Mobile Health Monitoring With Predictive Models for Atrial Fibrillation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing health monitoring devices struggle to effectively utilize continuous health-indicator data from mobile sensors due to the lack of clinical guidance and complexity in interpreting sequences of measurements, particularly for asymptomatic conditions like atrial fibrillation, which are difficult to diagnose and require cumbersome and expensive monitoring solutions.
Innovation Solution
A system utilizing predictive machine learning models to analyze sequences of health-indicator data, combined with other-factor data, to detect abnormalities in an unsupervised fashion, notifying users of potential health events and prompting high-fidelity measurements when necessary, trained on both population and individual data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If continuous monitoring of health indicators is implemented using mobile sensors, then monitoring capability and data collection are improved, but the complexity of interpreting sequences of measurements and lack of clinical guidance make effective utilization difficult
Solution Approach 1:
The patent introduces machine learning models as an intermediary between the continuous health indicator data and clinical interpretation. The ML models process the sequences of measurements and provide actionable insights, bridging the gap between raw data collection and clinical guidance without requiring users to manually interpret complex sequences.
Solution Approach 2:
The system enables self-service by automatically analyzing health indicator sequences and generating alerts or notifications based on detected patterns. The machine learning models autonomously interpret the data and provide recommendations, eliminating the need for users to manually analyze complex measurement sequences.
2Reliability
If conventional monitoring solutions are used for asymptomatic conditions like atrial fibrillation, then diagnosis capability is improved, but the solutions become cumbersome and expensive
Solution Approach 1:
The patent employs cost-effective mobile sensors and wearable devices that can be easily deployed and discarded, replacing expensive conventional monitoring solutions. These disposable-like devices continuously monitor health indicators and use machine learning to detect asymptomatic conditions such as atrial fibrillation, providing reliable diagnosis capability at a fraction of the cost.
Solution Approach 2:
The system changes the approach by monitoring multiple health indicator parameters continuously over time rather than relying on single-point measurements. This parameter-based approach enables detection of asymptomatic conditions through pattern recognition in the data, eliminating the need for cumbersome and expensive specialized monitoring equipment.
3Measurement precision
If intermittent arrhythmias are monitored using traditional ECG techniques, then diagnosis accuracy is improved, but the difficulty increases because the arrhythmia may not be present at the time of measurement
Solution Approach 1:
The patent implements continuous monitoring of health indicators over extended periods using mobile sensors. This continuous data collection ensures that intermittent arrhythmias are captured when they occur, eliminating the timing coincidence problem inherent in traditional intermittent ECG measurements. The machine learning models continuously analyze the data streams to detect arrhythmian patterns.
Solution Approach 2:
The system performs preliminary actions by continuously collecting and storing health indicator data before the arrhythmia occurs. The machine learning models are trained to recognize patterns that precede or indicate intermittent arrhythmias, enabling early detection and alerting users to seek medical attention before the condition becomes critical.
Data Source
AI summary
Disclosed herein are devices, systems, methods and platforms for continuously monitoring the health status of a user, for example the cardiac health status. The present disclosure describes systems, methods, devices, software, and platforms for continuously monitoring a user's health-indicator data (for example and without limitation PPG signals, heart rate or blood pressure) from a user-device in combination with corresponding (in time) data related to factors that may impact the health-indicator (“other-factors”) to determine whether a user has normal health as judged by or compared to, for example and not by way of limitation, either (i) a group of individuals impacted by similar other-factors, or (ii) the user him/herself impacted by similar other-factors.