Pruning the path to optimal care: Identifying systematically suboptimal medical decision-making with inverse reinforcement learning
Inko Bovenzi, Adi Carmel, Michael Hu, Rebecca Hurwitz, Fiona McBride, Leo Benac, Jose Roberto Tello Ayala, Finale Doshi-Velez
May, 2025
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.
- Type
- Conference paper
- Publication
- In AMIA Annual Symposium Proceedings 2024

PhD Candidate in Applied Mathematics
I develop interpretable machine-learning methods for clinical decision-making, with applications in cardiovascular imaging and precision psychiatry.