Scholarlink

Background <p>Dengue fever remains a persistent public health threat in Dhaka, Bangladesh, necessitating effective early warning systems to enable timely interventions and mitigate impacts. This study develops and evaluates modeling approaches to produce a projection of the 2026 dengue season in Dhaka, which may help inform public health preparedness.</p> Methods <p>Daily dengue case data from Dhaka (January 1, 2020 – December 30, 2024; 1,826 observations) were obtained from a publicly available Kaggle repository. A comprehensive modeling framework was developed comparing Seasonal Auto-Regressive Integrated Moving Average (SARIMA) with machine learning models (Random Forest, XGBoost, Support Vector Regression). A weighted ensemble model was constructed using inverse RMSE weights derived from validation performance to combine the strengths of individual approaches. Models were trained on a chronological 80% split (2020–2023) and evaluated on a 20% hold-out validation set (2024) using RMSE, MAE, MASE, and R<sup>2</sup>. A recursive multi-step strategy with fixed training median (48 cases) was employed to generate the 2026 projection while preventing data leakage.</p> Results <p>Machine learning models were shown to have higher predictive performance as compared to the time series model - SARIMA. Random Forest was the most accurate with the lowest (RMSE: 34.64, MAE: 19.14, MASE: 0.47) as well as the highest R-square (R<sup>2</sup>: 0.95). The weighted ensemble combining SARIMA and Random Forest (weights are 0.179 and 0.821) produced a balanced forecast (RMSE: 44.32, MAE: 28.79, MASE: 0.71, R<sup>2</sup>: 0.50). Using a recursive multi-step approach, our proposed hybrid predictive model projects approximately 11,500 dengue cases for Dhaka in 2026 under the assumption that past patterns hold, with a high transmission period from February 22 to December 27, and a core peak transmission phase of 71 days (February 22 – May 3) peaking at 38 cases on March 15.</p> Conclusion <p>The proposed weighted ensemble model provides a projection for the 2026 dengue season in Dhaka, offering potential early warning of the timing and scale of the high transmission period. This work adds importantly to the evidence base for dengue transmission in the region and helps to refine public health practitioners’ understanding of the seasonal transmission pattern of dengue, helping inform their annual planning. This may support proactive public health planning, such as vector management in January-February and healthcare resource mobilization from March onward.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Bridging ensemble model and public health practice: an approach for refining understanding of seasonal dengue transmission patterns in Bangladesh

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月20日

查看全文
  • Sharmin Akther,
  • Md. Al-Mamun,
  • Md. Kamrul Hossain

摘要

Background

Dengue fever remains a persistent public health threat in Dhaka, Bangladesh, necessitating effective early warning systems to enable timely interventions and mitigate impacts. This study develops and evaluates modeling approaches to produce a projection of the 2026 dengue season in Dhaka, which may help inform public health preparedness.

Methods

Daily dengue case data from Dhaka (January 1, 2020 – December 30, 2024; 1,826 observations) were obtained from a publicly available Kaggle repository. A comprehensive modeling framework was developed comparing Seasonal Auto-Regressive Integrated Moving Average (SARIMA) with machine learning models (Random Forest, XGBoost, Support Vector Regression). A weighted ensemble model was constructed using inverse RMSE weights derived from validation performance to combine the strengths of individual approaches. Models were trained on a chronological 80% split (2020–2023) and evaluated on a 20% hold-out validation set (2024) using RMSE, MAE, MASE, and R2. A recursive multi-step strategy with fixed training median (48 cases) was employed to generate the 2026 projection while preventing data leakage.

Results

Machine learning models were shown to have higher predictive performance as compared to the time series model - SARIMA. Random Forest was the most accurate with the lowest (RMSE: 34.64, MAE: 19.14, MASE: 0.47) as well as the highest R-square (R2: 0.95). The weighted ensemble combining SARIMA and Random Forest (weights are 0.179 and 0.821) produced a balanced forecast (RMSE: 44.32, MAE: 28.79, MASE: 0.71, R2: 0.50). Using a recursive multi-step approach, our proposed hybrid predictive model projects approximately 11,500 dengue cases for Dhaka in 2026 under the assumption that past patterns hold, with a high transmission period from February 22 to December 27, and a core peak transmission phase of 71 days (February 22 – May 3) peaking at 38 cases on March 15.

Conclusion

The proposed weighted ensemble model provides a projection for the 2026 dengue season in Dhaka, offering potential early warning of the timing and scale of the high transmission period. This work adds importantly to the evidence base for dengue transmission in the region and helps to refine public health practitioners’ understanding of the seasonal transmission pattern of dengue, helping inform their annual planning. This may support proactive public health planning, such as vector management in January-February and healthcare resource mobilization from March onward.