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

OBJECTIVE: 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. METHODS: 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. RESULTS: 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; P < .001), ICU admission during stay (aOR, 1.5; 95% CI, 1.2-1.9; P < .001), Charlson comorbidity score (aOR, 1.1; 95% CI, 1.1-1.2; P < .001), the number of different prescribed antibiotics (aOR, 1.6; 95% CI, 1.5-1.7; P < .001), and the number of rooms the patient stayed in during their hospitalization(s) (aOR, 1.1; 95% CI, 1.1-1.2; P < .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. CONCLUSIONS: 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.

Nosocomial outbreak of vancomycin-resistant Enterococcus faecium (VRE) ST796, Switzerland, 2017 to 2020.

A large clonal outbreak caused by vancomycin-resistant Enterococcus faecium (VRE) affected the Bern University Hospital group from the end of December 2017 until July 2020. We describe the characteristics of the outbreak and the bundle of infection prevention and control (IPC) measures implemented. The outbreak was first recognised when two concomitant cases of VRE bloodstream infection were identified on the oncology ward. During 32 months, 518 patients in the 1,300-bed hospital group were identified as vanB VRE carriers. Eighteen (3.5%) patients developed an invasive infection, of whom seven had bacteraemia. In 2018, a subset of 328 isolates were analysed by whole genome sequencing, 312 of which were identified as sequence type (ST) 796. The initial IPC measures were implemented with a focus on the affected wards. However, in June 2018, ST796 caused another increase in cases, and the management strategy was intensified and escalated to a hospital-wide level. The clinical impact of this large nosocomial VRE outbreak with the emergent clone ST796 was modest. A hospital-wide approach with a multimodal IPC bundle was successful against this highly transmissible strain.

Handrub Consumption Mirrors Hand Hygiene Compliance.

We assessed handrub consumption as a surrogate marker for hand hygiene compliance from 2007 to 2014. Handrub consumption varied substantially between departments but correlated in a mixed effects regression model with the number of patient-days and the observed hand hygiene compliance. Handrub consumption may supplement traditional hand hygiene observations. Infect Control Hosp Epidemiol 2016;37:707-710.

Improved hand hygiene compliance after eliminating mandatory glove use from contact precautions-Is less more?

BACKGROUND: Guidelines recommend that health care personnel (HCP) wear gloves for all interactions with patients on contact precautions. We aimed to assess hand hygiene (HH) compliance during contact precautions before and after eliminating mandatory glove use. METHODS: We assessed HH compliance of HCP in the care of patients on contact precautions in 50 series before (2009) and 6 months after (2012) eliminating mandatory glove use and compared these results with the hospital-wide HH compliance. RESULTS: We assessed 426 HH indications before and 492 indications after the policy change. Compared with 2009, we observed a significantly higher HH compliance in patients on contact precautions in 2012 (52%; 95% confidence interval [95% CI], 47-57) vs 85%; 95% CI, 82-88; P < .001). During the same period, hospital-wide HH compliance also increased from 63% (95% CI, 61-65) to 81% (95% CI 80-83) (P < .001). However, the relative improvement (RI) of HH compliance during contact precautions was significantly higher than the hospital-wide relative improvement (RI, 1.6; 95% CI, 1.49-1.81 vs 1.29; 95% CI, 1.25-1.34), with a relative improvement ratio of 1.27 (95% CI, 1.15-1.41). CONCLUSION: Eliminating mandatory glove use in the care of patients on contact precautions increased HH compliance in our institution, particularly before invasive procedures and before patient contacts. Further studies on the effect on pathogen transmission are needed before revisiting the current official guidelines on the topic.