Key result
ECG-only deep learning predicts malignant ventricular arrhythmia with a 0.79 C-statistic, comparable to multimodality models.
Why the study?
Risk stratification for malignant ventricular arrhythmia in phospholamban p.(Arg14del) variant carriers currently requires a multimodality model, prompting investigation into whether an explainable deep learning approach could predict risk using only ECG data.
Does an explainable deep learning-based ECG-only algorithm accurately predict the risk of malignant ventricular arrhythmia in PLN p.(Arg14del) cardiomyopathy patients compared to multimodality models?
Cohort (n=679)
Does an explainable deep learning-based ECG-only algorithm accurately predict the risk of malignant ventricular arrhythmia in PLN p.(Arg14del) cardiomyopathy patients compared to multimodality models?
Effect estimate: C statistic 0.79 (95% CI 0.76-0.83)
p-value: p=0.054
An explainable deep learning algorithm using only baseline ECG data can accurately predict malignant ventricular arrhythmia in PLN p.(Arg14del) carriers, potentially reducing the need for extensive multimodality testing.
May support ECG-only DL screening to reduce testing in PLN carriers; leaves open prospective validation versus multimodality models.
BACKGROUND: Phospholamban (PLN) p.(Arg14del) variant carriers are at risk for development of malignant ventricular arrhythmia (MVA). Accurate risk stratification allows timely implantation of intracardiac defibrillators and is currently performed with a multimodality prediction model. OBJECTIVE: This study aimed to investigate whether an explainable deep learning-based approach allows risk prediction with only electrocardiogram (ECG) data. METHODS: A total of 679 PLN p.(Arg14del) carriers without MVA at baseline were identified. A deep learning-based variational auto-encoder, trained on 1.1 million ECGs, was used to convert the 12-lead baseline ECG into its FactorECG, a compressed version of the ECG that summarizes it into 32 explainable factors. Prediction models were developed by Cox regression. RESULTS: The deep learning-based ECG-only approach was able to predict MVA with a C statistic of 0.79 (95% CI, 0.76-0.83), comparable to the current prediction model (C statistic, 0.83 [95% CI, 0.79-0.88]; P = .054) and outperforming a model based on conventional ECG parameters (low-voltage ECG and negative T waves; C statistic, 0.65 [95% CI, 0.58-0.73]; P < .001). Clinical simulations showed that a 2-step approach, with ECG-only screening followed by a full workup, resulted in 60% less additional diagnostics while outperforming the multimodal prediction model in all patients. A visualization tool was created to provide interactive visualizations (https://pln.ecgx.ai). CONCLUSION: Our deep learning-based algorithm based on ECG data only accurately predicts the occurrence of MVA in PLN p.(Arg14del) carriers, enabling more efficient stratification of patients who need additional diagnostic testing and follow-up.
No takes yet. Share an insight, caveat, or question.
Leur et al. (2024) conducted a cohort in Phospholamban cardiomyopathy (n=679). Deep learning-based ECG-only prediction model vs. Current multimodality prediction model was evaluated on Malignant ventricular arrhythmia (C statistic 0.79, 95% CI 0.76-0.83, p=0.054). A deep learning-based ECG-only algorithm predicted malignant ventricular arrhythmia with a C statistic of 0.79 (95% CI 0.76-0.83), comparable to the current multimodality model (P=0.054).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: