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

Autor: Cotia ALF; Hospital Israelita Albert Einstein, São Paulo, Brazil. Electronic address: andre.cotia@einstein.br., Scorsato AP; Hospital Israelita Albert Einstein, São Paulo, Brazil., da Silva Victor E; Hospital Israelita Albert Einstein, São Paulo, Brazil., Prado M; Universidade de São Paulo, São Carlos, Brazil., Gagliardi G; Universidade de São Paulo, São Carlos, Brazil., de Barros JEV; Hospital Israelita Albert Einstein, São Paulo, Brazil., Generoso JR Jr; Department of Biomedical Informatics, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA., de Menezes FG; Hospital Israelita Albert Einstein, São Paulo, Brazil., Hsieh MK; Program of Hospital Epidemiology, University of Iowa Health Care, Iowa City, IA, USA., Lopes GOV; Hospital Israelita Albert Einstein, São Paulo, Brazil., Edmond MB; Department of Medicine, West Virginia University School of Medicine, Morgantown, WV, USA., Perencevich EN; Department of Internal Medicine, University of Iowa Carver College of Medicine, Iowa City, IA, USA; Center for Access & Delivery Research & Evaluation (CADRE), Iowa City Veterans Affairs Health Care System, Iowa City, IA, USA., Goto M; Department of Internal Medicine, University of Iowa Carver College of Medicine, Iowa City, IA, USA; Center for Access & Delivery Research & Evaluation (CADRE), Iowa City Veterans Affairs Health Care System, Iowa City, IA, USA., Wey SB; Hospital Israelita Albert Einstein, São Paulo, Brazil., Marra AR; Hospital Israelita Albert Einstein, São Paulo, Brazil; Department of Internal Medicine, University of Iowa Carver College of Medicine, Iowa City, IA, USA; Center for Access & Delivery Research & Evaluation (CADRE), Iowa City Veterans Affairs Health Care System, Iowa City, IA, USA.
Jazyk: angličtina
Zdroj: American journal of infection control [Am J Infect Control] 2024 Sep 21. Date of Electronic Publication: 2024 Sep 21.
DOI: 10.1016/j.ajic.2024.09.012
Abstrakt: Background: Hospital-acquired infections (HAIs) increase morbidity, mortality, and health care 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/National Healthcare Safety Network 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.
(Copyright © 2024 Association for Professionals in Infection Control and Epidemiology, Inc. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: