Analyzing the impact of COVID-19 on seasonal infectious disease outbreak detection using hybrid SARIMAX-LSTM model

초록

Background: This study estimates the incidence of seasonal infectious diseases, including influenza, norovirus, severe fever with thrombocytopenia syndrome (SFTS), and tsutsugamushi disease, in the Republic of Korea from 2005 to 2023. It also examines the impact of the COVID-19 pandemic on their transmission patterns. Methods: We employed the Seasonal AutoRegressive Integrated Moving Average with eXogenous variables (SARIMAX) model, long short-term memory (LSTM) neural networks, and a hybrid SARIMAX-LSTM model to predict disease incidence and identify outbreak periods. Meteorological data were incorporated into the models, and change point detection (CPD) was used to identify shifts in outbreak trends. Model predictions were compared with actual data to evaluate the influence of COVID-19 on disease incidence. Results: The incidence of influenza and norovirus was significantly affected by COVID-19, whereas SFTS and tsutsugamushi disease showed no substantial changes. Influenza did not return to pre-pandemic levels post-COVID-19, while norovirus incidence reverted to previous patterns. Despite a decrease in influenzalike illness (ILI) cases during the pandemic, predictive models indicated a potential resurgence of outbreaks. Conclusions: These findings highlight the need for tailored public health strategies for each disease. Early detection and timely interventions are essential for reducing healthcare burdens and improving health outcomes. (c) 2025 The Authors. Published by Elsevier Ltd on behalf of King Saud Bin Abdulaziz University for Health Sciences. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

키워드