Monitoring and processing physiological signals to detect and predict dysfunction of an anatomical feature of an individual
Inventors
Toth, Landy • Schwartz, Robert S. • Schwartz, Jonathan G.
Assignees
Publication Number
US-12310760-B2
Publication Date
2025-05-27
Expiration Date
2040-05-07
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Abstract
Systems and methods are provided for monitoring and processing physiological signals (e.g., electrocardiogram signals) to detect and predict for possible dysfunction of an anatomical feature (e.g., cardiac dysfunction) or otherwise predict a likelihood of future cardiac dysfunction of the individual. For example, a system comprises a plurality of sensors, a physiological signal processing system, and a feature analysis system. The sensors are configured to monitor physiological signals from an individual that has undergone a medical procedure on an anatomical feature. The physiological signal processing system is configured to analyze the physiological signals and extract features from the physiological signals which are indicative of a function of the anatomical feature. The feature analysis system is configured to analyze the extracted features and predict a risk of the individual developing a post-procedural dysfunction of the anatomical feature as a result of the medical procedure on the anatomical feature.
Core Innovation
The invention provides systems and methods for monitoring and processing physiological signals, such as electrocardiogram signals, to detect and predict possible dysfunction of an anatomical feature, for example, cardiac dysfunction, following a medical procedure on that anatomical feature. A system is described that includes a plurality of sensors to monitor physiological signals from an individual post-procedure, a physiological signal processing system to analyze these signals and extract features indicative of anatomical function, and a feature analysis system to assess the extracted features and predict the risk of developing post-procedural dysfunction.
The background highlights challenges associated with structural heart interventions, which, while advancing the treatment of valvular heart disease and anatomic cardiac defects, may lead to interruption or degradation of normal heart functionality due to electrical or mechanical pressures from the intervention. Existing techniques can have difficulty reliably identifying early signs of complications or dysfunction resulting from such procedures.
This invention addresses the problem by leveraging advanced sensors to acquire both primary physiological signals indicative of function (such as ECG) and secondary physiological signals (including electromyogram, respiratory rhythm, blood pressure, heart movement, body movement, phonogram, and cardiac output). Signal processing modules generate, time-synchronize, and group these signals into self-similar sets for more precise analysis. Features are then extracted and compared to known trends from patient cohorts, enabling risk stratification and early prediction of dysfunction, with the potential to alert clinicians when trends indicate increasing risk.
Claims Coverage
There are multiple independent claims covering system, method, and computer program product aspects, each centered on monitoring and analyzing physiological signals to predict post-procedural dysfunction.
System for monitoring and analyzing physiological signals to predict post-procedural dysfunction
A system comprises: - A plurality of sensors that monitor physiological signals—including both primary signals indicative of anatomical function and secondary signals—concurrently from an individual post-medical procedure. - A physiological signal processing system that: - Generates primary and secondary signal waveforms. - Time-synchronizes these waveforms. - Groups segments of the primary signal into self-similar groups based on synchronization with secondary signals. - Extracts features from the self-similar group segments. - A feature analysis system that analyzes the extracted features from at least one self-similar group to predict risk of post-procedural dysfunction of the anatomical feature.
Feature extraction and risk prediction from self-similar signal groups
- Extraction of features indicative of anatomical function (including morphological waveform features and event timing) from grouped, time-synchronized signal segments. - Analysis of these features to compute trend lines based on collected time series data. - Comparison of computed trend lines with known trend lines from cohort populations to perform risk stratification. - Rendering and display of time series data and trend lines on a display system, including stratification into low, increasing, and high-risk zones, with alert notification when a high-risk zone is entered.
Method for processing and analyzing physiological signals for dysfunction prediction
A method comprising: 1. Monitoring primary and secondary physiological signals concurrently after a medical procedure. 2. Generating and time-synchronizing primary and secondary signal waveforms. 3. Grouping segments of the primary signal into self-similar groups based on synchronization with secondary signals. 4. Extracting features from these self-similar groups. 5. Analyzing the features to predict the risk of developing post-procedural dysfunction.
Computer program product for automated physiological signal monitoring and analysis
A computer program product with instructions to: - Monitor physiological signals via sensors (worn devices or patches). - Process these signals by generating and time-synchronizing primary and secondary waveforms, grouping segments into self-similar groups, and extracting features from them. - Analyze features from self-similar groups to predict post-procedural dysfunction risk. - Compute, compare, and render trend lines; stratify risk; and generate alert notifications when high-risk is detected.
The claims collectively protect integrated hardware and software solutions for multi-signal, time-synchronized physiological monitoring, advanced signal processing to identify self-similar segments, extraction and trend analysis of function-indicative features, and prediction—using risk stratification or neural networks—of post-procedural dysfunction, with options for wearable or skin-patch sensors and real-time notifications.
Stated Advantages
Enables early detection and risk prediction of post-procedural dysfunction of an anatomical feature by extracting and analyzing physiological signal features over time.
Allows more precise analysis by time-synchronizing primary signal data with secondary physiological signals and organizing data into self-similar groups, enhancing detection of small or early changes.
Supports high-fidelity measurement and low-noise recording of physiological signals, including detection of subtle features in waveform morphology not accessible with conventional monitoring.
Provides ability to stratify patient risk and generate alert notifications when trends indicate increased likelihood of dysfunction, enabling timely clinical intervention.
Documented Applications
Monitoring and assessing cardiac function after a structural heart intervention to predict risks such as blocks, arrhythmias, or other post-procedural cardiac complications.
Detecting dysfunction of an anatomical feature (e.g., heart) following medical procedures such as structural heart intervention, ablation procedures, shunt or filter placements.
Establishing baseline conduction and rhythmic system data pre-procedure, and using that data for comparison during and after a therapeutic procedure.
Guiding intra-procedural decisions, providing indicators of procedure completion, safety, and warnings of potential or imminent post-procedural complications.
Interested in licensing this patent?