Continuous detection and monitoring of heart arrhythmia using both wearable sensors and cloud-resident analyses
Inventors
Murphy, Mark • Bikhchandani, Nikhil
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12453471-B2
Publication Date
2025-10-28
Expiration Date
Abstract
Systems and methods are provided for continuously monitoring a user to determine when cardiovascular events are likely occurring and to responsively provide a prompt to a user to engage in additional physiological assessment of the putative cardiovascular event. Additional assessment can include the user engaging an additional sensor to provide signals that are more accurate, lower noise, or otherwise improved relative to a continuously-monitoring sensor used to initially detect the cardiovascular event. Detection of cardiovascular events includes using a cardiovascular classifier to determine, based on the output of such a continuously-monitoring sensor, whether the event is likely occurring. Such a classifier can be received from a cloud computing service or other remote system based on sensor outputs sent to such a system. Use of such a classifier can facilitate reduced false-positive detection of cardiovascular events based on the continuously-monitoring sensor, and thus reduce extraneous prompts to the user.
Core Innovation
A server receives information indicative of a photoplethysmographic signal detected by a first sensor of a wearable device associated with a user. The server determines information related to a cardiovascular classifier based on photoplethysmographic data, where the cardiovascular classifier is derived from photoplethysmographic data but is adapted to predict an occurrence of a cardiovascular event based on electrocardiographic data.
The cardiovascular event prediction is configured to be based on an electrocardiographic signal detected by a second sensor of the wearable device, where the second sensor is a different type of sensor than the first sensor from which the cardiovascular classifier was derived. The server transmits the information related to the cardiovascular classifier to the wearable device so that the cardiovascular classifier is stored at and used by the wearable device to detect or predict the occurrence of the cardiovascular event using the second sensor.
In addition to predicting whether a cardiovascular event is occurring, the server is configured to determine cardiovascular-event information and optionally additional determinations based on the event information. The cardiovascular-event information includes existence and timing of one or more cardiovascular events, and the server can determine information about a drug or treatment received by the user, including an indication of effectiveness.
Claims Coverage
The document provides two independent claim scopes built around the same inventive concept. Across the independent claims, there are three main inventive blocks: cross-sensor classifier derivation and adaptation, server-to-wearable transmission for on-wearable execution, and predicting cardiovascular event occurrence based on electrocardiographic signals while leveraging photoplethysmographic-derived classifier information.
Cross-sensor cardiovascular classifier derivation and event prediction
The server determines information related to a cardiovascular classifier based on photoplethysmographic signal information from a first sensor, where the cardiovascular classifier is derived from photoplethysmographic data but adapted to predict whether a cardiovascular event is occurring based on electrocardiographic signal information detected by a second sensor.
Server transmission of classifier for use on a different-type sensor
The server transmits the information related to the cardiovascular classifier to the wearable device so that the cardiovascular classifier is stored at and used by the wearable device to detect the occurrence of the cardiovascular event with the second sensor that is a different type of sensor than the first sensor.
Remote server with wearable multi-sensor architecture and on-wearable execution
A system includes a wearable device having a first sensor configured to detect photoplethysmographic signals and a second sensor configured to detect electrocardiographic signals, and a remote server that determines information related to a cardiovascular classifier derived from photoplethysmographic signals and adapted to predict cardiovascular event occurrence based on electrocardiographic signals; the server transmits the classifier information so it is stored in and executed by the wearable controller using the second sensor.
Overall, the independent claims cover server-side derivation and adaptation of a cardiovascular classifier from photoplethysmographic data, followed by transmission to a wearable that executes the classifier using electrocardiographic data from a different-type sensor to predict cardiovascular event occurrence.
Stated Advantages
Reducing false positives and false negatives via cloud-generated cardiovascular classifier training and updating from multi-device and clinical data.
Documented Applications
Continuous cardiovascular or arrhythmia monitoring using a wearable device with photoplethysmographic signals and electrocardiographic signals, including predicting cardiovascular event likelihood and prompting a user upon event likelihood.
Providing downstream determinations related to a drug or treatment received by the user, including deriving an indication of effectiveness from cardiovascular-event information.
Interested in licensing this patent?