A1 Refereed original research article in a scientific journal
Machine Learning‐Based Prediction of Drug‐Induced QTc Changes in a Large Finnish Biobank Cohort
Authors: Langén, Ville; Winstén, Aleksi; Teppo, Konsta; Pohjonen, Timo; Laukkanen, Jari; Mannermaa, Arto; Niiranen, Teemu J.; Palmu, Joonatan
Publisher: Wiley
Publication year: 2026
Journal: Clinical and Translational Science
Article number: e70577
Volume: 19
Issue: 5
ISSN: 1752-8054
eISSN: 1752-8062
DOI: https://doi.org/10.1111/cts.70577
Publication's open availability at the time of reporting: Open Access
Publication channel's open availability : Open Access publication channel
Web address : https://doi.org/10.1111/cts.70577
Self-archived copy’s web address: https://research.utu.fi/converis/portal/detail/Publication/523487311
Self-archived copy's licence: CC BY NC
Self-archived copy's version: Publisher`s PDF
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.
Downloadable publication This is an electronic reprint of the original article. |  |
Funding information in the publication:
V.L. was supported by a grant from the State Research Funding of the Wellbeing Services County of Southwest Finland. K.T. has received research grants from The Finnish Foundation for Cardiovascular Research, The Finnish Medical Foundation, and The Finnish Foundation for Alcohol studies. J.P. was funded by Paavo Nurmi Foundation and the Finnish Medical Foundation. The funding bodies had no role in the design of the study and collection, analysis, and interpretation of data and in writing the manuscript. This study used FinnGen data, which is funded by two grants from Business Finland (HUS 4685/31/2016 and UH 4386/31/2016) and 14 industry partners: AbbVie Inc., AstraZeneca UK Ltd., Biogen MA Inc., Bristol Myers Squibb (including Celgene Corporation & Celgene International II Sàrl), Genentech Inc., Merck Sharp & Dohme LCC, Pfizer Inc., GlaxoSmithKline Intellectual Property Development Ltd., Sanofi US Services Inc., Maze Therapeutics Inc., Johnson&Johnson Innovative Medicine Inc., Novartis AG, Boehringer Ingelheim International GmbH and Bayer AG. Biobank samples were provided by Auria Biobank, THL Biobank, Helsinki Biobank, Biobank Borealis of Northern Finland, Finnish Clinical Biobank Tampere, Biobank of Eastern Finland, Central Finland Biobank, Finnish Red Cross Blood Service Biobank, Terveystalo Biobank, and Arctic Biobank; all Finnish biobanks are members of the BBMRI.fi infrastructure, coordinated by the Finnish Biobank Cooperative (FINBB).
Open access publishing facilitated by Turun yliopisto, as part of the Wiley - FinELib agreement.
