Abstract: Disclosed is a stethoscope digital adapter configured to enhance usability of an acoustic stethoscope. The stethoscope digital adapter may include a body comprising an exterior shell configured to form an interior space. Further, the body may include a microphone disposed in the interior space. Further, the microphone may be configured to convert an acoustic wave into an electrical sound signal. Further, the body may include an electrical interconnect electrically coupled to the microphone. Further, the electrical interconnect may be configured to be electrically coupled with an external electronic device configured to process the electrical sound signal. Further, the body may include a conduit attached to the exterior shell. Further, the stethoscope digital adapter may include a fastener attached to the body.

Abstract: A digital stethoscope includes a stethoscope housing defining a housing edge. The digital stethoscope also includes a surface region secured to the stethoscope housing at the housing edge, and a number of microphones. The digital stethoscope also includes a processing device disposed within the stethoscope housing and in communication with the microphones. The processing device receives the digital audio data from the microphones.

Abstract: An implantable medical device includes a plurality of electrodes to detect electrical activity, a motion detector to detect mechanical activity, and a controller to determine at least one electromechanical interval based on at least one of electrical activity and mechanical activity. The activity detected may be in response to delivering a pacing pulse according to an atrioventricular (AV) pacing interval using the second electrode. The electromechanical interval may be used to adjust the AV pacing interval. The electromechanical interval may be used to determine whether cardiac therapy is acceptable or whether atrial or ventricular remodeling is successful.

Abstract: This document discusses, among other things, systems and methods to receive physiologic information from a patient and to generate a heart failure status using the received physiologic information. Based on the received physiologic information, the generated heart failure status can be classified into at least one of a set of predetermined phenotype clusters.

Abstract: A patient monitoring hub can communicate bidirectionally with external devices such as a board-in-cable or a dongle. Medical data can be communicated from the patient monitoring hub to the external devices to cause the external devices to initiate actions. For example, an external device can perform calculations based on data received from the patient monitoring hub, or take other actions (for example, creating a new patient profile, resetting baseline values for algorithms, calibrating algorithms, etc.). The external device can also communicate display characteristics associated with its data to the monitoring hub. The monitoring hub can calculate a set of options for combined layouts corresponding to different external devices or parameters. A display option may be selected for arranging a display screen estate on the monitoring hub.

Abstract: Discloses herein is an electronic stethoscope, including a connector, wherein a membrane type auscultation head is in threaded connection with one end of the connector, a piezoelectric sheet is fixedly mounted in the membrane type auscultation head, a grip is in threaded connection with the other end of the connector, a circuit board is clamped in the grip, the circuit board is electrically connected to the membrane type auscultation head, a storage battery is electrically connected to one side of the circuit board, the storage battery is clamped in the grip, a microswitch and a loudspeaker are mounted on the other side of the circuit board in an electrically connected manner, a main silicone key body is clamped in the grip, and the main silicone key body is attached to the microswitch.

Abstract: An anomaly detection technique which realizes high accuracy while reducing cost required for normal model learning is provided. An anomaly detection apparatus includes an anomaly degree estimating unit configured to estimate an anomaly degree indicating a degree of anomaly of anomaly detection target equipment from sound emitted from the anomaly detection target equipment (hereinafter, referred to as anomaly detection target sound) based on association between a first probability distribution indicating distribution of normal sound emitted from one or more pieces of equipment different from the anomaly detection target equipment and normal sound emitted from the anomaly detection target equipment (hereinafter, referred to as normal sound for adaptive learning).

Abstract: A method of obtaining a clinical assessment of a user of a user device may include obtaining, by the user device and from a hand-held diagnostic device configured to communicate with the user device, first diagnostic information of the user obtained by one or more sensors of the hand-held diagnostic device; obtaining, by the user device, second diagnostic information based on a user input of the second diagnostic information via the user device; obtaining, by the user device and using an artificial intelligence (AI) model, the clinical assessment based on the first diagnostic information and the second diagnostic information; and displaying, by the user device, the clinical assessment to permit the user to visualize the clinical assessment.

Abstract: An apparatus for locating a source of vibrational cardiac energy within a human, includes a data processing system configured to accept vibrational cardiac data collected by at least three transducers during a plurality of heart cycles. A computer readable medium containing executable computer program instructions which, when executed by the data processing system, cause the data processing system to perform steps that include, performing a time-to-frequency transformation on the vibrational cardiac data acquired within at least a portion of the heart cycles. The time-to-frequency transformation is applied to the vibrational cardiac data acquired synchronously from each transducer to obtain a plurality of complex frequency spectra. The steps include identifying a vernier band (VB) of frequency associated with a feature derived from the plurality of complex frequency spectra.

Abstract: A system and method for monitoring heart function based on heart sounds (HS) is provided. The system includes electrodes configured to sense electrical cardiac activity (CA) signals over a period of time. An HS sensor is configured to sense HS signals over the period of time. The system includes memory to store specific executable instructions and includes one or more processors that, when executing the specific executable instructions, is configured to: identify a characteristic of interest (COI) of a heartbeat from the CA signals. The processors overlay a HS search window onto an HS segment of the HS signals based on the COI from the CA signals and calculate a center of mass (COM) for at least one of S1 or S2 HS based on the HS segment of the HS signals within the search window to obtain a corresponding at least one of S1 COM or S2 COM.

Abstract: Provided are a biological sound measurement device capable of detecting contact with a body surface of a living body with a simple configuration, a control method for the biological sound measurement device, and a non-transitory recording medium storing a control program for the biological sound measurement device. The biological sound measurement device (1) includes: a measuring unit (3) that detects a biological sound of a living body in a state of contact with a body surface S of the living body; and a contact state determination unit (41) that determines whether or not a contact state is active in which the measuring unit (3) is in contact with the body surface S, based on a change in a sound pressure level of sounds detected by the measuring unit (3).

Abstract: An apparatus for estimating blood pressure is provided. The apparatus for estimating blood pressure according to an example embodiment includes: a sensor configured to measure a photoplethysmogram (PPG) signal from an object; and a processor configured to detect a position of a dicrotic notch based on a local maximum point and a local minimum point of a second-order derivative signal of the PPG signal, to obtain a first value and a second value from a first section and a second section of the PPG signal divided based on the dicrotic notch of the PPG signal, to obtain a pulse pressure feature value based on the first value and the second value, and to estimate blood pressure based on a variation in the obtained pulse pressure feature value compared to a reference pulse pressure feature value.

Abstract: Acoustic touch and/or force sensing system architectures and methods for acoustic touch and/or force sensing can be used to detect a position of an object touching a surface and an amount of force applied to the surface by the object. The position and/or an applied force can be determined using time-of-flight (TOF) techniques, for example. Acoustic touch sensing can utilize transducers (e.g., piezoelectric) to simultaneously transmit ultrasonic waves along a surface and through a thickness of a deformable material. The location of the object and the applied force can be determined based on the amount of time elapsing between the transmission of the waves and receipt of the reflected waves. In some examples, an acoustic touch sensing system can be insensitive to water contact on the device surface, and thus acoustic touch sensing can be used for touch sensing in devices that may become wet or fully submerged in water.

Abstract: A medical device (20) includes a case (32), having a front surface that is configured to be brought into contact with a body of the living subject (24). A microphone (34) is contained in the case and configured to sense acoustic waves emitted from the body and to output an acoustic signal in response thereto. A proximity sensor (56) is configured to output a proximity signal indicative of contact between the front surface and the body. At least one speaker (49) is configured to output audible sounds. Processing circuitry (50) is coupled to detect, in response to the proximity signal, that the front surface is in contact with the body, and in response to the detected contact, to process the acoustic signal so as to generate an audio output and to convey the audio output to the at least one speaker.

Abstract: An intelligent and real-time cardio-pulmonary screening device (100) is disclosed. The device comprises a housing that encloses a body, said body comprising: a display unit (101); a plurality of light emitting diode (LED) indicators (102, 103); a first toggle switch (104); a second toggle switch (105); a plurality of volume controls (106, 107); a third toggle switch; an output port (109); a switch (110); a charging port (111); a temperature sensor; a transducer unit (112); and an artificial intelligence module. The artificial intelligence module analyses the sounds received in real-time and presents the results in the display unit (101), as well as in the plurality of the LED indicators (102, 103); it comprises an artificial intelligence processor that is configured to run machine learning algorithms on the device (100), with said artificial intelligence module syncing from and to the cloud when connected to internet.

Abstract: This document discusses, among other things, systems and methods to determine an indication of contractility of a heart of a patient using received physiologic information, and to determine blood pressure information of the patient using the heart sound information and the determined indication of contractility of the heart. The system can include an assessment circuit configured to determine an indication of contractility of a heart of the patient using first heart sound (S1) information of the patient, and to determine blood pressure information of the patient using second heart sound (S2) information of the patient and the determined indication of contractility of the heart.

Abstract: Systems and methods are provided for managing patient assistance requests in a healthcare facility, documenting items (e.g., minor, routine, and/or frequently-performed items) in association with a patient's records in an Electronic Healthcare Information System, and cancelling patient requests for assistance. Indications that requests for assistance have been received and/or are being addressed by an appropriate healthcare team member may be audibly output from a speaker associated with a personal assistant device. Healthcare team members may verbally provide items for documentation in association with a patient's medical records, the items for documentation being received by a listening component of a personal assistant device and transmitted to an EHIS for documentation.

Abstract: According to certain described aspects, multiple acoustic sensing elements are employed in a variety of beneficial ways to provide improved physiological monitoring, among other advantages. In various embodiments, sensing elements can be advantageously employed in a single sensor package, in multiple sensor packages, and at a variety of other strategic locations in the monitoring environment. According to other aspects, to compensate for skin elasticity and attachment variability, an acoustic sensor support is provided that includes one or more pressure equalization pathways. The pathways can provide an air-flow channel from the cavity defined by the sensing elements and frame to the ambient air pressure.

Abstract: Systems, devices, and methods for monitoring and assessing blood glucose level in a patient are discussed. An exemplary system receives physiologic information from a patient using an ambulatory medical device. The physiologic information is correlated to, and different from, a direct glucose level measurement. The system determines a glucose index indicative of an abnormal blood glucose level using the received physiologic information by the two or more physiologic sensors. The system may use the glucose index to initiate or adjust a therapy, or to trigger a glucose sensor, separate from the two or more physiologic sensors, to directly measure blood glucose concentration.

Abstract: This invention describes a magnetoresistive inertial sensor chip, comprising a substrate, a vibrating diaphragm, a magnetic field sensing magnetoresistor and at least one permanent magnet thin film. The vibrating diaphragm is located on one side surface of the substrate. The magnetic field sensing magnetoresistor and the permanent magnet thin film are set on the surface of the vibrating diaphragm displaced from the base of the substrate. A contact electrode is also arranged on the surface of the vibrating diaphragm away from the base of the substrate. The magnetic field sensing magnetoresistor is connected to the contact electrode through a lead. The substrate comprises a cavity formed through etching and either one or both of the magnetic field sensing magnetoresistors and the permanent magnet thin film are arranged in a vertical projection area of the cavity in the vibrating diaphragm portion.

Abstract: Embodiments disclosed herein generally relate to systems and methods for communicating data with a tone-emitting device. A system for communicating an inaudible tone includes a tone-emitting device. The tone-emitting device includes a tone-emitting speaker for emitting an inaudible tone and a tone-determining computing device communicatively coupled to the tone-emitting speaker. The tone-determining computing device includes a non-transitory computer-readable medium that stores logic that, when executed by the tone-determining computing device, causes the tone-determining computing device to receive data related to a characteristic of an object, encode an inaudible tone that represents at least a portion of the data and send instructions to the tone-emitting speaker for outputting the inaudible tone.

Abstract: A occupant detection and monitoring system has a sensor unit having a radio wave transmitter, a radio wave receiver, and a wireless transmitter configured to detect and receive vital signs of an occupant; a user interface having a microcontroller, a wireless receiver configured to receive the wireless signals transmitted from the sensor unit, a means for user input, and a network card; and a means for alerting occupants and third-parties to a triggering event; wherein the microcontroller, based upon logic, activates the alerting means at the triggering event. The sensor unit may be a camera that detects the presence of an individual and register their unique heart rhythm for identification purposes. This camera can be installed at the entry points of a home, behind the counter of a business near a cash register or at a bank or any other place that desires to use surveillance as a form of security. The sensor unit may be a light bulb that comprises the components of the sensor unit.

Abstract: An electronic stethoscope system comprising a device to capture an acoustic heart signal from a patient and a neural network to classify the data into heart sound categories to provide time series sound category data comprising, for each of a succession of time intervals, category probability data representing a probability of the acoustic signal falling into each of the categories. The stethoscope also includes one or more heart state models each having a sequence of heart cardiac cycle states, a system to fit the time series sound category data to the models and determine timing data for the sequence of heart states and a confidence value for the model fit, and an output to output one or both of a model fit indication dependent upon the confidence value and an indication of the timing data.

Abstract: A digital stethoscope includes a stethoscope housing defining a housing edge. The digital stethoscope also includes a surface region secured to the stethoscope housing at the housing edge, and a number of microphones. The digital stethoscope also includes a processing device disposed within the stethoscope housing and in communication with the microphones. The processing device receives the digital audio data from the microphones.

Abstract: A tele-health apparatus includes a telephone having a microphone, an auscultation piece to acquire sounds, and a solid medium acoustically coupling the auscultation piece to the microphone. The auscultation piece is part of a stethoscope, and the solid medium is a windpipe of the stethoscope. The tele-health apparatus also includes an otoscope operable to be disposed in front of a camera of the telephone. A clip holds the stethoscope and the otoscope, and is fixed to the phone. Software modules installed in the telephone enable the tele-health apparatus to engage a user in a two-way audio and/or video consultation with a physician at a remote device in real-time.

Abstract: Provided is a biological sound measurement device capable of smoothly performing tasks from measurement initiation to result confirmation, that includes a sound measurement unit including a contact surface configured to be brought into contact with the body surface of a subject, a gripping portion supporting the sound measurement unit and configured to be gripped by a measurer, and a display unit provided to the gripping portion and configured to display an analysis result of a biological sound measured by the sound measurement unit. The gripping portion is configured to be gripped by the measurer in a state in which an index finger of the measurer is placed on a back surface of the sound measurement unit, and the display unit is provided on a surface of the gripping portion on the body surface side in a state in which the contact surface is in contact with the body surface.

Abstract: Predicting gastrointestinal impairment may involve obtaining intestinal sounds of a patient to generate audio data, identifying predefined spectral events in the audio data that are predictive of subsequent gastrointestinal impairment, the spectral events being defined by predefined parameters, and predicting the likelihood of subsequent gastrointestinal impairment relative to the identified spectral events.

Abstract: Aspects of the subject technology relate to a system including a reference device, a measurement device and a processor. The measurement device provides a three-dimensional (3-D) point map corresponding to first positions of a plurality of selected points on a torso of a user. The processor determines a shape of the torso based on the 3-D point map. The measurement device is sequentially placed on the plurality of selected points, and the 3-D point map represents the first positions of the plurality of selected points relative to a second position associated with a location in 3-D space of the reference device.

Abstract: A system for sterilizing and wireless tethering of a stethoscope includes a portable electronic device configured to be coupled to a stethoscope and having a wireless transmitter configured to transmit a signal. The system further includes an enclosure defining a cavity for housing the stethoscope. The enclosure includes at least one light source configured to emit light at a wavelength designed to damage or destroy microbes. The enclosure further includes a wireless receiver configured to receive the signal transmitted by the wireless transmitter of the portable electronic device. The enclosure further includes a controller coupled to the wireless receiver and configured to determine a notification event in response to the portable electronic device being further from the enclosure than a predetermined distance based on the signal received by the wireless receiver.

Abstract: Systems and methods for quantifying the duration of S1 and/or S2 heart sounds, in order to identify markers of heart failure and/or lung failure, are provided. Cardiac cycles containing S1 and S2 sound can be identified in a phonocardiogram and normalized. In order to quantify S1 and S2 sound length, the envelope of the absolute value of the signal can be obtained for each cycle. The sound waves of two components can be separated using the identified single sound wave. These features can be correlated to measures of heart failure and/or lung failure.

Abstract: A method of determining a fitness level of user with a physiological sensor. The method includes measuring a physiological value of the user with the physiological sensor, correlating the measured physiological value into a measurement of the user's respiratory rate and tidal volume, calculating a second respiratory rate value using the measured tidal volume, calculating a breathing efficiency (BE) ratio based on a comparison of the user's measured respiratory rate and the calculated second respiratory rate value, correlating the calculated BE ratio to a predetermined threshold, and assigning a classification to the user based on the calculated BE ratio. The classification is indicative of the user's respiratory function performance.

Abstract: A system for monitoring heart activity may provide a power source, digital storage, a processor, a main body with an alignment mechanism facilitating proper placement, and one or more microphones for receiving audio signals and positioned for placement at auscultatory areas. The alignment mechanism may be a dip, depression, notch, or combinations thereof that align the system centrally on the sternum, suprasternal notch, or jugular notch. Further, the audio signals from the microphones may be monitored or recorded as individual tracks corresponding to different auscultatory areas. The auscultatory areas may be selected from an aortic area, pulmonic area, tricuspid area, mitral area, Erb's point, first alternate tricuspid area, and/or second alternate tricuspid area.

Abstract: Embodiments of the subject matter include a heart lung machine (HLM), including a plurality of actuators and a peripheral processing unit configured to receive a set of parameter data from the plurality of actuators. The HLM also may include a peripheral display device configured to present a subset of the set of parameter data and a control assembly comprising a control display device configured to present a user interface having a representation of a parameter value and an associated indication, where at least a portion of the associated indication overlaps at least a portion of the representation of the parameter value.

Abstract: Embodiments of the present disclosure relate to detecting implantable medical device orientation changes. In an exemplary embodiment, a medical device having a processor, comprises an acceleration sensor and memory. The acceleration sensor is configured to generate acceleration data that comprises a plurality of acceleration measurements. The memory comprises instructions that when executed by the processor, cause the processor to: obtain the acceleration data from the acceleration sensor; and determine, based on the acceleration data, that the medical device has flipped.

Abstract: Certain aspects of the present disclosure provide methods and apparatus for managing an esophagus of a subject during a medical procedure, such as cardiac tissue ablation or bronchial tissue ablation. Managing the esophagus may include displacing the esophagus, imaging the esophagus, and/or measuring temperature at one or more locations inside the esophagus. One example esophageal management system generally includes a tube configured for insertion through a mouth and into the esophagus of the subject. The tube generally includes a first port located at a proximal end of the tube and in fluid communication with a distal portion of the tube via a first path, a second port located at the proximal end of the tube, and a third port located between the proximal end of the tube and a distal end of the tube and in fluid communication with the second port via a second path.

Abstract: A method of determining a fitness level of user with an acoustic measurement device configured to measure sound associated with airflow through a mammalian trachea. The acoustic measurement device is in communication with a controller having processing circuitry. The method includes correlating the measured sound into a measurement of the user's respiratory rate and tidal volume; calculating a second respiratory rate value using the measured tidal volume; calculating a breathing efficiency (BE) ratio based on a comparison of the user's measured respiratory rate and the calculated second respiratory rate value; correlating the calculated BE ratio to a predetermined threshold; and assigning a classification to the user based on the calculated BE ratio. The classification is indicative of the user's respiratory function performance.

Abstract: A neurostimulation system provides for capture verification and stimulation intensity adjustment to ensure effectiveness of vagus nerve stimulation in modulating one or more target functions in a patient. In various embodiments, stimulation is applied to the vagus nerve, and evoked responses are detected to verify that the stimulation captures the vagus nerve and to adjust one or more stimulation parameters that control the stimulation intensity.

Abstract: This document describes methods and materials for improving the delivery of electroporation. For example, this document describes methods and devices for delivering electroporation while mitigating risks of ventricular fibrillation.

Abstract: Each conductor of a plurality of insulated conductors of a wiring harness extends between, and electrically connects, a corresponding terminal of a first electrical connector to either a corresponding terminal of an electrical connector jack of a plurality of electrical jacks located along the wiring harness, or to a corresponding terminal of a corresponding auscultatory sound-or-vibration sensor of the plurality of auscultatory sound-or-vibration sensors. The plurality of insulated conductors are organized in a plurality of distinct branches, each distinct branch originating either from the first electrical connector or from another portion of the wiring harness, and the locations of the plurality of distinct branches, in cooperation with the plurality of electrical jacks, if present, are implicitly suggestive of a corresponding location of the corresponding auscultatory sound-or-vibration sensor on a thorax of a test subject.

Abstract: This document discusses, among other things, systems and methods to determine an indication of heart failure with preserved ejection fraction (HFpEF) of a subject using a determined change in cardiac acceleration information of the subject at exertion relative to cardiac acceleration information of the subject at rest. The system can include a signal receiver circuit configured to receive cardiac acceleration information of a subject and exertion information of the subject, and an assessment circuit configured to determine the change in cardiac acceleration information of the subject at exertion relative to cardiac acceleration information of the subject at rest, and to determine an indication of HFpEF of the subject using the determined change in cardiac acceleration information.

Abstract: An auscultatory sound signal from at least one auscultatory sound-or-vibration sensor is segmented into a plurality of associated heart cycle segments responsive to associated R-peak locations of an electrographic envelope signal representing an envelope response to an even power of an associated electrographic signal from an ECG sensor. A representation an envelope responsive to an even power of said auscultatory sound signal within said at least one heart cycle is locally modeled about at least a second peak to provide for locating the start of diastole of said at least one heart cycle.

Abstract: Systems and methods are described herein for evaluation and adjustment of a left ventricular assist device (LVAD). The systems and methods may utilize at least a plurality of external electrodes to monitor cardiac electrical activity before and during LVAD therapy. The cardiac electrical activity as well as other information such cardiac sound information may be used to determine and adjust one or more LVAD output parameters such as pump speed.

Abstract: Methods, systems and storage medium for separating a target signal from noise are disclosed. A method comprises providing a plurality of input signals, each of the plurality of input signals comprising the target signal; synchronizing the plurality of input signals; and separating the plurality of synchronized input signals into the target signal and the noise.

Abstract: A measurement apparatus for measuring biological information includes a sensor that executes selectively at least a first detection mode or a second detection mode, and a controller. The controller controls switching to the second detection mode based on output of the sensor while the sensor is in the first detection mode.

Abstract: A fetal phonocardiogram system featuring an array of acoustic sensors designed to be temporarily affixed to a pregnant patient to convert the vibrations associated with a fetal heartbeat and/or fetal movement into a signal. The signal can be amplified and transferred to a processing element for filtering non-fetal sounds in order to resolve the fetal heartbeat. The filtered signal can be used in conjunction with an array of multiple acoustic sensors to locate a fetal position relative to the array.

Abstract: According to one embodiment, an electrocardiographic (ECG) waveform timing detector includes an ECG waveform receiving circuit, a threshold value determining circuit, and a comparator. The threshold value determining circuit includes a heart rate calculating circuit, a threshold value setting circuit, and a comparing/determining circuit. The heart rate calculating circuit calculates the heart rate based on ECG waveform received by the ECG waveform receiving circuit. The threshold value setting circuit sets a threshold value. The comparing/determining circuit compares the heart rate with the number of R wave detection triggers detected using the threshold value to determine a threshold value for R wave detection trigger. The comparator compares the ECG waveform output from the ECG waveform receiving circuit with the threshold value for R wave detection trigger to output an R wave detection trigger.

Abstract: A computer implemented method and system for detecting arrhythmias in cardiac activity are provided. The method is under control of one or more processors configured with specific executable instructions. The method obtains cardiac activity (CA) signals at the electrodes of an implantable medical device (IMD) in connection multiple cardiac beats and with different IMD orientations relative to gravitational force. The method obtains acceleration signatures at a sensor of the IMD that are indicative of heart sounds generated during the cardiac beats. The method obtains device location information at the IMD, with respect to the gravitational force during the cardiac beats. The method groups the acceleration signatures associated with the first and second set of cardiac beats into the corresponding one of first and second posture bins based on the device location information.

Abstract: A method for real-time vascular modeling and assessment is disclosed. Modeling, in some embodiments, comprises receiving a plurality of 2-D angiographic images of a portion of a vasculature of a subject, and processing the images to automatically detect 2-D features, for example, paths along vascular extents, which are projected into 3-D to determine homologous features among blood vessels and construct 3-D vascular extents and determine other vascular characteristics. Assessment, in some embodiments, comprises processing models selectively different from one another to produce one or more vascular indexes which indicate a diagnostic preference, for example, to perform a medical intervention such as a stent implantation. Speed is achieved, for example, by the method being optimized for determining the effects of a medical intervention. In some embodiments, results are produced quickly enough to allow use of the method to perform PCI within the same catheterization used to perform diagnostic imaging.

Abstract: A disease diagnosis system including a processor and a storage device for storing a neural network and using a biometric image and the neural network, the disease diagnosis system including a micro-neural network for receiving a first tile included in the biometric image through a first input layer, and including a plurality of first layers and an output layer, and a macro-neural network for receiving a macro-tile including the first tile and at least one or more second tiles adjacent to the first tile through a second input layer, and including a plurality of second layers and the output layer, in which the output layer includes at least one state channel indicating a state of a disease of a biological tissue corresponding to the first tile.

Abstract: A heartbeat detection device includes a bone conduction microphone that converts, into a signal, displacement on the body surface of a user in a thickness direction of the body of the user, and an extractor that extracts a first frequency component and a second frequency component which are included in the signal. The first frequency component is based on audio information of the user, and the second frequency component is based on heartbeat information of the user. The heartbeat detection device is capable of estimating the physical and psychological state of the user based on the heartbeat information by extracting both the audio information and the heartbeat information, from a signal that has been output by the bone conduction microphone.