Data-Driven Hybrid Model of SARIMA-CNNAR For Tuberculosis Incidence Time Series Analysis in Nepal

Abstract Background Tuberculosis (TB) remains a major public health challenge in Nepal, with incidence rates substantially higher than global estimates. Accurate forecasting of TB incidence is essential for early warning systems, resource allocation, and targeted interventions. This study aimed to develop and validate a hybrid Seasonal Autoregressive Integrated Moving Average (SARIMA) and Convolutional Neural Network Auto-Regressive (CNNAR) model for TB incidence forecasting in Nepal. Methods Monthly TB incidence data (January 2015 to December 2024) were obtained from the National Tuberculosis Control Center (NTCC), Nepal. A hybrid SARIMA-CNNAR model was developed, where SARIMA modeled linear seasonal trends and CNNAR captured nonlinear patterns in the residuals. Hyperparameters were optimized using grid search with 5-fold cross-validation. Model performance was evaluated using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and R{superscript 2} on the 2024 test set. Structural break analysis and sensitivity analysis assessed model robustness. The hybrid model was compared against standalone SARIMA, CNNAR, and three state-of-the-art benchmarks: Long Short-Term Memory (LSTM), Facebook Prophet, and XGBoost. Results TB incidence in Nepal increased from a monthly average of 2,048 cases in 2015 to 3,447 in 2024 (68.4% increase). The hybrid SARIMA-CNNAR model demonstrated strong performance with test set metrics of MAE=248.35, RMSE=294.31, MAPE=7.2%, and R{superscript 2}=0.79. Comparative performance: CNNAR (MAE=251.08, RMSE=336.55, MAPE=7.7%, R{superscript 2}=0.73); LSTM (MAE=267.91, RMSE=324.55, MAPE=7.5%, R{superscript 2}=0.75); XGBoost (MAE=314.74, RMSE=373.99, MAPE=8.5%, R{superscript 2}=0.66); Prophet (MAE=371.15, RMSE=478.40, MAPE=10.4%, R{superscript 2}=0.45); SARIMA (MAE=401.11, RMSE=503.93, MAPE=10.99%, R{superscript 2}=0.39). All models captured seasonal peaks in March-May and July-August, with forecasts for 2025 indicating continued seasonal patterns. Sensitivity analysis confirmed robustness with <5% metric variation across parameter configurations. Conclusions This first validated hybrid model for TB prediction in Nepal demonstrates high forecasting accuracy by integrating linear seasonal modeling with nonlinear pattern detection. The approach offers a robust tool for evidence-based public health planning in resource-limited settings and it is suitable for integration into national surveillance systems.