obstruction, while during expiration, there is less filling and more outflow obstruction

[17] . Heart murmurs may decrease in amplitude during inspiration and increase in amplitude during expiration. Similarly, the detected vibrations of the shockcardiographic and / or phonocardiographic signals may decrease in amplitude during inspiration and increase in amplitude during expiration. Similarly, the detected vibrations of the shockcardiographic and / or phonocardiographic signals may increase in amplitude through a physiological maneuver known as the Valsalva maneuver. The Valsalva maneuver is a breathing technique that is performed by forcefully exhaling into a closed airway, typically by closing the mouth and pinching the nose while exhaling air like blowing up a balloon.

[0070] Indeed, as described above, the aforementioned body physiology and HCM physiological effects can produce vibrations, electrical patterns, and frequency components that are indicative of or unique to HCM and the conditions that cause it. These physical manifestations can be evaluated by the features described herein or machine learning-based analysis to estimate indicators associated with the presence, absence, and / or severity of hypertrophic cardiomyopathy.

[0071] Additionally, the presence of ventricular tachycardia can be an indication of the presence of hypertrophic cardiomyopathy. Ventricular tachycardia (V-tach or VT) is characterized by a rapid heart rate originating from the lower chambers of the heart. Programmed ventricular stimulation (PVS) resulted in nonsustained ventricular tachycardia (VT) in 14% of patients and sustained ventricular arrhythmias in 43%. Sustained ventricular arrhythmias manifested as polymorphic VT in 73% of patients, monomorphic VT in 24%, and ventricular fibrillation in 2 (3%) patients.

[0072] Machine Learning Analysis Module

[0073] exist Figure 1In the example, the analysis system 104 includes an analysis engine including an analysis feature analysis module 110 configured to calculate features or parameters to generate one or more estimated indicators associated with the presence, absence and / or severity of hypertrophic cardiomyopathy via a classifier (e.g., a machine learning classifier). The analysis system 104 may include additional analysis engines configured to perform additional machine learning-based analyses to assess other physiological states of the patient, including the presence, absence and / or severity of other diseases, medical conditions or indications thereof, such as (i) heart failure (e.g., left-sided or right-sided heart failure; heart failure with preserved ejection fraction (HfpEF), heart failure with reduced ejection fraction (HfrEF)), (ii) coronary artery disease (CAD), (iii) various forms of pulmonary hypertension (PH), including but not limited to pulmonary arterial hypertension (PAH), (iv) abnormal left ventricular ejection fraction (LVEF), etc. Examples of indicators of certain forms of disease that may be evaluated include the presence or absence of elevated or abnormal left ventricular end-diastolic pressure (LVEDP) as an indication of heart failure, or elevated or abnormal mean pulmonary artery pressure (mPAP) as an indication of pulmonary hypertension.

[0074] Table 1 shows a list of feature categories and corresponding descriptions that can be used to calculate estimates associated with the presence, absence, and / or severity of hypertrophic cardiomyopathy. The features listed below are also shown in Figure 2 middle.

[0075] Table 1

[0076]

[0077]

[0078]

[0079]

[0080]

[0081]

[0082]

[0083] Detailed descriptions of some of the analyses in Table 1, which can be applied to SCG signals and used to determine the presence, absence, and / or severity of HCM, can be found in [1]-

[13] and

[20] -

[56] , among others, each of which is hereby incorporated by reference in its entirety.

[0084] Other feature modules that may be used are described in the following documents: U.S. Patent Nos. 9,289,150; 9,655,536; 9,968,275; 8,923,958; 9,408,543; 9,955,883; 9,737,229; 10,039,468; 9,597,021; 9,968,265; 9,910,964; 10,672,518; 10,566,091; 10,566,092; 10,542,897; 10,362,950; 10,292,596; 10,806,349; U.S. Patent Publication Nos. 2020 / 0335217; 2020 / 0229724; 2019 / 0214137; 2018 / 0249960; 2019 / 0200893; 2019 / 0384757; 2020 / 0211713; 2019 / 036 5265; 2020 / 0205739; 2020 / 0205745; 2019 / 0026430; 2019 / 0026431; PCT Publication Nos. WO2017 / 033164; WO2017 / 221221; WO2019 / 130272; WO2018 / 158749; WO2019 / 077414; WO2019 / 130273; WO2019 / 244043; WO2020 / 136569; WO2019 / 234587; WO2020 / 136570; WO2020 / 136571; U.S. Patent Application Nos. 16 / 831,264; 16 / 831,380; 17 / 132869; PCT Application No. PCT / IB2020 / 052889; PCT / IB2020 / 052890, each of which is hereby incorporated by reference in its entirety.

[0085] The analysis and correlation module (e.g., 110), in addition to evaluating the PPG and cardiac signals, can also evaluate the provided features associated with the SCG or phonocardiographic signals, as well as extend various analyses (frequency, dynamics, periodic variability, etc., as described above) to evaluate changes in feature values ​​between the inspiratory and expiratory portions of the signal.

[0086] A module (eg, 110 ) may include analysis of an estimate of LVET or a parameter associated with elevated LVET.

[0087] MEMS Accelerometer Systems

[0088] exist Figure 1In the example shown, the measurement system 102 includes a chest-worn or mounted SCG / PCG measurement device 118 configured with two or more MEMS accelerometers, transducers, or sensors to provide at least two or more SCG / PCG measurements at least in the apex region and the base region of the heart. The SCG / PCG device 118 can be connected to a biophysical signal capture system 120 configured to measure cardiac signals via a set of surface electrodes 122 (shown as 122a-122f) and / or photoplethysmographic signals via a PPG sensor device 124. Example wireless communication operations and circuits are described in

[14] , which is hereby incorporated by reference in its entirety.

[0089] The SCG / PCG measurement device 118 includes a first MEMS accelerometer, transducer, or sensor 126 and a second MEMS accelerometer, transducer, or sensor 128. Two or more MEMS accelerometers, transducers, or sensors can provide a seismogram signal to the analysis system, and the analysis engine can perform phase difference and differential evaluation on the signal. For example, the first MEMS accelerometer, transducer, or sensor 126 can be configured to be located near the apex 130, and the second MEMS accelerometer, transducer, or sensor 128 can be configured to be located near or at the bottom region 132 of the left ventricle. Figure 1 In the example shown, device 118 and associated sensors 126 and 128 are non-invasively placed on the subject's skin at the illustrative areas shown. Figure 1 A cross-section of the heart is shown in FIG. 1 merely to illustrate the placement of sensors relative to certain cardiac structures in certain embodiments.

[0090] Example Biophysical Signals for Hypertrophic Cardiomyopathy Assessment

[0091] Figure 3 A graph showing example biophysical signals acquired for the evaluation of hypertrophic cardiomyopathy according to an illustrative embodiment. Figure 3In the example shown, example systolic cardiotocography signals, phonocardiography signals, cardiac signals (displayed as "electrocardiograms"), and photoplethysmographic signals acquired simultaneously within one cardiac cycle are shown. The figure also shows examples of aortic pressure, atrial pressure, ventricular volume, and ventricular pressure within the same cardiac cycle. Registration / landmark points can be determined in a single signal (e.g., a peak of a cardiac waveform, systolic cardiotocography signal, and / or phonocardiography signal) or between signals (e.g., two photoplethysmographic waveforms, intersections between two systolic cardiotocography waveforms, etc.), and their synchronization and phase can be evaluated relative to other acquired biophysical signals; for example, as described in U.S. Publication No. 2020 / 0397324, entitled "Method and System to Assess Disease Using Dynamical Analysis of Cardiac and Photoplethysmographic Signals", which is hereby incorporated by reference in its entirety.

[0092] Example SCG / PCG Measurement System #1

[0093] Figure 4A A diagram of an example SCG / PCG measurement device 118 is shown in accordance with an illustrative embodiment. Figure 4AIn the example shown, the SCG / PCG measurement device 118 includes two or more MEMS accelerometers, transducers, or sensors 126, 128 (shown as 126a, 128a). In this example, the MEMS accelerometers, transducers, or sensors 126a, 128a include 3-axis accelerometers 302 (shown as 302a, 302b), such as a small, low power, ADXL335, 3-axis accelerometer manufactured by Analog Devices, Inc., located in Wilmington, Massachusetts, which is integrated into a small 4mmx4mmx1.45mm package IC. The 3-axis accelerometers 302a, 302b are coupled to amplifiers and filters 303 to provide epicardiographic signals 304 to a cable 306 connected to the measurement system 102. In the example, the cardiac signal 308 is acquired at each of the six surface electrodes 312 and carried on the six conductors through the cable 306 to the measurement system 102. A reference electrode is also used. In the example, the photoplethysmographic signal 310 is generated at the PPG lead clip 314 because the photoplethysmographic sensor is carried on three conductors (two signals and GND) through the cable 306 to the measurement system 102. The measurement system 102 includes a conversion circuit for converting and digitizing the acquired biophysical signals. In some embodiments, the surface electrode 312 and / or the PPG lead clip 314 may include an accelerometer, for example, as described in

[14] (A4LBCG application), which is hereby incorporated by reference in its entirety.

[0094] The MEMS accelerometer and associated acquisition circuitry are configured to have a measurement range of at least ±1g or ±2g and a bandwidth of up to 1kHz. In some embodiments, the SCG / PCG measurement device 118 is configured to have a sensitivity of at least 0.164μs / μg and a noise density of less than MEMS accelerometer. Figure 4A In the example of the embodiment, the MEMS accelerometer and associated acquisition circuit are configured for unipolar output, but in other embodiments, the MEMS accelerometer and associated acquisition circuit are configured for bipolar and / or differential operation. Other configurations of MEMS accelerometers and associated acquisition circuits that may be used are described in

[15] (Sensor Manuscript), which is hereby incorporated by reference in its entirety.

[0095] In some embodiments, the MEMS sensor includes an acoustic sensor or transducer, such as an acoustic respiration sensor (e.g., Model RAS-45, manufactured by Masimo, Inc., Irvine, Calif.) Another example of an acoustic-based sensor is a sensor used in a digital stethoscope system, such as an ECG+ digital stethoscope (e.g., the DUO ECG+ digital stethoscope manufactured by Eko Devices, Inc., Oakland, Calif.).

[0096] In some embodiments, the MEMS sensor includes an accelerometer-based sensor, such as 9DoF inertial sensing, including an accelerometer, a gyroscope, a magnetic and a pressure sensor (e.g., Shimmer3IMU, manufactured by Shimmer in Cambridge, Massachusetts). Another example of an accelerometer-based sensor is an IMU sensor (Movesense IMU, manufactured by Movesense in Vantaa, Finland), including a 9-axis motion sensor including an accelerometer, a gyroscope and a magnetometer. An example of an accelerometer-based sensor is an IMU tracking sensor (ICM-20948, manufactured by TDK, InvenSense in San Jose, California), including a 9-axis motion sensor including an accelerometer, a gyroscope and a magnetometer. An example of an accelerometer-based sensor is an IMU tracking sensor (Sense Connect Detect model SCD110, manufactured by Bosch Connected Devices and Solutions GmbH (Germany)).

[0097] These MEMS sensors (acoustic, accelerometer, IMU) can be used alone or in combination with one or more other sensors, including but not limited to our current two sensor types or other sensor types described herein, to collect information for use in generating diagnostic tools for any indication or related conditions or indications for various forms of at least one of HCM, HF, PH, CAD, or a combination thereof. In addition, these MEMS sensors can be used to generate diagnostic tools for any indication described herein for various forms of non-HCM, HF, PH, and CAD.

[0098] Figure 4B Shows Figure 4A An example SCG / PCG measurement device 118 (shown as 118a) is configured as a wireless measurement module including a wireless transceiver module 402. The wireless transceiver module 402 includes a front-end conversion circuit 403, a microcontroller 404, and a wireless transceiver circuit 406. The wireless transceiver circuit 406 can interface with an interface device via a wireless connection.

[0099] The cardiac signal 308 and the photoplethysmography signal 310 may be acquired using the circuits and computing hardware, software, firmware, middleware, etc. in the biophysical signal capture system described in U.S. Patent No. 10,542,898 (titled “Method and Apparatus for Wide-Band Phase Gradient Signal Acquisition”) or U.S. Patent Publication No. 2018 / 0249960 (titled “Method and Apparatus for Wide-Band Phase Gradient Signal Acquisition”), each of which is hereby incorporated by reference in its entirety.

[0100] Other configurations and topologies discussed in this article may be employed, such as MEMS microphones or acoustic transducers, etc.

[0101] Example SCG / PCG Measurement System #2

[0102] Figure 4C A diagram of another example SCG / PCG measurement device 118 (shown as 118b) is shown in accordance with an illustrative embodiment. Figure 4C In the example shown, the SCG / PCG measurement device 118b includes a wireless module (in Figure 4D The phonocardiogram device 408 (shown as 403) in FIG. 4 (including an acoustic transducer) and a MEMS accelerometer.

[0103] The phonocardiogram device 408 includes one or more microphones 410 and a microphone front end circuit 412. The microphone front end circuit 412 includes conversion, filter and amplifier circuits for converting and digitizing the acquired biophysical signals. The microphone 410 and the microphone front end 412 are configured to capture the acoustic characteristics of the heart and nearby structures and murmurs. In some embodiments, the phonocardiogram device 408 is configured to acquire acoustic signals with a rate of at least 8kHz and a resolution of 12 bits. Other sampling rates and resolutions may be used. Other examples of the phonocardiogram device 408 include an acoustic respiration sensor (e.g., model RAS-45, manufactured by Masimo, Inc., Irvine, California) or a digital stethoscope system, such as an ECG+digital stethoscope (e.g., DUO ECG+digital stethoscope manufactured by Eko Devices, Inc., Oakland, California).

[0104] exist Figure 4CIn the example shown, the SCG / PCG measurement device 118b includes a controller 414, a wireless transceiver 416, and an energy storage device 418. The SCG / PCG measurement device 118b is configured as a wireless measurement module, for example, as a wearable device as described herein, including a wireless transceiver module 416 that communicates with a base station 402 (shown as 402a), and the base station 402 includes a wireless transceiver 406. In this configuration, the base station 402a includes a front-end conversion circuit 403 (for acquiring the cardiac signal 308 and the PPG signal 310), a microcontroller 404, and a wireless transceiver circuit 406.

[0105] As about Figure 4B As described, the MEMS accelerometer and associated acquisition circuitry can be configured to have a measurement range of at least ±1g or ±2g and a bandwidth of up to 1kHz. In some embodiments, the SCG / PCG measurement device (e.g., 118b) is equipped with a MEMS accelerometer having a sensitivity of at least 0.164μs / μg and a noise density of less than 6.5μg / √Hz. The MEMS sensor may include a 9-DoF inertial sensor, including an accelerometer, a gyroscope, a magnetic sensor, and a pressure sensor (e.g., Shimmer3IMU, manufactured by Shimmer in Cambridge, Massachusetts) or an IMU sensor (Movesense IMU, manufactured by Movesense in Vantaa, Finland), including a 9-axis motion sensor including an accelerometer, a gyroscope, and a magnetometer. An example of an accelerometer-based sensor is an IMU tracking sensor (ICM-20948, manufactured by TDK, InvenSense in San Jose, California), including a 9-axis motion sensor including an accelerometer, a gyroscope, and a magnetometer. An example of an accelerometer-based sensor is an IMU tracking sensor (Sense Connect Detect model SCD110, manufactured by Bosch Connected Devices and Solutions GmbH (Germany)).

[0106] These MEMS sensors (acoustic, accelerometer, IMU) can be used alone or in combination with one or more other sensors (including but not limited to the sensor types described herein) to collect information for generating diagnostic tools for any indication or related conditions or indications for various forms of at least one of HCM, HF, PH, CAD, or any combination thereof. In addition, these MEMS sensors can be used to generate diagnostic tools for any indication described herein for various forms of non-HCM, HF, PH, and CAD.

[0107] The cardiac signal 308 and the photoplethysmography signal 310 may be acquired using the circuits and computing hardware, software, firmware, middleware, etc. in the biophysical signal capture system described in U.S. Patent No. 10,542,898 (titled “Method and Apparatus for Wide-Band Phase Gradient Signal Acquisition”) or U.S. Patent Publication No. 2018 / 0249960 (titled “Method and Apparatus for Wide-Band Phase Gradient Signal Acquisition”), each of which is hereby incorporated by reference in its entirety.

[0108] During signal acquisition, the patient may be tapped (eg, struck firmly) to provide a spike in the measurement, which may be used to synchronize the measurements between the two acquisition systems 402 and 118b.

[0109] Example Wearable MEMS Sensor

[0110] Figure 4D 4 is a diagram of an example measurement system 102 (shown as 403) configured as a wearable MEMS sensor device 403. The wearable MEMS sensor device 403 includes a housing 420 configured to house one or more electronic boards 422, the electronic boards 422 including the MEMS accelerometer 302 (shown as “accelerometer” 302), the phonocardiogram device 408 (shown as “acoustic sensor” 408), a controller 414, a wireless transceiver 416 (integrated with 414), and an energy storage device 418, for example, as described with respect to Figure 4C described.

[0111] exist Figure 4D In the example shown, the housing 420 has an outer wall 424 and an inner wall 426. The inner wall 426 has a tapered area 427 that confines and focuses sound at an inlet area 428 of the housing 420 (see graphic 431) to the phonocardiographic device 408. The phonocardiographic device 408 is located on a portion of the electronic board 422 that faces the inlet area 428. The inlet area 428 can form a volume defined by the housing surface and the body to guide and maintain acoustic energy in the volume. The housing 420 also includes an elastic member 430 that can be used as a gasket-type interface to attach and maintain contact (434) with the body (shown as 432). Graphic 436 (see also Figure 4E ) is an image of an example fabricated wearable MEMS sensor device 403.

[0112] Figure 4E Shows Figure 4D An image of an example fabricated wearable MEMS sensor device 403 configured as a wearable chest sensor device. Figure 4E , another example of a wearable MEMS sensor device 403 of example fabrication is shown in FIG438 , wherein a front plate 440 is placed over an inlet region 428. FIG438 shows an example placement of a wearable MEMS sensor device 403 on a person. As shown in FIG438 , the inlet region 428 of the wearable MEMS sensor device 403 is placed toward the person and can be placed over the heart (as shown) and at various locations on the body, as described herein. FIG438 also shows surface electrodes 312. Each electrode 312 is an ECG pad 442 coupled to a clip-on connector 444.

[0113] Diagram 440 shows a wearable MEMS sensor device 403 placed on a wireless charging station. Examples of placement are described in U.S. Patent No. 10,542,898, which is hereby incorporated by reference in its entirety.

[0114] Example HCM Treatment

[0115] After generating an estimate of an indicator associated with the presence or absence of hypertrophic cardiomyopathy, the generated estimate can be used in a report provided to the patient, such as in a healthcare portal, or as an output to a wearable device or as an output to a medical device for treatment of an indication for a disease, condition, or either thereof.

[0116] Treatment for HCM may include medication or surgery. Medication may include administration of beta-blockers (such as metoprolol, propranolol, or atenolol), calcium channel blockers (such as verapamil or diltiazem), heart rhythm medications (such as amiodarone or disopyramide), mavacattan, etc. Surgical interventions may include: septectomy, which is used to remove part of the thickened, overgrown septal wall; apical resection, which is used to remove the thickened heart muscle near the apex of the heart; septal ablation, which is used to destroy part of the thickened heart muscle; or an implantable cardioverter-defibrillator (ICD) to continuously monitor the heartbeat.

[0117] While the present disclosure relates to the actual evaluation of biophysical signals (e.g., raw or preprocessed photoplethysmographic signals, biopotential / cardiac signals, ephemeral cardiographic signals, phonocardiographic signals, etc.) in the diagnosis and treatment of cardiac-related pathologies and conditions, such evaluation can be applied to the diagnosis, treatment, and tracking / monitoring of any pathology or condition (including but not limited to surgical, minimally invasive, lifestyle, nutritional, and / or drug therapy, etc.), where the biophysical signals involve any relevant system of the organism. The evaluation can be used for control or monitoring applications of medical devices or wearable devices.

[0118] An exemplary biophysical sensor system can be implemented as a modular medical evaluation system

[18] , which is hereby incorporated by reference in its entirety.

[0119] Example Clinical Evaluation System

[0120] Figure 5A An example clinical evaluation system 500 (also referred to as a clinical and diagnostic system) is shown, which implements Figure 1 The module of the invention non-invasively performs a machine learning-based analysis to generate one or more indicators associated with an HCM-related state of a patient or subject through a classifier (e.g., a machine learning classifier). In fact, the feature module (e.g., Figure 1 5-14) can generally be considered as part of a system (e.g., clinical evaluation system 500), where any number and / or type of features can be utilized for disease states, medical conditions, indications of either, or combinations of interest, etc., e.g., different embodiments have different feature module configurations. This is Figure 5A 5 , wherein the clinical evaluation system 500 is a modular design, wherein disease-specific additional modules 502 (e.g., assessing HCM, elevated LVEDP or mPAP, CAD, PH / PAH, abnormal LVEF, hFpEF, and other modules described herein) can be integrated with a single platform (i.e., base system 504) either individually or in multiple instances to enable full operation of the system 500. Modularity allows the clinical evaluation system 500 to be designed to utilize the same synchronously acquired biophysical signals and data sets and base platform to assess the presence of multiple different diseases, such as developing such disease-specific algorithms, thereby reducing testing and certification time and cost.

[0121] In various embodiments, different versions of the clinical evaluation system 500 may be implemented by including different feature calculation modules to implement the evaluation system 103 ( Figure 1 ), the different feature calculation modules can be configured for a given disease state, medical condition, or condition of interest indicated. In another embodiment, the clinical evaluation system 500 can include more than one evaluation system 103 and can be selectively used to generate different scores for the classifier 112 specific to that engine 103. In this way, Figure 1 5 can be viewed as a configuration of a modular system in a more general sense, where different and / or multiple engines 103 with different and / or multiple corresponding classifiers 112 can be used depending on the desired module configuration. Figure 1 Any number of embodiments of the module.

[0122] exist Figure 5AIn the system 500, a disease-specific algorithm of machine learning can be used to analyze one or more biophysical signal data sets (e.g., 110) to assess the likelihood of elevated LVEDP for a pathological or abnormal state, as an example. The system 500 includes hardware and software components that are designed to work together to facilitate the use of an algorithm to analyze and present an estimated score to allow a physician to use the score, for example, to assess the presence, absence, and / or severity of a disease state, a medical condition, or an indication of either.

[0123] The base system 504 may provide a foundation of functionality and instructions upon which each additional module 502 (which may include disease-specific algorithms) may then interface to assess the pathology or indicated condition. Figure 5A As shown in the example of , the base system 504 includes a base analysis engine or analyzer 506, a network service data transfer API 508 (shown as "DTAPI" 508), a reporting database 510, a portal website service module 513, and a data repository 111 (shown as 111a).

[0124] The data repository 111a, which can be cloud-based, stores data from the signal capture system 102 (shown as 102b). In some embodiments, the biophysical signal capture system 102b can be a reusable device designed as a single unit, with a seven-channel lead set and a photoplethysmography (PPG) sensor firmly attached (i.e., non-removable). The signal capture system 102b, together with its hardware, firmware, and software, provides a user interface to collect patient-specific metadata (e.g., name, gender, date of birth, medical record number, height and weight, etc.) entered therein to synchronously acquire the patient's electrical and hemodynamic signals. The signal capture system 102b can securely transmit the metadata and signal data directly to a cloud-based data repository as a single data packet. In some embodiments, the data repository 111a is a secure cloud-based database that is configured to accept and store patient-specific data packets and allow them to be retrieved by an analysis engine or analyzer 506 or 514.

[0125] The basic analysis engine or analyzer 506 is a secure cloud-based processing tool that can perform a quality assessment of the acquired signals (performed by the "SQA" module 516), the results of which can be communicated to the user at the point of care. The basic analysis engine or analyzer 506 can also perform quality assessment of the acquired biophysical signals (e.g., 110-see Figure 1) performs preprocessing (shown by preprocessing module 518). Portal 513 is a secure web-based portal designed to provide healthcare providers with access to their patient reports. An example output of portal 513 is shown by visualization 536. Report database (RD) 512 is a secure database and can interface and communicate securely with other systems, such as hospital or physician hosted, remotely hosted, or remote electronic health record systems (e.g., Epic, Cerner, Allscrips, CureMD, Kareo, etc.), so that the output score (e.g., 118) and related information can be integrated into the patient's general health record and saved with it. In some embodiments, portal 513 is accessed by a call center to provide output clinical information by phone. Database 512 can be accessed by other systems capable of generating reports to be delivered by mail, courier service, fax, personal delivery, etc.

[0126] The additional module 502 includes a second portion 514 (also referred to herein as the analysis engine (AE) or analyzer 514 and shown as the "AE additional module" 514) that operates with the base analysis engine (AE) or analyzer 506. The analysis engine (AE) or analyzer 514 may include the main functional loop of a given disease-specific algorithm, such as a feature calculation module 520, a classifier model 524 (shown as the "set" module 524), and an outlier evaluation and rejection module 524 (shown as the "outlier detection" module 524). In certain modular configurations, the analysis engines or analyzers (e.g., 506 and 514) may be implemented in a single analysis engine module.

[0127] The main function loop may include instructions to (i) validate the execution environment to ensure that all required environment variable values ​​are present, and (ii) execute an analysis pipeline that analyzes a new signal capture data file including acquired biophysical signals to calculate a patient score using a disease-specific algorithm. To execute the analysis pipeline, the AE add-on module 514 may include and execute instructions for Figure 1The various feature modules 110 and classifier modules 112 described determine instructions for output scores (e.g., 116) of indicators associated with the patient's physiological state. The analysis pipeline in the AE additional module 514 can calculate features or parameters (shown as "feature calculation" 520) and identify whether the calculated feature is an outlier by providing an outlier detection return for a signal level response based on an outlier versus a non-outlier of the feature (shown as "outlier detection" 522). Outliers can be evaluated for a training data set used to establish a classifier (e.g., of module 112). The AE additional module 514 can use the calculated values ​​of the features and the classifier model to generate an output score (e.g., 116) for the patient (e.g., via a classifier module 524). In the example of an evaluation algorithm for estimating HCM, the output score (e.g., 116) is the HCM score.

[0128] The clinical evaluation system 500 can use a web service DTAPI 508 (which may also be referred to as an HCPP web service in some embodiments) to manage data within and across components. The DTAPI 508 can be used to retrieve acquired biophysical data sets from the data repository 111a and store signal quality analysis results to the data repository 111a. The DTAPI 508 can also be called to retrieve stored biophysical data files and provide them to an analysis engine or analyzer (e.g., 506, 514), and the analysis results of the analysis engine on the patient signal can be transmitted to a report database 510 using the DTAPI 508. The DTAPI 508 can also be used to retrieve a given patient data set to a portal module 513 upon request by a healthcare professional, which can provide reports to the healthcare practitioner for review and interpretation in a secure web-accessible interface.

[0129] The clinical evaluation system 500 includes one or more feature libraries 526 that store machine learning-based analyses as, for example, features. The feature library 526 may be an additional module 502 (e.g., Figure 5A ) or part of the base system 504 (not shown), and in some embodiments, accessed by the AE add-on module 514.

[0130] Example Operation of Modular Clinical Evaluation System

[0131] Figure 5B According to an illustrative embodiment, Figure 5A Schematic diagram of the operation and workflow of the analysis engine or analyzer (e.g., 506 and 514) of the clinical evaluation system 500.

[0132] Signal quality assessment / rejection (530). Figure 5B, the base analysis engine or analyzer 506 evaluates (530) the quality of the acquired biophysical signal data set via the SQA module 516 while the analysis pipeline is executing. The evaluation results (e.g., pass / fail) are immediately returned to the user interface of the signal capture system for the user to read. Acquired signal data that meets the signal quality requirements is considered acceptable (i.e., "pass") and is further processed and analyzed by the AE additional module 514 for the presence of indicators associated with pathology or indicated conditions (e.g., HCM, elevated LVEDP or mPAP, CAD, PH / PAH, abnormal LVEF and / or hFpEF). Acquired signals that are deemed unacceptable are rejected (e.g., "fail") and a notification is immediately sent to the user to notify the user to immediately acquire additional signals from the patient (see Figure 2 ).

[0133] The basic analysis engine or analyzer 506 performs two sets of signal quality assessments, one for the electrical signal and one for the hemodynamic signal. The electrical signal assessment (530) confirms that the electrical signal has sufficient length, that high frequency noise (e.g., above 170 Hz) is absent, and that power line noise from the environment is absent. The hemodynamic signal assessment (530) confirms that the percentage of outliers in the hemodynamic data set is below a predefined threshold, and that the percentage and maximum duration of the signal that is railed or saturated of the hemodynamic data set is below a predefined threshold.

[0134] Feature value calculation (532). The AE append module 514 performs feature extraction and calculations to calculate feature output values. In the example of the LVEDP algorithm, in some embodiments, the AE append module 514 determines feature outputs belonging to different feature families (eg, generated in module 110).

[0135] Additional descriptions of various features that HCM algorithms and related machine learning analyses may be based on are provided [1], [2], [3], [4], [5], [6], [7], [8],

[12] ,

[13] ,

[19] , each of which is hereby incorporated by reference in its entirety.

[0136] Classifier output calculation (534). The AE append module 514 then uses the feature outputs calculated in the classifier model (e.g., a machine-learned classifier model) to generate a set of model scores. The AE append module 514 can add the set of model scores to, for example, a set of constituent models, which in some embodiments averages the outputs of the classifier model.

[0137] In some embodiments, the classifier model may include a model developed based on the ML techniques described in U.S. Patent Publication No. 20190026430, entitled “Discovering Novel Features to Use in Machine Learning Techniques, such as Machine Learning Techniques for Diagnosing Medical Conditions”; or U.S. Patent Publication No. 20190026431, entitled “Discovering Genomes to Use in Machine Learning Techniques”, each of which is hereby incorporated by reference in its entirety. Another example of a training system that can be used to configure an analysis engine is described in

[19] , which is hereby incorporated by reference in its entirety.

[0138] In this example, the machine learning classifier model can adopt an ElasticNet machine learning classifier model, a RandomForest machine learning classifier model, and an extreme gradient boosting (XGB) classifier model, etc., including the classifier model described herein. In some embodiments, the patient's metadata information, such as age, gender, and BMI value, can be used. The output of the set estimation can be a continuous score.

[0139] Physician portal visualization (536). The patient's report can include a visualization of the acquired patient data and signals and the disease analysis results 536. In some embodiments, the analysis is presented in multiple views in the report. A healthcare provider (e.g., a physician) can review the report and interpret it to provide a diagnosis of the disease or develop a treatment plan.

[0140] If the acquired signal data set for a given patient meets the signal quality criteria, the healthcare portal can list the patient's report. If signal analysis can be performed, the report can indicate that disease-specific results (e.g., HCM) are available. The patient's estimated score for disease-specific analysis can be interpreted relative to established thresholds.

[0141] The report can be presented in a healthcare portal, for example, by a physician or healthcare provider for use in their diagnosis of an indication for HCM. In some embodiments, the indication includes a probability or severity score for the presence of a disease, medical condition, or an indication of either.

[0142] Outlier evaluation and rejection detection (538). After the AE add-on module 514 calculates the feature value outputs (in process 532) and before applying them to the classifier model (in process 534), the AE add-on module 514 is configured in some embodiments to perform an outlier analysis of the feature value outputs (shown in process 538). In some embodiments, the outlier analysis evaluation process 538 executes a machine-learned outlier detection module (ODM) to identify and exclude abnormal feature output values ​​by referring to feature values ​​generated from validation and training data. The outlier detection module evaluates outliers that appear within sparse clusters of isolated regions that are not identically distributed with the rest of the observations. Process 538 can reduce the risk of outlier signals being inappropriately applied to the classifier model and producing inaccurate evaluations for review by patients or healthcare providers. The accuracy of the outlier module has been verified using a held-out validation set, where the ODM was able to generalize to identify all labeled outliers in the test set with an acceptable outlier detection rate (ODR).

[0143] Experimental results and examples

[0144] A study was conducted to evaluate ML features for evaluating phonocardiograms, for example, to determine the presence or absence of HCM. Figures 6A-6G Experimental results of various developed ML features are shown.

[0145] exist Fig. 6A , a phonocardiogram / phonocardiogram (PCG) continuous wavelet transform (CWT) scalogram 602 of a high-intensity systolic murmur generated from the DigiScope phonocardiogram dataset provided by Physionet is shown. A similar signal may be obtained as an acoustic signal 604, for example, using Figure 1 and Figures 4A-4E From Fig. 6A It can be seen that the holosystolic murmur displayed in the scale graph 602 has a higher pitch, that is, the energy is more concentrated in the high frequency.

[0146] Figure 6B A scalogram 602 (shown as 602a, 602b) is shown with a wavelet transform 606 (shown as 606a, 606b) applied to an input signal 604 (shown as 604a). Figure 6B In the example above, the Morlet wavelet transform is applied. Transform 606a applies a lower ω o To obtain better temporal resolution, transform 606b applies a higher ω o To obtain better frequency domain resolution. Wavelets can be configured by shape, mother wavelet and transform type.

[0147] Figure 6CThe results of an example operation of ensemble averaging the time and CWT scalograms of the input signal 602 are shown. In this operation, an energy scalogram is first calculated from the original PCG. The operation then determines the maximum energy scale (e.g., ~100 Hz) to identify the "S1" sound using the turning point and expected pulse rate. The "S1" reference point (see, e.g., Figure 6D-6E ) as the trigger point for ensemble mean derivation. Figure 6C In the results shown, a Morlet transform is performed, where ω o =5.5.

[0148] In some embodiments, a 1-D continuous wavelet transform, such as the Morlet (also known as Gabor) wavelet, is applied as the mother wavelet, as shown above. Other wavelets may be used, for example, wavelets with the same variance in time and frequency, such as Gaussian, Mexican Hat, Spline, and Mayer wavelets, etc. The resolution of the wavelet may be, for example, 48 sounds per octave. The Morlet wavelet is a wavelet consisting of a complex exponential (carrier) multiplied by a Gaussian window (envelope), as shown in Equation 1.

[0149] ψ(t)=exp(iωt)exp(-t 2 / 2σ 2 )(Equation 1)

[0150] In Formula 1, ω is the wavelet center frequency, σ=n / 2πf is the width of the Gaussian window, where n (number of periods) controls the time-frequency resolution tradeoff.

[0151] A coherent waveform may be determined as a measure of correlation between time series signals, such as between two observations of a phonocardiogram signal dataset, or between a phonocardiogram signal and a cardiac and / or photoplethysmographic signal dataset. For example, wavelet coherence may be determined by Equation 2.

[0152]

[0153] In Equation 2, the cross spectrum C xy is a measure of the power distribution of two signals x and y in the time-frequency domain and is given by Equation 3.

[0154]

[0155] In Equation 3, the superscript * represents complex conjugate, and S is a smoothing operator in time and scale. In some embodiments, a coherence spectrum operator is performed, for example, 32 sounds per octave, to find coherence spectra for pairs of channels (e.g., between channels X and Y, channels x and X, and channels Y and Z). A coherence spectrum can be generated between (i) a phonocardiogram signal and (ii) a cardiac signal and / or a photoplethysmographic signal.

[0156] A high-power spectral image or data may be generated from the scalogram, for example, by generating a spectral image of the high-power spectral content of a waveform signal of interest (eg, the spectral content of noise) or a binarized spectral image of the spectral data. Figure 6G An example method of generating a binarized spectral image 614 of a spectral image or spectral data is shown. The method may include performing a wavelet transform to generate a spectral image or spectral data of a given waveform region of interest, applying a threshold operator thereto to generate a binarized spectral image or data corresponding to high spectral power characteristics of the waveform region. Calculations may be performed over multiple cardiac cycles to extract statistical characterizations of the time range, frequency range, temporal centroid, surface area, eccentricity, circularity, range, orientation, and / or power centroid of high spectral energy characteristics of the waveform region as wavelet-based features or parameters. Figure 6G An example of a binarized spectral image 614 generated from a spectral image or spectral data of high-power spectral content of a waveform signal of interest from a scalogram of an input signal is shown.

[0157] An example of a method for generating such a binary spectral image is provided in U.S. patent application Ser. No. 17 / 891,259, filed on August 18, 2022, and entitled “METHOD AND SYSTEM TO ASSESSDISEASE USING WAVELET ANALYSIS OF CARDIAC AND PHOTOPLETHYSMOGRAPHIC SIGNALS,” the entire contents of which are incorporated herein by reference.

[0158] Table 2 shows an example set of high spectral energy features of waveform regions of interest that can be extracted from the generated binarized spectral image or data.

[0159] Table 2

[0160]

[0161] exist Fig.6D and Fig. 6E It can be observed that, as regards Figure 6C As mentioned above, the ensemble average output can easily identify obvious noise in a clean, well-behaved signal (II-IV). Fig.6DThe ensemble average output of the acoustic signal without noise is shown. Fig. 6E An ensemble average output of a set of acoustic signals with various full contraction stages is shown (shown as "I / VI Early Contraction" 608, "II / VI Full Contraction" 610, and "III / VI Full Contraction" 612). It can be observed that "pitch" appears to be as related to amplitude as to frequency content. It can also be observed that a higher proportion of "I" grade murmurs appear to be early contractions rather than full contractions.

[0162] Fig. 6F Shows Fig.6D and Fig. 6E An example of an analysis of an ensemble average output analysis of is parameterized, for example, according to the features described in Table 1 and / or Table 2. The parameterized features can be used for a categorical output of the presence, absence, and / or severity of HCM, as well as other diseases and conditions described herein.

[0163] In some embodiments, the patient's respiratory state may be considered for analysis. Examples of respiratory estimation may be found in U.S. Patent Application No. 17 / 891,224, entitled "METHOD AND SYSTEM TO ASSESSDISEASE USING ESTIMATED RESPIRATION PARAMETERS FROM CARDIAC AND PHOTOPLETHYS-MOGRAPHIC SIGNALS."

[0164] Figure 6H An example scalogram with detected noise is shown. Noise on the scalogram can be evaluated using wavelet feature analysis as described herein.

[0165] Conclusion. 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 embodiments set forth, as the embodiments herein are intended in all respects to be illustrative and not restrictive. The clinical evaluation systems and methods discussed herein can be used to perform non-invasive diagnosis or determine the presence, absence, and / or severity of other diseases and / or conditions, or to assist physicians or other healthcare providers in performing non-invasive diagnosis or determining the presence, absence, and / or severity of other diseases and / or conditions, such as, for example, coronary artery disease (CAD), pulmonary hypertension, and other pathologies described herein, using similar or other developed methods. In addition, the example clinical evaluation systems and methods can be used to diagnose and treat other cardiac-related pathologies and conditions, as well as neurological-related pathologies and conditions; such evaluations can be applied to the diagnosis and treatment (including surgical, minimally invasive, and / or drug treatment) of any pathology or condition, where the biophysical signals involve any relevant system of the organism. An example of a cardiac context is the diagnosis of CAD and other diseases and conditions disclosed herein, and treatment with a variety of therapies, alone or in combination, such as placement of stents in the coronary arteries, performing plaque removal, angioplasty, prescription of drug therapy and / or exercise prescription, nutritional and other lifestyle changes, etc. Other cardiac-related pathologies or conditions that may 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 (e.g., blood or other diseases), and other cardiac-related pathologies, conditions, and / or diseases. Non-limiting examples of neurological-related diseases, pathologies, or conditions that may be diagnosed include, for example, epilepsy, schizophrenia, Parkinson's disease, Alzheimer's disease (and all other forms of dementia), autism spectrum (including Asperger's syndrome), attention deficit hyperactivity disorder, Huntington's disease, muscular dystrophy, depression, Bipolar disorder, brain / spinal cord tumors (malignant and benign), movement disorders, cognitive disorders, speech disorders, various mental illnesses, brain / spinal cord / nerve injuries, chronic traumatic encephalopathy, cluster headaches, migraines, neuropathy (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 disorders, anxiety disorders, conditions caused by infectious or exogenous factors (e.g. Lyme disease, encephalitis, rabies), narcolepsy and other sleep disorders, post-traumatic stress disorder, neurological conditions / effects related to stroke, aneurysm, hemorrhagic injury, etc., tinnitus and other hearing-related diseases / conditions and vision-related diseases / conditions.

[0166] In addition, the clinical evaluation system described herein can be configured to analyze biophysical signals, such as electrocardiogram (ECG), electroencephalogram (EEG), gamma synchronization features in the signal, respiratory function signal, photoplethysmography signal, phonocardiography signal, pulse oximetry signal, perfusion data signal; quasi-periodic biosignal, fetal ECG signal, blood pressure signal; cardiac magnetic field signal, heart rate signal, etc. As described herein, the clinical evaluation system can use a single type of biophysical signal for HCM estimation, or can use multiple types of signals for HCM estimation. In addition, although it is conceivable to use a 3-sensor system in which the third sensor is based on MEMS, (a) the third sensor may not be based on MEMS, (b) it may be a single type of sensor (PPG, ECG, MEMS, etc.), (c) it may be a dual sensor system (using three or more sensors of two types), (d) it may involve more than three sensors. Any combination of known sensor types may be used, including contact or non-contact (e.g., non-contact thermometer) sensors.

[0167] Additional examples of processes that may be used with the exemplary methods and systems disclosed herein are described in the following documents: U.S. Patent Nos. 9,289,150; 9,655,536; 9,968,275; 8,923,958; 9,408,543; 9,955,883; 9,737,229; 10,039,468; 9,597,021; 9,968,265; 9,910,964; 10,672,518; 10,566,091; 10,566,092; 10,542,897; 0,362,950, 10,292,596, 10,806,349; 11,133,109; 11,141,114; 11,160,509; 11,147,516; U.S. Patent Publication Nos. 2020 / 0335217; 2020 / 0229724; 2019 / 0214137; 2018 / 0249960; 2019 / 0200893; 2019 / 0384757; 2020 / 0211713; 2019 / 0365265; 2020 / 0205739; 202 0 / 0205745; 2019 / 0026430; 2019 / 0026431; PCT Publication Nos. WO2017 / 033164; WO2017 / 221221; WO2019 / 130272; WO2018 / 158749; WO2019 / 077414; WO2019 / 130273; WO2019 / 244043; WO2020 / 136569; WO2019 / 234587; WO2020 / 136570; WO2020 / 136571; U.S. Design Patent Nos. Nos. D810947; D855064; D895661; D843382; D880501; D858532; U.S. Patent Application Nos. 16 / 232586; 16 / 831,264; 16 / 429593; 16 / 725402; 16 / 831,380; 16 / 725430; 16 / 725416; 17 / 132869; PCT Application Nos. PCT / IB2020 / 052889; PCT / IB2020 / 052890, each of which is hereby incorporated by reference in its entirety.

[0168] Each of the following patents, applications, and publications listed below and in this document are hereby incorporated by reference in their entirety:

[0169] References

[0170] [1] U.S. Provisional Patent Application No. 63 / 236,072, filed on August 23, 2021, entitled “METHOD AND SYSTEM TO ASSESS DISEASE USING VISUAL FEATURES OF CARDIAC AND PHOTOPLETHYSMOGRAPHIC SIGNALS,” attorney docket number 10321-49pv1.

[0171] [2] U.S. Provisional Patent Application No. 63 / 235,963, filed on August 23, 2021, entitled “METHOD AND SYSTEM TO ASSESS DISEASE USING POWER SPECTRAL ANALYSIS OF CARDIACAND PHOTOPLETHYSMOGRAPHIC SIGNALS,” attorney docket number 10321-50pv1.

[0172] [3] U.S. Provisional Patent Application No. 63 / 235,968, filed on August 23, 2021, entitled “METHOD AND SYSTEM TO ASSESSDISEASE USING ESTIMATED RESPIRATION PARAMETERSFROM CARDIAC AND PHOTOPLETHYSMOGRAPHIC SIGNALS,” attorney docket number 10321-51pv1.

[0173] [4] U.S. Provisional Patent Application No. 63 / 235,968, filed on August 23, 2021, entitled “METHOD AND SYSTEM TO ASSESSDISEASE USING WAVELET ANALYSIS OF CARDIAC AND PHOTOPLETHYSMOGRAPHIC SIGNALS,” attorney docket number 10321-52pv1.

[0174] [5] U.S. patent application Ser. No. 17 / 558,702, filed on December 22, 2021, entitled “METHODAND SYSTEM TO ASSESSDISEASE USING CYCLE VARIABILITY ANALYSIS OF BIOPHYSICALSIGNALS,” attorney case number 10321-053us1.

[0175] [6] U.S. Provisional Patent Application No. 63 / 235,971, filed on August 23, 2021, entitled “METHOD AND SYSTEM TO ASSESSDISEASE USING ANALYSIS OF PHOTOPLETHYSMOGRAPHICSIGNALS,” attorney case number 10321-054pv1.

[0176] [7] U.S. Provisional Patent Application No. 63 / 236,193, filed on August 23, 2021, entitled “METHOD AND SYSTEM TO ASSESSDISEASE USING MORPHOLOGICAL ANALYSIS OF CARDIACSIGNALS,” attorney case number 10321-055pv1.

[0177] [8] U.S. Provisional Patent Application No. 63 / 235,974, filed on August 23, 2021, entitled “METHOD AND SYSTEM TO ASSESSDISEASE USING DEPLORIZATION WAVE PROPAGATION DEVIATIONS,” attorney docket number 10321-056pv1.

[0178] [9] H.Zou and T.Hastie, "Regularization and variable selection via theelastic net," Journal of the Roy.Statist.Soc., ser.B, vol.67, no.2, pp.301–320, 2005.

[0179]

[10] Breiman, "Random Forests," Machine Learning, 45(1), 5-32, 2001.

[0180]

[11] Chen, Tianqi; Guestrin, Carlos (2016). "XGBoost: A Scalable TreeBoosting System" In Krishnapuram, Balaji; Shah, Mohak; Smola, Alexander J.; Aggarwal, Charu C.; Shen, Dou; Rastogi, Rajeev (eds.). Proceedings of the 2 2nd ACMSIGKDDInternational Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, August 13-17, 2016. ACM.pp.785–794.

[0181]

[12] U.S. patent application Ser. No. 16 / 831,264, filed on April 30, 2020, entitled “METHODAND SYSTEM TO ASSESS DISEASE USING DYNAMICAL ANALYSIS OF BIOPHYSICALSIGNALS,” attorney docket number 10321-040us1.

[0182]

[13] U.S. patent application Ser. No. 16 / 831,380, filed on April 30, 2020, entitled “METHODAND SYSTEM TO ASSESS DISEASE USING DYNAMICAL ANALYSIS OF CARDIAC AND PHOTOPLETHYSMOGRAPHIC SIGNALS,” attorney docket number 10321-041us1.

[0183]

[14] U.S. Application No. 17,486,609, filed on September 27, 2021, entitled “METHOD AND SYSTEM TO ASSESS DISEASE USING MULTI-SENSOR SIGNALS,” attorney docket number 10321-047us1.

[0184]

[15] Fábio Eurico Moreira,Filipe Alves,Mário Olga Azevedo, Gaspar and Luis A. Rocha, "High-Resolution Seismocardiogram Acquisition and Analysis System," Journal of Sensors 2018, 18, 3441; doi:10.3390 / s18103441.

[0185]

[16] Martin S Maron, Jennifer L Hellawell, Jaime C Lucove, Ramin Farzaneh-Far, Iacopo Olivotto, "Occurrence of Clinically Diagnosed Hypertrophic Cardiomyopathy in the United States," Am J Cardiol 2016May 15;117(10):1651-1654.

[0186]

[17] European heart journal cardiovascular imaging,2018-10-01,Vol.19(10),p.1126-1133

[0187]

[18] U.S. Provisional Application No. 63,234,772, filed on August 19, 2021, entitled “MEDICALEVALUATION SYSTEMS AND METHODS USING ADD-ON MODULES,” attorney case number 10321-060pv1.

[0188]

[19] U.S. Provisional Application No. 63,235,960, filed on August 23, 2021, entitled “METHODAND SYSTEM TO NON-INVASIVELY ASSESS ELEVATED LEFT VENTRICULAR END-DIASTOLICPRESSURE,” attorney case number 10321-048pv1.

[0189]

[20] https: / / www.umms.org / ummc / health-services / heart-vascular / services / hypertroph ic-cardiomyopathy / types-symptoms-causes

[0190]

[21] Raj MA, Ranka S, Goyal A., “Hypertrophic Obstructive Cardiomyopathy,” [Updated 2021 Nov 4]. In: StatPearls [Internet]. Treasure Island (FL): StatPearls Publishing; 2022 Jan-. Available from: https: / / www.ncbi.nlm.nih.gov / books / NBK430820 /

[0191]

[21] Maron BJ, Wolfson JK, Roberts WC. Relation between extent of cardiac muscle cell disorganization and left ventricular wall thickness in hypertrophic cardiomyopathy. Am J Cardiol. 1992 Sep 15;70(7):785-90.

[0192]

[22] Marian AJ, Braunwald E. Hypertrophic Cardiomyopathy: Genetics, Pathogenesis, Clinical Manifestations, Diagnosis, and Therapy. Circ Res. 2017;121(7):749-770. doi:10.1161 / CIRCRESAHA.117.311059.

[0193]

[23] Electrophysiologic abnormalities in patients with hypertrophic cardiomyopathy. A consecutive analysis in 155 patients, L Fananapazir, C M Tracy, M B Leon, J B Winkler, R O Cannon, 3r d, R O Bonow, B J Maron and S E Epstein.

[0194]

[24] Dubin, Dale. Rapid Interpretation of EK’s: An Interactive Course. Sixth edition. Tampa, Fla.: Cover Pub. Co., 2000.

[0195]

[25] The electrocardiogram in the diagnosis and management of patients with hypertrophic cardiomyopathy, Finocchiaro, Gherardo et al., Heart Rhythm, Volume 17, Issue 1, 142–151.

[0196]

[26] Savelieva, Irina et al “Comparative reproducibility of QT, QT peak, and Tpeak-T end intervals and dispersion in normal subjects, patients with myocardial infarction, and patients with hypertrophic cardiomyopathy” Pacing and clinical electrophysiology 21.11(1998):2376-2381.

[0197]

[27] Dinshaw, Leon et al “The T-peak-to-T-end interval: a novel ECG marker for ventricular arrhythmia and appropriate ICD therapy in patients with hypertrophic cardiomyopathy,” Clinical Research in Cardiology 107.2(2018):130-137.

[0198]

[28] Finocchiaro, Gherardo et al. “The electrocardiogram in the diagnosis and management of patients with hypertrophic cardiomyopathy”. Heart Rhythm 17.1 (2020): 142 - 151.

[0199]

[29] Jothiramalingam, R., Jude, A., Patan, R. et al. Machine learning - based left ventricular hypertrophy detection using multi - lead ECG signal. Neural Comput & Applic 33, 4445–4455 (2021). https: / / doi.org / 10.1007 / s00521 - 020 - 05238 - 2.

[0200]

[30] A. Englund, K. Hnatkova, P. M. Elliot, W. J. McKenna, M. Malik, Wavelet decomposition analysis of the signal averaged electrocardiogram used for risk stratification of patients with hypertrophic cardiomyopathy, European Heart Journal, Volume 19, Issue 9, 1 September 1998, pp. 1383–1390,

[0201]

[31] Edhouse J, Thakur RK, Khalil JM. ABC of clinical electrocardiography. Conditions affecting the left side of the heart. BMJ. 2002 May 25;324(7348):1264 - 7.

[0202]

[32] Harrigan RA, Jones K. ABC of clinical electrocardiography. Conditions affecting the right side of the heart. BMJ. 2002 May 18;324(7347):1201-4.

[0203]

[33] Green, E.M., van Mourik, R., Wolfus, C. et al. Machine learning detection of obstructive hypertrophic cardiomyopathy using a wearable biosensor. npj Digit. Med. 2, 57(2019).

[0204]

[34] Eleid MF, Konecny T, Orban M, Sengupta PP, Somers VK, Parish JM, Mookadam F, Brady PA, Sullivan BL, Khandheria BK, Ommen SR, Tajik AJ., “High prevalence of abnormal nocturnal oximetry in patients with hypertrophic cardiomyopathy,” J Am Coll Cardiol. 2009 Nov 3;54(19):1805-9.

[0205]

[35] Andrés Ricardo Pérez-Riera, “Electro / Vectorcardiogram in Left Ventricular Hypertrophy / Enlargement-Part 1,” Accessed January 13, 2022, from http: / / cardiolatina.com / wp-content / uploads / 2020 / 07 / ECG-VCG-in-Left-Ventricular-Hypertr ophy-Enlargements-LVH-Part-1.pdf.

[0206]

[36] Erick Jimenez, Amr El-Bokl, Daniel Cortez, "Vectorcardiography asaprognostic tool in hypertrophic cardiomyopathy," Journal of Electrocardiology, Volume 68, 2021, pp. 80-84, ISSN 0022-0736.

[0207]

[37] Pérez-Riera AR, de Lucca AA, Barbosa-Barros R, et al., "Value of electro-vectorcardiogramin hypertrophic cardiomyopathy," Ann. Noninvasive Electrocardiol. 2013; 18(4): 311-326.

[0208]

[38] Green, EM, van Mourik, R., Wolfus, C., et al., “Machine learning detection of obstructive hypertrophic cardiomyopathy using a wearable biosensor,” npj Digit. Med. 2, 57 (2019).

[0209]

[39] Houston BA, Stevens GR, “Hypertrophic cardiomyopathy: a review,” ClinMed Insights Cardiol. 2015;8(Suppl 1):53-65. Published January 26, 2015. doi:10.4137 / CMC.S15717.

[0210]

[40] Takahashi K, Ono K, Arai H et al., “Detection of Pathologic Heart Murmurs Using a Piezoelectric Sensor,” Sensors (Basel). 2021; 21(4): 1376. Published on February 16, 2021. doi: 10.3390 / s21041376.

[0211]

[41] Folino, A.F., Buja, G., Bauce, B., Thiene, G., Volta, S.D. and Nava, A., “Heart Rate Variability in Arrhythmogenic Right Ventricular Cardiomyopathy Correlation with Clinical and Prognostic Features,” Pacing and Clinical Electrophysiology, 25:1285-1292 (2002).

[0212]

[42] F. Laurent et al., “Heart Rate Variability in Idiopathic Dilated Cardiomyopathy: Characteristics and Prognostic Value,” Journal of the American College of Cardiology, 1997; 30(4):1109-1014.

[0213]

[43] Tavakolian, Kouhyar, “Systolic time intervals and new measurement methods,” Cardiovascular engineering and technology 7.2 (2016):118-125.

[0214]

[44] Reant P, Dijos M, Donal E, Mignot A, Ritter P, Bordachar P, Dos Santos P, Leclercq C, Roudaut R, Habib G, Lafitte S, “Systolic time intervals as simple echocardiographic parameters of left ventricular systolic performance: correlation with ejection fraction and longitudinal two-dimensional strain,” Eur J Echocardiogr. 2010 Dec; 11(10):834-44.

[0215]

[45] Claria, Francesc et al., "Heart rate variability analysis based on time–frequency representation and entropies in hypertrophic cardiomyopathy patients," Physiological measurement 29.3 (2008): 401.

[0216]

[46] U.S. Patent Application No. 17 / 891,526, entitled “METHOD AND SYSTEM TO ASSESSDISEASE USING VISUAL FEATURES OF CARDIAC AND PHOTOPLETHYSMOGRAPHIC SIGNALS.”

[0217]

[47] U.S. Patent Application No. 17 / 891,229, entitled “METHOD AND SYSTEM TO ASSESSDISEASE USING POWER SPECTRAL ANALYSIS OF CARDIAC AND PHOTOPLETHYSMOGRAPHIC SIGNALS.”

[0218]

[48] ​​U.S. Patent Application No. 17 / 891,380, entitled “METHOD AND SYSTEM TO ASSESSDISEASE USING DEPLORIZATION WAVE PROPAGATION DEVIATIONS.”

[0219]

[49] U.S. patent application Ser. No. 17 / 558,702, entitled “METHOD AND SYSTEM TO ASSESSDISEASE USING CYCLE VARIABILITY ANALYSIS OF BIOPHYSICAL SIGNALS.”

[0220]

[50] U.S. Patent Application No. 11,291,379.

[0221]

[51] U.S. Publication No. 2020 / 0397322.

[0222]

[52] U.S. Patent Application No. 17 / 891,278, entitled “METHOD AND SYSTEM TO ASSESSDISEASE USING ANALYSIS OF PHOTOPLETHYSMOGRAPHIC SIGNALS.”

[0223]

[53] U.S. Patent Application No. 17 / 891,259, entitled “METHOD AND SYSTEM TO ASSESSDISEASE USING WAVELET ANALYSIS OF CARDIAC AND PHOTOPLETHYSMOGRAPHIC SIGNALS.”

[0224]

[54] U.S. Patent Application No. 17 / 891,526, entitled “METHOD AND SYSTEM TO ASSESSDISEASE USING VISUAL FEATURES OF CARDIAC AND PHOTOPLETHYSMOGRAPHIC SIGNALS.”

[0225]

[55] U.S. Patent Application No. 17 / 891,224, entitled “METHOD AND SYSTEM TO ASSESSDISEASE USING ESTIMATED RESPIRATION PARAMETERS FROM CARDIAC AND PHOTOPLETHYSMOGRAPHIC SIGNALS.”

[0226]

[56] U.S. patent application Ser. No. 17 / 891,533, entitled “METHOD AND SYSTEM TO ASSESSDISEASE USING MORPHOLOGICAL ANALYSIS OF CARDIAC SIGNALS.”

Claims

1. A method for non-invasively estimating the presence, absence and / or severity of hypertrophic cardiomyopathy in a mammalian subject, the method comprising: include: obtaining, by one or more processors, one or more biophysical signals of the patient from one or more sensors; determining, by the one or more processors, one or more values ​​associated with one or more features and / or machine learning-based analysis using at least a portion of the one or more signals; as well as determining, by the one or more processors, an estimate of the presence, absence, and / or severity of hypertrophic cardiomyopathy using the one or more values ​​associated with the one or more features or the machine learning-based analysis, The one or more processors output an estimate of the presence, absence and / or severity of hypertrophic cardiomyopathy, wherein the estimate of the presence, absence and / or severity of hypertrophic cardiomyopathy is output for diagnosis of hypertrophic cardiomyopathy and / or guiding treatment of the hypertrophic cardiomyopathy.

2. A method for non-invasively estimating the presence, absence and / or severity of hypertrophic cardiomyopathy in a mammalian subject, the method comprising: include: obtaining, by one or more processors, one or more seismocardiographic signals (SCG signals) and / or phonocardiographic signals (PCG signals) from a multi-sensor device placed on or worn on the patient; determining, by the one or more processors, a plurality of values ​​associated with a plurality of features or machine learning-based analyses utilizing at least a portion of the one or more epicardiographic and / or phonocardiographic signals; as well as determining, by the one or more processors, an estimate of the presence, absence, and / or severity of hypertrophic cardiomyopathy using the plurality of values ​​associated with the plurality of features or the machine learning-based analysis, The one or more processors output an estimate of the presence, absence and / or severity of hypertrophic cardiomyopathy, wherein the estimate of the presence, absence and / or severity of hypertrophic cardiomyopathy is output for diagnosis of hypertrophic cardiomyopathy and / or guiding treatment of the hypertrophic cardiomyopathy.

3. A method for non-invasively estimating the presence, absence and / or severity of hypertrophic cardiomyopathy in a mammalian subject, the method comprising: include: obtaining, by one or more processors, a first biophysical signal dataset associated with a first photoplethysmographic signal and a second photoplethysmographic signal, wherein the first biophysical signal dataset has been acquired over a plurality of cardiac cycles of the subject; obtaining, by the one or more processors, a second biophysical signal dataset associated with the cardiac signal, wherein the second biophysical signal dataset has been acquired simultaneously with the first biophysical signal dataset over the plurality of cardiac cycles; determining, by the one or more processors, a plurality of values ​​associated with a plurality of features or machine learning-based analyses using at least a portion of the first biophysical signal and the second biophysical signal; as well as determining, by the one or more processors, an estimate of the presence, absence, and / or severity of hypertrophic cardiomyopathy using a plurality of values ​​associated with the plurality of features or the machine learning-based analysis, The presence, absence and / or severity estimate of hypertrophic cardiomyopathy is output for diagnosis of hypertrophic cardiomyopathy and / or guiding treatment of the hypertrophic cardiomyopathy.

4. The method according to any one of claims 1 to 3, in, The plurality of features or machine learning-based analysis are configured to quantify deviations of the VD wave trajectory from a three-dimensionally modeled VD wave trajectory.

5. The method according to any one of claims 1 to 3, in, The plurality of features or machine learning-based analyses are configured to quantify beat-to-beat variations in the cardiac signal.

6. The method according to any one of claims 1 to 3, in, The plurality of features or machine learning based analysis is configured to quantify the variability of registered landmarks in cardiac, PPG, SCG and / or PCG signals through Poincare analysis and histogram analysis.

7. The method according to any one of claims 1 to 3, in, The plurality of features or machine learning-based analyses are configured to quantify dynamic characteristics of cardiac, PPG, SCG and / or PCG signals.

8. The method according to any one of claims 1 to 3, in, The plurality of features or machine learning-based analyses are configured to quantify (i) properties of cardiac, PPG and / or SCG signals.

9. The method according to any one of claims 1 to 3, in, The plurality of features or machine learning based analyses are configured to quantify dominant frequency components of cardiac, PPG, SCG and / or PCG signals using wavelet analysis.

10. The method according to any one of claims 1 to 3, in, The plurality of features or machine learning based analyses are configured to quantify the power spectrum and frequency content of cardiac, PPG, SCG and / or PCG signals using power spectrum and coherence analysis.

11. The method according to any one of claims 1 to 3, in, The plurality of features or machine learning based analyses are configured to quantify properties of cardiac, PPG, SCG and / or PCG signals on loop areas, their projections and loop vectors in 3D phase space.

12. The method according to any one of claims 1 to 3, in, The multiple features or machine learning-based analysis are configured to approximate a respiratory waveform using (i) PPG and cardiac signals or (ii) SCG and / or PCG signals to evaluate one of (1) heart rate variability, (2) respiratory rate, (3) a difference feature representing the distance between respiratory and modulation signals, and (4) a squared coherence representing the correlation between modulation and respiratory rate signals, wherein the approximated respiratory waveform is used for HCM assessment by generating an inspiratory portion and an expiratory portion of a depiction of an SCG signal and / or PCG signal for analysis.

13. The method according to any one of claims 1 to 3, in, The plurality of features or machine learning-based analyses are configured to quantify physiological aspects of cardiac, SCG and / or PCG signals.

14. The method according to any one of claims 1 to 3, in, The multiple features or machine learning-based analyses are configured to quantify characteristic changes in cardiac, SCG, and / or PCG signals associated with inspiration versus expiration versus Valsalva maneuvers to identify HCM patients.

15. The method according to any one of claims 1 to 3, in, The multiple features or machine learning-based analyses are configured to quantify characteristic changes in cardiac, SCG, and / or PCG signals associated with inspiration versus expiration versus Valsalva maneuvers to identify a subset of HCM patients with obstructive HCM (OHCM).

16. The method according to any one of claims 1 to 3, in, The plurality of features or machine learning-based analyses are configured to approximate left ventricular ejection time using one or more SCG and / or PCG signals.

17. The method according to any one of claims 1 to 3, in, The plurality of features or machine learning-based analyses are configured to quantify propagation characteristics of a ventricular depolarization (VD) wave and / or a ventricular repolarization (VR) wave in three-dimensional space.

18. The method according to any one of claims 1-2 and 4-17, in, The plurality of features or machine learning based analysis are evaluated at (i) an inspiratory region of one or more episiocardiographic signals and / or phonocardiographic signals and / or (ii) an expiratory region of one or more episiocardiographic signals and / or phonocardiographic signals.

19. A device, include: a sensor body configured to be worn externally or placed on a chest region of a subject to acquire biophysical signals from the chest region of the subject, including signals from the subject's heart; as well as two or more MEMS-based biophysical sensors, including a first MEMS-based sensor and a second MEMS-based sensor, wherein the two or more MEMS-based sensors are located within the sensor body and connected to electrodes configured to be placed on a subject, Wherein, the first MEMS-based sensor and the second MEMS-based sensor generate a first biophysical signal and a second biophysical signal during operation to be provided to an analysis system, wherein the analysis system is configured to evaluate multiple features or machine learning-based analysis to generate an estimate of the presence, absence and / or severity of hypertrophic cardiomyopathy.

20. A device, include: a sensor body configured to be externally worn or placed on a chest region of a subject to acquire biophysical signals from the chest region of the subject, including signals from the heart of the subject; as well as two or more MEMS-based sensors, including a first MEMS-based sensor and a second MEMS-based sensor, wherein the two or more MEMS-based sensors are located within the sensor body and connected to electrodes configured to be placed on a subject, Wherein, the first MEMS-based sensor and the second MEMS-based sensor generate a first shock tracing signal and / or a first acoustic signal and a second shock tracing signal and / or a second acoustic signal during operation to be provided to an analysis system, wherein the analysis system is configured to evaluate multiple features or machine learning-based analysis to generate an estimate of the presence, absence and / or severity of hypertrophic cardiomyopathy.

21. The device according to claim 19 or 20, further comprising: include: a plurality of surface electrodes configured to be placed on a surface of a chest region of a subject to provide a plurality of cardiac signals of a heart of the subject, Wherein, the plurality of cardiac signals are provided to the analysis system to evaluate the plurality of features or machine learning based analysis to generate an estimate of the presence, absence and / or severity of hypertrophic cardiomyopathy.

22. The device according to any one of claims 19 to 21, further comprising: include: a plurality of photoplethysmographic sensors configured to be placed on a subject to provide one or more photoplethysmographic signals, Wherein the one or more photoplethysmographic signals are provided to the analysis system for evaluating the plurality of features or a machine learning based analysis to generate an estimate of the presence, absence and / or severity of hypertrophic cardiomyopathy.

23. The device according to any one of claims 19 to 21, in, The first MEMS-based sensor, which is an accelerometer or an acoustic sensor, is configured to be non-invasively placed on the subject's chest, near the apex region of the subject's heart.

24. The device according to any one of claims 19 to 23, in, The second MEMS-based sensor, which is an accelerometer or an acoustic sensor, is configured to be non-invasively placed on the subject's chest, near a base region of the subject's heart.

25. A system, include: The device according to claims 19-23; as well as An analysis system, wherein the analysis system is implemented in a cloud-based processing and network infrastructure.

26. A system, include: one or more processors; as well as One or more memories, each storing instructions thereon, wherein the one or more processors execute the instructions so that the one or more processors perform any one of the steps in method claims 1-25.

27. A non-transitory computer-readable medium comprising instructions stored thereon, wherein the one or more processors execute the instructions so that the one or more processors perform any one of the steps of method claims 1-25.

Citation Information

Cited By

  • Heart health state detection method and device and electronic equipment

    CN120458531A

  • Myocardiopathy risk early warning method and device based on wearable device, medium and product

    CN122423835A

  • A physiological sensing device, a sensing system and sensing methods

    TWI925780B