WO2018208950A1 - Évaluation de la fonction mécanique et de la viabilité de valvules cardiaques prothétiques au moyen d'une nouvelle technologie de détection - Google Patents

Évaluation de la fonction mécanique et de la viabilité de valvules cardiaques prothétiques au moyen d'une nouvelle technologie de détection Download PDF

Info

Publication number
WO2018208950A1
WO2018208950A1 PCT/US2018/031849 US2018031849W WO2018208950A1 WO 2018208950 A1 WO2018208950 A1 WO 2018208950A1 US 2018031849 W US2018031849 W US 2018031849W WO 2018208950 A1 WO2018208950 A1 WO 2018208950A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
kit
sensors
electrical
loaded
Prior art date
Application number
PCT/US2018/031849
Other languages
English (en)
Inventor
Marie Ann Johnson
Jixing YAO
Janine WOTTON
Micahela Nenagh G. JOHNSON
Original Assignee
Aum Cardiovascular, Inc.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Aum Cardiovascular, Inc. filed Critical Aum Cardiovascular, Inc.
Publication of WO2018208950A1 publication Critical patent/WO2018208950A1/fr

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
    • A61B5/0015—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network characterised by features of the telemetry system
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/25—Bioelectric electrodes therefor
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
    • A61B2562/02—Details of sensors specially adapted for in-vivo measurements
    • A61B2562/0209—Special features of electrodes classified in A61B5/24, A61B5/25, A61B5/283, A61B5/291, A61B5/296, A61B5/053
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/021—Measuring pressure in heart or blood vessels
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
    • A61B5/14542—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue for measuring blood gases
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/369—Electroencephalography [EEG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4869—Determining body composition
    • A61B5/4875—Hydration status, fluid retention of the body
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/74—Details of notification to user or communication with user or patient ; user input means
    • A61B5/7465—Arrangements for interactive communication between patient and care services, e.g. by using a telephone network
    • A61B5/747—Arrangements for interactive communication between patient and care services, e.g. by using a telephone network in case of emergency, i.e. alerting emergency services
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems

Definitions

  • Embodiments described herein relate generally to the medical diagnostics field, including improved systems and methods for detection of heart valve defects, diagnoses of bioprosthetic and transcatheter replacements, and detection of disease through combinations of acoustic and electrical biometric signals.
  • Health diagnostic equipment can be used to detect a variety of indicators of the physical condition of a patient.
  • Examples of known health diagnostic equipment can include, for example, sensors for pressure (e.g., blood pressure sensors), acoustics (e.g., stethoscopes), optical sensors (e.g., magnetic resonance imaging machines), or electrical sensors (e.g., electroencephalography (EEG) or electrocardiogram sensors (ECG)), among others.
  • sensors for pressure e.g., blood pressure sensors
  • acoustics e.g., stethoscopes
  • optical sensors e.g., magnetic resonance imaging machines
  • electrical sensors e.g., electroencephalography (EEG) or electrocardiogram sensors (ECG)
  • Diagnostic tests for health conditions are often performed only infrequently, such as at an annual physical or during a follow-up wellness check after a medical procedure.
  • Self-diagnosis or remote diagnosis is becoming more readily available with increased network connectivity between patients and healthcare providers. For example, video conferencing between people seeking healthcare and doctors or nurse practitioners has become common.
  • Networked devices that can receive or send information regarding medication schedules, blood pressure or blood sugar levels, or other vital statistics, disease symptoms, or appointments have also become ubiquitous.
  • a kit for diagnosing a health condition includes a plurality of sensors configured to simultaneously detect mechanical data and electrical data.
  • the kit further includes a networked device communicatively coupled to the plurality of sensors, the networked device having a display configured to show the mechanical data and the electrical data on a common time axis.
  • the kit further includes an interpretive guide depicting information representative of a plurality of diagnoses.
  • a method for diagnosing a health condition includes loading data from a plurality of sensors, wherein the data from the plurality of sensors includes mechanical data and electrical data corresponding to the health condition, and wherein the mechanical data and the electrical data have been measured simultaneously.
  • the method further includes removing a baseline from the loaded data, removing noise from the loaded data.
  • the method further includes transforming the segmented data and classifying the transformed data to provide a diagnosis.
  • a system for diagnosing a health condition includes a sensor device having a plurality of sensors configured to simultaneously detect mechanical data and electrical data.
  • the system further includes a networked device communicatively coupled to the sensor device, the networked device configured analyze the mechanical data and the electrical data to detect a medical condition.
  • the system further includes a safety mechanism configured to activate upon detection of the medical condition. That safety mechanism can include one or more of sending an alert to a patient, sending an alert to a healthcare provider, sending an alert to a centralized location, or activating an emergency protocol in a vehicle to prevent unsafe operation of the vehicle.
  • FIG. 1 depicts a kit for performing diagnostic tests according to an embodiment.
  • FIG. 2A is a top perspective view of a device for collecting data according to an embodiment.
  • FIG. 2B is a simplified bottom perspective view of the device of FIG. 2A.
  • FIG. 2C is a bottom view of a device according to an embodiment that includes pressure sensing.
  • FIG. 2D is a bottom view of an embodiment of a device that includes both pressure and electrical sensing elements.
  • FIG. 3 is an exploded, disassembled view of a device including a memory and an antenna for network connectivity according to an embodiment.
  • FIG. 4A is a perspective view of a device cradle according to an embodiment.
  • FIG. 4B is a perspective view of a device cradle according to another embodiment.
  • FIG. 4C depicts a juxtaposition of a device cradle and corresponding device according to an embodiment.
  • FIG. 5 is a flowchart of a method for analyzing detected signal at a centralized location according to an embodiment.
  • FIG. 6A is a schematic view of locations for sensing of data related to cardiovascular health
  • FIG. 6B is a corresponding portion of a guide for sensing the data, according to an embodiment.
  • FIGS. 7 A and 7B are interpretive graphs according to two embodiments in which data is aligned along a common time axis to identify health conditions or other information that can be determined by the interrelationships of multiple types of data.
  • FIG. 8 A is a graph showing the alignment of ECG and phonocardiogram data, with segments of data identified according to an embodiment of an interpretive guide.
  • FIG. 8B is a graph showing a Wiggers diagram corresponding to ECG and PCG data aligned in an embodiment of an interpretive guide.
  • FIG. 9 includes a series of interpretive graphs in which alignment between spectrogram data, energy data, and phonocardiogram data are aligned on a common time scale to diagnose cardiac conditions according to an embodiment of an interpretive guide.
  • FIG. 10 is an interpretive graph according to an embodiment, depicting the alignment between electrocardiogram, phonocardiogram, energy, and spectrogram data on a common time scale.
  • FIG. 11A is a simplified graph of phonocardiogram data associated with a variety of cardiac abnormalities, as depicted in an interpretive guide according to an embodiment.
  • FIG. 11B is a simplified graph of acoustic data associated with a variety of cardiac abnormalities of a prosthetic valve, according to an embodiment.
  • FIG. 12 is an acoustic assessment chart according to an embodiment of an interpretive guide.
  • FIG. 13 is a chart depicting a variety of heart murmurs by grade of severity, as depicted in an interpretive guide according to an embodiment.
  • FIG. 14 is a chart depicting early systolic low frequency sound and breathing sounds, as depicted in an interpretive guide according to an embodiment.
  • FIG. 15 is a chart depicting phonocardiogram, energy, and frequency information indicative of congestive heart failure, as depicted in an interpretive guide according to an embodiment.
  • FIG. 16A is a chart depicting phonocardiogram, energy, and spectrogram information corresponding a series of cardiovascular defects from FIG. 11 as depicted in an interpretive display according to an embodiment.
  • FIG. 16B is a chart depicting normal and abnormal readings for electrocardiogram, phonocardiogram, energy, and spectrogram data corresponding to a bileaflet aortic valve according to an embodiment.
  • FIG. 16C is a chart depicting normal and abnormal readings for electrocardiogram, phonocardiogram, energy, and spectrogram data corresponding to a bioprosthetic aortic valve according to an embodiment.
  • FIG. 16D is a chart depicting normal and abnormal readings for electrocardiogram, phonocardiogram, energy, and spectrogram data corresponding to a bileaflet mitral valve according to an embodiment.
  • FIG. 16E is a chart depicting normal and abnormal readings for electrocardiogram, phonocardiogram, energy, and spectrogram data corresponding to a bioprosthetic mitral valve according to an embodiment.
  • FIG. 17 depicts a report according to an embodiment.
  • FIG. 18 depicts a flowchart depicting a method for diagnosing a health condition according to an embodiment.
  • FIG. 19 depicts a system for health monitoring in an automotive application according to an embodiment.
  • Embodiments herein include systems and methods for detecting disease, monitoring the condition of prostheses, or detecting other physical conditions that produce electrical data, mechanical data (e.g., pressure pulse or acoustic data), optical data, or some combination thereof.
  • these measurements can be made simultaneously such that they can be displayed on a common time axis for ease of interpretation.
  • An interpretive guide can be used to aid with analysis of the data measured in this way, to provide fast, accurate diagnoses without the use of conventional large or expensive equipment that is typically found only in hospital or clinic settings. Therefore, the systems and methods described herein can be implemented outside of the clinics and hospitals where such tests have previously been performed, in embodiments.
  • diagnoses can be performed more easily, rapidly, efficiently, and accurately, improving health outcomes and access to healthcare for patients.
  • the special-purpose display can be an augmented reality headset, a virtual reality headset, a smart phone screen, a personal assistant display, or a display on another handheld device such as a tablet.
  • Diagnosing whether or not a vascular system is in good health can include several measurements. For example, in vascular systems that have been surgically modified such as in patients who have received a prosthetic valve or a pacemaker, measurements can be conducted routinely to ensure that the operation did not result in any adverse effects and any implanted components (such as prosthetic valves) are functioning as intended.
  • the primary detection mechanism for assessing the health of a valve or other defects in the heart is echocardiogram.
  • ultrasound is directed to the area of interest. After the ultrasonic waves interact with the targeted area, they are detected to form an image. In some embodiments, the direction of propagation of the reflected waves can be used to form a three-dimensional image of the target area. In others, referred to as Doppler echocardiogram, the phase shift of the ultrasonic waves is used to determine the speed at which blood is traveling through portions of the heart.
  • Other tests include exercise treadmill test, stress echocardiogram, computed tomography, calcium heart scanning and angiography. Each of these tests might be ordered by clinicians after a patient is suspected to have Coronary Artery Disease (CAD).
  • CAD Coronary Artery Disease
  • Exercise ECG testing is a commonly used test because clinical guidelines dictate it as the first test that should be employed and because it is relatively simple and inexpensive. The patient must be able to exercise to at least 85 percent of the predicted maximal heart rate to rule out ischemic heart disease if the test is otherwise negative. Patients who cannot exercise, have baseline ECG abnormalities that could interfere with exercise ECG testing, or in whom the exercise ECG test suggests intermediate risk, a number of alternative noninvasive tests are available including echocardiography with exercise or pharmacologic, radionuclide myocardial perfusion imaging (rMPI), using either planar or photon emission computed tomographic as the imaging method, positron emission tomography (PET) or using coronary calcium scores.
  • rMPI radionuclide myocardial perfusion imaging
  • PET positron emission tomography
  • ECG typically requires complex equipment and can be conducted only by a medical professional in a hospital or clinic setting where such equipment is located. Therefore, while echocardiogram is a useful tool for detecting clots or malfunctioning valves, problems often are not detected for days or weeks after they first arise.
  • one or more sensors are configured for collection of ECG information.
  • a transducer is configured to collect mechanical waves, such as vibrations or acoustic waves that are generated at a patient's vasculature.
  • the device can further include telemetric components such as an antenna configured to operate on Wi-Fi, Bluetooth, Zigbee, cellular, or other wired or wireless networks.
  • Analysis of data collected at the device can be conducted at the device itself, or at another computing device remote from the device, in various embodiments.
  • the analysis includes frequency analysis, in embodiments, and can make use of machine learning, artificial intelligence, or an expert system (i.e., a piece of software programmed using artificial intelligence techniques to emulate the decision-making ability of a human expert and offer advice or make decisions regarding medical diagnosis).
  • the analysis can produce a determination that a condition is present such as a blood clot or a change in valve function, for example.
  • FIG. 1 depicts at least a portion of a diagnostic system, and in particular kit 100.
  • Kit 100 includes components that can be used in conjunction with one another to diagnose health conditions such as those described above.
  • the embodiment of kit 100 shown in FIG. 1 includes device 102, cradle 104, packaging 106, indicators 108, and networked device 110.
  • Device 102 is a reusable electromechanical device that contains high fidelity pressure sensors and electronics to collect and optionally filter the acoustic (i.e., mechanical) and electrical signal. In some embodiments, device 102 can also convert that signal, such as from analog signal to digital. In some embodiments device 102 includes wireless network capabilities, and in others device 102 can be connected to another device (such as cradle 104 or networked device 110) by a hard- wired connector (not shown).
  • Cradle 104 is included in kit 100 with device 102.
  • Cradle 104 can include charging capability, such as pins or receivers that couple with device 102, or alternatively a transmitter to provide wireless charging signal.
  • Device 102 can include power storage such as a battery such that device 102 can be used a number of times (e.g., 100 uses) before requiring charging on cradle 104.
  • Cradle 104 can also be used to test integrity of device 102.
  • Device 102 controls the signal generator in cradle 104, in embodiments, to generate specific sounds and electrical signals while device 102 is recording these signals. The recording can be send to a central server or other device for analysis to determine if the sensors of device 102 are still functioning as desired or need recalibration, for example.
  • Packaging 106 includes instructions for use of device 102, including an interpretation guide as described in more detail below.
  • Packaging 106 includes instructions for use and RFID markers that correspond to those instructions, as shown in the embodiment in FIG. 1.
  • a unique identifier RFID tag can be used to process patient data and to protect the security of the patient's data.
  • the patient booklet that includes a number label forms a part of packaging 106 that can be removed from the booklet and stored or recorded in the patient's medical record, in embodiments.
  • Indicators 108 of kit 110 are RFID tags. In alternative embodiments, different types of indicators 108 could be used. For example, indicators 108 could include optically recognizable patterns such as QR codes or color coding, or inductive or capacitive tags using NFC or other electronic communication protocols. Indicators 108 can correspond to counterparts in packaging 106. For example, indicators 108 can be placed at the locations on a patient chest where measurements should be taken to perform a certain test or diagnosis. Indicators 108 can correspond to RFID tags in packaging 106 as described above.
  • Networked device 110 can be configured to wirelessly communicate with device 102, as described above.
  • Networked device 110 is a device that is used at the test location.
  • devices 110 that are available at the test location have limited screen space and computing power.
  • Kit 100 can be used in a variety of outpatient settings. Whereas other diagnostic tests are typically performed in a hospital or clinic setting where computing power and screen space is abundant, kit 100 can be used with a networked device 110 that is, as shown in FIG. 1, a tablet.
  • kit 100 can be used with a networked device that is a smart phone or other small or handheld device.
  • kit 100 solves problems of prior graphical user interface devices used in health diagnoses in that it improves the speed, accuracy, and usability of the diagnosis, such that the diagnosis can be performed outside of the clinic or hospital.
  • Networked device 110 can be used to transfer data from device 102 to a remote server, in embodiments.
  • networked device 110 can be a mobile device with 4G LTE and WiFi connectivity, such that the methods described herein can be performed anywhere in the world with cellular or WiFi coverage.
  • Networked device 110 can also be used to review sound files and a corresponding report (e.g., FIGS. 11 and 16, respectively).
  • Networked device 110 can include a touch screen that facilitates zooming in to view smaller details on the report.
  • Networked device 110 can also include other utilities such as a sound meter, ASCVD calculator, and instructions for use, in embodiments.
  • networked device 110 e.g., a tablet
  • networked device 110 can include a SEVI card that facilitates data connectivity even where pure data networks are not available.
  • a user can select which available network to use, or networked device 110 can autonomously detect and use the network that is most appropriate.
  • networked device 110 may not be necessary to acquire or send data.
  • Networked device 110 can still be used in such embodiments to display data or reports as data is acquired.
  • data can be acquired, sent to any other desired location, and analyzed, all within minutes. This represents a significant improvement over conventional diagnostic techniques such as ECG.
  • FIGS. 2 A and 2B show data collection devices 200 A and 200B, respectively, which are handheld coronary artery disease (CAD) detection devices that can be used in a non-invasive manner to determine whether an internal coronary artery blockage is present (rule in) or not present (rule-out).
  • CAD handheld coronary artery disease
  • Data collection device 200A of FIG. 2A includes a display 202.
  • Display 202 can be used to depict information relevant to the collection of data.
  • display 202 includes battery or test progress monitor 204 and position indicator 206.
  • Monitor 204 displays an indication corresponding to the remaining battery life of device 200A before recharging will be required, while position indicator 206 displays an indication corresponding to the actual or desired placement of device 200A (i.e., at a specific location on a patient or on a sensor as described in more detail below.
  • monitor 204 includes an indication of percentage of battery life remaining (e.g., between 0 and 100%) and in other embodiments, monitor 204 can display a total number of tests that can be performed before data collection device 200A needs to be charged.
  • FIG. 2B shows data collection device 200B from a bottom perspective view.
  • Data collection device 200B can include the same features described above with respect to FIG. 2A. Additionally, data collection device 200B includes peripheral portion 208 and central portion 210. Peripheral portion 208 and central portion 210 can come into contact with a patient, an identification element, or a cradle (e.g., cradle 104 described above with respect to FIG. 1). Peripheral portion 208 and central portion 210 can each include sensors (not shown in FIG. 2B) to detect acoustic or electrical signal, in embodiments.
  • peripheral portion 208 and central portion 210 can each be configured to detect one or the other—for example, peripheral portion 208 can be configured to detect electrical ECG signals whereas central portion 210 can be configured to detect acoustic signals indicative of a pressure pulse corresponding to a patient's heartbeat.
  • FIG. 2C shows an embodiment of a data collection device 200C that includes peripheral portion 208C, central portion 210C, pressure indicator 212, and body 214.
  • Peripheral portion 208C and central portion 2 IOC are functionally equivalent to their counterparts 208B and 210B described above with respect to FIG. 2B.
  • Each of peripheral portion 208C and central portion 2 IOC can detect signal (such as acoustic signal, electrical signal such as a potential difference, electromagnetic signal, or optical signal).
  • peripheral portion 208C and central portion 210C detect different signals.
  • Pressure indicator 212 comprises one or more LEDs, electroluminescent wire or some other suitable visual indicator in embodiments. Pressure indicator 212 provides feedback to a user regarding whether proper pressure is being applied to device 200C when in use.
  • Body 214 is economically sized and shaped to be easy and comfortable to grasp by a medical professional while scanning a patient.
  • body 214 can be smooth or textured and firm or somewhat pliable to provide an enhanced gripping surface.
  • Body 214 can also comprise one or more ports and/or contacts (not depicted) to provide for charging and/or exchanging data, or body 214 can have wireless capabilities such as cellular, RFID, BLUETOOTH, WIFI or some other suitable wireless communication technique, such that ports and/or contacts are optional.
  • FIG. 2D is a cutaway bottom view of a device 200D according to another embodiment.
  • device 200D includes ECG sensors 216.
  • ECG sensors 216 are arranged in a peripheral portion 208D of device 200D, whereas a central portion 210D of device 200D includes a pressure sensor.
  • Device 200D can be used in conjunction with an identification element, such as scanning area identification pads (e.g., indicators 108 of FIG. 1) and a patient scan sequence guide (e.g., the portions of packaging 106 described above with respect to FIG. 1), to aid in the proper placement of device 200D while scanning a patient.
  • an identification element such as scanning area identification pads (e.g., indicators 108 of FIG. 1) and a patient scan sequence guide (e.g., the portions of packaging 106 described above with respect to FIG. 1)
  • an identification element such as scanning area identification pads (e.g., indicators 108 of FIG. 1) and a patient scan sequence guide (e.g., the portions of packaging 106 described above with respect to FIG. 1), to aid in the proper placement of device 200D while scanning a patient.
  • Such systems are described in International Publication Nos. WO 2013/023041 and WO 2011/071989, U.S. Patent Pub. No. 2009/0177107, and U.S. Patent No. 7,520,860, all
  • Data collection device 200 can be used in conjunction with an identification element, such as an RFID tag or scanning area identification pad, as described in co-pending PCT Publication WO 2016/033521 to Johnson et al., the contents of which are incorporated herein by reference in their entirety. Unlike traditional cardiac monitoring equipment and methods, and as shown in more detail with respect to FIG. 2C, data collection device 200 can be used to simultaneously measure multiple types of data. Conventional diagnostic systems such as ECG tests or angiogram measure one type of data at a time. Diagnostic tools that are available outside of a hospital or clinic, such as a stethoscope or blood pressure cuff, are limited to single types of data.
  • diagnosis tools detect multiple types of data at the same time (e.g., a blood pressure cuff combined with stethoscope) these tools rely on a human operator to combine the data manually.
  • these tools rely on a human operator to combine the data manually.
  • the simultaneous measurement and analysis of multiple types of data at an outpatient location facilitates positioning the data on a common time axis, which in turn makes diagnosis possible that previously required either uncommon and expensive equipment in a hospital or clinic setting, or experienced medical professionals who have the capacity to manually combine the data, often in their head and in real time.
  • FIG. 3 is an exploded view of device 300, according to an embodiment.
  • Device 300 includes peripheral portion 308 and central portion 310, which can detect electrical and acoustic data as described above.
  • Device 300 further includes body 314, which houses memory 318 and transmitter 320.
  • Memory 318 can be flash memory, for example.
  • Transmitter 320 is configured to send, either autonomously or on-demand, data that has been collected by device 300.
  • Transmitter 320 can send signal through a network such as WiFi, Bluetooth, Zigbee, and various cellular networks (such as Code Division Multiple Access (CDMA), Global System for Mobile (GSM), or Long Term Evolution (LTE) networks).
  • CDMA Code Division Multiple Access
  • GSM Global System for Mobile
  • LTE Long Term Evolution
  • FIG. 4A is a perspective view of cradle 400, which includes sound transducer 402, charging/communication pins 404, and contoured surface 406.
  • Sound transducer 402 can be used to calibrate an acoustic sensor of a device, in embodiments. During calibration, sound transducer 402 can provide signal of a known frequency range and amplitude, and the corresponding device held in cradle 400 can self-calibrate based upon the difference between the known emitted signal and the detected signal levels.
  • Charging pins 404 are used in embodiments to provide power for recharging a corresponding device (e.g., device 300). Charging pins 404 can have counterparts in the device to provide electrical power. Charging pins 404 can be configured for data transmission as well as power transmission in some embodiments. In still further embodiments, charging pins 404 can be used to provide a signal for testing electrical sensors such as ECG sensors that are arranged on the bottom surface of a corresponding device. Charging pins 404 need not be present in all embodiments, such as embodiments in which the corresponding device is capable of wireless charging, or includes a side-port for receiving a charging cable.
  • Contoured surface 406 is shaped to engage with a corresponding device, such as device 300 depicted above with respect to FIG. 3. Contoured surface can be shaped to match the bottom surface of a corresponding device so that energy consumption of acoustic and electrical signals generated by sound transducer 402 and electrical pins 404 is reduced, also ambient noise is reduced or eliminated.
  • FIG. 4B is a perspective view of an alternative embodiment of a cradle that includes sound transducer 402B and contoured surface 406B, similar to sound transducer 402 and contoured surface 406 described above with respect to FIG. 4A. Contoured surface 406B covers electrical transducers that can communicate with corresponding portions of a device as described in more detail below with respect to FIG. 4C.
  • the cradle shown in FIG. 4B includes indicator light 408. If the handheld device (e.g., 102) screen shows empty battery or does not power on, the handheld can be charged in the cradle. Indicator light 408 comes on to indicate handheld is charging or charged, in embodiments.
  • FIG. 4C shows a top partial view of cradle 400C and a bottom view of a corresponding device 401C.
  • cradle 400C includes sound transducer 402C and electrical transducers 404C.
  • Device 401C includes corresponding central portion 411C and ECG sensors 404C.
  • sound transducer 402C is aligned with central portion 411C
  • electrical transducers 404C are aligned with ECG sensors 404C. Alignment is maintained by pins 410C of cradle 400C, which are received in ports 412C of device 401C.
  • Pins 410C and ports 412C can interact to provide one or more of electrical charging for device 401C, data upload or download between cradle 400C and device 401C, and mechanical alignment, in various embodiments.
  • FIG. 5 is a flowchart of a system for diagnosing heart health according to an embodiment.
  • the diagnosis can utilize both acoustic data (e.g., turbulence) and ECG data together to make a diagnosis about presence or absence of turbulence as well as presence of ECG abnormality.
  • acoustic data e.g., turbulence
  • ECG data e.g., ECG data
  • the presence or absence of turbulence detected by the acoustic sensor(s) and the location of an ECG-detected abnormality can be used in combination to provide a diagnosis.
  • the turbulence lends a diagnosis separate from the ECG diagnosis, as both can provide individual information. Together they can provide more specificity than either type of test could provide in isolation, in embodiments.
  • Network map 500 depicts one way in which data can be collected, stored, and transmitted.
  • Network map 500 includes device portion 502 and cloud portion 504.
  • Device portion 502 generates sensor data 506, which includes both ECG sensor data and acoustic data.
  • Sensor data 506 is sent to controller 508, which combines the data into a data package and sends the packaged data to cloud portion 504.
  • the systems described herein, including network map 500, provide contemporaneously- acquired electrical and acoustic data.
  • This contemporaneous data in two modes can diagnose cardiac and/or pulmonary conditions quickly and accurately, without the need for invasive and expensive alternatives such as angiography.
  • Embodiments are small, portable, and versatile, and can be used for both human medical evaluations and in veterinary applications.
  • the packaged data is analyzed by an analytical engine 510 to determine whether turbulence exists, as described in more detail below. If analytical engine 510 detects that a turbule exists, and then also detects a recognized ECG signal corresponding to a particular medical condition, then a diagnosis 512 is generated. If a turbule is detected and no ECG signal is recognized, or if no turbule is detected but an ECG signal corresponding to a particular medical condition is recognized, then a referral for further analysis 514 is generated. If no turbule id detected and no ECG signal is recognized by analytical engine 510, then a negative indication of "Rule-Out" 516 is generated.
  • the analytical engine 510 could be arranged at a local device, such as networked device 110 of FIG. 1. Analysis of the data could take place on the device 502 itself, in embodiments, and a diagnosis (512, 514, 516) can be generated on the display of the device itself (e.g., display 202 of FIG. 2A).
  • FIG. 6A is a schematic view of an example series of sites on a patient where electrical and acoustic data can be detected. As shown in FIGS. 6 A and 6B, tests are conducted adjacent tricuspid valve site B, mitral valve site A, pulmonic valve site C, and aortic valve site D. As described above with respect to FIG. 1, instructions can be provided to measure acoustic signal, electrical signal, or both, at each of these locations or others in order to provide a diagnosis.
  • FIG. 6B depicts a portion of an interpretive guide 600 that instructs a user of a kit or device on how and when to measure data at each of the thorax sites A-D.
  • sensors need not be placed on the skin of the patient, but could instead be permanently fixed within the patient. This typically occurs when the patient has an implanted device such as a pacemaker or prosthetic valve.
  • the prosthetic valve can include or be coupled to a sensor that transmits signal corresponding to electrical or mechanical (e.g., pressure, acoustic) waves in its vicinity. This transmission can be powered in embodiments where a power source is available, such as a pacemaker, or alternatively the sensor can be configured to respond to an external stimulus, such as an RFID prompt.
  • Sensors can be provided at a valve leaflet, a transcatheter valve stent, or pacemaker leads or within the body of a pacemaker device, among others. Sensors can also be contained within a handheld device, a watch, a patch, an implanted can, an NFC device, a telephone, a tablet, or an AR headset, in various other embodiments.
  • FIGS. 7A and 7B are examples of interfaces 700 for interpretation of health reports.
  • a computer interface presents a specific and limited set of information in a specific manner. This display resolves the deficiencies of several previous displays, which often required navigating between multiple views or screens, and did not align the data along a common time axis to identify health conditions or other information that can be determined by the combinations of multiple types of data.
  • diagnosis of a health condition can occur on a networked device 110 such as a tablet or smart phone.
  • a networked device 110 such as a tablet or smart phone.
  • interface 700 in combination with a diagnostic interpretation sheet, presents the data in a new and useful way that facilitates diagnosis of a variety of conditions using data from a sensing device (e.g., 102, 200A, 200B, 200C, 200D, 300).
  • a sensing device e.g., 102, 200A, 200B, 200C, 200D, 300.
  • the interpretation guide is described in more detail below with respect to FIGS. 7-19.
  • the comparison of these separate pieces of information is accomplished by comparing simultaneously-acquired data. Because the devices described herein obtain both acoustic and electrical data at the same time and from the same location, it is possible to arrange the data on the same time axis. This is not possible in most conventional systems, because only one type of data, either electrical or acoustic, is detected at any given time.
  • FIGS. 7 A and 7B four or more types of partially processed data are compared on a common time axis. As shown in the header 710, heart rate is calculated, and ischemia can be localized.
  • ECG data 702 is arranged on a first row
  • phonocardiogram (PCG) data 704 is arranged on the row directly beneath that
  • energy data 706 is arranged on the third row
  • spectrogram data 708 is on the fourth row.
  • PCG phonocardiogram
  • FIG. 7B the data is arranged from top to bottom as spectrogram data 708,
  • This arrangement can help a user identify cardiac cycles from the spectrogram with ECG signals directly underneath.
  • interface 700 includes four rows of these four groups of data (702, 704, 706, 708), but in embodiments where interface 700 is displayed on a smaller screen, fewer rows of the four sets of data need be displayed. In embodiments, only one row of data is displayed.
  • data e.g., one or more of 702, 704, 706, and 708 can be presented vertically or horizontally, in embodiments.
  • Interface 700 can include a scale to show heart rate and murmur intensity, in embodiments, which can be included in header information 710. Intensity of a murmur can be shown in color to facilitate rapid determination of murmur grade by a healthcare professional or other user of interface 700.
  • the data (702, 704, 706, 708) detected and displayed on interface 700 can also be saved for later review and documentation if desired.
  • ECG data 702 correlates with the heart's electrical activity.
  • ECG data 702 can be used to determine the first and second heart sounds SI and S2 of the phonocardiogram (first heart sound SI corresponds to the closing of the mitral and tricuspid valves, and second heart sound S2 corresponds to the closure of the aortic and pulmonary valves).
  • SI normally occurs just after the QRS complex and the S2 at the end of the T wave.
  • the ECG data is shown on the top in FIG. 8.
  • the heart sounds SI and S2 (as well as other heart sounds) are periodic in nature, and their alignment or misalignment can provide information relating to the overall health of a heart muscle, valves, or prostheses, including providing specific diagnoses in some cases.
  • Phonocardiogram data 704 is a graphical representation of the heart sounds shown as amplitude as a function of time.
  • the closing of the atrioventricular valves indicates the beginning of systolic (SI) and the closing of the semilunar valves (aortic and pulmonic) S2 marks the beginning of the diastolic period.
  • SI and S2 are typically visible as spikes in amplitude. Other sounds such as murmurs, turbulence or noise artifacts may be seen as changes in amplitude between the SI and S2 events.
  • SI typically lasts for about 140 msec, while S2 typically lasts about 110 msec.
  • Energy data 706 can be compared with phonocardiogram data 704 in that it allows the clinician to quantify the intensity of sounds, such as heart sounds and murmurs, found in the cardiac cycle. Therefore positioning PCG data 704 adjacent to energy data 706 provides for useful comparison.
  • interface 700 can be created as a single PDF file, with one page with time broken into sections of 5 seconds as shown.
  • interface 700 could be presented as a "strip chart” or Digital Imaging and Communications in Medicine (DICOM) chart.
  • Interface 700 can be accompanied by an interpretive guide that is provided in any of a number of formats.
  • the interpretive guide could be provided as a book, an online repository of information, an app, an electronic PDF, an electronic guide provided on a USB device, and a computer algorithm that interprets the simultaneously detected mechanical data and electrical data using a machine learning algorithm.
  • FIG. 8A shows ECG and PCG data alignment for a healthy heart. Similar alignments and comparisons can be performed for other data.
  • FIG. 8B shows the Wiggers diagram corresponding to ECG and PCG data aligned as they typically will be in a healthy heart.
  • energy data 706 can be displayed to provide a clinician with decibel level as a function of time for SI, systole, S2 and diastole. This information helps a clinician by providing quantitative information that can be used to track a condition over time. Data is tracked over time by uploading to a remote processing unit via Cellular, Bluetooth, Zigbee, WiFi, NFC, infrared, or other wired or wireless communication protocols. Information related to exercise and health habits can be directly input by a patient via a health tracker, cellular phone/tablet, or other personal device and cross- referenced with acoustic/ECG information related to a pacemaker or valves to give the patient interactive assessment of symptoms and data.
  • Spectrogram data 708 is a visual representation of the spectrum of frequencies in a sound or other signal as they vary with time.
  • the horizontal axis is time (as with the other three types of data 702, 704, and 706) while the vertical axis represents frequency in a logarithmic format
  • color can be used to indicate intensity. The lighter the color, the more the intensity, for example.
  • This time and frequency view works in conjunction with the phonocardiogram data 706 and allows the clinician to better understand the timing, frequency, and intensity of heart sounds in comparison to one another and systole/diastole.
  • a scan can be conducted for sufficient time to collect data corresponding to multiple heart beats. For example, in one embodiment at least 20 seconds of data is collected.
  • FIGS. 7A and 7B This provides the clinician a visual display of the data collected using a handheld device such as those described above.
  • FIG. 9 is a portion of an interpretive guide 900 that can be used by a medical professional, a patient, or anyone who wishes to interpret a scan result such as the results depicted on interface 700.
  • FIG. 9 shows examples of PCG data 904, energy data 906, and spectrogram data 908, arranged in the same order as their presentation on interpretive guide 700 described above with respect to FIGS. 7 A and 7B.
  • Interpretive guide 900 can be compared to a display of data on interpretive guide 700 to diagnose a variety of conditions. For example, FIG.
  • FIG. 9 is a portion of the interpretive guide 900 that shows a comparison of PCG data 904, energy data 906, and spectrogram data 908 on a common time axis indicative of a normal heart 912, pulmonic stenosis 914, aortic stenosis 916, mitral stenosis 918, aortic insufficiency 920, mitral regurgitation 922, ventricular septal defect 924, patent ductus arteriosus 926, and atrial septal defect 928.
  • Each of these indicators (912-928) shows a different appearance to the three sets of data (904, 906, 908), a different relationship between the temporal arrangements of the three sets of data (904, 906, 908) with respect to one another, or both.
  • heart sounds SI and S2 are identified for each of the indicators (912-928), which can be useful for associating a particular measured data set on an interface (e.g., 700) with a corresponding indicator (912-928).
  • FIG. 10 shows an alternative embodiment of an interface 1000, according to an embodiment.
  • interface 1000 of FIG. 10 shows ECG data 1002, PCG data 1004, energy data 1006, and spectrogram data 1008.
  • the interface 1000 of FIG. 10 shows only one row of each of the four types of data (1002-1008) such that interface 1000 can be displayed on a small screen size or portable device.
  • interface 1000 includes synchronization lines
  • Synchronization lines 1010 indicate the synchronized occurrence of expected features corresponding to the SI heart sound or the S2 heart sound, for example. Synchronization lines can be used to determine whether any one or more of the signals (1002-1008) is time-shifted with respect to the other signals (1002-1008), and can help a user of a kit including interface 1000 and a corresponding interpretive guide (e.g., 900) diagnose diseases or defects.
  • a kit including interface 1000 and a corresponding interpretive guide e.g., 900
  • FIG. 11 A is a portion of an interpretive guide 1100.
  • Interpretive guide 1100 can be used to diagnose conditions based on one or more sets of detected data. Whereas interpretive guide 900 related to three sets of simultaneously-measured data, interpretive guide 1100 relies exclusively on PCG data. Despite the fact that the PCG data is considered in isolation, the interpretation of that PCG data is informed by the detection of other data. Specifically, as shown in FIG. 11 A, the SI and S2 onset time points are marked, corresponding to the first heart sound and the second heart sound. When PCG data shows a particular wave form before, between, or after the SI and S2 onset time points, this can indicate that the heart has a specific condition and can simplify diagnosis.
  • Interpretive guide 1100 shows a series of eight wave forms that correspond to particular diagnoses.
  • wave form 1102 shows a PCG signal corresponding to a late diastolic murmur.
  • Wave form 1104 shows a PCG signal corresponding to a holosystolic murmur.
  • Wave form 1106 shows a PCG signal corresponding to an aortic ejection murmur beginning with an ejection click.
  • Wave form 1108 shows a PCG signal corresponding to a systolic murmur with split S2 sound. Juxtaposition of A2 and P2 sounds can be an indicator of pathology as can timing between the two.
  • Wave form 1110 shows a PCG signal corresponding to an aortic or pulmonary diastolic murmur.
  • Wave form 1112 shows a PCG signal corresponding to a mitral stenosis after opening snap.
  • Wave form 1114 shows a PCG signal corresponding to a S3 extra heart sound, oftentimes correlated with compliance issues in the myocardium.
  • Wave form 1116 shows a PCG signal corresponding to patent ductus arteriosus.
  • FIG. 1 IB shows collected data that is produced in an interpretive guide in FIG. 16.
  • Data 1118 showing a series of acoustic wave forms and defining corresponding heart conditions in a prosthesis.
  • the diagnoses provided by the portions of data 1100 and 1118 shown in FIGS. 11A and 11B can be useful for diagnosing conditions in fully-biological hearts and at least partially prosthetic hearts, respectively.
  • the change in a particular sound or sounds over longer periods of time can also be used for diagnostic purposes.
  • prosthetic components in human hearts can accumulate thrombus or develop cracks or other defects that become worse over time. Often these defects are difficult to diagnose at their early stages.
  • heart sounds such as SI and S2 can be detected and the acoustic data 1118 can be mapped and interpreted with the guide shown in FIG. 16. This diagnosis can be compared with previous measurements taken in the same location or locations. Where the evidence of a thrombus of other defect or disease increases over time, it is more likely that corrective treatment is needed.
  • FIG. 12 is another portion of an interpretive guide 1200.
  • Interpretive guide 1200 can be provided in combination with one or more of interpretive guides 600, 900, 1100, or 1118, in embodiments.
  • Interpretive guide 1200 shows a chart of conditions and corresponding data that correspond to a diagnosis of that condition.
  • FIG. 13 is another portion of an interpretive guide 1300.
  • Interpretive guide 1300 can be provided in combination with one or more of interpretive guides 600, 900, 1100, 1118, and 1200, in embodiments.
  • Interpretive guide 1300 shows the PCG, energy, and spectrogram outputs corresponding to different grades of murmur. As shown in FIG. 12, higher or lower grades of detected murmur can correspond to different diagnoses.
  • FIG. 14 is another portion of interpretive guide 1400.
  • Interpretive guide 1400 can be provided in combination with one or more of interpretive guides 600, 900, 1100, 1118, 1200, and 1300, in embodiments.
  • Interpretive guide 1400 indicates phenomena such as breathing sound 1402, which does not necessarily correlate with a particular diagnosis, and early systolic low frequency sound 1404.
  • FIG. 15 the PCG, Energy, and spectrogram data corresponding to a patient having congestive heart failure is depicted.
  • FIG. 16A is a chart depicting phonocardiogram, energy, and spectrogram information corresponding a series of cardiovascular defects as depicted in an interpretive display according to an embodiment.
  • FIG. 16B is a chart depicting normal and abnormal readings for electrocardiogram, phonocardiogram, energy, and spectrogram data corresponding to a bileaflet aortic valve according to an embodiment.
  • FIG. 16C is a chart depicting normal and abnormal readings for electrocardiogram, phonocardiogram, energy, and spectrogram data corresponding to a bioprosthetic aortic valve according to an embodiment.
  • FIG. 16A is a chart depicting phonocardiogram, energy, and spectrogram information corresponding a series of cardiovascular defects as depicted in an interpretive display according to an embodiment.
  • FIG. 16B is a chart depicting normal and abnormal readings for electrocardiogram, phonocardiogram, energy, and spectrogram data corresponding to a bileaflet
  • FIG. 16D is a chart depicting normal and abnormal readings for electrocardiogram, phonocardiogram, energy, and spectrogram data corresponding to a bileaflet mitral valve according to an embodiment.
  • FIG. 16E is a chart depicting normal and abnormal readings for electrocardiogram, phonocardiogram, energy, and spectrogram data corresponding to a bioprosthetic mitral valve according to an embodiment.
  • Each of these FIGS. 16A-16E shows "normal findings" on the left, and "abnormal findings" indicating a diagnosable defect or disease on the right. By providing such comparisons, accuracy and speed of diagnosis is improved.
  • Prosthetic mechanical heart valve malfunction can either be structural or non- structural.
  • the malfunction can be caused by pedprosthetic leak, paravalvular insufficiency, or abnormal function of one or several pads of the prosthesis, for example. These can be caused by prosthetic valve thrombosis, endocarditis, pannus formation, interference of the prosthetic occluder with cardiac or non-cardiac structures, faults it the material, material fatigue in mechanical prosthesis or degeneration of tissue structures.
  • Mechanical dysfunction can be caused by wear, faults in materials (structural fractures), inadequate allocation of the valve housing and occlude (leaflet escape) or inexpert handling during implantation.
  • a normal SI is followed by the opening click (OC) of the prostheses.
  • an opening click is not present.
  • a systolic ejection murmur (SEM) is present in all cases.
  • the SEM is louder than in the other prostheses.
  • the SEM is followed by a closing click (CC) of the prostheses.
  • Abnormal findings for all prosthetics except the single tilting-disk are marked by an aortic diastolic murmur. Decreased intensity of opening or closing click in all mechanical prostheses is abnormal.
  • normal findings include a closing click in place of a normal SI, a normal S2 followed by opening click of the mitral prostheses.
  • a diastolic murmur is normal
  • a low-frequency apical diastolic murmur and high frequency holosystolic murmur mark abnormal function.
  • a high frequency holosystolic murmur with decreased intensity of closing click is abnormal in Single-Tilting-Disk and Bileaflet Tilting Disk valves.
  • An abnormal mitral heterograft bioprosthesis is indicated by a high frequency holosystolic murmur.
  • FIG. 17 depicts a diastolic murmur report 1700 that can form a part of an interpretive guide, according to an embodiment.
  • Other reports similar to report 1700 can be generated to indicate chordae ischemic markers, mitral regurgitation, S3, S4, and other sounds.
  • Artificial intelligence and comparison of multiple data sets can be used to extract meaningful information from ECG and acoustic data.
  • machine learning can be used to provide diagnoses for both normal and obstructive disease, such as by detection of turbulence or other sounds.
  • This artificial intelligence or machine learning aspect of the system can be semi -supervised or unsupervised, using big data models.
  • the x-axis is the algorithm score, which ranges from “turbulence detected” to "turbulence not detected”.
  • the y-axis is a measure of data quality the color or shade is confidence level.
  • the confidence ranges from about 0% to about 28%, while on the left 1702 confidence ranges from about 55% to about 100%.
  • an analytics engine For each patient data set, an analytics engine generates a score after a series of complex computation, which is shown in the horizontal axis. The further away from the center, the better an indication is that a condition has or has not been detected. Often, data quality of the patient data set has significant impact on the accuracy of the diagnosis, which is shown on the vertical axis.
  • the square 1706 on the report 1700 indicates these two metrics of the processed patient data set.
  • the background colormap shows the confidence of detection result, where bright color means higher confidence and dark color means lower confidence.
  • the color maps of 'Turbulence Detected' 1704 and 'No Turbulence Detected' 1702 are independent.
  • turbulence can be used to label markers of cardiac disease that have been identified by a machine learning algorithm, or in alternative embodiments other detected characteristics (whether acoustic or electrical) can be used to reveal relevant information corresponding to a diagnosis that is not necessarily associated with turbulent blood flow.
  • FIG. 18 is a flowchart depicting a method 1800 for diagnosing a health condition, according to an embodiment. As shown in FIG. 18, method 1800 can include loading data 1802, removing a baseline 1804, removing noise 1806, data segmentation 1808, transformation 1810, and classification 1812.
  • method 1800 can be implemented in an analytics engine data flow.
  • the analytics engine could include artificial intelligence or expert systems functionality, such that over time the diagnostic accuracy of method 1800 improves.
  • the analytics engine that carries out method 1800 can be arranged at a centralized facility such as a server that communicates with systems, kits, or devices as described above.
  • a centralized facility such as a server that communicates with systems, kits, or devices as described above.
  • method 1800 can be implemented in a device, such as networked device 110 described above with respect to FIG. 1.
  • diagnostic time can be improved and diagnoses can be provided even in locations where network connectivity is not available.
  • Hybrids of these two approaches can also be used, wherein some of the elements of method 1800 are performed at a central location and some are performed at a peripheral location, for various purposes such as anonymizing patient data, reducing computer resource demands, and benefitting from larger pools of data for machine learning, among others.
  • Loading data 1802 can include sending data from the device having sensors to a local device (e.g., networked device 110 of FIG. 1) for either local analysis or for transmission to a central location for analysis, or some combination thereof as described above.
  • a local device e.g., networked device 110 of FIG. 1
  • a baseline is removed from the loaded data at 1802. Removing the baseline 1804 is not necessary in all embodiments, but can be used where, for example, loaded data at 1802 included ECG signal with a DC baseline.
  • Baseline removal 1804 can include removing DC bias from this recording by a pre-determined value, or in embodiments such DC bias can be calculated from the incoming data.
  • the baseline can also be removed via filters.
  • background noise or other pressure pulses can also be removed as a baseline. As described above with respect to FIGS. 1 and 4, this background noise or pressure can be detected by a reference/background microphone in the handheld (104, 400).
  • Remove noise 1804 can include a data filter such as a high pass filter, low pass filter, band pass filter, or band stop filter. In embodiments, two or more of these filters can be applied to the data received at remove noise 1806. More sophisticated filters including adaptive filters can be employed in some embodiments, including a least-mean square filter, a normalized least-mean square filter, a Wiener filter, spectral subtraction, or a Kalman filter, in embodiments. Wavelet thresholding can be used for denoising data, using a Bayesian technique to remove Gaussian noise.
  • background signal can also contribute to noise, and sensors can be used to make background recordings that are analyzed to remove electrical, acoustic, optical, or other noise from the data.
  • Trained neural networks can be used to determine the amount of noise to be removed, resulting in a more accurate dataset after noise removal 1806 than merely subtracting the measured noise from the measured signal.
  • data can optionally be separated into different sections based on a corresponding physiological event.
  • the heart sound can be segmented based on cardiac cycles.
  • data could be segmented corresponding to time frames for the four heart sounds (first heart sound SI corresponding to the closing of the mitral and tricuspid valves, second heart sound S2 corresponding to the closure of the aortic and pulmonary valves, third heart sound S3 corresponding to "ventricular gallop" after the mitral valve opens, allowing passive filling of the left ventricle, and fourth heart sound S4 corresponding to the "atrial gallop" as the atria contract to force blood into the left ventricle).
  • Data segmentation 1808 can be made by human annotation, alignment with electrocardiogram or photoplethysmogram data, or based on signal length, in embodiments.
  • machine learning algorithms can be used, such as Hidden Markov Model, to create specific time segmentation.
  • Neural networks including recurrent neural networks, can use data that has been loaded (1802), normalized by removal of baseline (1804), and cleaned up to remove noise (1806), to create appropriate segments using thresholding or peak detection, for example.
  • noise can be removed from a loaded data set before removal of baseline signal.
  • data segmentation models that have been refined and improved can be used prior to loading additional data.
  • Data transformation 1810 can include modifying the form or vector-space in which the data are presented, analyzed, or compared with one another.
  • data transformation 1810 can include conducting a Fourier transform of the data (including Fast Fourier Transforms or short-time Fourier transforms), calculating a power spectral density, defining a signal envelope of the data, conducting Wavelet transforms, or determining Mel-frequency cepstrum coefficients, based upon a representation of the short-term power spectrum of detected acoustic or pressure data and a linear cosine transform of a log power spectrum on a nonlinear Mel scale of frequency.
  • Classification 1812 identifies individual data as within classes corresponding to specific diseases or diagnoses. Classification mechanisms can include logistic regression, decision tree analysis, Naive Bayes, support vector machine or data mining, or combinations thereof. Artificial intelligence is a technique that can be used to iteratively improve the accuracy of the classification. Using artificial intelligence, measured results can be compared with previously-measured results and classifications, and the classification mechanism or combinations that are used can evolve over time for improved diagnostic accuracy. Additionally or alternatively, classification 1812 can include the use of neural networks such as Long Short Term Memory (LSTM) techniques, time delay neural networks, convolutional neural networks, or ensemble classifiers and neural networks, among others.
  • LSTM Long Short Term Memory
  • classification 1812 The table below indicates some potential classifications that can be provided at classification 1812:
  • FIG. 19 depicts an alternative embodiment, system 1900.
  • System 1900 includes a plurality of seatback sensors 1902 and a display 1904.
  • system 1900 is implemented in a vehicle, so that a driver will be informed of a potential medical event upon sitting in the seat and therefore coming into contact with sensors 1902.
  • similar systems could be implemented in office chairs, massage tables, beds, or other areas where a person might stay for a period of time with his or her back or chest in contact with a surface that can house sensors 1902.
  • Sensors 1902 can be similar to those described above, in that they can sense one or more of acoustic or electrical signal to create diagnoses.
  • data can be collected for some time and then sent to a server or other device or system for processing.
  • the report will be returned to the person (in this case, at the car via display 1904).
  • display 1904 can include a health report, including data regarding heart rate, ECG, EEG, and vital signs like oxygen level, hydration, and body temperature.
  • Display 1904 can include a health tip, which can be customized based on that measured data. For example, where the sensors 1902 detect dehydration, the health tip could be to drink more water.
  • System 1900 can improve the ability of people with health conditions to safely drive. People with epilepsy or heart conditions that could lead to cardiac arrest, for example, can drive knowing that in the event of a medical event the data from system 1900 can be sent automatically to healthcare professionals. In embodiments, a telemedicine consultation can begin immediately upon detection of such an event (or upon request). In some models, the driving functions of the car can be modified by a health event, such as by turning on autopilot to drive to a nearby hospital or by safely stopping the vehicle.
  • System 1900 can diagnose a health condition or a likelihood of a health condition and, if a high likelihood of a condition is found that would prevent safe operation of the vehicle or of some impending injury such as a cardiac event, system 1900 can take appropriate action including but not limited to sending an alert to a patient (i.e., the driver or passenger), sending an alert to a healthcare provider, sending an alert to a centralized location (e.g., emergency services or the driver or passenger's medical team). In some circumstances, the appropriate action can include activating an emergency protocol in a vehicle to prevent unsafe operation of the vehicle such as slowing or stopping the vehicle.
  • Memory can comprise volatile or non-volatile memory as required by the coupled computing device or processor to not only provide space to execute the instructions or algorithms, but to provide the space to store the instructions themselves.
  • volatile memory can include random access memory (RAM), dynamic random access memory (DRAM), or static random access memory (SRAM), for example.
  • non-volatile memory can include read-only memory, flash memory, ferroelectric RAM, hard disk, floppy disk, magnetic tape, or optical disc storage, for example.
  • the system or components thereof can comprise or include various modules or engines, each of which is constructed, programmed, configured, or otherwise adapted to autonomously carry out a function or set of functions.
  • engine as used herein is defined as a real-world device, component, or arrangement of components implemented using hardware, such as by an application-specific integrated circuit (ASIC) or field programmable gate array (FPGA), for example, or as a combination of hardware and software, such as by a microprocessor system and a set of program instructions that adapt the engine to implement the particular functionality, which (while being executed) transform the microprocessor system into a special-purpose device.
  • ASIC application-specific integrated circuit
  • FPGA field programmable gate array
  • An engine can also be implemented as a combination of the two, with certain functions facilitated by hardware alone, and other functions facilitated by a combination of hardware and software.
  • at least a portion, and in some cases, all, of an engine can be executed on the processor(s) of one or more computing platforms that are made up of hardware (e.g., one or more processors, data storage devices such as memory or drive storage, input/output facilities such as network interface devices, video devices, keyboard, mouse or touchscreen devices, etc.) that execute an operating system, system programs, and application programs, while also implementing the engine using multitasking, multithreading, distributed (e.g., cluster, peer-peer, cloud, etc.) processing where appropriate, or other such techniques.
  • hardware e.g., one or more processors, data storage devices such as memory or drive storage, input/output facilities such as network interface devices, video devices, keyboard, mouse or touchscreen devices, etc.
  • multitasking multithreading
  • distributed e.g., cluster, peer-peer, cloud, etc.
  • each engine can be realized in a variety of physically realizable configurations, and should generally not be limited to any particular implementation exemplified herein, unless such limitations are expressly called out.
  • an engine can itself be composed of more than one sub-engines, each of which can be regarded as an engine in its own right.
  • each of the various engines corresponds to a defined autonomous functionality; however, it should be understood that in other contemplated embodiments, each functionality can be distributed to more than one engine.
  • multiple defined functionalities may be implemented by a single engine that performs those multiple functions, possibly alongside other functions, or distributed differently among a set of engines than specifically illustrated in the examples herein.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Cardiology (AREA)
  • Physiology (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Psychiatry (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Pulmonology (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

L'invention concerne des dispositifs et des procédés décrivant la détection simultanée de données pouvant être affichées sur un axe de temps commun pour une facilité d'interprétation. Un guide interprétatif peut être utilisé pour aider à l'analyse des données détectées pour fournir des diagnostics rapides et précis sans l'utilisation d'un équipement classique ou coûteux qui est typiquement trouvé uniquement dans des environnements hospitaliers ou cliniques. Un affichage à usage spécial simplifié et personnalisé, comprenant un guide interprétatif associé, facilite des diagnostics qui peuvent être effectués plus facilement, rapidement, efficacement et avec précision, améliorant les résultats de santé et l'accès à des soins de santé pour des patients. Selon des modes de réalisation, l'interprétation de telles données peut améliorer le diagnostic et peut être automatisée pour augmenter la sécurité.
PCT/US2018/031849 2017-05-09 2018-05-09 Évaluation de la fonction mécanique et de la viabilité de valvules cardiaques prothétiques au moyen d'une nouvelle technologie de détection WO2018208950A1 (fr)

Applications Claiming Priority (8)

Application Number Priority Date Filing Date Title
US201762602857P 2017-05-09 2017-05-09
US201762602858P 2017-05-09 2017-05-09
US62/602,857 2017-05-09
US62/602,858 2017-05-09
US201762602942P 2017-05-10 2017-05-10
US62/602,942 2017-05-10
US201762604365P 2017-07-05 2017-07-05
US62/604,365 2017-07-05

Publications (1)

Publication Number Publication Date
WO2018208950A1 true WO2018208950A1 (fr) 2018-11-15

Family

ID=64104919

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2018/031849 WO2018208950A1 (fr) 2017-05-09 2018-05-09 Évaluation de la fonction mécanique et de la viabilité de valvules cardiaques prothétiques au moyen d'une nouvelle technologie de détection

Country Status (1)

Country Link
WO (1) WO2018208950A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200289057A1 (en) * 2019-03-12 2020-09-17 Cardiac Pacemakers, Inc. Prosthetic heart valve assessment using heart sounds
EP4014881A1 (fr) * 2020-12-15 2022-06-22 Ravnovesje d.o.o. Dispositif de surveillance de données physiologiques et système comprenant un tel dispositif

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6524250B1 (en) * 2000-09-19 2003-02-25 Pearl Technology Holdings, Llc Fat layer thickness mapping system to guide liposuction surgery
US20080281168A1 (en) * 2005-01-13 2008-11-13 Welch Allyn, Inc. Vital Signs Monitor
US20130303922A1 (en) * 2010-12-13 2013-11-14 Scosche Industries, Inc. Heart rate monitor
US20140100465A1 (en) * 2012-10-05 2014-04-10 Korea Electronics Technology Institute Ecg sensing apparatus and method for removal of baseline drift in the clothing
US20150065814A1 (en) * 2012-10-15 2015-03-05 Rijuven Corporation Mobile front-end system for comprehensive cardiac diagnosis

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6524250B1 (en) * 2000-09-19 2003-02-25 Pearl Technology Holdings, Llc Fat layer thickness mapping system to guide liposuction surgery
US20080281168A1 (en) * 2005-01-13 2008-11-13 Welch Allyn, Inc. Vital Signs Monitor
US20130303922A1 (en) * 2010-12-13 2013-11-14 Scosche Industries, Inc. Heart rate monitor
US20140100465A1 (en) * 2012-10-05 2014-04-10 Korea Electronics Technology Institute Ecg sensing apparatus and method for removal of baseline drift in the clothing
US20150065814A1 (en) * 2012-10-15 2015-03-05 Rijuven Corporation Mobile front-end system for comprehensive cardiac diagnosis

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200289057A1 (en) * 2019-03-12 2020-09-17 Cardiac Pacemakers, Inc. Prosthetic heart valve assessment using heart sounds
EP4014881A1 (fr) * 2020-12-15 2022-06-22 Ravnovesje d.o.o. Dispositif de surveillance de données physiologiques et système comprenant un tel dispositif

Similar Documents

Publication Publication Date Title
EP3840642B1 (fr) Systèmes pour déterminer un état ou une condition physiologique ou biologique d'un sujet
US20180108440A1 (en) Systems and methods for medical diagnosis and biomarker identification using physiological sensors and machine learning
US20140243616A1 (en) Systems and methods for detecting cardiovascular disease
US20170188978A1 (en) System and method of measuring hemodynamic parameters from the heart valve signal
JP6443517B2 (ja) 生体情報測定装置および生体情報測定装置もしくは生体情報測定システムの作動方法
US20210166812A1 (en) Apparatus and methods for the management of patients in a medical setting
TW200526174A (en) Analysis of auscultatory sounds using single value decomposition
KR20160047838A (ko) 생체 신호 처리 방법 및 그 장치
Chowdhury et al. Machine learning in wearable biomedical systems
US20220005601A1 (en) Diagnostic device for remote consultations and telemedicine
Convertino et al. Wearable sensors incorporating compensatory reserve measurement for advancing physiological monitoring in critically injured trauma patients
WO2018208950A1 (fr) Évaluation de la fonction mécanique et de la viabilité de valvules cardiaques prothétiques au moyen d'une nouvelle technologie de détection
US10327648B2 (en) Blood vessel mechanical signal analysis
WO2020257609A1 (fr) Diagnostics et traitements pour une maladie cardiaque
US12023165B2 (en) Screening cardiac conditions using cardiac vibrational energy spectral heat maps
US20240065568A1 (en) Acousteomic sensing and monitoring using a human-centric intelligent acousteomic array
Bisgin et al. Thrilling AI–A novel, signal-based digital biomarker for diagnosing canine heart diseases
US20240188835A1 (en) System and method for non-invasive assessment of cardiovascular and pulmonary murmurs
US20230072872A1 (en) System and method of marking cardiac time intervals from the heart valve signals using a Near-Field Communication based patch biosensor
Sighvatsson et al. Wearable Heart Monitor
CN118119331A (zh) 用于将来自生物物理信号的视觉特征工程化以用于表征生理系统的方法和系统
CN118139576A (zh) 用于将来自生物物理信号的心脏波形特征工程化以用于表征生理系统的方法和系统
JP2024517992A (ja) Ａｂｐ信号の決定方法、及び、ａｂｐ信号の決定システム、並びにコンピュータプログラム製品
KR20210070574A (ko) 비접촉식 생체신호 측정 시스템

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18799282

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18799282

Country of ref document: EP

Kind code of ref document: A1