Deep learning analysis of electrocardiogram for risk prediction of drug-induced arrhythmias and diagnosis of long QT syndrome

Edi Prifti (1, 2) , Ahmad Fall (1) , Giovanni Davogustto (3) , Alfredo Pulini (1, 4) , Isabelle Denjoy (5, 4) , Christian Funck-Brentano (6, 7) , Yasmin Khan (8) , Alexandre Durand-Salmon (8) , Fabio Badilini (9) , Quinn Wells (3) , Antoine Leenhardt (5, 4) , Jean-Daniel Zucker (1, 2) , Dan M. Roden (3) , Fabrice Extramiana (4, 5) , Joe-Elie Salem (10, 3)

1 UMMISCO - Unité de modélisation mathématique et informatique des systèmes complexes [Bondy]
2 Nutriomics - Nutrition et obésités: approches systémiques (UMR-S 1269)
3 Vanderbilt University Medical Center [Nashville]
4 Centre de Référence Maladies Cardiaques Héréditaires
5 AP-HP - Hôpital Bichat - Claude Bernard [Paris]
6 ICAN - Unité de Recherche sur les Maladies Cardiovasculaires, du Métabolisme et de la Nutrition = Research Unit on Cardiovascular and Metabolic Diseases
7 CHU Pitié-Salpêtrière [AP-HP]
8 Cardiabase-Banook group [Nancy]
9 AMPS-LLC [New York]
10 CIC Paris-Est - Centre d'investigation clinique Paris Est [CHU Pitié Salpêtrière]

Abstract Aims Congenital long-QT syndromes (cLQTS) or drug-induced long-QT syndromes (diLQTS) can cause torsade de pointes (TdP), a life-threatening ventricular arrhythmia. The current strategy for the identification of drugs at the high risk of TdP relies on measuring the QT interval corrected for heart rate (QTc) on the electrocardiogram (ECG). However, QTc has a low positive predictive value. Methods and results We used convolutional neural network (CNN) models to quantify ECG alterations induced by sotalol, an IKr blocker associated with TdP, aiming to provide new tools (CNN models) to enhance the prediction of drug-induced TdP (diTdP) and diagnosis of cLQTS. Tested CNN models used single or multiple 10-s recordings/patient using 8 leads or single leads in various cohorts: 1029 healthy subjects before and after sotalol intake (n = 14 135 ECGs); 487 cLQTS patients (n = 1083 ECGs: 560 type 1, 456 type 2, 67 type 3); and 48 patients with diTdP (n = 1105 ECGs, with 147 obtained within 48 h of a diTdP episode). CNN models outperformed models using QTc to identify exposure to sotalol [area under the receiver operating characteristic curve (ROC-AUC) = 0.98 vs. 0.72, P ≤ 0.001]. CNN models had higher ROC-AUC using multiple vs. single 10-s ECG (P ≤ 0.001). Performances were comparable for 8-lead vs. single-lead models. CNN models predicting sotalol exposure also accurately detected the presence and type of cLQTS vs. healthy controls, particularly for cLQT2 (AUC-ROC = 0.9) and were greatest shortly after a diTdP event and declining over time (P ≤ 0.001), after controlling for QTc and intake of culprit drugs. ECG segment analysis identified the J-Tpeak interval as the best discriminator of sotalol intake. Conclusion CNN models applied to ECGs outperform QTc measurements to identify exposure to drugs altering the QT interval, congenital LQTS, and are greatest shortly after a diTdP episode.

Mots clés: Machine learning; Risk prediction; Interpretability; Long QT

Mots clés: Torsades de pointes

Domaines: Sciences du Vivant [q-bio]

Edi Prifti, Ahmad Fall, Giovanni Davogustto, Alfredo Pulini, Isabelle Denjoy, et al.. Deep learning analysis of electrocardiogram for risk prediction of drug-induced arrhythmias and diagnosis of long QT syndrome. European Heart Journal, 2021, 42 (38), pp.3948-3961. ⟨10.1093/eurheartj/ehab588⟩. ⟨hal-04006395⟩