Identifying Key Drivers of Foodborne Diseases in Zhejiang, China: A Machine Learning Approach

Foodborne diseases represent a significant public health challenge worldwide. This study systematically analyzed the temporal dynamics, key predictors, and seasonal patterns of pathogen-specific foodborne diseases using a dataset of 56,970 cases from Zhejiang Province, China, spanning 2014 to 2023. A comprehensive set of 91 candidate variables was constructed by integrating epidemiological, environmental, socioeconomic, and agricultural data. Lasso regression was employed to identify 41 important predictors. Based on these variables, supervised machine learning models (Random Forest and XGBoost) were trained and evaluated, achieving training set classification accuracies of 86% and 87%, respectively, demonstrating robust performance. Feature importance analysis revealed that patient age, food type, climate policy, and processing methods were the most influential determinants, highlighting the combined impact of host, exposure, and environmental factors on disease risk. The results demonstrated significant shifts in the pathogen spectrum over the past decade, including a steady decline in Vibrio parahaemolyticus, an increase in Salmonella after 2016, and persistent seasonal peaks in Norovirus and Vibrio parahaemolyticus during warmer months. Seasonal ARIMA modeling and time-series decomposition further confirmed the critical role of seasonal and trend components in bacterial incidence. Overall, this study demonstrates the value of integrating machine learning and time-series analysis for pathogen-specific surveillance, risk prediction, and targeted public health interventions.