Performance of machine learning versus the national early warning score for predicting patient deterioration risk: a single-site study of emergency admissions
Our findings suggests that machine learning models using free-text data have the potential to improve clinical decision-making in the ED; our techniques significantly reduce alert rate while detecting most high-risk patients missed by NEWS.
Authors
- Pinkie Chambers (ORCID: https://orcid.org/0000-0002-6669-9411)
- Darren Green (ORCID: https://orcid.org/0000-0002-9370-8176)
- Matthew Watson (ORCID: https://orcid.org/0000-0001-6375-3905)
- Noura Al Moubayed (ORCID: https://orcid.org/0000-0001-8942-355X)
- Stelios Boulitsakis Logothetis (ORCID: https://orcid.org/0009-0004-7622-9423)
- Mark Holland (ORCID: https://orcid.org/0000-0001-8336-5336)
Institutions
- University of Greater Manchester (GB)
- Durham University (GB)
- University of Cambridge (GB)
- University of Manchester (GB)
- University College London (GB)
Publication Details
- Journal
- BMJ Health & Care Informatics
- Published
- 2024-12-01
- DOI
- https://doi.org/10.1136/bmjhci-2024-101088
- Citations
- 3
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 1.04
Funders
- National Institute for Health and Care Research
- Innovate UK