This retrospective study used 10 machine learning algorithms to predict the risk of healthcare-associated infections (HAIs) in patients admitted to intensive care units (ICUs). A total of 2,517 patients treated in the ICU of a tertiary hospital in China from January 2019 to December 2023 were included, of whom 455 (18.1%) developed an HAI. Data on 32 potential risk factors for infection were considered, of which 18 factors that were statistically significant on single-factor analysis were used to develop a machine learning prediction model using the synthetic minority oversampling technique (SMOTE). The main HAIs were respiratory tract infections (28.7%) and ventilator-associated pneumonia (25.0%), and were predominantly caused by gram-negative bacteria (78.8%). The CatBoost model showed good predictive performance (area under the curve: 0.944, and sensitivity 0.872). The 10 most important predictors of HAIs in this model were the Penetration Aspiration Scale score, Braden score, high total bilirubin level, female, high white blood cell count, Caprini Risk Score, Nutritional Risk Screening 2002 score, low eosinophil count, medium white blood cell count, and the Glasgow Coma Scale score. The CatBoost model accurately predicted the occurrence of HAIs and could be used in clinical practice.
