System and method of extraction, identification, marking and display of heart valve signals

• US 10,362,997 B2
• Filed: 01/03/2017
• Issued: 07/30/2019
• Est. Priority Date: 01/04/2016
• Status: Active Grant

• Current Assignee: AventuSoft, LLC
• Original Assignee: AventuSoft, LLC
• Inventors: Kale, Kaustubh, Giraldo, Luis Gonzalo Sanchez
• Primary Examiner(s): Koharski, Christopher
• Assistant Examiner(s): So, Elizabeth K
• Application Number:
  US15/397,005
• Publication Number:
  US 20170188862A1
• Time in Patent Office: 938 Days
• Field of Search: None
• CPC Class Codes: A61B 2562/0204 Acoustic sensors
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 2562/06 Arrangements of multiple sensors of different types
• CPC Class Codes: A61B 5/0006 ECG or EEG signals
• CPC Class Codes: A61B 5/0008 Temperature signals
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/0044 for the heart
• CPC Class Codes: A61B 5/02028 Determining haemodynamic parameters not otherwise provided for, e.g. cardiac contractility or left ventricular ejection fraction
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/02055 Simultaneously evaluating both cardiovascular condition and temperature
• CPC Class Codes: A61B 5/024 Detecting, measuring or recording pulse rate or heart rate A61B5/0205, A61B5/021 take precedence
• CPC Class Codes: A61B 5/02438 with portable devices, e.g. worn by the patient
• CPC Class Codes: A61B 5/02444 Details of sensor A61B5/02427 takes precedence
• CPC Class Codes: A61B 5/0536 Impedance imaging, e.g. by tomography
• CPC Class Codes: A61B 5/0816 Measuring devices for examining respiratory frequency measuring frequency of electric signals G01R23/00
• CPC Class Codes: A61B 5/1102 Ballistocardiography
• CPC Class Codes: A61B 5/1107 Measuring contraction of parts of the body, e.g. organ, muscle apparatus for measuring work or force in general G01L
• CPC Class Codes: A61B 5/316 Modalities, i.e. specific diagnostic methods
• CPC Class Codes: A61B 5/332 Portable devices specially adapted therefor
• CPC Class Codes: A61B 5/335 using integrated circuit memory devices
• CPC Class Codes: A61B 5/346 : Analysis of electrocardiograms
• CPC Class Codes: A61B 5/352 : Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval
• CPC Class Codes: A61B 5/361 : Detecting fibrillation
• CPC Class Codes: A61B 5/364 : Detecting abnormal ECG interval, e.g. extrasystoles, ectopic heartbeats
• CPC Class Codes: A61B 5/366 : Detecting abnormal QRS complex, e.g. widening
• CPC Class Codes: A61B 5/6801 : specially adapted to be attached to or worn on the body surface
• CPC Class Codes: A61B 5/6802 : Sensor mounted on worn items
• CPC Class Codes: A61B 5/6831 : Straps, bands or harnesses
• CPC Class Codes: A61B 5/6833 : Adhesive patches
• CPC Class Codes: A61B 5/7203 : for noise prevention, reduction or removal
• CPC Class Codes: A61B 5/7214 : using signal cancellation, e.g. based on input of two identical physiological sensors spaced apart, or based on two signals derived from the same sensor, for different optical wavelengths
• CPC Class Codes: A61B 5/7225 : Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation A61B5/30, A61B5/316 take precedence; transformers for specific applications H01F38/00; amplifiers H03F
• CPC Class Codes: A61B 5/7246 : using correlation, e.g. template matching or determination of similarity
• CPC Class Codes: A61B 5/725 : using specific filters therefor, e.g. Kalman or adaptive filters A61B5/316 take precedence
• CPC Class Codes: A61B 5/7257 : using Fourier transforms
• CPC Class Codes: A61B 5/7275 : Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: A61B 5/7282 : Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence
• CPC Class Codes: A61B 7/04 : Electric stethoscopes microphones, acoustic transducers therefor H04R
• CPC Class Codes: G06N 3/044 : Recurrent networks, e.g. Hopfield networks
• CPC Class Codes: G06N 3/045 : Combinations of networks
• CPC Class Codes: G06N 3/047 : Probabilistic or stochastic networks
• CPC Class Codes: G06N 3/048 : Activation functions
• CPC Class Codes: G06N 3/088 : Non-supervised learning, e.g. competitive learning
• CPC Class Codes: G16H 40/67 : for remote operation
• CPC Class Codes: G16H 50/30 : for calculating health indices; for individual health risk assessment

Abstract

A system (100) for monitoring and diagnosing heart conditions includes a sensor array (102) with accelerometers, an electrocardiogram sensor, and a system to synchronously capture and process (103, 105, or 106) composite heart signals. The system performs separation, identification and marking (201-205 or 501-509) of the signals, to extract information in cardiac vibrations. Machine learning, auditory scene analysis, or spare coding approaches can be used to resolve source separation problems. Analysis of the composite signals separates different vibration signals (302, 303, 304, 305), identifies streams for particular valve signal, and marks them with event time information with respect to a synchronous electrocardiogram signal (306). The psychoacoustic analysis mimics human auditory processing to enhance hearing of heart valve sounds by separating valve vibrations from the composite signal, and providing extraction, identification, marking and display of individual valve signals.

Claims

1. A system for measuring cardiac time intervals, comprising:

a non-invasive sensor unit comprising a transducer array for capturing electrical signals and composite vibration objects;

a processor configured to use the captured electrical signals and composite vibration objects to provide the operations of;

separating a plurality of individual heart vibrations of events of a cardiohemic system from the composite vibration objects by performing source estimation to separate the plurality of individual heart vibration events from the composite vibration objects as separated vibration sources;

identifying the plurality of individual heart vibration events from the composite vibration objects wherein identification of the separated vibration sources in individual heart beats of the cardiohemic events are associated with heart wall motion, blood motion, and heart valve events;

marking individual heart events from the plurality of individual heart vibration events with respect to an electrocardiogram signal; and

presenting the individual heart vibration events on a visual display extracted from body sounds from the composite vibration objects to aid in diagnosing one or more among pulmonary disease, respiratory disease, coronary artery disease, heart murmurs, valve abnormalities, heart failure, heart rhythm abnormalities or arrhythmias, vascular disease, congenital heart disease, cardiac resynchronization and risk factor modification.

2. The system for measuring cardiac time intervals of claim 1, wherein heart valve events comprises one or more among a mitral valve closing and opening, a tricuspid valve closing and opening, an aortic valve opening and closing or a pulmonary valve opening and closing.

3. The system for measuring cardiac time intervals of claim 1, wherein the identification of the separated vibration sources in the individual heartbeats comprises individual vibration signals from a mitral valve, an aortic valve, a tricuspid valve, a coronary artery, murmurs, third sound, fourth sound, a pulmonary valve, a respiratory sound, a breathing sound, a heart wall motion, and a snoring sound.

4. The system for measuring cardiac time intervals of claim 1, wherein the non-invasive sensor unit includes the transducer array having at least one or more pads where at least one of the at least one or more pads comprises at least a vibration sensor and optionally an electrode for an electrocardiogram sensor.

5. The system for measuring cardiac time intervals of claim 1, further comprising a sensor for performing an electrocardiogram and wherein the non-invasive sensor unit comprises at least one among an accelerometer, an acoustic sensor, or a piezoelectric sensor for sensing heart vibrations and wherein the system presents the individual heart valve events with respect to a QRS of the electrocardiogram enabling diagnosticians to correlate detected vibrations or signaling with specific biological events selected among heart valve openings and closings, apnea signals, brain spikes, fetal signals, or pre-natal contractions using the non-invasive sensor unit.

6. The system for measuring cardiac time intervals of claim 1, wherein the processor is further configured to:

separate sources from the composite signals by source estimation using at least one among machine learning, auditory scene analysis, or sparse coding;

phase estimate a phase between the separated vibration sources; and

calculate time stamps for each of the separated vibration sources at each heart beat with respect to a synchronized electrocardiogram signal and one or more sensors of the non-invasive sensor unit.

7. The system of measuring cardiac time intervals of claim 6, wherein a number of vibration sensors in the non-invasive sensor unit is less than the number of the separated vibration sources and wherein the separating of the plurality of individual heart vibrations of events of the cardiohemic system uses one among a visual sensor, an endoscopy camera, an ultrasound sensor, a magnetic resonance imaging device, a computed tomography scanner, a positron emission tomography scanner, or an electroencephalogram scanner alone or in combination to enable improvement in terms of source separation or identification, or marking of events among heart valve openings, brain spikes, contractions, peristaltic movements or peristaltic vibrations.

8. The system for measuring cardiac time intervals of claim 1, wherein the processor is configured to separate the plurality of individual heart vibration events from the composite vibration objects from multichannel signals by decomposing the multichannel signals into sparse activation patterns and clustering the sparse activation patterns.

9. The system for measuring cardiac time intervals of claim 1, wherein the processor is configured to separate the plurality of individual heart vibration events from the composite vibration objects from multichannel signals by decomposing the multichannel signals into sparse activation patterns that appear sparsely across a time chart using a sparse coding module, clustering the sparse activation patterns, and recomposing a plurality of source streams by applying an activation mask to the sparse activation patterns assigned to a cluster using basis elements where time locations of activation patterns are clustered together and assigned to the same source.

10. The system for measuring cardiac time intervals of claim 8, wherein the processor decomposes the multichannel signals obtained from the transducer array having one or more tri-axial accelerometers into sparse activation patterns using a K-SVD algorithm and wherein the identified valve signals are marked to indicate their start and end of the individual heart vibration event with respect to the start of an electrocardiogram.

11. The system for measuring cardiac time intervals of claim 1, wherein the system comprises a wearable device in the form of a patch, band, necklace, belt, or bandage configured to communicate with a wireless node and further configured to capture an electrocardiogram signal synchronized with one or more accelerometer sensors of the non-invasive sensor unit.

12. The system for measuring cardiac time intervals of claim 8, wherein the processor separates the plurality of individual heart valve events from the composite vibration objects from multichannel signals using at least one source separation technique used for extracting the valve heart signals for application in a non-linear time variant system, among Determined Models, Principal Component Analysis (PCA), Independent Component Analysis ICA, Singular Value Decomposition (SVD), Bin-wise Clustering and Permutation posterior probability Alignment, Undetermined Models, Sparseness condition, Dictionary learning, Convolutive models, or K-SVD Matching Pursuit.

13. The system for measuring cardiac time intervals of claim 1, wherein the marking of individual valve events comprises at least the marking of one or more among a Mitral valve opening (MO), Aortic valve opening (AO), Tricuspid valve opening (TO), or Pulmonary valve opening (PO), and wherein it provides tracking of individual valve signals over time for short-term and long-term discrimination between signals.