ICU-Sepsis: A Benchmark MDP Built from Real Medical Data

By Kartik Choudhary, Dhawal Gupta, and Philip S. Thomas

Reinforcement Learning Journal, vol. 4, 2024, pp. 1546–1566.

Presented at the Reinforcement Learning Conference (RLC), Amherst Massachusetts, August 9–12, 2024.


Download:

Abstract:

We present *ICU-Sepsis*, an environment that can be used in benchmarks for evaluating reinforcement learning (RL) algorithms. Sepsis management is a complex task that has been an important topic in applied RL research in recent years. Therefore, MDPs that model sepsis management can serve as part of a benchmark to evaluate RL algorithms on a challenging real-world problem. However, creating usable MDPs that simulate sepsis care in the ICU remains a challenge due to the complexities involved in acquiring and processing patient data. ICU-Sepsis is a lightweight environment that models personalized care of sepsis patients in the ICU. The environment is a tabular MDP that is widely compatible and is challenging even for state-of-the-art RL algorithms, making it a valuable tool for benchmarking their performance. However, we emphasize that while ICU-Sepsis provides a standardized environment for evaluating RL algorithms, it should not be used to draw conclusions that guide medical practice.


Citation Information:

Kartik Choudhary, Dhawal Gupta, and Philip S Thomas. "ICU-Sepsis: A Benchmark MDP Built from Real Medical Data." Reinforcement Learning Journal, vol. 4, 2024, pp. 1546–1566.

BibTeX:

@article{choudhary2024sepsis,
    title={{ICU-Sepsis}: {A} Benchmark {MDP} Built from Real Medical Data},
    author={Choudhary, Kartik and Gupta, Dhawal and Thomas, Philip S.},
    journal={Reinforcement Learning Journal},
    volume={4},
    pages={1546--1566},
    year={2024}
}