Key result
Deep learning on implantable loop recorder ECGs predicts LVEF <40% with ~75% accuracy.
Why the study?
Studies using artificial intelligence to identify left ventricular systolic dysfunction from only a single lead ambulatory ECG are limited.
Does a CNN-based deep learning algorithm using single-lead ambulatory ECG accurately detect LVEF <40% in patients with implantable loop recorders?
Observational (n=2,999)
Does a CNN-based deep learning algorithm using single-lead ambulatory ECG accurately detect LVEF <40% in patients with implantable loop recorders?
Effect estimate: AUC 0.8
A deep learning algorithm applied to single-lead ambulatory ECG from implantable loop recorders can detect reduced ejection fraction with moderate accuracy, potentially enabling remote monitoring for left ventricular systolic dysfunction.
Early detection of left ventricular systolic dysfunction (LVSD) using minimally invasive electrocardiographic assessment in an ambulatory setting may be important considering the increasing economic burden of heart failure. Recently artificial intelligence (AI) algorithms have been reported to classify reduced ejection fraction using a 12-lead ECG measurement snapshot. However, the studies of AI to identify LVSD using only a single lead ambulatory ECG (aECG) are limited. We developed a convolution neural network based deep learning algorithm (CNN-aECG) to predict left ventricular ejection fraction (LVEF) less than 40% using aECG from implantable loop recorders (ILR). A total of 35,741 unique LVEF-aECG pairs collected from 2,249 ILR patients were used to train the model. The model yielded accuracy, sensitivity, specificity, and AUC of 75%, 70%, 76% and 0.8 respectively in the independent test set of 6,611 unique LVEF-aECG pairs from 750 patients. This proposed method of ambulatory CNN-aECG monitoring may allow for identifying reduced ejection fraction post ILR implant via remote monitoring.
No takes yet. Share an insight, caveat, or question.
Vasudevan et al. (2023) conducted an observational in Left ventricular systolic dysfunction (n=2,999). Convolution neural network based deep learning algorithm (CNN-aECG) was evaluated on Prediction of left ventricular ejection fraction (LVEF) <40% (AUC 0.8). A deep learning algorithm using single-lead ambulatory ECG from implantable loop recorders predicted left ventricular ejection fraction <40% with an AUC of 0.8, 75% accuracy, and 70% sensitivity.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: