Passive AF Burden Estimation With Wearable Sensor Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Accurately estimating atrial fibrillation (AF) burden in free-living scenarios is challenging due to the lack of controlled environments and the limitations of existing wearable devices, which often have limited battery life, inconvenience, and insufficient accuracy in detecting AF burden rather than its presence or absence, without providing notifications or management strategies.
Innovation Solution
A system using mobile sensors, such as smartphones and smartwatches, passively estimates AF burden, notifies the user, and provides personalized recommendations to reduce the burden, employing a Hidden Markov Model (HMM) for accurate estimation and management in daily life.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If continuous passive monitoring of heart rhythms is implemented in free-living scenarios, then AF burden estimation capability is improved, but measurement precision deteriorates due to lack of controlled environment
Solution Approach 1:
The system implements feedback mechanisms where detected heart rhythm data is continuously analyzed and compared against established AF patterns. The system provides feedback loops that refine detection algorithms based on accumulated data, allowing it to improve measurement precision over time while maintaining continuous monitoring in free-living conditions.
Solution Approach 2:
The wearable device performs self-calibration and automatic adjustment of detection parameters based on individual user characteristics. The system adapts to each user's baseline heart rate and rhythm patterns, enabling accurate AF burden estimation without requiring controlled environment setup or manual calibration by medical professionals.
2Reliability
If continuous monitoring is performed to estimate AF burden, then health risk prediction is improved, but use of energy deteriorates due to continuous sensor operation
Solution Approach 1:
The system employs periodic monitoring intervals rather than truly continuous sampling. It dynamically adjusts the monitoring frequency based on detected heart rate variability and potential AF episodes, performing intensive analysis only when AF is detected or suspected, thereby reducing overall energy consumption while maintaining effective health risk prediction.
Solution Approach 2:
The monitoring system dynamically adapts its operational characteristics based on real-time conditions. It transitions between low-power standby mode and active monitoring mode, adjusting sensor sampling rates and processing intensity according to detected physiological states, thus optimizing the balance between health risk prediction accuracy and energy consumption.
3Ease of operation
If existing wearable devices are used for AF detection, then portability is improved, but measurement precision deteriorates due to insufficient accuracy in detecting AF burden
Solution Approach 1:
The system combines multiple sensing modalities and data sources within a single wearable device, creating a composite monitoring system that integrates optical sensors, accelerometers, and physiological sensors. This multi-component approach enables accurate AF burden detection while maintaining the portability and comfort of wearable form factors.
Solution Approach 2:
The wearable device is designed with multi-functional capabilities that allow it to perform not only AF detection but also general health monitoring, fitness tracking, and fall detection. By consolidating multiple functions into a single universal device, it achieves accurate AF burden detection without compromising portability or user convenience.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method includes estimating, by a consumer electronic device, an atrial fibrillation (AF) burden of a subject based on multiple measurements passively collected by at least one sensor associated with the consumer electronic device while the subject is in a free-living environment. The method also includes outputting, by the consumer electronic device, an AF burden notification associated with the subject based on the estimated AF burden. The method further includes outputting, by the consumer electronic device, an AF burden recommendation based on the estimated AF burden.