Machine learning and clinician predictions of antibiotic resistance in Enterobacterales bloodstream infections
Predicting AMR in bloodstream infections is challenging for both clinicians and models. Despite modest performance, machine learning models could still increase the proportion of patients receiving active empirical treatment by up to 9% over current clinical practice in an environment prioritising antimicrobial stewardship.
Authors
- Jia Wei (ORCID: https://orcid.org/0000-0001-9621-529X)
- A Sarah Walker (ORCID: https://orcid.org/0000-0003-0421-9264)
- Kevin Yuan (ORCID: https://orcid.org/0000-0003-1283-2712)
- Tingting Zhu (ORCID: https://orcid.org/0000-0002-1552-5630)
- David W. Eyre (ORCID: https://orcid.org/0000-0001-5095-6367)
- Augustine Luk
Institutions
- Open Data Institute (GB)
- University of Oxford (GB)
- Oxford BioMedica (United Kingdom) (GB)
Publication Details
- Journal
- Journal of Infection
- Published
- 2024-12-30
- DOI
- https://doi.org/10.1016/j.jinf.2024.106388
- Citations
- 9
- Primary Topic
- Bacterial Identification and Susceptibility Testing
- Type
- article
- Field-Weighted Citation Impact
- 3.43
Funders
- National Institute for Health and Care Research
- University of Oxford
- NIHR Oxford Biomedical Research Centre