DEVELOPING CLINICAL PREDICTION MODELS

Abstract

Clinical prediction models are developed to estimate the absolute risk of clinically important outcomes in patients. These models are often designed with the purpose of guiding clinical decision making. Recently, there has been a deluge of publications regarding clinical prediction models due to the resurgence of interest in artificial intelligence. However, very few of these models end up being deployed in the real-world. In this thesis, we discuss the main obstacles facing effective model deployment in healthcare. Clinical prediction models are particularly susceptible to improper development and evaluation due to the inherent heterogeneities in clinical data. Two of the most prevalent heterogeneities in clinical data are batch effects and differences in patient treatment. We discuss these two issues in further detail, and propose a quantitative batch effects metric termed recursive variance partitioning. We also propose a subtype-specific prediction model for treatment outcome in paediatric acute lymphoblastic leukaemia patients.