SIM-ECG: A Signal Importance Mask-driven ECGClassification System
This addresses the need for more reliable and interpretable ECG diagnosis tools for medical personnel, though it appears incremental as it builds on existing machine learning approaches with added feedback mechanisms.
The paper tackles the problem of inaccurate and untrustworthy ECG classification by proposing a feedback-based system that improves accuracy and provides interpretable explanations, showing better F-score and MacroAUC compared to a baseline without feedback.
Heart disease is the number one killer, and ECGs can assist in the early diagnosis and prevention of deadly outcomes. Accurate ECG interpretation is critical in detecting heart diseases; however, they are often misinterpreted due to a lack of training or insufficient time spent to detect minute anomalies. Subsequently, researchers turned to machine learning to assist in the analysis. However, existing systems are not as accurate as skilled ECG readers, and black-box approaches to providing diagnosis result in a lack of trust by medical personnel in a given diagnosis. To address these issues, we propose a signal importance mask feedback-based machine learning system that continuously accepts feedback, improves accuracy, and ex-plains the resulting diagnosis. This allows medical personnel to quickly glance at the output and either accept the results, validate the explanation and diagnosis, or quickly correct areas of misinterpretation, giving feedback to the system for improvement. We have tested our system on a publicly available dataset consisting of healthy and disease-indicating samples. We empirically show that our algorithm is better in terms of standard performance measures such as F-score and MacroAUC compared to normal training baseline (without feedback); we also show that our model generates better interpretability maps.