Key result
Deep learning detects sotalol-induced ECG changes with an AUC of 0.98, outperforming standard QTc measurement.
Why the study?
Measuring QT duration on the ECG to identify individuals at high risk of Torsade-de-Pointes provides limited information.
Does a deep learning model trained on drug-induced ECG changes improve the detection of congenital long QT syndrome and prediction of Torsade-de-Pointes compared to standard QTc measurement?
Observational (n=1,525)
Yes
Does a deep learning model trained on drug-induced ECG changes improve the detection of congenital long QT syndrome and prediction of Torsade-de-Pointes compared to standard QTc measurement?
Deep learning models trained to recognize drug-induced ECG changes can accurately detect sotalol intake, discriminate congenital long-QT types, and predict drug-induced Torsade-de-Pointes better than standard QTc measurements.
Answers are grounded in this paper and cite their sources.
May aid congenital LQTS discrimination and TdP prediction; hypothesis-generating pending prospective validation versus QTc.
Congenital or drug-induced long-QT syndromes can cause Torsade-de-Pointes (TdP), a life-threatening ventricular arrhythmia. The current strategy to identify individuals at high risk of TdP consists on measuring the QT duration on the electrocardiogram (ECG), shown to provide limited information. We propose an original method, including training deep neural networks to recognize ECG alterations induced by QT-prolonging drugs, as a comprehensive evaluation of TdP risk. These models accurately detected patients taking QT prolonging drugs during ECGs, while discriminating for the presence and type of congenital long-QT. Moreover, they enhanced prediction of drug-induced TdP events in addition to QT measurement. Analyses of these models revealed footprints of the torsadogenic risk and clinically relevant patient stratification.
No takes yet. Share an insight, caveat, or question.
Prifti et al. (2021) conducted an observational in Congenital and drug-induced long QT syndrome (n=1,525). Deep learning convolutional neural network (CNN) model vs. QTc measurement was evaluated on Discrimination of sotalol intake on ECG using voting strategy (ROC AUC) (p=<1.5e-141). A deep learning convolutional neural network accurately detected sotalol-induced ECG changes with an AUC of 0.98, significantly outperforming standard QTc measurement.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: