FORECASTING URINARY TRACT INFECTION (UTI) CASES IN NORTHERN REGION USING MACHINE LEARNING APPROACHES

Abstract

Urinary Tract Infections (UTIs) continue to be a significant public health concern, with fluctuating incidence rates influenced by factors such as environmental conditions, healthcare accessibility, population diversity, and the rise in antimicrobial resistance. Accurate prediction of UTI trends is essential for health professionals and policymakers to implement timely interventions, optimize healthcare delivery, and develop effective disease prevention strategies. This study considers the modeling of UTI counts trend through the use of machine learning classification algorithms such as K-Nearest Neighbors (K-NN), Support Vector Classification (SVC), Decision Trees, and Random Forest Classification. These algorithms are best-suited for structured health data and can help uncover unique undiscovered patterns and relationships between multiple variables influencing UTIs.