A computer-implemented method for non-invasively identifying ablation locations in atrial tissue, can include: receiving three-dimensional imaging data representing atrial tissue of a left atrial flutter (LAFL) subject; generating a subject-specific model of the at least one of the atrial tissue from the three-dimensional imaging data; estimating tissue fiber orientations in the atrial tissue; assigning the estimated tissue fiber orientations to the subject-specific model of the atrial tissue; conducting simulations of LAFL using the subject-specific model to identify regions of slow conduction of a propagating wave within an atrial tissue region of the atrial tissue; a critical isthmus of a rotational wavefront within the atrial tissue region; or a region based on a minimum cut in a flow network; and identifying at least one ablation location in the atrial tissue region based on the identified regions of slow conduction, the critical isthmus, or the minimum cut.

A computer-implemented method for contact photoplethysmography, abbreviated contact PPG, comprises obtaining during a time interval plural PPG signals for sub-regions of a lens or video frame; and combining the plural PPG signals to thereby obtain a multi-region PPG signal.

A computer implemented method and system for identifying one or more areas of the heart muscle responsible for supporting or initiating abnormal heart rhythms using electrogram data recorded from a plurality of electrodes obtained from a corresponding series of sensing locations on the heart over a recording time period; the method including the steps of: setting a pre-defined geodesic distance, dividing the recording time period into several analysis time periods, and pairing each sensing location with a plurality of other sensing locations from within the defined geodesic distance, thus forming a plurality of location pairings; for each of the analysis time periods, defining the relative timing of each activation signal for each location within each pairing, determining whether the relative timing of activation signals falls within plausible biological parameters, defining the leading signal of the pair for each electrogram activation within the respective analysis time period; and assigning a series of lead signal scores to each electrogram pairing acquired within each analysis time period based on the proportion of time within the respective analysis time period that each activation signal is leading within each pairing; repeating the analysis at the same location at least once whilst varying the analysis time period; combining each analysis time period for each signal location to provide a statistical measure of the proportion that each signal location tends to lead relative to other locations within the defined geodesic area; and relating lead signal scores from overlapping geodesic areas to provide relative combined lead signal scores; to provide an indication of the relative likelihood that each sensing location is generally preceding other areas and is therefore at or adjacent to a driver area of the abnormal heart rhythm.

A medical device is disclosed that includes a service component for use in detecting patient data, at least one processor coupled with the service component, a care protocol module executable by the at least one processor to provide healthcare to a patient at least in part by generating a request for processing by the service component, and a resource module executable by the at least one processor to manage access to the service component by identifying a level of service associated with the care protocol module and responding to the request by managing the service component to meet the level of service. The care protocol module implements a patient care protocol that includes a sequence of actions directed to the patient. The level of service indicates a level of performance that the patient care protocol requires of the resource module. Selective offloading of modular functions is also enabled.

Apparatus and methods remove a voltage offset from an electrical signal, specifically a biomedical signal. A signal is received at a first operational amplifier and is amplified by a gain. An amplitude of the signal is monitored, by a first pair of diode stages coupled to an output of the first operational amplifier, for the voltage offset. The amplitude of the signal is then attenuated by the first pair of diode stages and a plurality of timing banks. The attenuating includes limiting charging, by the first pair of diode stages, of the plurality of timing banks and setting a time constant based on the charging. The attenuating removes the voltage offset persisting at a threshold for a duration of at least the time constant. Saturation of the signal is limited to a saturation recovery time while the saturated signal is gradually pulled into monitoring range over the saturation recovery time.

Conventionally, Atrial Fibrillation (AF) has been detected using atrial analyses which is vulnerable to background noise. Again there is a dependency on statistical features which are extracted from R-R intervals of long ECG recordings. The present disclosure addresses AF detection from single lead short ECG recordings of less than one minute wherein automatic detection of P-R and P-Q intervals is difficult, which introduces error in feature computing from the segregated intervals and compromises the performance of the classifier. In the present disclosure, a Recurrent Neural Network (RNN) based architecture comprising two Long Short Term Memory (LSTM) networks is provided for temporal analysis of R-R intervals and P wave regions in an ECG signal respectively. Output sates of the two LSTM networks are merged at a dense layer along with a set of hand-crafted statistical features to create a composite feature set for classification of the AF.

Techniques are disclosed for explaining and visualizing an output of a machine learning system that detects cardiac arrhythmia in a patient. In one example, a computing device receives cardiac electrogram data sensed by a medical device. The computing device applies a machine learning model, trained using cardiac electrogram data for a plurality of patients, to the received cardiac electrogram data to determine, based on the machine learning model, that an episode of arrhythmia has occurred in the patient and a level of confidence in the determination that the episode of arrhythmia has occurred in the patient. In response to determining that the level of confidence is greater than a predetermined threshold, the computing device displays, to a user, a portion of the cardiac electrogram data, an indication that the episode of arrhythmia has occurred, and an indication of the level of confidence that the episode of arrhythmia has occurred.

An apparatus for assisting a rescuer in performing chest compressions during CPR on a victim, the apparatus comprising a pad or other structure configured to be applied to the chest near or at the location at which the rescuer applies force to produce the chest compressions, at least one sensor connected to the pad, the sensor being configured to sense movement of the chest or force applied to the chest, processing circuitry for processing the output of the sensor to determine whether the rescuer is substantially releasing the chest following chest compressions, and at least one prompting element connected to the processing circuitry for providing the rescuer with information as to whether the chest is being substantially released following chest compressions.

Disclosed are various examples and embodiments of systems, devices, components and methods configured to detect a location of a source of at least one cardiac rhythm disorder in a patient's heart. In some embodiments, electrogram signals are acquired from a patient's body surface, and subsequently normalized, adjusted and/or filtered, followed by generating a two-dimensional spatial map, grid or representation of the electrode positions, processing the amplitude-adjusted and filtered electrogram signals to generate a plurality of three-dimensional electrogram surfaces corresponding at least partially to the 2D map, one surface being generated for each or selected discrete times, and processing the plurality of three-dimensional electrogram surfaces through time to generate a velocity vector or other type of map using one or more of optical flow, video tracking analysis, motion capture analysis, motion estimation analysis, data association and segmentation tracking analysis, particle tracking analysis, and single-particle tracking analysis methods corresponding at least partially to the 2D map. Trained atrial discriminative machine learning models that facilitate the foregoing systems and methods, and that provide predictions or results concerning a patient's condition, are also disclosed.

A system and method for non-invasively generating a report of cardiac electrical activities of a subject includes determining, using cardiac electrical activation information, equivalent current densities (ECDs). The ECDs are assembled into time-course ECD information and a spectrum of the time-course ECD information is analyzed to determine peaks for spectral characteristics of atrial fibrillation (AF). The spectral characteristics of AF are correlated with potential electrical sources of the AF and a report is generated indicating the potential electrical sources of the AF spatially registered with the medical imaging data.