A novel, standardised approach to balancing effectiveness, efficiency and utility of surveillance AI prediction models for hospitalised patients using sepsis prediction as an exemplar
Evaluations of prediction models for adverse events in hospitalised patients should incorporate the EEU approach in assessing model suitability and selecting alert thresholds.
Authors
- Paul Lane (ORCID: https://orcid.org/0000-0002-9936-1310)
- Robert Webb
- Steven McPhail (ORCID: https://orcid.org/0000-0002-1463-662X)
- Amith Shetty (ORCID: https://orcid.org/0000-0001-7349-1128)
- Anton H. van der Vegt (ORCID: https://orcid.org/0000-0001-5642-5188)
- Ian A Scott (ORCID: https://orcid.org/0000-0002-7596-0837)
- Michael J. Rice (ORCID: https://orcid.org/0000-0001-5189-9587)
- Balasubramanian Venkatesh
- Adam Irwin (ORCID: https://orcid.org/0000-0001-8974-6789)
- Ahmad Abdel‐Hafez (ORCID: https://orcid.org/0000-0001-6022-9745)
- T. Isaacs
- Stephen Whebell (ORCID: https://orcid.org/0000-0002-2604-8657)
- Rudolf J Schnetler (ORCID: https://orcid.org/0000-0001-5129-5601)
- Kathryn Wilks (ORCID: https://orcid.org/0000-0001-9670-4050)
- Victoria Campbell (ORCID: https://orcid.org/0000-0001-9846-9410)
Institutions
- Griffith University (AU)
- The University of Sydney (AU)
- Queensland Health (AU)
- New South Wales Department of Health (AU)
- Queensland University of Technology (AU)
- The University of Queensland (AU)
- The George Institute for Global Health (GB)
- Gold Coast Hospital (AU)
- Townsville Hospital (AU)
- Metro South Health (AU)
- Sunshine Coast University Hospital (AU)
- The George Institute for Global Health (AU)
- Prince Charles Hospital (AU)
- Children's Health Queensland Hospital and Health Service (AU)
- Qatar University (QA)
- National Patient Safety Foundation (US)
Publication Details
- Journal
- Journal of the American Medical Informatics Association
- Published
- 2025-11-11
- DOI
- https://doi.org/10.1093/jamia/ocaf192
- Primary Topic
- Sepsis Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00