Deep reinforcement learning extracts the optimal sepsis treatment policy from treatment records
Our results demonstrate that the patient treatment model can extract potential optimal sepsis treatment policy. We also extract core information about sepsis treatment by analyzing its policy. These results may not apply directly in clinical settings because they were only tested on a database. However, they are expected to serve as important guidelines for further research.
Authors
- Ho-Taek Joo (ORCID: https://orcid.org/0000-0002-2286-3216)
- Hosu Lee (ORCID: https://orcid.org/0000-0002-8702-5993)
- Jin Won Huh (ORCID: https://orcid.org/0000-0002-3449-0461)
- Weiyi You (ORCID: https://orcid.org/0000-0003-4993-1204)
- Kyung-Joong Kim (ORCID: https://orcid.org/0000-0002-7732-0817)
- Jae Hun Choi (ORCID: https://orcid.org/0000-0002-2988-6955)
- Yunho Choi (ORCID: https://orcid.org/0000-0002-6804-1891)
- S. T. Oh (ORCID: https://orcid.org/0000-0002-0532-1386)
- Cheng-mok Bae
Institutions
- Electronics and Telecommunications Research Institute (KR)
- Gyeongsang National University (KR)
- Asan Medical Center (KR)
- Gwangju Institute of Science and Technology (KR)
Publication Details
- Journal
- Communications Medicine
- Published
- 2024-11-22
- DOI
- https://doi.org/10.1038/s43856-024-00665-x
- Citations
- 10
- Primary Topic
- Sepsis Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 3.87
Funders
- National Research Foundation
- Gwangju Institute of Science and Technology
- Gyeongsang National University
- Ministry of Education
- Electronics and Telecommunications Research Institute
- National Research Foundation of Korea
- Ministry of Science and ICT, South Korea
- Institute for Information and Communications Technology Promotion