Feed

Prolongation of the QT interval is a known precursor to serious arrhythmias and sudden cardiac death, often triggered by medication use. Current medication risk evaluation platforms rely on literature-based synthesis and may lag behind real-world developments. We aimed to evaluate whether a machine learning (ML) model trained on real-world genomic and medication data can identify associations between drug use and QTc duration, potentially enabling automated risk detection in clinical workflows. We included 10,208 individuals from the FinnGen biobank Expansion Area 3 substudy, integrating prescription records, clinical variables, and genetic information. We applied a nested-cross-validation approach to develop an ML framework to predict QTc duration using clinical characteristics, recent medication purchases, and polygenic score for QTc duration. We performed conventional linear regression analyses to estimate the robustness of the findings. Only a minority of ML-detected drug-QTc associations aligned with known effects listed in expert-curated reference. Several apparent false positives were observed, and effect sizes for true positives, such as amiodarone, were small and likely interpreted as clinically not meaningful (+1 ms in ML vs. +49 ms in linear regression). These findings highlight challenges in using ML to detect meaningful drug effects on ECG. ML models did not reliably identify medications associated with QT-interval prolongation. Consequently, risk quantification using QTc as an intermediate marker of electrophysiological vulnerability was limited in this framework. While new approaches continue to develop in medication safety assessment, a systematic evidence review conducted by clinical pharmacology experts is unlikely to be supplanted in the foreseeable future.