Abstract: The present disclosure generally relates to systems and methods for detecting and/or treating obstructive sleep apnea (OSA) experienced by a subject, using one or more implanted or external sensors. In some aspects, the systems and methods described herein are configured to classify the human subject as being awake or asleep by comparing a calculated standard deviation and/or variance of one or more respiratory parameters against a predetermined threshold and to control the delivery of stimulation based on this classification.

Abstract: Methods for electrical modulation of inflammation or serum TNF levels in a subject.

Abstract: A device includes a physiological sensor having a plurality of sensing electrodes, and a signal combining chip having a plurality of input channels, a waveform generator, a summing circuit, and an output channel. The plurality of input channels are configured to receive a plurality of voltage signals. Each input channel is configured to receive a respective one of the plurality of voltage signals from a respective one of the plurality of sensing electrodes. The waveform generator is configured to generate a set of modulation signals, each of which modulates a corresponding voltage signal of the plurality of voltage signals to generate a corresponding encoded voltage signal and form a set of encoded voltage signals. The summing circuit is configured to superimpose the set of encoded voltage signals to form a combined voltage signal that is outputted through the output channel.

Abstract: Waveforms for a stimulator device, and methods and circuitry for generating them, are disclosed having high- and low-frequency aspects. The waveforms comprise a sequence of pulses issued at a low frequency which each pulse comprising first and second charge-balanced phases. One or both of the phases comprises a plurality a monophasic sub-phase pulses issued at a high frequency in which the sub-phase pulses are separated by gaps. The current during the gaps in a phase can be zero, or can comprise a non-zero current of the same polarity as the sub-phase pulses issued during that phase. The disclosed waveforms provide benefits of high frequency stimulation such as the promotion of paresthesia free, sub-threshold stimulation, but without drawbacks inherent in using high-frequency biphasic pulses.

Abstract: A computer-implemented method is disclosed. The method includes determining whether one or more messages have been received while a user performs a treatment plan. The one or more messages may pertain to at least one of a user and a usage of the electromechanical machine by the user. The electromechanical machine may be configured to be manipulated by the user while the user is performing a treatment plan. The method also includes, responsive to determining that the one or more messages have not been received, determining, using one or more machine learning models, one or more preventative actions to perform. The method also includes causing the one or more preventative actions to be performed.

Abstract: Systems, apparatus, articles of manufacture, and methods are disclosed to detect a pace pulse in an electrocardiogram (ECG) signal. An example apparatus includes programmable circuitry configured to execute instructions to: identify a leading edge of a pulse in an input signal based on an amplitude change; identify a transition time of the leading edge of the pulse; validate the leading edge of the pulse based on the amplitude change and transition time; identify a trailing edge of the pulse; determine a width of the pulse between the leading edge and the trailing edge; and validate the pulse based on the width.

Abstract: Systems and method for seizure detection. A seizure detection device utilizes frequency discrimination, time series features, and machine learning clustering algorithms to distinguish between the EEG signal of those experiencing a seizure compared to those who are not experiencing a seizure.

Abstract: Methods and devices for treating nasal airways are provided. Such devices and methods may improve airflow through an internal and/or external nasal valve, and comprise the use of mechanical re-shaping, energy application and other treatments to modify the shape, structure, and/or air flow characteristics of an internal nasal valve, an external nasal valve or other nasal airways.

Abstract: A system for verifying a candidate pathologic episode of a patient is provided that includes an accelerometer configured to be implanted in the patient. The accelerometer is configured to obtain accelerometer data along at least one axis. The system also includes a memory configured to store program instructions, and one or more processors that, when executing the program instructions, are configured to obtain accelerometer data. The one or more processors are also configured to determine a plurality of control three-dimensional point vectors related to the accelerometer data, and obtain a biological signal and identify a candidate pathologic episode based on the biological signal. The one or more processors are also configured to analyze the plurality of control three-dimensional point vectors to identify a physical action experienced by the patient, and verify the candidate pathologic episode based on the physical action.

Abstract: An implantable neuro-modulator device, including a hermetically sealed housing, wherein an antenna for communicating with external devices and/or for wirelessly receiving electrical energy is positioned within the housing, wherein a major part of the housing is electromagnetically transparent to radiation in the frequency range below 20 MHz, in particular between 5 and 15 MHz.

Abstract: A method includes receiving a package of data comprising electrocardiogram (ECG) data and metadata. The metadata includes determined RR intervals associated with the ECG data. The method further includes displaying, on a user interface, at least a subset of the determined RR intervals and overriding the determined RR intervals associated with a time period that is greater than a time period associated with a selected RR interval.

Abstract: A computer-implemented system includes an assistant interface for providing remote medical assistance to aid a patient in performing various aspects of a rehabilitation regimen for a body part comprising a joint, a bone, or a muscle group. The assistant interface is configured to communicate, via a network connection, a telemedicine signal with the patient interface. The telemedicine signal is configured to control the patient interface and/or a treatment apparatus configured to be manipulated by the patient to perform the rehabilitation regimen. The patient interface and the treatment apparatus are at a patient location geographically separate from a location of the assistant interface. The telemedicine signal includes one or more of an audio signal, an audiovisual signal, an interface control signal for controlling a function of the patient interface, and/or an apparatus control signal for changing an operating parameter of the treatment apparatus.

Abstract: Systems and methods for filtering time-varying data for filtering and extracting a predicted physiological signal. A method including: segmenting the time-varying data into temporal windows; using a trained filter machine learning model, predicting an error for each prediction of the physiological signal for each window of time-varying data, the filter machine learning model trained using physiological signal predictions based on training time-varying data and known values of the physiological signal for the training time-varying data; discarding each window of time-varying data when the predicted error for such window is greater than a threshold; and where the window of time-varying data is not discarded, outputting at least one of the window of time-varying data and the predicted error for each prediction of the physiological signal.

Abstract: A method includes receiving—by a first computing system—electrocardiogram (ECG) data and metadata associated with the ECG data, where the metadata includes an initial cardiac event classification and an initial beat classification for beats occurring during a first event associated with the initial cardiac event classification. The method further includes causing the ECG data to be displayed in a user interface (UI) and receiving a command, via the UI, to change the initial beat classifications to subsequent beat classifications. The method also includes automatically modifying, by the first computing system, the initial cardiac event classification to a subsequent cardiac event classification based on the subsequent beat classifications.

Abstract: State of art techniques hardly provide data balancing for multi-label multi-class data. Embodiments of the present disclosure provide a method and system for identifying cardiac abnormality in multi-lead ECGs using a Hybrid Neural Network (HNN) with fulcrum based data re-balancing for data comprising multiclass-multilabel cardiac abnormalities. The fulcrum based dataset re-balancing disclosed enables maintaining natural balance of the data, control the re-sample volume, and still support the lowly represented classes there by aiding proper training of the DL architecture. The HNN disclosed by the method utilizes a hybrid approach of pure CNN, a tuned-down version of ResNet, and a set of handcrafted features from a raw ECG signal that are concatenated prior to predicting the multiclass output for the ECG signal. The number of features is flexible and enables adding additional domain-specific features as needed.

Abstract: An apparatus is provided. A strip has first and second end sections, and a first surface and second surface. Two electrocardiographic electrodes are provided on the strip with one of the electrocardiographic electrodes provided on the first surface of the first end section of the strip and another of the electrocardiographic electrodes positioned on the first surface on the second end section of the strip. A flexible circuit is mounted to the second surface of the strip and includes a circuit trace electrically coupled to each of the electrocardiographic electrodes. A wireless transceiver is affixed on one of the first or second end sections, and a battery is positioned on one of the first or second end sections. A processor is positioned on one of the first or second end sections and is housed separate from the battery.

Abstract: A medical data and diagnostics management system for processing classified electrogram (EGM) datasets includes a server system that receives transmissions of classified EGM datasets, each corresponding to an arrhythmic episode detected by an implantable medical device (IMD), and applies a machine-learning model to each classified EGM dataset, thereby determining confidence indicator(s) relating to the IMD classification for each arrhythmic episode. Based upon the confidence indicator(s), the server system generates a set of machine-adjudicated EGM datasets, assigns a ranking score to each machine-adjudicated EGM dataset, and selects for display (for clinical analysis) a subset of the machine-adjudicated EGM datasets based upon their ranking scores. The machine-adjudicated EGM datasets are also stored in a database and further processed to generate diagnostic information and/or diagnostic alerts relating to the arrhythmic episodes detected by the IMD over time.

Abstract: Disclosed herein are system, method, and computer-readable medium aspects for improving the accuracy of an ablation model through synchronization. An aspect operates by activating a catheter energy source, acquiring a catheter energy signal from the catheter energy source, assigning an activation time stamp and deactivation time stamp to the catheter energy signal, and determining a time of ablation based on a time period between the activation time stamp and deactivation time stamp. The aspect continues to operate by acquiring an optical measurement signal from a catheter optical port, assigning an input time stamp and switching time stamp to the optical measurement signal, and processing the optical measurement signal in order to acquire a denaturation result. The aspect concludes by synchronizing the time of ablation and the denaturation result using the time stamps in order to generate a synchronized model and generating an estimated lesion depth from the synchronized model.

Abstract: The invention relates to a system for body-condition-dependent stimulation by means of function modules, e.g. an action module (2, D/A module) for stimulating tissue and a capture module (3, A/D module) for deriving/measuring bio data or bio signals, characterized in that the two modules communicate via a communication link (5) that meets hard or at least firm real-time requirements. The communication link (5) preferably comprises a real-time-capable bus to which the two modules are connected, above all an EtherCAT bus.

Abstract: A method includes detecting a first event within electrocardiogram (ECG) data, transmitting a first subset of the ECG data from a first computing system to a second computing system, displaying the first subset of the ECG data in a first window of a user interface (UI) of the second computing system, and selectively transmitting additional subsets of the ECG data from the first computing system to the second computing system as a user interacts with the UI.