EUVIMEDEUVIMED entdecken
Crossref

Machine-learning-based risk assessment tool to rule out empirical use of ESBL-targeted therapy in endemic areas

H D Ravkin, R M Ravkin, E Rubin, L Nesher

Journal of Hospital Infection · 2024

DOI: 10.1016/j.jhin.2024.04.005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Hospital Infection, 2024. Verfasst von H D Ravkin und 3 weiteren Autor:innen. Beteiligte Einrichtung: Goldman Medical School, Faculty of Health Sciences, Ben-Gurion University of the Negev, Beer Sheva, Israel. Hauptthemen laut MEDLINE: Machine Learning, Klebsiella pneumoniae, beta-Lactamases, Escherichia coli. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 19 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Antimicrobial stewardship focuses on identifying patients who require extended-spectrum beta-lactamase (ESBL)-targeted therapy. 'Rule-in' tools have been researched extensively in areas of low endemicity; however, such tools are inadequate for areas with high prevalence of ESBL-producing pathogens, as almost all patients will be selected. AIM: To develop a machine-learning-based 'rule-out' tool suitable for areas with high levels of resistance. METHODS: Gradient-boosted decision trees were used to train and validate a risk prediction model on data from 17,913 (45% ESBL) patients with Escherichia coli and Klebsiella pneumoniae in urine cultures. The predictive power of different sets of variables was evaluated using Shapley values to evaluate the contributions of variables. FINDINGS: The model successfully identified patients with low risk of ESBL resistance in ESBL-endemic areas (area under receiver operating characteristic curve 0.72). When used to select the 30% of patients with the lowest predicted risk, the model yielded a negative predictive value ≥0.74. A simplified model with seven input features was found to perform nearly as well as the full model. This simplified model is freely accessible as a web application. CONCLUSIONS: This study found that a risk calculator for antibiotic resistance can be a viable 'rule-out' strategy to reduce the use of ESBL-targeted therapy in ESBL-endemic areas. The robust performance of a version of the model with limited features makes the clinical use of such a tool feasible. This tool provides an important alternative in an era with growing rates of ESBL-producing pathogens, where some experts have called for empirical use of carbapenems as first-line therapy for all patients in areas with high prevalence of ESBL-producing pathogens.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningKlebsiella pneumoniaebeta-LactamasesEscherichia coliKlebsiella InfectionsHumansRisk AssessmentMaleEscherichia coli InfectionsFemaleAnti-Bacterial AgentsMiddle AgedAgedAntimicrobial StewardshipAged, 80 and overAdultbeta-Lactam Resistance

Stichwörter der Autor:innen

Antibiotic stewardshipAntimicrobial resistanceArtificial intelligenceData scienceExtended-spectrum beta-lactamaseMedical informatics

Substanzen

beta-LactamasesAnti-Bacterial Agents

Autor:innen und Institutionen

  • Goldman Medical School, Faculty of Health Sciences, Ben-Gurion University of the Negev, Beer Sheva, Israel.
  • Department of Medical Applications, Clalit Health Services, Tel-Aviv, Israel.
  • Shraga Segal Department of Microbiology, Immunology and Genetics, Ben-Gurion University of the Negev, Beer Sheva, Israel.
  • Goldman Medical School, Faculty of Health Sciences, Ben-Gurion University of the Negev, Beer Sheva, Israel; Infectious Diseases Institute, Soroka University Medical Centre, Beer-Sheva, Israel. Electronic address: nesher…

Zitieren

APA

Ravkin, H. D., Ravkin, R. M., Rubin, E., & Nesher, L. (2024). Machine-learning-based risk assessment tool to rule out empirical use of ESBL-targeted therapy in endemic areas. Journal of Hospital Infection. https://doi.org/10.1016/j.jhin.2024.04.005

Vancouver

Ravkin HD, Ravkin RM, Rubin E, Nesher L. Machine-learning-based risk assessment tool to rule out empirical use of ESBL-targeted therapy in endemic areas. Journal of Hospital Infection. 2024. doi:10.1016/j.jhin.2024.04.005

BibTeX
@article{Ravkin2024,
  author = {Ravkin, H D and Ravkin, R M and Rubin, E and Nesher, L},
  title = {Machine-learning-based risk assessment tool to rule out empirical use of ESBL-targeted therapy in endemic areas},
  journal = {Journal of Hospital Infection},
  year = {2024},
  doi = {10.1016/j.jhin.2024.04.005}
}
Kostenlos starten →