An implantable neurostimulator-implemented method for managing tachyarrhythmias through vagus nerve stimulation is provided. An implantable neurostimulator, including a pulse generator, is configured to deliver electrical therapeutic stimulation in a manner that results in creation and propagation (in both afferent and efferent directions) of action potentials within neuronal fibers of a patient's cervical vagus nerve. Operating modes of the pulse generator are stored. A maintenance dose of the electrical therapeutic stimulation is delivered to the vagus nerve via the pulse generator to restore cardiac autonomic balance through continuously-cycling, intermittent and periodic electrical pulses. A restorative dose of the electrical therapeutic stimulation is delivered to prevent initiation of or disrupt tachyarrhythmia through periodic electrical pulses delivered at higher intensity than the maintenance dose. The patient's normative physiology is monitored via a physiological sensor, and upon sensing a condition indicative of tachyarrhythmia, is switched to delivering the restorative dose to the vagus nerve.

An implantable medical device for stimulating a human/animal heart having a stimulation unit which stimulates the His bundle and a detection unit which detects an electrical signal at the His bundle. The device performs: a) determining a first value of a parameter of a first measuring pulse measured between a first electrode pole and a housing; b) determining a second value of the same parameter of a second measuring pulse measured between the first electrode pole and a second electrode pole; c) comparing the first and second values; d) determining, based on the comparing step, whether the first or second measuring pulses enables a higher available level control range of the analog-to-digital converter; e) measuring an impedance in a unipolar manner between the first electrode pole and the housing or in a bipolar manner between the first electrode pole and the second electrode pole depending on the determining step.

A method for processing electrocardiograph (ECG) data using a garment includes determining, by a processor, a current working lead from ECG leads formed in advance using flexible electrodes in the garment based on a current ECG monitor type, and receiving, by the processor through lead wires corresponding to the current working lead, ECG data collected by flexible electrodes corresponding to the current working lead. A wearable apparatus for processing ECG data includes at least two flexible electrodes, in which the at least two flexible electrodes are capable of forming different leads based on predetermined configurations, at least two lead wires, and an ECG data collector configured to receive ECG data collected by the at least two flexible electrodes, in which each of the at least two flexible electrodes connects to the ECG data collector via at least one of the at least two lead wires.

A system and method for display of subcutaneous cardiac monitoring data are provided. Cutaneous action potentials of a patient and other sensed data associated with the patient are recorded as electrocardiogram (EGC) data over a set time period using a subcutaneous insertable cardiac monitor. A set of R-wave peaks is identified within the ECG data and an R-R interval plot is constructed. A difference between recording times of successive pairs of the R-wave peaks in the set is determined. A heart rate associated with each difference is also determined. The pairs of the R-wave peaks and associated heart rate are plotted as the R-R interval plot. A diagnosis of cardiac disorder is facilitated based on patterns of the plotted pairs of the R-wave peaks, the associated heart rates in the R-R interval plot, and background data based on the other sensed data.

A medical device is configured to sense an electrical signal and determine that signal to noise criteria are met based on electrical signal segments stored in response to sensed electrophysiological events. The medical device is configured to determine an increased gain signal segment from one of the stored electrical signal segments in response to determining that the signal to noise criteria are met. The medical device determines a noise metric from the increased gain signal segment. The stored electrical signal segment associated with the increased gain signal segment may be classified as a noise segment in response to the noise metric meeting noise detection criteria.

A medical device is configured to sense an electrical signal and determine that signal to noise criteria are met based on electrical signal segments stored in response to sensed electrophysiological events. The medical device is configured to determine an increased gain signal segment from one of the stored electrical signal segments in response to determining that the signal to noise criteria are met. The medical device determines a noise metric from the increased gain signal segment. The stored electrical signal segment associated with the increased gain signal segment may be classified as a noise segment in response to the noise metric meeting noise detection criteria.

A method of determining a fused sensor measurement is disclosed including: obtaining sensor measurements from sensors detecting a same type of physiological measurement; determining a signal quality index (SQI) of each sensor including determining an extent to which a sensor measurement differs from others among the sensor measurements obtained from each sensor; determining a weightage of each sensor based on the SQI of each sensor; and determining a fused sensor measurement from the plurality of sensors based on the weightage of each sensor and filtered sensor measurements of each sensor obtained from a Kalman filter operation. A vehicle safety system includes: a vehicle electronic control unit configured to: determine the sensor measurement extent, to determine the SQI of each sensor, determine the weightage of each sensor, determine the fused sensor measurement, determine the occupant's physiological condition, and if the physiological condition is abnormal, perform at least one vehicle operation.

Methods and systems are provided for predicting cardiac arrhythmias based on multi-modal patient monitoring data via deep learning. In an example, a method may include predicting an imminent onset of a cardiac arrhythmia in a patient, before the cardiac arrhythmia occurs, by analyzing patient monitoring data via a multi-arm deep learning model, outputting an arrhythmia event in response to the prediction, and outputting a report indicating features of the patient monitoring data contributing to the prediction. In this way, the multi-arm deep learning model may predict cardiac arrhythmias before their onset.

Methods and systems are provided for predicting cardiac arrhythmias based on multi-modal patient monitoring data via deep learning. In an example, a method may include predicting an imminent onset of a cardiac arrhythmia in a patient, before the cardiac arrhythmia occurs, by analyzing patient monitoring data via a multi-arm deep learning model, outputting an arrhythmia event in response to the prediction, and outputting a report indicating features of the patient monitoring data contributing to the prediction. In this way, the multi-arm deep learning model may predict cardiac arrhythmias before their onset.

A system includes harvester circuitry configured to charge a battery for a medical device using a displacement of a harvester mass, one or more accelerometers configured to detect a motion associated with the harvester mass, and processing circuitry. The processing circuitry is configured to determine, with the one or more accelerometers, motion information for the implanted medical device during a time range that occurs when the harvester circuitry charges the battery using the displacement of the harvester mass. The processing circuitry are further configured to determine a harvester output generated by the harvester circuitry during the time range and output an indication of a potential failure of the harvester mechanism based on the motion information and the harvester output.