|
Abstract:
|
There has recently been an explosion of interest and activity in personalized medicine. However, the goal of personalized medicine-wherein treatments are targeted to take into account patient heterogeneity-has been a focus of medicine for centuries. Precision medicine, on the other hand, is a much more recent refinement which seeks to develop personalized medicine that is empirically based, scientifically rigorous, and reproducible. In this presentation, we describe several new machine learning developments which advance this quest through discovering either prognostic biomarkers or predictive biomarkers associated with individualized treatment rules based on patient-level features. One of these new approaches is latent supervised learning which can identify prognostic biomarkers delineating between unknown subgroups differing in clinical outcomes. Another new approach is outcome weighted learning, or O-learning, which identifies predictive biomarkers obtained from directly estimating decision rules without requiring regression modeling and are thus robust to model misspecification. Several clinical examples illustrating these approaches will be given.
|
