From the COVID-19 Pandemic to the Mental Health of the Philippines: Modelling the Cascade of Disasters using an Influence Diagram

Bayesian Networks and Influence Diagrams for Public Health Modeling

This preprint operates within the established paradigm of applying Bayesian networks and influence diagrams to public health challenges. It doesn't challenge existing methodologies or propose radical new theories but extends existing models to a specific case study (mental health in the Philippines during the COVID-19 pandemic). The study aims to refine and apply the existing paradigm to gain a deeper understanding of a particular phenomenon, thus falling under the classification of normal science. While the authors propose using the model for policy recommendations, this application is still within the existing paradigm's framework and doesn't signify a paradigm shift or model revolution. It could potentially be considered 'model drift', as it applies the existing Bayesian Network model to an influence diagram, but the core methodology and aims remain consistent with established practices. Thus, I classify it as 'Normal Science' with 'Model Drift' as a secondary consideration.