Integration of an electronic hand hygiene auditing system with electronic health records using machine learning to predict hospital-acquired infection in a healthcare setting

Andre Luis Franco Cotia; Anderson Paulo Scorsato; Elivane da Silva Victor; Marcelo Prado; Guilherme Gagliardi; José Edgar Vieira; José R Generoso Jr; Fernando Gatti de Menezes; Mariana Kim Hsieh; Gabriel O.V. Lopes; Michael B. Edmond; Eli N. Perencevich; Michihiko Goto; Sérgio B. Wey; Alexandre R. Marra

doi:10.1016/j.ajic.2024.09.012

Back

Integration of an electronic hand hygiene auditing system with electronic health records using machine learning to predict hospital-acquired infection in a healthcare setting

Journal article

Peer reviewed

Integration of an electronic hand hygiene auditing system with electronic health records using machine learning to predict hospital-acquired infection in a healthcare setting

Andre Luis Franco Cotia, Anderson Paulo Scorsato, Elivane da Silva Victor, Marcelo Prado, Guilherme Gagliardi, José Edgar Vieira, José R Generoso Jr, Fernando Gatti de Menezes, Mariana Kim Hsieh, Gabriel O.V. Lopes, …

American journal of infection control, Vol.53(1), pp.58-64

01/2025

DOI: 10.1016/j.ajic.2024.09.012

PMID: 39312966

View Online

Abstract

Background Hospital-acquired infections (HAIs) increase morbidity, mortality, and healthcare costs. Effective hand hygiene (HH) is crucial for prevention, but achieving high compliance remains challenge. This study explores using machine learning to integrate an electronic HH auditing system with electronic health records to predict HAIs. Methods A retrospective cohort study was conducted at a Brazilian hospital during 2017-2020. HH compliance was recorded electronically, and patient data were collected from electronic health records. The primary outcomes were HAIs per CDC/NHSN surveillance definitions. Machine learning algorithms, balanced with Random Over Sampling Examples (ROSE), were utilized for predictive modeling, including generalized linear models (GLM); generalized additive models for location, scale, and shape (GAMLSS); random forest; support vector machine; and extreme gradient boosting (XGboost). Results 125 of 6,253 patients (2%) developed HAIs and 920,489 HH opportunities (49.3% compliance) were analyzed. A direct correlation between HH compliance and HAIs was observed. The GLM algorithm with ROSE demonstrated superior performance, with 84.2% sensitivity, 82.9% specificity, and a 93% AUC. Conclusions Integrating electronic HH auditing systems with electronic health records and using machine learning models can enhance infection control surveillance and predict patient outcomes. Further research is needed to validate these findings and integrate them into clinical practice.

Hand hygiene

Health care-associated infection

Supervising learning

Predictive models

Infection prediction

Details

Title: Subtitle: Integration of an electronic hand hygiene auditing system with electronic health records using machine learning to predict hospital-acquired infection in a healthcare setting
Creators: Andre Luis Franco Cotia - Hospital Israelita Albert Einstein
Anderson Paulo Scorsato - Hospital Israelita Albert Einstein
Elivane da Silva Victor
Marcelo Prado - Universidade de São Paulo
Guilherme Gagliardi - Universidade de São Paulo
José Edgar Vieira
José R Generoso Jr
Fernando Gatti de Menezes - Hospital Israelita Albert Einstein
Mariana Kim Hsieh - University of Iowa
Gabriel O.V. Lopes
Michael B. Edmond - West Virginia University
Eli N. Perencevich - Iowa City VA Health Care System
Michihiko Goto - University of Iowa
Sérgio B. Wey - Hospital Israelita Albert Einstein
Alexandre R. Marra - University of Iowa
Resource Type: Journal article
Publication Details: American journal of infection control, Vol.53(1), pp.58-64
Publisher: MOSBY-ELSEVIER; NEW YORK
DOI: 10.1016/j.ajic.2024.09.012
PMID: 39312966
ISSN: 0196-6553
eISSN: 1527-3296
Language: English
Electronic publication date: 09/21/2024
Date published: 01/2025
Academic Unit: Epidemiology; General Internal Medicine; Internal Medicine
Record Identifier: 9984719238802771

Metrics

6 Record Views

See more details