Atrial Fibrillation Classification via Activity Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting and classifying atrial fibrillations (AFs) require patients to be present in a physician's office and rely on short-term monitoring, which limits the ability to diagnose underlying causes effectively.
Innovation Solution
A system and method that uses an adherent device to monitor electrocardiogram (ECG) signals and additional physiological parameters over an extended period, allowing for the detection and classification of AF episodes based on activity levels, thereby determining whether they are adrenergic or vagal, and generating reports for physician review.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Duration of action of moving object
If short-term monitoring is used in a physician's office, then the monitoring process is simple and quick, but the monitoring duration is insufficient to detect AF episodes effectively
Solution Approach 1:
The system automatically detects AF episodes, determines activity levels, classifies etiology, and generates reports without requiring physician intervention during the monitoring period. The device performs self-diagnosis and self-reporting functions that would otherwise require complex clinical assessment
Solution Approach 2:
The system performs preliminary classification of AF etiology based on activity level correlation before physician review. By pre-processing the data to identify adrenergic vs vagal patterns, the system reduces the complexity of the physician's diagnostic task while enabling long-term monitoring
2Measurement precision
If long-term monitoring is implemented, then AF detection accuracy improves, but the amount of data requiring physician review increases
Solution Approach 1:
The system extracts only the essential diagnostic information from long-term monitoring data by automatically classifying AF episodes based on activity level correlation. Instead of presenting all raw data, it extracts and presents only the classified etiology patterns that are clinically relevant
Solution Approach 2:
The system creates a simplified representation (copy) of the complex monitoring data by generating structured reports that summarize AF classification patterns. This copy contains the essential diagnostic information in a condensed format that is easy for physicians to review
3Productivity
If manual AF classification is performed by physicians, then diagnostic accuracy can be ensured, but time consumption increases
Solution Approach 1:
The system performs automatic AF classification by correlating detected AF episodes with activity level data. This self-service classification function handles the time-consuming analysis task, allowing physicians to review pre-classified results rather than manually analyzing all monitoring data
Solution Approach 2:
The system provides feedback to physicians in the form of classified AF etiology patterns based on activity level correlation. This automated feedback mechanism preserves diagnostic accuracy by presenting pre-analyzed information that maintains clinical relevance while reducing review time
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
A system and method of detecting and classifying atrial fibrillations (AFs) monitors an electro-cardiogram (ECG) signal of the patient. Based on the monitored ECG signals, AF episodes are detected (218). Monitored physiological parameters are utilized to determine an activity level (220)of the patient at the time of the detected AF episode, wherein the activity level is associated with the detected AF episode. The etiology of the detected AF episodes is classified as adrenergic if the AF episodes occur while the patient is active, and classified as vagal if the AF episodes occur while the patient is at rest.