Modeling Urban Transformation and Predicting Respiratory Disease Trends in Thailand with Machine Learning

This study investigates how urban environmental, social, and economic factors influence the prevalence of respiratory diseases across nine provinces in Thailand. Utilizing data from 2017 to 2021, various regression models were tested to forecast respiratory disease cases in 2023. The optimized Random Forest Regression model was identified as the most accurate, achieving an R2 Score of 0.82, MAE of 160.45, and RMSE of 185.32. These results highlight the role of urbanization in respiratory health trends and provide insights for policymakers to mitigate health risks. The findings emphasize the necessity for improved urban planning and environmental management to minimize adverse health impacts and highlight the potential of machine learning techniques for time-series health forecasting.