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.

Abstract: A mobile device, having a processor, includes an accelerometer configured to generate acceleration data, the acceleration data including a plurality of acceleration measurements. The mobile device also includes a memory having embodied thereon computer-executable instructions that are configured to, when executed by the processor, cause the processor to: obtain the acceleration data from the accelerometer; and generate, based on the acceleration data, heart sound data, the heart sound data including data associated with one or more heart sounds.

Abstract: A vibration transducer for sensing vibrations includes a first flexible triboelectric member, a second flexible triboelectric member, a plurality of attachment points, a first electrode and a second electrode. The first flexible triboelectric member includes a first triboelectric layer and a material being on a first position on a triboelectric series. A conductive layer is deposited on the second side thereof. The second flexible triboelectric member includes a second triboelectric layer and a material being on a second position on the triboelectric series that is different from the first position on the triboelectric series. The second triboelectric member is adjacent to the first flexible triboelectric member. When the first triboelectric member comes into and out of contact with the second triboelectric member as a result of the vibrations, a triboelectric potential difference having a variable intensity corresponding to the vibrations can be sensed between the first and second triboelectric members.

Abstract: A system and method for automatically analyzing heart failure in a patient, including collecting physiological data from a patient using at least a first sensor and a second sensor to collect two or more sensor measurements, and calculating a first composite value based on at least a first sensor measurement wherein the first composite value is an indication of a likelihood that the patient's heart failure status has changed. If the first composite value is outside of a first specified range, then a second composite value is calculated based on at least a second sensor measurement, wherein the second composite value is an indication of a likelihood that the patient's heart failure status has changed. If the second composite value is outside of a second specified range, then an alert of change in heart failure status is generated.

Abstract: A method of monitoring respiration with an acoustic measurement device, the acoustic measurement device having a sound transducer, the sound transducer configured to measure sound associated with airflow through a mammalian trachea, the method includes correlating the measured sound into a measurement of tidal volume and generating at least one from the group consisting of an alert and an alarm if the measured tidal volume falls outside of a predetermined range.

Abstract: A computer-implemented method, computerized apparatus and computer program product for activity recognition using adaptive window size segmentation of sensor data stream. A data stream generated by one or more sensors is obtained. A frequency analysis of the data in a first segment of the data stream is performed. A size of a second segment is determined based on the frequency analysis. Activity recognition is performed for the second segment by extracting one or more features of the data therein and applying a machine learning process on the extracted features to obtain a classification of the data into an activity class.

Abstract: A system for monitoring a fetal heartbeat sound has a sensor matrix adapted to be placed adjacent to a fetus, a processor for receiving signals transmitted by the sensor matrix, a processor for receiving signals transmitted by the sensor matrix, and a display connected to the processor so as to provide a humanly perceivable indication of the heartbeat sound. The sensor matrix has a plurality of sensors of which at least one of which is facing the fetus. The processor identifies a fetal heartbeat sound from among other sounds. The sensor array is affixed to a wearable article that is adapted to be worn by mother.

Abstract: A heartbeat detection device includes a peak search unit (4) for searching for one of a peak at which a value M obtained from a sampling data sequence of an electrocardiographic waveform of a living body changes from an increase to a decrease and a peak at which the value M changes from a decrease to an increase, and a heartbeat time determination unit (5) for checking the value M in a predetermined time domain before a time of the peak and the value M in a predetermined time domain after the time of the peak, and setting the time of the peak as a heartbeat time if differences between the value M at the time of the peak and the values M in the predetermined time domains are not smaller than a predetermined amount.

Abstract: Described is a multi-input cognitive signal processor (CSP) for estimating time-difference-of-arrival (TDOA) of incoming signals. The multi-input CSP receives a mixture of input signals from an antenna a and an antenna b. The multi-input CSP predicts and temporally de-noises input signals a and b received from antennas a and b, respectively, using an input corresponding to each input signal, resulting in de-noised state vectors for input signals a and b. Using the de-noised state vectors for input signals a and b, cross-predicting and spatially de-noising the other of the de-noised state vectors for input signals a and b. TDOA values of signal pulses to each of antennas a and b are estimated and converted into estimated angles of arrival for each signal pulse.

Abstract: A sensor unit capable of protecting a piezoelectric element and detecting vibration and sound is provided. The sensor unit comprises a sheet-like piezoelectric element having a porous layer, and a sound propagation sheet covering at least one face of the piezoelectric element and permitting transmission of sound from a first face toward a second face of the sound propagation sheet. A difference in acoustic pressure level between the sound incident on the sound propagation sheet and the transmitted sound is preferably no greater than 10 dB. A surface density of the sound propagation sheet is preferably from 0.03 g/m2 to 100 g/m2. The sound propagation sheet is preferably flexible and preferably has voids. The sensor unit preferably further comprises a sound insulation sheet covering another face of the piezoelectric element and substantially preventing transmission of sound from a second face toward a first face of the sound insulation sheet.

Abstract: Broadly speaking, embodiments of the present invention provide a device, systems and methods for capturing sounds, generating a sound model (or “sound pack”) for each captured sound, and identifying a detected sound using the sound model(s). Preferably, a single device is used to capture a sound, store sound models, and to identify a detected sound using the stored sound models.

Abstract: An R-wave of a heartbeat signal accompanied by periodic fluctuation is detected to obtain the average value of an RR interval. Further, a waveform of a heart sound signal, which periodically fluctuates in synchronization with the heartbeat signal, is forcibly repositioned at an interval equivalent to the average value of the RR interval. After performing reposition, noise is removed by using orthogonal transformation and orthogonal inverse transformation, so that the position of obtained waveform is restored to its original position.

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: Techniques for transmitting diagnostic information stored in an implantable medical device (IMD) based on patient hospitalization are described. For example, the IMD may transmit higher resolution diagnostic information to a clinician and/or an external device during a hospitalization period to aid the clinician in evaluating heart failure treatment and when discharge is proper. This higher resolution diagnostic information may include one or more patient metrics automatically generated and transmitted by the IMD at least once every two hours. During a post-hospitalization period, the IMD may transmit lower resolution diagnostic information to a clinician that indicates a risk level of re-hospitalization. The lower resolution diagnostic information may include the risk level and/or patient metrics once a day, for example. In this manner, the IMD transmitted diagnostic information may be tailored to the specific heart failure monitoring needed by the patient.

Abstract: Systems and methods for detecting events indicative of worsening using heart sounds are disclosed. A system can include a signal sensor circuit to sense a heart sound (HS) signal. The system can detect at least first and different second HS components using the HS signal, and generate respective first and second HS metrics. The system can determine a trend indicator for the first or second HS metric, and selectively generate one or more composite HS metrics using the first and second HS metrics, according to the trend indicator indicating a growing or decay trend. The system can include a heart failure (HF) event detector to produce a HF status using the composite HS metrics, and output an indication of the HF status, or deliver therapy according to the HF status.

Abstract: An apparatus comprises a cardiac signal sensing circuit configured to sense a plurality of intrinsic cardiac signals using a plurality of cardiac pacing sites, a heart sound sensing circuit, a stimulus circuit configured to provide an electrical cardiac pacing stimulus to the plurality of pacing sites, and a control circuit electrically coupled to the cardiac signal sensing circuit and the stimulus circuit. The control circuit includes a pacing site locating circuit configured to generate an indication of a preferred pacing site as one of a) a subset of the respective cardiac pacing sites selected using the intrinsic ventricular activation time interval value, from which subset the preferred pacing site is selected using the heart sound characteristic value; or b) a subset of the respective cardiac pacing sites selected using the heart sound characteristic value, from which subset the preferred pacing site is selected using the ventricular activation time interval value.

Abstract: An add-on device and method for an Endo-Tracheal Tube (ETT), the add-on device including a lengthy body having a major arc-shaped cross section sized and shaped to tightly fit over an ETT, at least one longitudinal cavity passing along the lengthy body, including a distal suction cavity ending with a suction inlet at a distal end of the lengthy body; and a distal suction outlet channel extending from a proximal end of the lengthy body, the channel is a continuous extension of the distal suction cavity and configured to provide suction to the distal suction cavity. The add-on device senses moisture at a distal end of the add-on device, and in case of detection of excessive wetness, provides suction to the distal end of the device through a cavity passing along the device, the suction is provided via a suction outlet channel extending from a proximal end of the device.

Abstract: Systems and methods for tracking heart sounds are disclosed. The system can include a heart sound (HS) receiver circuit configured to receive HS information, and a HS analyzer circuit coupled to the HS receiver circuit. The HS analyzer circuit can determine a HS timing parameter of a specified HS component. The HS component includes at least a portion of one of S1 S2, S3, or S4 heart sound. The HS analyzer circuit can include first and second feature detector circuits each configured to respectively detect first and second one or more candidate features. The HS analyzer circuit can also include a feature selection circuit that can produce an inter-categorical metric, and determine first and second selected features using at least the inter-categorical metric. A HS recognition circuit can determine the timing parameter of the HS component using the first and second selected features.

Abstract: An earpiece assembly has a pair of earpieces, a pair of foldable flex spring members, and a manifold with each foldable flex spring member connecting one of the earpieces to the manifold. A drum assembly has a diaphragm mounted therein and a tube extending therefrom with the diaphragm being particularly adapted to expand and contract in response to pressure changes within a patient when the drum assembly is in proximity to the patient. A stem assembly has a housing, a pressure sensor extending from the housing, a circuit board positioned within the housing, and a light source connected to the circuit board and extending from the housing. The stem assembly connects the manifold to the tube to connect the earpiece assembly to the drum assembly.