In The Journal of hospital infection
BACKGROUND : Increasing prevalence of antibiotic resistant organisms (AROs) is a growing economic and healthcare challenge. Increasing utilization of electronic medical record (EMR) systems and improvements in computation and analytical techniques afford an opportunity to reduce the spread of AROs through the development of clinical prediction tools to identify ARO carriers on admission to hospitals.
AIM : To identify existing clinical prediction tools for methicillin-resistant Staphylococcus aureus (MRSA) and carbapenemase-producing organisms (CPO), their predictive performance, and risk factors utilized in these tools.
METHODS : The CHARMS checklist was followed. We searched Medline, EMBASE, Cochrane SR, CRD databases (DARE, NHS EED), CINAHL and Web of Science from database inception to July 26, 2021. Full-text articles were independently assessed, and quality assessment was conducted using the PROBAST risk of bias tool.
FINDINGS : A total of 3809 abstracts were identified, and 22 studies were included. Among these studies, risk score models were the most common prediction tool (n=16). Previous admission, recent antibiotic exposure, age, and sex were the most common risk factors for ARO carriage. Prediction tools were commonly evaluated on sensitivity and specificity with ranges of 15-100% and 46-98.6% respectively for MRSA; 30-81.3% and 79.8-99.9% for CPO.
CONCLUSION : There is no gold standard ARO prediction tool, however high-performance clinical prediction tools and identification of key risk factors for the early detection of AROs exist. Risk score models are easier to use and interpret; however, with recent improvements in machine learning techniques, highly robust models can be developed with data stored in an EMR.
Jeon David, Chavda Swati, Rennert-May Elissa, Leal Jenine
2023-Jan-16
CPO, MRSA, antimicrobial resistant organisms, clinical prediction, electronic medical records, screening
