Pruning the path to optimal care: Identifying systematically suboptimal medical decision-making with inverse reinforcement learning

Abstract

This work uses inverse reinforcement learning to identify systematically suboptimal clinical decisions from observational care trajectories, helping distinguish care patterns that align with better downstream outcomes.

J. Roberto Tello Ayala

Fourth-year PhD Candidate in Applied Mathematics

I develop interpretable model architectures for healthcare and other high-stakes applications.