Can Machine Learning from Real-World Data Support Drug Treatment Decisions? A Prediction Modeling Case for Direct Oral Anticoagulants

Abstract

Decision making for the “best” treatment is particularly challenging in situations in which individual patient response to drugs can largely differ from average treatment effects. By estimating individual treatment effects (ITEs), we aimed to demonstrate how strokes, major bleeding events, and a composite of both could be reduced by model-assisted recommendations for a particular direct oral anticoagulant (DOAC). In German claims data, we selected 29 901 new users of the DOACs rivaroxaban and apixaban. Random forests considered binary events within 1 y to estimate ITEs under each DOAC according to the X-learner algorithm with 29 potential effect modifiers; treatment recommendations were based on these estimated ITEs. Model performance was evaluated by the c-for-benefit statistics, absolute risk reduction, and absolute risk difference by trial emulation. A significant proportion of patients would be recommended a different treatment option than they actually received. The stroke model significantly discriminated patients for higher benefit and thus indicated improved decisions by reduced outcomes. In the group with apixaban recommendation, the model also improved the composite endpoint. In trial emulations, model-assisted recommendations significantly reduced the composite event rate. If prescribers are undecided about the potential benefits of different treatment options, ITEs can support decision making, especially if evidence is inconclusive, risk-benefit profiles of therapeutic alternatives differ significantly, and the patients’ complexity deviates from “typical” study populations. In the exemplary case for DOACs and potentially in other situations, the significant impact could also become practically relevant if recommendations were available in an automated way as part of decision making.

Andreas D. Meid

Post-doctoral researcher in Clinical Pharmacology & Pharmacoepidemiology

My research interests include the study of appropriate drug therapy using methods of pharmacoepidemiology, quantitative pharmacology, and pharmacometrics.