Prediction of impending central-line-associated bloodstream infections in hospitalized cardiac patients: development and testing of a machine-learning model.

BACKGROUND: While modelling of central-line-associated blood stream infection (CLABSI) risk factors is common, models that predict an impending CLABSI in real time are lacking. AIM: To build a prediction model which identifies patients who will develop a CLABSI in the ensuing 24 h. METHODS: We collected variables potentially related to infection identification in all patients admitted to the cardiac intensive care unit or cardiac ward at Boston Children's Hospital in whom a central venous catheter (CVC) was in place between January 2010 and August 2020, excluding those with a diagnosis of bacterial endocarditis. We created models predicting whether a patient would develop CLABSI in the ensuing 24 h. We assessed model performance based on area under the curve (AUC), sensitivity and false-positive rate (FPR) of models run on an independent testing set (40%). FINDINGS: A total of 104,035 patient-days and 139,662 line-days corresponding to 7468 unique patients were included in the analysis. There were 399 positive blood cultures (0.38%), most commonly with Staphylococcus aureus (23% of infections). Major predictors included a prior history of infection, elevated maximum heart rate, elevated maximum temperature, elevated C-reactive protein, exposure to parenteral nutrition and use of alteplase for CVC clearance. The model identified 25% of positive cultures with an FPR of 0.11% (AUC = 0.82). CONCLUSIONS: A machine-learning model can be used to predict 25% of patients with impending CLABSI with only 1.1/1000 of these predictions being incorrect. Once prospectively validated, this tool may allow for early treatment or prevention.

Combating the rise of antibiotic resistance in children.

Antibiotics are a cornerstone to treat bacterial infections and children received more frequently these drugs than any other class of medication. However, the improper and excessive use of antibiotics in the past decades has increased the emergence of resistant bacterial strains. Moreover, the lack of specific pediatric clinical trials on antibiotics led to a scarcity of high-evidence-level knowledge. The problem of the increase in antibiotic resistance should be known by all medical figures and probably by all members of the society, and a plan for an efficient strategy to improve antibiotic use in the entire world is highly needed. This review summarizes how antibiotics are mainly used in pediatrics and highlights the main problems related to the increase of antimicrobial-resistant bacterial strains, suggesting possible methods for reducing this increase. An excellent instrument to contain the emergence of antimicrobial resistance appeared the antibiotic stewardship program, that should be proposed and actualized in all contests in which antibiotics use is a common practice. Targeting the existing antibiotics with specific updated guidelines is also an essential measure to avoid antibiotics misuse. Moreover, educational on-line tools and their diffusions are useful strategies to diffuse knowledge on when and how to use antibiotics.