Using Machine Learning to Predict Antimicrobial Resistance of Acinetobacter Baumannii, Klebsiella Pneumoniae and Pseudomonas Aeruginosa Strains

Hospital-acquired infections, particularly in ICU, are becoming more frequent recent years, with the most serious of them being Gram-negative bacterial infections. Among them, Acinetobacter baumannii, Klebsiella pneumoniae, and Pseudomonas aeruginosa considered resistant bacteria encountered ICU other wards. Given fact that about 24 hours usually required to perform common antibiotic resistance tests after identification, use machine learning techniques could be an additional decision support tool selecting empirical treatment based on sample type, bacteria, patient’s basic characteristics. In this article, five (ML) models were evaluated predict antimicrobial aeruginosa. We suggest implementing ML forecast using data from clinical microbiology laboratory, available Laboratory Information System (LIS).