**Knowledge, Practices, and Behavioral Predictors of Antimicrobial Resistance Among University Students in Uganda: A Non-Parametric and Machine Learning Analysis with Regional Insights for East Africa

This study evaluates antimicrobial resistance (AMR)-related knowledge, practices, and behavioral predictors among university students in Uganda using a mixed-method approach that combines descriptive statistics, non-parametric analysis, and machine learning. A cross-sectional online survey (**n = 123**) was conducted among university students in Uganda. The results revealed high AMR awareness, with **76.4%** of participants having heard of AMR and **85.4%** aware of the risks associated with improper antibiotic dosage. However, inconsistent practices persisted, with **35.8%** reporting self-medication and **32.5%** sharing antibiotics. Logistic regression and CatBoost classifier analysis identified belief in AMR severity, field of study, gender, and perceived cost as the most significant behavioral predictors. Younger students and those enrolled in non-medical programs were more likely to exhibit non-compliant behaviors. K-Means clustering and Principal Component Analysis (PCA) identified three behavioral profiles—**Compliant, At Risk,** and **Unaware**—demonstrating the value of machine learning for behavioral segmentation. The findings confirm a cognitive–behavioral disconnect, where knowledge alone does not guarantee safe antibiotic use, and highlight the importance of integrating **Health Belief Model (HBM)** constructs into AMR education. This study contributes methodologically by introducing a **Behavioral Risk Profiling Framework** and offers practical implications for designing tailored university-based interventions. Institutional strategies should include belief-targeted education, curriculum integration in non-medical programs, and cost-reduction initiatives. Overall, the study underscores the need for precision public health models to promote antimicrobial stewardship among young people in resource-limited settings.