Key result
A convolutional neural network applied to single-lead ECG data distinguished patients with heart failure from healthy controls with an AUC of 0.996 and accurately classified heart failure severity.
Why the study?
Does a CNN algorithm applied to single-lead ECG data accurately classify the severity of heart failure?
Observational (n=7,865)
Does a CNN algorithm applied to single-lead ECG data accurately classify the severity of heart failure?
A deep learning algorithm using single-lead ECG data can highly accurately distinguish heart failure patients from healthy controls, potentially enabling early detection.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Single-lead ECG CNN may enable point-of-care HF screening; leaves open prospective validation before clinical adoption.
Convolutional neural networks (CNNs) applied to electrocardiograms (ECGs) have been showing utility for detecting left ventricular (LV) dysfunction 1 . Although early detection of reduced LV ejection fraction (rEF) could improve handling of heart failure (HF) with rEF (HFrEF), it is not sufficient to detect HF with preserved EF (HFpEF). Here we developed a CNN algorithm to classify the severity of HF based on single-lead ECG data, irrespective of EF. We trained a CNN using ECG data and the HF classification from 7,865 patients with HF. The CNN achieved an area under the receiver-operating characteristic curve (AUC) of 0.996 for distinguishing patients with HF of various severity from healthy controls. It is anticipated that early detection of HF and therapeutic management of HF patients can be improved by employing this CNN with a single-lead ECG device.
Hasumi et al. (2020) conducted an observational in Heart Failure (n=7,865). Convolutional neural network (CNN) applied to single-lead ECG vs. Healthy controls was evaluated on Distinguishing patients with heart failure from healthy controls (AUC 0.996, 95% CI 0.994-0.997). A convolutional neural network applied to single-lead ECG data distinguished patients with heart failure from healthy controls with an AUC of 0.996 and accurately classified heart failure severity.