Graph convolutional network-based fusion model to predict risk of hospital acquired infections
Authors:
- 7 April 2023
- journal article
- research article
- Published by Oxford University Press (OUP) in Journal of the American Medical Informatics Association
- Vol. 30 (6) , 1056-1067
Abstract
Objective: Hospital acquired infections (HAIs) are one of the top 10 leading causes of death within the United States. While current standard of HAI risk prediction utilizes only a narrow set of predefined clinical variables, we propose a graph convolutional neural network (GNN)-based model which incorporates a wide variety of clinical features. Materials and Methods: Our GNN-based model defines patients’ similarity based on comprehensive clinical history and demographics and predicts all types of HAI rather than focusing on a single subtype. An HAI model was trained on 38 327 unique hospitalizations while a distinct model for surgical site infection (SSI) prediction was trained on 18 609 hospitalization. Both models were tested internally and externally on a geographically disparate site with varying infection rates. Results: The proposed approach outperformed all baselines (single-modality models and length-of-stay [LoS]) with achieved area under the receiver operating characteristics of 0.86 [0.84–0.88] and 0.79 [0.75–0.83] (HAI), and 0.79 [0.75–0.83] and 0.76 [0.71–0.76] (SSI) for internal and external testing. Cost-effective analysis shows that the GNN modeling dominated the standard LoS model strategy on the basis of lower mean costs ($1651 vs $1915). Discussion: The proposed HAI risk prediction model can estimate individualized risk of infection for patient by taking into account not only the patient’s clinical features, but also clinical features of similar patients as indicated by edges of the patients’ graph. Conclusions: The proposed model could allow prevention or earlier detection of HAI, which in turn could decrease hospital LoS and associated mortality, and ultimately reduce the healthcare cost.Keywords
Funding Information
- National Institute of Health (1U01CA269264-01)
This publication has 30 references indexed in Scilit:
- Cost-effectiveness of national mandatory screening of all admissions to English National Health Service hospitals for meticillin-resistant Staphylococcus aureus: a mathematical modelling studyThe Lancet Infectious Diseases, 2016
- A Simple Prediction Score for Developing a Hospital-Acquired Infection after Acute Ischemic StrokeJournal of Stroke and Cerebrovascular Diseases, 2015
- Updating Cost-Effectiveness — The Curious Resilience of the $50,000-per-QALY ThresholdNew England Journal of Medicine, 2014
- Cost-effectiveness of Competing Strategies for Management of Recurrent Clostridium difficile Infection: A Decision AnalysisClinical Infectious Diseases, 2014
- Health Care–Associated InfectionsJAMA Internal Medicine, 2013
- Predicting Hospital-Acquired Infections by Scoring System with Simple ParametersPLOS ONE, 2011
- The Business Case for QualityAmerican Journal of Medical Quality, 2011
- Hospital-Acquired Infections Due to Gram-Negative BacteriaNew England Journal of Medicine, 2010
- Nosocomial Infection UpdateEmerging Infectious Diseases, 1998
- Recommendations of the Panel on Cost-Effectiveness in Health and MedicineJAMA, 1996