EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Informing antimicrobial stewardship with explainable AI

Massimo Cavallaro iD, Ed Moran, Benjamin Collyer, Noel D McCarthy, Christopher Green iD, Matt J Keeling

PLOS Digital Health · 05.01.2023 · 2 (1) · e0000162

DOI: 10.1371/journal.pdig.0000162 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Digital Health, online erschienen am 05.01.2023. Verfasst von Massimo Cavallaro und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Life Sciences and Mathematics Institute, University of Warwick, Coventry, United Kingdom. Die Arbeit wurde bisher 51-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Medical Research Council, HDRUK, UK Research and Innovation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The accuracy and flexibility of artificial intelligence (AI) systems often comes at the cost of a decreased ability to offer an intuitive explanation of their predictions. This hinders trust and discourage adoption of AI in healthcare, exacerbated by concerns over liabilities and risks to patients’ health in case of misdiagnosis. Providing an explanation for a model’s prediction is possible due to recent advances in the field of interpretable machine learning. We considered a data set of hospital admissions linked to records of antibiotic prescriptions and susceptibilities of bacterial isolates. An appropriately trained gradient boosted decision tree algorithm, supplemented by a Shapley explanation model, predicts the likely antimicrobial drug resistance, with the odds of resistance informed by characteristics of the patient, admission data, and historical drug treatments and culture test results. Applying this AI-based system, we found that it substantially reduces the risk of mismatched treatment compared with the observed prescriptions. The Shapley values provide an intuitive association between observations/data and outcomes; the associations identified are broadly consistent with expectations based on prior knowledge from health specialists. The results, and the ability to attribute confidence and explanations, support the wider adoption of AI in healthcare.

Autor:innen und Institutionen

  • School of Life Sciences and Mathematics Institute, University of Warwick, Coventry, United Kingdom.
  • The Zeeman Institute for Systems Biology & Infectious Disease Epidemiology Research, University of Warwick, Coventry, United Kingdom.
  • Department of Infectious Disease, North Bristol NHS Trust, Bristol, United Kingdom.
  • Faculty of Medicine, School of Public Health, Imperial College London, London, United Kingdom.
  • Institute of Population Health, Trinity College Dublin, University of Dublin, Dublin, Ireland.
  • Warwick Medical School, University of Warwick, Coventry, United Kingdom.

ORCID-Profile: Massimo Cavallaro, Christopher Green

Förderung

  • Medical Research Council
  • HDRUK
  • UK Research and Innovation
  • National Institute for Health Research Health Protection Research Unit

Zitieren

APA

Cavallaro, M., Moran, E., Collyer, B., McCarthy, N. D., Green, C., & Keeling, M. J. (2023). Informing antimicrobial stewardship with explainable AI. PLOS Digital Health, 2(1), e0000162. https://doi.org/10.1371/journal.pdig.0000162

Vancouver

Cavallaro M, Moran E, Collyer B, McCarthy ND, Green C, Keeling MJ. Informing antimicrobial stewardship with explainable AI. PLOS Digital Health. 2023;2(1):e0000162. doi:10.1371/journal.pdig.0000162

BibTeX
@article{Cavallaro2023,
  author = {Cavallaro, Massimo and Moran, Ed and Collyer, Benjamin and McCarthy, Noel D and Green, Christopher and Keeling, Matt J},
  title = {Informing antimicrobial stewardship with explainable AI},
  journal = {PLOS Digital Health},
  year = {2023},
  volume = {2},
  number = {1},
  pages = {e0000162},
  doi = {10.1371/journal.pdig.0000162}
}
Kostenlos starten →