Key result
A signal importance mask-driven ECG classification system trained with doctor feedback achieved higher Fmax and Macro AUC scores compared to a normal training baseline.
Why the study?
Existing machine learning systems for ECG interpretation are not as accurate as skilled readers, and black-box diagnostic approaches result in a lack of trust by medical personnel.
Does a signal importance mask feedback-based machine learning system improve classification accuracy and interpretability of 12-lead ECGs compared to standard training?
Does a signal importance mask feedback-based machine learning system improve classification accuracy and interpretability of 12-lead ECGs compared to standard training?
Incorporating expert signal importance mask feedback into machine learning training improves the accuracy and interpretability of automated 12-lead ECG classification.
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.
No takes yet. Share an insight, caveat, or question.
Kc et al. (2021) studied Heart disease (n=21,837). Signal Importance Mask-driven training (FEEDBACK) vs. Normal training baseline (NORMAL) was evaluated on Fmax and Macro AUC scores. A signal importance mask-driven ECG classification system trained with doctor feedback achieved higher Fmax and Macro AUC scores compared to a normal training baseline.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: