Cardiac Electrogram Arrhythmia Detection With Delineation and ML
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing implantable medical devices (IMDs) face challenges in accurately detecting and classifying cardiac arrhythmias, particularly malignant tachyarrhythmias like ventricular fibrillation, which can lead to sudden cardiac death, due to limitations in power consumption and computational complexity of current detection methods.
Innovation Solution
Combining feature delineation and machine learning techniques to analyze cardiac electrogram data, where IMDs perform initial detection and an external device performs more comprehensive analysis, reducing power consumption and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If feature-based delineation is used for arrhythmia detection, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent divides the arrhythmia detection task into two segments: feature-based delineation performed by the implantable medical device (IMD) and machine learning classification performed by an external computing device. This segmentation allows the IMD to perform only lightweight feature extraction while offloading the computationally intensive machine learning operations to the external device, thereby maintaining high detection accuracy without increasing the complexity of the implanted device.
Solution Approach 2:
The patent introduces an external computing device as an intermediary between the IMD and the final arrhythmia classification. The IMD extracts features from cardiac electrogram data and transmits them to the external device, which then applies machine learning models for classification. This intermediary approach enables sophisticated analysis without requiring the IMD itself to have high computational capabilities.
2Measurement precision
If machine learning model is applied to cardiac electrogram data, then arrhythmia classification accuracy is improved, but power consumption increases
Solution Approach 1:
The patent segments the computational workload by performing only feature extraction within the power-constrained IMD and relocating the machine learning model execution to an external computing device with adequate power supply. This segmentation enables accurate arrhythmia classification through machine learning while preventing excessive power consumption in the implanted device.
Solution Approach 2:
The patent extracts the computationally intensive machine learning operations from the IMD and places them in the external computing device. By taking out the power-intensive processing tasks from the implanted device, the system maintains high classification accuracy while preserving the limited power resources of the IMD for essential functions like sensing and feature extraction.
3Measurement precision
If comprehensive arrhythmia analysis is performed by IMD, then detection accuracy is improved, but battery lifetime is reduced
Solution Approach 1:
The patent segments the analysis pipeline into lightweight feature extraction (performed by IMD) and comprehensive machine learning classification (performed by external device). This segmentation allows the IMD to maintain accurate detection capabilities through feature-based delineation while avoiding the battery drain associated with running complex machine learning models locally, thereby extending battery lifetime.
Solution Approach 2:
The patent applies partial action by having the IMD perform only the essential feature extraction needed for accurate arrhythmia detection, rather than performing the complete analysis pipeline. The remaining classification tasks are performed partially or excessively by the external device, which has unlimited power resources. This approach achieves comprehensive analysis accuracy without compromising the IMD's battery lifetime.
Data Source
AI summary
Techniques are disclosed for using both feature delineation and machine learning to detect cardiac arrhythmia. A computing device receives cardiac electrogram data of a patient sensed by a medical device. The computing device obtains, via feature-based delineation of the cardiac electrogram data, a first classification of arrhythmia in the patient. The computing device applies a machine learning model to the received cardiac electrogram data to obtain a second classification of arrhythmia in the patient. As one example, the computing device uses the first and second classifications to determine whether an episode of arrhythmia has occurred in the patient. As another example, the computing device uses the second classification to verify the first classification of arrhythmia in the patient. The computing device outputs a report indicating that the episode of arrhythmia has occurred and one or more cardiac features that coincide with the episode of arrhythmia.