Comparison of OneChoice(R) AI-based clinical decision support recommendations with infectious disease specialists and non-specialists for bacteremia treatment in Lima, Peru

Bacteremia is a major contributor to global morbidity and mortality, particularly in low- and middle-income countries where diagnostic delays and empirical antimicrobial misuse exacerbate resistance. This study assessed the accuracy of OneChoice(R), an artificial intelligence (AI)-based Clinical Decision Support System (CDSS), in guiding antimicrobial therapy for bloodstream infections (BSIs) in Lima, Peru. A retrospective, observational design was used, comparing therapeutic recommendations generated by OneChoice(R)--based on molecular (FilmArray(R)) and phenotypic (MALDI-TOF MS, VITEK2) data--with the clinical decisions of 94 physicians (35 infectious disease [ID] specialists and 59 non-specialists) across 366 survey-based evaluations of bacteremia cases. Concordance between CDSS and physician decisions was analyzed using Cohens Kappa and logistic regression. The overall concordance rate was 96.14% when considering any suggested treatment, and 74.59% for the top recommendation, with a substantial agreement ({kappa} = 0.70). ID specialists showed significantly higher concordance ({kappa} = 0.78) than non-ID physicians ({kappa} = 0.61), and specialization was the strongest predictor of agreement (OR = 2.26, p = 0.001). Escherichia coli cases had the highest concordance, while Pseudomonas aeruginosa showed the lowest. The CDSS reduced inappropriate antibiotic use, particularly unnecessary carbapenem prescriptions. These findings support the utility of AI-CDSS tools in enhancing antimicrobial stewardship and standardizing care, especially in resource-limited healthcare settings.