Challenges with reinforcement learning model transportability for sepsis treatment in emergency care
Pivotal moments in sepsis care occur in the emergency department (ED), however, and it is unclear whether ED data is adequate to inform reinforcement learning (RL) models. We evaluated the early opportunity for the AI Clinician, a validated ICU-based RL-model, as a use case. Amongst emergency sepsis patients, model parameters were often missing and invariably measured. Current iterations of RL-models trained on ICU data face challenges in emergency sepsis care.
Authors
- Derek C. Angus (ORCID: https://orcid.org/0000-0002-7026-5181)
- Peter C. Nauka (ORCID: https://orcid.org/0000-0002-6575-4757)
- Romain Pirracchio (ORCID: https://orcid.org/0000-0002-7007-4908)
- Jason Kennedy (ORCID: https://orcid.org/0000-0001-7604-899X)
- Emily Brant (ORCID: https://orcid.org/0000-0002-0207-8210)
- Matthieu Komorowski (ORCID: https://orcid.org/0000-0003-0559-5747)
- Christopher W. Seymour (ORCID: https://orcid.org/0000-0002-6257-6764)
Institutions
- San Francisco General Hospital (US)
- University of Pittsburgh (US)
- University of California, San Francisco (US)
- UPMC Health System (US)
- University of Pittsburgh Medical Center (US)
- Imperial College London (GB)
Publication Details
- Journal
- npj Digital Medicine
- Published
- 2025-02-06
- DOI
- https://doi.org/10.1038/s41746-025-01485-6
- Citations
- 3
- Primary Topic
- Sepsis Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 4.06
Funders
- National Institutes of Health