Artificial Intelligence and Machine Learning for Next-Generation Model-Informed Precision Medicine: A Tutorial on Practical Applications and Pitfalls
Nadia Terranova (1) and Uri Nahum (2,3)
(1) Merck Institute for Pharmacometrics, Ares Trading S.A. (an affiliate of Merck KGaA, Darmstadt, Germany), Lausanne, Switzerland . (2) Institute for Medical Engineering and Medical Informatics, University of Applied Sciences and Arts Northwestern Switzerland, Muttenz, Switzerland. (3) University Children’s Hospital Basel (UKBB), University of Basel
This tutorial will cover the integration of advanced data analytics, specifically Artificial Intelligence (AI) and Machine Learning (ML), into model-informed drug development (MIDD) approaches like Pharmacometrics.
The tutorial will begin with an overview of the value of integrating AI/ML tools into drug-disease modeling approaches by highlighting emerging opportunities coming from the availability of high-dimensional and multimodal data, novel biomarkers and digital, real-world data.
Then, the first main part of the tutorial will cover the application of ML for solving classification and regression problems, with emphasis on revealing the "black box" behavior and preventing overfitting. It discusses approaches to covariate selection using statistics and ML methods, the pitfalls and opportunities of using ML methods, practical advice based on lessons learned, and the integration of domain experts' knowledge into ML algorithms.
In the second main part of the tutorial, attendees will be given an overview of opportunities to advance MIDD at various levels through integration of AI/ML. Examples of applications used to address practical and clinical pharmacometrics questions will be shared, providing attendees with a real-world understanding of how to apply AI/ML to improve drug development.
Overall, this tutorial will provide attendees with an understanding of how to integrate AI/ML into MIDD to improve precision dosing and drug development towards next-generation model-informed precision medicine. Attendees will leave the tutorial with practical knowledge and examples of how to apply AI/ML in the field.