Machine learning-enabled assessment of risk of drug-induced QT prolongation at the time of prescribing.

BACKGROUND

Many medications are associated with long QTc. Current long QTc predictors have limited generalizability and/or modest performance.

OBJECTIVE

This study aimed to compare the performance of machine learning-enabled approaches to drug-induced long QTc prediction with current risk scores, including Tisdale and RISQ-PATH.

METHODS

We identified patients who began QTc-prolonging medications (QTdrugs) and had follow-up 12-lead electrocardiograms (ECGs) within 1 year. Using 5-fold cross-validation, we trained XGBoost (XGB), an ECG-based deep neural network, and combined models using electronic health record data and ECG traces to predict QTc of ≥500 ms within 1 year. We assessed performance using the area under the receiver operating characteristic (AUROC) curves and compared them with corresponding Tisdale and RISQ-PATH scores.

RESULTS

QTdrug records were identified for 345,371 patients, 5.7% of whom had long QTc within 1 year. In the subset with baseline ECGs available (N = 182,448; 7.7% events), both the XGB and deep neural network models demonstrated high performance (AUROC 0.869 and 0.864, respectively) but their combination yielded no significant improvement (AUROC 0.874). Therefore, focusing on the XGB model, we observed superior performance vs RISQ-PATH in the overall population (AUROC 0.859 vs 0.701), as well as Tisdale in predominantly inpatients (N = 110,558; 8.8% events; AUROC 0.855 vs 0.770). Positive predictive value was 61.5% vs 28.35% and 54.0% vs 28.3% at equivalent operating points for the XGB model vs RISQ-PATH and Tisdale, respectively.

CONCLUSION

Development and retrospective validation of 3 machine learning-based models for predicting drug-induced long QTc at the time of new QTdrug starts demonstrated superior performance compared with current clinical risk calculators and may be useful tools to support medical decision making when initiating new therapies.