Application of Machine Learning in Drug Development and Regulation: Current Status and Future Potential

Application of Machine Learning for Tumor Growth Inhibition – Overall Survival Modeling Platform

“…Increasingly, ML has been explored and accepted as a complementary analytical tool in model-informed drug development. [27][28][29][30] The reported use of ML for survival outcome in oncology has been few and typically limited to using high-dimensional imaging or gene expression data as predictors, [31][32][33] and recently ML was applied to identify the association between baseline biomarker signature and nivolumab clearance, which is linked to survival outcome. 34 An evaluation by the FDA of simulated data showed that ML-based methods outperformed Cox model in survival prediction performance and in identifying the preset influential variables, and the authors of that analysis concluded that ML-based methods provide a powerful tool for time-to-event analysis, due to their capacity for high-dimensional data and better performance when the predictor variables assume nonlinear relationships in the hazard function.…”

“…Because of this capability, a large number of variables that might not reach statistical significance and would be excluded using traditional methods, but nevertheless could cumulatively predict outcome, can be incorporated into an ML model. Increasingly, ML has been explored and accepted as a complementary analytical tool in model‐informed drug development 27–30 …”

Data Science in Clinical Pharmacology and Drug Development for Improving Health Outcomes in Patients

“…23 In our view, there are many exciting opportunities for machine learning to help clinical pharmacologists and drug discovery and development. 24,25 Often the biggest advances occur when different disciplines intersect, and pharmacometrics should be fertile ground to benefit from machine learning-indeed there is already quite a literature on this topic. In this issue we add to the discussion with examples of how machine learning can help pharmacometricians, 26 precision medicine and precision dosing, 25,27 identification of useful drug combinations, 28 and pharmacovigilance.…”

“…The second tutorial in this issue provides a primer in basic machine learning to demystify some concepts, methods, and applications . In our view, there are many exciting opportunities for machine learning to help clinical pharmacologists and drug discovery and development . Often the biggest advances occur when different disciplines intersect, and pharmacometrics should be fertile ground to benefit from machine learning—indeed there is already quite a literature on this topic.…”

“…Often the biggest advances occur when different disciplines intersect, and pharmacometrics should be fertile ground to benefit from machine learning—indeed there is already quite a literature on this topic. In this issue we add to the discussion with examples of how machine learning can help pharmacometricians, precision medicine and precision dosing, identification of useful drug combinations, and pharmacovigilance. We are happy to agree with Brian Corrigan that AI will not replace clinical pharmacologists but instead will help us be more successful.…”