False hope of a single generalisable AI sepsis prediction model: bias and proposed mitigation strategies for improving performance based on a retrospective multisite cohort study
Implementing a single sepsis prediction model across all sites and care locations within multihospital systems may be unacceptable given large variances in NNE across multiple sites. Bias mitigation methods can identify models demonstrating improved performance across most sites in reducing alert burden but with no impact on the length of the prediction window.
Authors
- Paul Lane (ORCID: https://orcid.org/0000-0002-9936-1310)
- Anton H. van der Vegt (ORCID: https://orcid.org/0000-0001-5642-5188)
- Ian A Scott (ORCID: https://orcid.org/0000-0002-7596-0837)
- Vikrant R Kalke (ORCID: https://orcid.org/0000-0002-0854-6177)
- Rudolf J Schnetler (ORCID: https://orcid.org/0000-0001-5129-5601)
Institutions
- The University of Queensland (AU)
- Townsville Hospital (AU)
- Queensland Government (AU)
- Metro South Health (AU)
- Prince Charles Hospital (AU)
Publication Details
- Journal
- BMJ Quality & Safety
- Published
- 2025-03-26
- DOI
- https://doi.org/10.1136/bmjqs-2024-018328
- Citations
- 6
- Primary Topic
- Sepsis Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 8.13