Abstract
In the recent years, public health has become a core issue addressed by researchers. However, because of our limited knowledge, studies mainly focus on the causes of public health issues. On the contrary, this study provides forecasts of public health issues using software engineering techniques and determinants of public health. Our empirical findings show significant impacts of carbon emission and health expenditure on public health. The results confirm that support vector machine (SVM) outperforms the forecasting of public health when compared to multiple linear regression (MLR) and artificial neural network (ANN) technique. The findings are valuable to policymakers in forecasting public health issues and taking preemptive actions to address the relevant health concerns.