Implantable Arrhythmia Detection Validation Using Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing implantable cardiac monitors (ICMs) frequently declare false arrhythmia episodes due to conditions like sick sinus rhythms and premature ventricular contractions, leading to excessive storage of incorrect data sets and a significant burden on clinicians.
Innovation Solution
Implementing a machine learning model, such as a convolutional neural network, to analyze device classified arrhythmia data sets and identify valid and invalid subsets, providing confidence indicators and recommendations to validate or refute arrhythmia detections.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional arrhythmia detection algorithms are used in implantable cardiac monitors, then arrhythmia detection capability is provided, but false arrhythmia detections occur frequently due to conditions like sick sinus rhythms and premature ventricular contractions
Solution Approach 1:
A machine learning model serves as an intermediary between the traditional arrhythmia detection algorithm and the final diagnosis. The ML model receives device-classified arrhythmia data sets as input and processes them to determine whether they represent true or false positives, thereby mediating the detection process to reduce false alarms while maintaining detection capability
Solution Approach 2:
The system implements feedback by using the machine learning model to evaluate previously detected arrhythmias and provide confidence indicators. This feedback loop allows the system to learn from past detections and improve future detection accuracy, reducing false positives while maintaining sensitivity to true arrhythmias
2Loss of information
If false arrhythmia episodes are declared and stored, then complete data sets are maintained for review, but excessive storage burden and clinical workload are created
Solution Approach 1:
The machine learning model performs preliminary filtering of arrhythmia data sets before they are stored or presented for clinical review. By pre-processing the data and identifying likely false positives, the system reduces the volume of data that needs to be stored and reviewed, while maintaining complete information for confirmed true positives
Solution Approach 2:
The system discards data sets that are determined to be false positives by the machine learning model, while recovering and preserving data sets that are confirmed as true arrhythmias. This selective retention approach reduces storage burden while ensuring that clinically relevant information is maintained
Data Source
AI summary
System and method for declaring arrhythmias in cardiac activity are provided. The system includes memory to store specific executable instructions and a machine learning (ML) model. One or more processors are configured to execute the instructions to obtain device classified arrhythmia (DCA) data sets generated by an implantable medical device (IMD) for corresponding candidate arrhythmias episodes declared by the IMD. The DCA data sets include cardiac activity (CA) signals for one or more beats sensed by the IMD and one or more device documented (DD) markers generated by the IMD. The system applies the ML model to the DCA data sets to identify a valid sub-set of DCA data sets that correctly characterize the corresponding CA signals and an invalid sub-set of the DCA data sets that incorrectly characterize the corresponding CA signals. A display is configured to present information concerning at least one of the valid sub-set or invalid sub-set.