Abstract

Chronic obstructive pulmonary disease (COPD) remains a major cause of respiratory morbidity and healthcare utilization, creating challenges for healthcare planning, resource allocation, and early intervention. This study aimed to develop a forecasting framework for quarterly age- adjusted COPD outpatient visit rates across 762 regions in Pennsylvania from 2019 to 2023, using multi-source data including PHC4 outpatient records, satellite-derived environmental pollutant variables, and meteorological variables. To compare models that capture nonlinear relationships with those that explicitly model temporal dependencies, several machine learning models and a deep learning long short-term memory (LSTM) model, designed to learn sequential patterns and lagged temporal effects, were evaluated. The seasonal naïve baseline achieved R2=0.570, classical machine learning models achieved R2=0.58–0.62, and the LSTM model achieved R2=0.705 with lower prediction error. Lagged COPD activity was the strongest predictor, while environmental, meteorological, and geographic variables provided additional predictive information. These findings highlight the value of integrating multi-source environmental data with sequence-based modeling for forecasting regional COPD activity and suggest that environmental and meteorological variables can provide additional predictive information beyond historical COPD activity alone.

IPC Classification

Keywords