Key result
Convolutional neural network detects HCM from single-lead ECGs with ~96% accuracy.
Why the study?
The diagnosis of hypertrophic cardiomyopathy is significant for early sudden cardiac death risk classification and family screening, but conventional detection methods face technical limitations from relying on multi-lead ECG.
Can a deep convolutional neural network model accurately detect hypertrophic cardiomyopathy using single-lead ECG signals?
Population
108 ECG records (14,459 heartbeats) from three PhysioNet public databases
Comparison
CNN model automatic detection vs reference standard
Design
Algorithm development and validation study
Authors
Loading...
May enable convenient single-lead ECG screening for HCM; leaves open prospective validation and outcome impact.
Can a deep convolutional neural network model accurately detect hypertrophic cardiomyopathy using single-lead ECG signals?
A deep convolutional neural network model using single-lead ECG signals can accurately detect hypertrophic cardiomyopathy, potentially aiding in fast and convenient large-scale preliminary screening.
Bu et al. (2022) studied Hypertrophic cardiomyopathy (n=78). Convolutional neural network (CNN) model vs. Control group (healthy subjects and other non-HCM conditions) was evaluated on Accuracy of HCM detection. The optimized convolutional neural network model effectively detected hypertrophic cardiomyopathy using single-lead ECG signals, achieving an accuracy of 95.98%, sensitivity of 98.03%, and specificity of 95.79%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: