Evaluating the Underreporting of Diseases in the Philippines During the COVID-19 Pandemic through Comparative Forecast Analysis

Abstract

Abstract Background The COVID-19 pandemic has significantly impacted global health systems, particularly in the Philippines. The redirection of healthcare resources towards COVID-19 has raised concerns about the potential underreporting and surveillance of other communicable diseases. This study explores whether the pandemic has led to the underreporting of these diseases. Methods The study employs Predictive Mean Matching (PMM) for data completeness and uses Seasonal Autoregressive Integrated Moving Average (SARIMA), Neural Network Autoregressive (NNAR), and Holt-Winters (HW) models for disease forecasting. The actual reported cases of diseases for the years 2020 and 2021 are compared with the forecasts to identify discrepancies. Results Significant underreporting was observed for most diseases studied, with notable exceptions such as AFP. NNAR models outperformed SARIMA and HW in forecasting accuracy. Diseases like Measles, Diphtheria, and Rubella showed substantial underreporting, while vector-borne diseases like Dengue and Chikungunya, and waterborne diseases such as Typhoid Fever and Cholera, also indicated underreporting. Conclusions The study reveals significant underreporting of various diseases in the Philippines during the COVID-19 pandemic. The effective use of advanced predictive models underscores the potential of these tools in enhancing disease surveillance and highlights the need for robust health systems capable of sustaining surveillance during crises.