Vital Signs–Only Machine Learning Model for Acute Inpatient Deterioration: A Retrospective Multicenter Study
Achieving a high PPV is crucial because it ensures a larger proportion of alerts are true positives, reducing the burden of false alarms. The considerable improvement in results comes from the novel 2-window feature extraction method. This technique enables the model to capture both long-term trends and recent changes in patient status, enhancing predictive performance.
Authors
- Thanawin Trakoolwilaiwan
- Santiago Romero‐Brufau (ORCID: https://orcid.org/0000-0002-9922-0083)
- Gurpreet Singh (ORCID: https://orcid.org/0000-0001-8282-2048)
- Radit Smunyahirun
- Timothée Filhol
- Lucille Niederhauser
Institutions
- Harvard University (US)
- AMS (Singapore) (SG)
- University of Minnesota Rochester (US)
- École Polytechnique Fédérale de Lausanne (CH)
Publication Details
- Journal
- Mayo Clinic Proceedings Innovations Quality & Outcomes
- Published
- 2025-09-23
- DOI
- https://doi.org/10.1016/j.mayocpiqo.2025.100663
- Primary Topic
- Sepsis Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00