A deep learning model using only lead-I ECG data detected myocardial infarction with an AUC of 0.92, compared to an AUC of 0.99 for 6-lead and 12-lead configurations.
Does a deep learning model using lead-I ECG data accurately detect myocardial infarction compared to multi-lead configurations?
Deep learning applied to single-lead (lead-I) ECG data demonstrates high diagnostic accuracy for detecting myocardial infarction, highlighting the potential for wearable device-based screening.
Effect estimate: AUC 0.92
Absolute Event Rate: 0.92% vs 0.99%
Myocardial Infarction (MI) is a major global health concern due to its high mortality and morbidity rates. Early detection of MI is crucial for timely medical intervention and improved patient outcomes. In this study, we investigate the feasibility of predicting MI using lead-I of electrocardiogram (ECG) data, with a focus on practical applications for wearable monitoring systems. Utilizing the PTB-XL dataset, which includes a comprehensive collection of 12-lead ECG recordings with both normal and various MI samples, we employ deep learning techniques to develop a binary classification model. For MI detection using lead-I, we achieved an AUC of 0.92 and an AUPR of 0.82 on the test set. In comparison, using 6-lead and 12-lead configurations both resulted in an AUC of 0.99. These findings demonstrate the potential for detecting MI using only lead-I, as measured by wearable devices. This advancement could significantly enhance clinical outcomes for MI patients by enabling timely detection and intervention.
Davarmanesh et al. (Tue,) conducted a other in Myocardial Infarction. Deep learning model using lead-I ECG data vs. 6-lead and 12-lead ECG configurations was evaluated on MI detection (AUC) (AUC 0.92). A deep learning model using only lead-I ECG data detected myocardial infarction with an AUC of 0.92, compared to an AUC of 0.99 for 6-lead and 12-lead configurations.