How do experts classify sepsis cases for sepsis surveillance? Lessons learned from a Behavioural Artificial Intelligence Technology (BAIT) approach
Inflammatory parameters contributed most to retrospective sepsis and 'suspected infection' identification by experts. BAIT-model accuracy for surveillance was 74-75 %.
Authors
- Hugo R. W. Touw (ORCID: https://orcid.org/0000-0001-5970-0157)
- Jaap ten Oever (ORCID: https://orcid.org/0000-0003-2397-0125)
- Nicolaas Heyning
- Jacobien J. Hoogerwerf (ORCID: https://orcid.org/0000-0001-9957-3703)
- Annebel ten Broeke
- Renée A M Tuinte (ORCID: https://orcid.org/0000-0003-4225-9400)
Institutions
- Radboud University Nijmegen (NL)
- Radboud University Medical Center (NL)
- Radboud Institute for Molecular Life Sciences (NL)
- Delft University of Technology (NL)
Publication Details
- Journal
- Journal of Critical Care
- Published
- 2025-08-08
- DOI
- https://doi.org/10.1016/j.jcrc.2025.155214
- Primary Topic
- Sepsis Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00