SYSTEMATIC ANALYSIS AND CLASSIFICATION OF FOODBORNE DISEASE OUTBREAKS

Abstract

Foodborne diseases, primarily resulting from the consumption of contaminated food and beverages, pose significant public health risks. Timely identification and classification of foodborne disease outbreaks are essential to mitigate illness and mortality. This study aims to rapidly identify causative agents to enhance food safety and prevent disease-related consequences. Through analysis of the dataset, key outbreak patterns were identified, including trends in the frequency of outbreaks by year, food type, location, and affected species. Classification of these outbreaks was performed using Decision Tree, Naïve Bayes, and Random Forest algorithms. Experimental results demonstrate the effectiveness of the proposed approach in accurately identifying and classifying outbreak patterns, providing valuable insights for disease prevention and food safety management.