Personalising intravenous to oral antibiotic switch decision making through fair interpretable machine learning.

Bolton, William J, Wilson, Richard ORCID: 0000-0002-3275-6932, Gilchrist, Mark, Georgiou, Pantelis, Holmes, Alison ORCID: 0000-0001-5554-5743 and Rawson, Timothy M ORCID: 0000-0002-2630-9722 (2024) Personalising intravenous to oral antibiotic switch decision making through fair interpretable machine learning. Nature communications, 15 (1). p. 506.

Access the full-text of this item by clicking on the Open Access link.

Official URL: http://dx.doi.org/10.1038/s41467-024-44740-2

Abstract

Antimicrobial resistance (AMR) and healthcare associated infections pose a significant threat globally. One key prevention strategy is to follow antimicrobial stewardship practices, in particular, to maximise targeted oral therapy and reduce the use of indwelling vascular devices for intravenous (IV) administration. Appreciating when an individual patient can switch from IV to oral antibiotic treatment is often non-trivial and not standardised. To tackle this problem we created a machine learning model to predict when a patient could switch based on routinely collected clinical parameters. 10,362 unique intensive care unit stays were extracted and two informative feature sets identified. Our best model achieved a mean AUROC of 0.80 (SD 0.01) on the hold-out set while not being biased to individuals protected characteristics. Interpretability methodologies were employed to create clinically useful visual explanations. In summary, our model provides individualised, fair, and interpretable predictions for when a patient could switch from IV-to-oral antibiotic treatment. Prospectively evaluation of safety and efficacy is needed before such technology can be applied clinically.

Item Type:	Article
Uncontrolled Keywords:	Humans, Anti-Bacterial Agents, Administration, Oral, Decision Making, Administration, Intravenous, Machine Learning
Divisions:	Faculty of Health and Life Sciences Faculty of Health and Life Sciences > Institute of Systems, Molecular and Integrative Biology
Depositing User:	Symplectic Admin
Date Deposited:	30 Jan 2024 09:56
Last Modified:	30 Jan 2024 10:56
DOI:	10.1038/s41467-024-44740-2
Open Access URL:	https://doi.org/10.1038/s41467-024-44740-2
Related URLs:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3178070