Identifying Decision Points for Safe and Interpretable Reinforcement Learning in Hypotension Treatment
By Kristine Zhang, Yuanheng Wang, Jianzhun Du, Brian Chu, Leo Anthony Celi, R. Kindle, Finale Doshi-Velez. 2021
5 citations recorded by the source corpus.
Many batch RL health applications first discretize time into fixed intervals. However, this discretization both loses resolution and forces a policy computation at each (potentially fine) interval. In this work, we develop a novel framework to compress continuous trajectories into a few, interpretable decision points --places where the batch data support multiple alternatives. We apply our approach to create recommendations from a cohort of hypotensive patients dataset. Our reduced state space results in faster planning and allows easy inspection by a clinical expert.
Subfields: Artificial Intelligence, Epidemiology, Reinforcement Learning, Medical & Health AI
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Lesia Semenova
- Chudi Zhong
- Zhi Chen
- Haiyang Huang
- Cynthia Rudin
- Tong Wang
- Octavio Loyola-González
- Berk Ustun
In Epidemiology
In Reinforcement Learning
In Medical & Health AI
- Lesia Semenova
- Chudi Zhong
- Zhi Chen
- Haiyang Huang
- Cynthia Rudin
- Berk Ustun
- Tong Wang
- Atoosa Kasirzadeh
Citations in the corpus
- Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges (2021, background): “For example, (Zhang et al., 2021) improve over batch RL by computing the policy only at specific decision points, where clinicians treat patients differently, instead of at every timestep.”