Clinical Research Directory

Predicting the Optimal Empirical Antibiotic Therapy for Bacteremia Using an Artificial Intelligence-based Model

Sponsor: Nantes University Hospital

Summary

Bacteremia, a common infection associated with high morbidity and mortality, requires prompt and appropriate antibiotic treatment. Numerous studies have shown that the appropriate use of antibiotics helps improve the prognosis of patients, reduce the selection of pathogenic organisms, the emergence of antibiotic resistance, adverse treatment effects, and healthcare costs. The Nantes University Hospital Center has operated a Biomedical Data Warehouse (BDW) since 2018. The growing availability of data through BDWs thus enables the development of decision-support tools based on machine learning. The primary objective of the OPTIBact project is to predict the optimal empirical antibiotic for hospitalized patients with bacteremia using a machine learning-based predictive model using data from the Nantes University Hospital's BDW. As secondary objectives, the study aims: * To compare the performance of the predictive model for the optimal empirical antibiotic against standard patient care * To estimate the expected benefit of the predictive model compared to real-world practice in terms of clinical outcomes * To predict the optimal dosage of empirical antibiotic therapy * To compare the performance of the predictive model for optimal empirical antibiotic therapy dosing with standard patient care * To describe inpatient patients in Nantes University Hospital who received optimal antibiotic therapy and those who did not * To Identify predictors of antibiotic resistance in bacteria isolated from blood cultures, stratified by pathogen type.

Key Details

Conditions

Interventions