Optimizing Antimicrobial Stewardship: A Machine Learning Approach to Predict Resistance Patterns in Healthcare Settings

Abstract

Antimicrobial resistance (AMR) poses a significant challenge to global health, leading to increased morbidity, mortality, and healthcare costs. This study employs a machine learning framework to analyze large datasets from hospitals, focusing on predicting bacterial resistance patterns to guide more effective antimicrobial stewardship practices. Utilizing a combination of clinical and microbiological data, we implemented various classification algorithms, including Random Forest and Support Vector Machines, achieving a predictive accuracy of 87%. Our findings indicate that integrating machine learning into antimicrobial strategy can significantly enhance decision-making in prescribing practices and reduce unnecessary antibiotic use. This work emphasizes the potential of AI to contribute to combating AMR by providing actionable insights tailored to specific healthcare environments.