Paper ID: 2412.07895 • Published Dec 10, 2024
How Should We Represent History in Interpretable Models of Clinical Policies?
Anton Matsson, Lena Stempfle, Yaochen Rao, Zachary R. Margolin, Heather J. Litman, Fredrik D. Johansson
TL;DR
Get AI-generated summaries with premium
Get AI-generated summaries with premium
Modeling policies for sequential clinical decision-making based on
observational data is useful for describing treatment practices, standardizing
frequent patterns in treatment, and evaluating alternative policies. For each
task, it is essential that the policy model is interpretable. Learning accurate
models requires effectively capturing the state of a patient, either through
sequence representation learning or carefully crafted summaries of their
medical history. While recent work has favored the former, it remains a
question as to how histories should best be represented for interpretable
policy modeling. Focused on model fit, we systematically compare diverse
approaches to summarizing patient history for interpretable modeling of
clinical policies across four sequential decision-making tasks. We illustrate
differences in the policies learned using various representations by breaking
down evaluations by patient subgroups, critical states, and stages of
treatment, highlighting challenges specific to common use cases. We find that
interpretable sequence models using learned representations perform on par with
black-box models across all tasks. Interpretable models using hand-crafted
representations perform substantially worse when ignoring history entirely, but
are made competitive by incorporating only a few aggregated and recent elements
of patient history. The added benefits of using a richer representation are
pronounced for subgroups and in specific use cases. This underscores the
importance of evaluating policy models in the context of their intended use.