Treatment Recommendations for Clinical Deterioration on the Wards: Development and Validation of Machine Learning Models
We found variability in the discrimination of ML models across tasks and model approaches for predicting lifesaving treatments in patients with clinical deterioration. Overall performance was high, and these models could be paired with early warning scores to provide clinicians with timely and actionable treatment recommendations to improve patient care.
Authors
- Yonatan Mintz (ORCID: https://orcid.org/0000-0002-0670-1794)
- MATTHEW M CHURPEK
- Urmila Ravichandran (ORCID: https://orcid.org/0000-0002-3119-2151)
- Madeline Oguss (ORCID: https://orcid.org/0000-0002-4983-8109)
- L. Nezirova
- L. Penumalee
- Kyle A. Carey (ORCID: https://orcid.org/0000-0002-5038-6074)
- Tonela Qyli
- EMILY R GILBERT
- Dana P Edelson
- Majid Afshar
- Sean T Tully
- Eric Pulick
- Nirav S Shah
- Jamila K Picart
Institutions
- Loyola University Medical Center (US)
- NorthShore University HealthSystem (US)
- University of Wisconsin–Madison (US)
- University of Michigan (US)
- University of Chicago (US)
- Northwestern Memorial Hospital (US)
- Evanston Hospital (US)
Publication Details
- Journal
- JMIR AI
- Published
- 2026-01-16
- DOI
- https://doi.org/10.2196/81642
- Primary Topic
- Sepsis Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00