Journal Article

Extending outbreak investigation with machine learning and graph theory: Benefits of new tools with application to a nosocomial outbreak of a multidrug-resistant organism

Ellenberger, Benjamin, Piezzi, Vanja, Leichtle, Alexander B., Marschall, Jonas, Salazar-Vizcaya, Luisa, Endrich, Olga, Atkinson, Andrew, Kaspar, Tanja

2023

Overview

From January 1, 2018, until July 31, 2020, our hospital network experienced an outbreak of vancomycin-resistant enterococci (VRE). The goal of our study was to improve existing processes by applying machine-learning and graph-theoretical methods to a nosocomial outbreak investigation. We assembled medical records generated during the first 2 years of the outbreak period (January 2018 through December 2019). We identified risk factors for VRE colonization using standard statistical methods, and we extended these with a decision-tree machine-learning approach. We then elicited possible transmission pathways by detecting commonalities between VRE cases using a graph theoretical network analysis approach. We compared 560 VRE patients to 86,684 controls. Logistic models revealed predictors of VRE colonization as age (aOR, 1.4 (per 10 years), with 95% confidence interval [CI], 1.3-1.5; < .001), ICU admission during stay (aOR, 1.5; 95% CI, 1.2-1.9; < .001), Charlson comorbidity score (aOR, 1.1; 95% CI, 1.1-1.2; < .001), the number of different prescribed antibiotics (aOR, 1.6; 95% CI, 1.5-1.7; < .001), and the number of rooms the patient stayed in during their hospitalization(s) (aOR, 1.1; 95% CI, 1.1-1.2; < .001). The decision-tree machine-learning method confirmed these findings. Graph network analysis established 3 main pathways by which the VRE cases were connected: healthcare personnel, medical devices, and patient rooms. We identified risk factors for being a VRE carrier, along with 3 important links with VRE (healthcare personnel, medical devices, patient rooms). Data science is likely to provide a better understanding of outbreaks, but interpretations require data maturity, and potential confounding factors must be considered.

• Publisher: Cambridge University Press
• Subject: Anti-Bacterial Agents - therapeutic use / Antibiotic resistance / Antibiotics / Artificial intelligence / Child / Colonization / Contact tracing / Cross Infection - drug therapy / Cross Infection - epidemiology / Cross Infection - prevention & control / Decision trees / Disease control / Disease Outbreaks / Drug resistance / Drug Resistance, Multiple, Bacterial / Electronic health records / Employees / Gram-Positive Bacterial Infections - drug therapy / Gram-Positive Bacterial Infections - epidemiology / Health care / Hospital costs / Hospitals / Humans / Infections / Machine learning / Medical equipment / Medical records / Medical technology / Multidrug resistant organisms / Nosocomial infection / Original / Original Article / Outbreaks / Patients / Regression analysis / Risk Factors / Statistical methods / Vancomycin-Resistant Enterococci