Techniques are disclosed for using both feature delineation and machine learning to detect cardiac arrhythmia. A computing device receives cardiac electrogram data of a patient sensed by a medical device. The computing device obtains, via feature-based delineation of the cardiac electrogram data, a first classification of arrhythmia in the patient. The computing device applies a machine learning model to the received cardiac electrogram data to obtain a second classification of arrhythmia in the patient. As one example, the computing device uses the first and second classifications to determine whether an episode of arrhythmia has occurred in the patient. As another example, the computing device uses the second classification to verify the first classification of arrhythmia in the patient. The computing device outputs a report indicating that the episode of arrhythmia has occurred and one or more cardiac features that coincide with the episode of arrhythmia.

A method for time-synchronizing waveforms from different patient monitors that does not require devices to have high-precision synchronized clocks or to be coupled to a triggering synchronization signal generator. Comparable signals may be obtained from different devices either by placing selected sensors from the devices in the same locations, or by filtering signals from one device to obtain a signal comparable to signals from another device. Filtering may for example transform waveforms into independent components and identify a component that matches a signal from another device. The comparable signals may then be transformed into frequency variation curves, such as time intervals between peak values, to facilitate detection of the time shift between the signals. Cross correlation of the frequency variation curves may be used to locate the precise time shift between the signals. Use of frequency variation curves may be more robust than directly comparing and correlating the original signals.

A method for time-synchronizing waveforms from different patient monitors that does not require devices to have high-precision synchronized clocks or to be coupled to a triggering synchronization signal generator. Comparable signals may be obtained from different devices either by placing selected sensors from the devices in the same locations, or by filtering signals from one device to obtain a signal comparable to signals from another device. Filtering may for example transform waveforms into independent components and identify a component that matches a signal from another device. The comparable signals may then be transformed into frequency variation curves, such as time intervals between peak values, to facilitate detection of the time shift between the signals. Cross correlation of the frequency variation curves may be used to locate the precise time shift between the signals. Use of frequency variation curves may be more robust than directly comparing and correlating the original signals.

An apparatus and method for estimating one or more hemodynamic parameters such as cardiac output or stroke volume. Embodiments are based on the concept of incorporating information about vascular tone into hemodynamic parameter estimation to improve accuracy. More particularly, embodiments use a measurement of a time duration for a blood pulse to travel from the heart along a certain length of an arterial path as a proxy measure for vascular tone, and incorporate this into hemodynamic parameter estimation. Embodiments are also based on incorporating vascular tone proxy measurements for multiple different arterial paths to take account of vascular tone variations between different portions of the circulatory system.

Methods and apparatuses for stimulation of the vagus nerve to treat inflammation including adjusting the stimulation based on one or more metric sensitive to patient response. The one or more metrics may include heart rate variability, level of T regulatory cells, particularly memory T regulatory cells, temperature, etc. Stimulation may be provided through an implantable microstimulator.

Methods and apparatuses for stimulation of the vagus nerve to treat inflammation including adjusting the stimulation based on one or more metric sensitive to patient response. The one or more metrics may include heart rate variability, level of T regulatory cells, particularly memory T regulatory cells, temperature, etc. Stimulation may be provided through an implantable microstimulator.

A computer generates an accident risk definition model to estimate a probability of hazard occurrence as an accident risk by inputting first in-vehicle sensor data collected in the past and hazard occurrence data having information on hazard occurrence from the first in-vehicle sensor data preset therein, generates accident risk estimation data by inputting second in-vehicle sensor data collected in the past to the accident risk definition model and estimating the probability of the hazard occurrence, generates an accident risk prediction model to predict the accident risk after a predetermined time by inputting first biological index data corresponding to the second in-vehicle sensor data and the accident risk estimation data, calculates second biological index data from second biological sensor data by acquiring the second biological sensor data of a driver, and predicts the accident risk after the predetermined time by inputting second biological index data to the accident risk prediction model.

A computer generates an accident risk definition model to estimate a probability of hazard occurrence as an accident risk by inputting first in-vehicle sensor data collected in the past and hazard occurrence data having information on hazard occurrence from the first in-vehicle sensor data preset therein, generates accident risk estimation data by inputting second in-vehicle sensor data collected in the past to the accident risk definition model and estimating the probability of the hazard occurrence, generates an accident risk prediction model to predict the accident risk after a predetermined time by inputting first biological index data corresponding to the second in-vehicle sensor data and the accident risk estimation data, calculates second biological index data from second biological sensor data by acquiring the second biological sensor data of a driver, and predicts the accident risk after the predetermined time by inputting second biological index data to the accident risk prediction model.

An implantable medical device system is configured to sense cardiac events in response to a cardiac electrical signal crossing a cardiac event sensing threshold. A control circuit is configured to determine a drop time interval based on a heart rate and control a sensing circuit to hold the cardiac event sensing threshold at a threshold value during the drop time interval.

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 far field cardiac activity (CA) signals and applies a direction related responsiveness (DRR) filter to the CA signals to produce DRR filtered signals. The method compares a current sample from the CA signals to a prior sample from the DRR filtered signals to identify a direction characteristic of the CA signals and defines the DRR filter based on a timing constant that is set based on the direction characteristic identified. The method analyzes the CA signals in connection with the DRR filtered signals to identify a peak characteristic of the CA signals and determines peak to peak intervals between successive peak characteristic. The method detects at least one of noise or an arrhythmia based on the peak to peak intervals and records results of the detecting.