tetano
Editor, Senior Moderator
BMC Public Health
. 2026 Feb 16.
doi: 10.1186/s12889-026-26562-7. Online ahead of print.
A hybrid model for influenza forecasting in Xinjiang: adapting to complex seasonality and post-COVID-19 structural breaks
Yanran Liu[SUP] #[/SUP][SUP] 1 2 3 4 [/SUP], Jingxia Guo[SUP] #[/SUP][SUP] 1 [/SUP], Yongmei Ge[SUP] #[/SUP][SUP] 1 [/SUP], Di Wang[SUP] 2 3 [/SUP], Xubin Zheng[SUP] 5 6 [/SUP], Xiaoming Peng[SUP] 7 [/SUP]
Affiliations
Background: Influenza forecasting in Xinjiang is critical but hindered by unique dual challenges: complex, multi-modal routine seasonality and extreme post-COVID-19 structural breaks. This study develops a two-stage hybrid model that fuses local epidemiological features to provide accurate forecasts where general-purpose models may fail.
Methods: We utilize data from 2011 to 2023 provided by the Disease Prevention and Control Center of Xinjiang Production and Construction Corps, Urumqi, Xinjiang, China, stratifying it into pre-pandemic and COVID-19-affected periods to test model performance against routine complexity and major structural breaks. We propose a two-stage Long Short-Term Memory-Gradient Boosting Regression (LSTM-GBR) model that fuses an epidemic trend baseline, extracted from historical cases by an LSTM, with engineered virological and demographic features via a GBR. We systematically compare its performance across key metrics against a breadth of benchmarks, including classical statistical models, automated forecasting tools, and state-of-the-art pre-trained foundation models.
Results: The proposed LSTM-GBR framework demonstrates superior performance and yields the lowest error. It is the only model to accurately resolve the complex bimodal seasonality in the pre-pandemic test set. Furthermore, it is the only model to successfully anticipate and forecast the extreme 2023 post-COVID-19 rebound. All baseline models, including state-of-the-art foundation models, fail to predict these critical dynamics.
Conclusion: The proposed LSTM-GBR model provides a validated, robust, high-accuracy forecasting tool specifically for Xinjiang. It successfully addresses the failures of general-purpose models, which are unable to capture the region's complex local dynamics and emergent structural breaks. This localized feature-fusion approach is essential to strengthen public health surveillance in Xinjiang.
Keywords: Feature engineering; Hybrid model; Influenza forecasting; Structural break; Xinjiang.
. 2026 Feb 16.
doi: 10.1186/s12889-026-26562-7. Online ahead of print.
A hybrid model for influenza forecasting in Xinjiang: adapting to complex seasonality and post-COVID-19 structural breaks
Yanran Liu[SUP] #[/SUP][SUP] 1 2 3 4 [/SUP], Jingxia Guo[SUP] #[/SUP][SUP] 1 [/SUP], Yongmei Ge[SUP] #[/SUP][SUP] 1 [/SUP], Di Wang[SUP] 2 3 [/SUP], Xubin Zheng[SUP] 5 6 [/SUP], Xiaoming Peng[SUP] 7 [/SUP]
Affiliations
- PMID: 41699546
- DOI: 10.1186/s12889-026-26562-7
Background: Influenza forecasting in Xinjiang is critical but hindered by unique dual challenges: complex, multi-modal routine seasonality and extreme post-COVID-19 structural breaks. This study develops a two-stage hybrid model that fuses local epidemiological features to provide accurate forecasts where general-purpose models may fail.
Methods: We utilize data from 2011 to 2023 provided by the Disease Prevention and Control Center of Xinjiang Production and Construction Corps, Urumqi, Xinjiang, China, stratifying it into pre-pandemic and COVID-19-affected periods to test model performance against routine complexity and major structural breaks. We propose a two-stage Long Short-Term Memory-Gradient Boosting Regression (LSTM-GBR) model that fuses an epidemic trend baseline, extracted from historical cases by an LSTM, with engineered virological and demographic features via a GBR. We systematically compare its performance across key metrics against a breadth of benchmarks, including classical statistical models, automated forecasting tools, and state-of-the-art pre-trained foundation models.
Results: The proposed LSTM-GBR framework demonstrates superior performance and yields the lowest error. It is the only model to accurately resolve the complex bimodal seasonality in the pre-pandemic test set. Furthermore, it is the only model to successfully anticipate and forecast the extreme 2023 post-COVID-19 rebound. All baseline models, including state-of-the-art foundation models, fail to predict these critical dynamics.
Conclusion: The proposed LSTM-GBR model provides a validated, robust, high-accuracy forecasting tool specifically for Xinjiang. It successfully addresses the failures of general-purpose models, which are unable to capture the region's complex local dynamics and emergent structural breaks. This localized feature-fusion approach is essential to strengthen public health surveillance in Xinjiang.
Keywords: Feature engineering; Hybrid model; Influenza forecasting; Structural break; Xinjiang.