EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Advancing outbreak detection: Hybridizing machine learning with wavelets for weekly dengue case forecasting

Angelica Anne Eligado, Takanori Hasegawa, Yuta Hattori, Keiko Nakamura iD

PLOS Neglected Tropical Diseases · 09.07.2026 · 20 (7) · e0014444

DOI: 10.1371/journal.pntd.0014444 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Neglected Tropical Diseases, online erschienen am 09.07.2026. Verfasst von Angelica Anne Eligado und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Global Health Entrepreneurship, Institute of Science Tokyo, Tokyo, Japan. Hauptthemen laut MEDLINE: Dengue, Disease Outbreaks, Machine Learning, Wavelet Analysis. Die Arbeit nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Traditional surveillance systems often struggle with the volatility of weekly case data, limiting timely prevention and control efforts. In the Philippines, the standard method for setting outbreak thresholds relies on historical moving averages that are highly affected by extreme values and slow to reflect recent epidemiological shifts. This study assessed the performance of hybrid discrete wavelet transform (DWT)-seasonal autoregressive moving average (SARMA) and DWT-SARMA-long short-term memory (LSTM) models in forecasting weekly case counts and explored their potential in defining dynamic alarm and epidemic thresholds in Quezon City, Philippines. Methodology An ecologic time-trend study was conducted using weekly dengue case counts from 2012 to 2022. The data was decomposed using DWT, and SARMA was applied to the resulting approximate and detail coefficients. The DWT-SARMA model was enhanced by applying an LSTM to the SARMA residuals. The DWT-SARMA-LSTM model demonstrated superior performance, achieving a Mean Absolute Percentage Error (MAPE) of 12.4%, and successfully captured the case peaks and troughs. In contrast, the DWT-SARMA model produced a MAPE of 25.8%. Model-derived thresholds were more adaptive and context-sensitive than the traditional 3-year moving mean threshold, which was skewed by pre-pandemic data.

Conclusion

The hybrid DWT-SARMA-LSTM model is an accurate and robust approach for forecasting weekly dengue cases. It provides a more responsive basis for an early warning system than traditional thresholding methods, and has practical value for outbreak detection and resource planning in dynamic public health environments, particularly in resource-limited settings where timely and accurate data are critical.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

DengueDisease OutbreaksMachine LearningWavelet AnalysisHumansForecastingPhilippinesLong Short Term MemoryPredictive Learning ModelsPrediction Algorithms

Autor:innen und Institutionen

  • Department of Global Health Entrepreneurship, Institute of Science Tokyo, Tokyo, Japan.
  • Department of Epidemiology and Biostatistics, College of Public Health, University of the Philippines-Manila, Manila, Philippines.
  • Department of Integrated Analytics, Medical and Dental Data Science Center, Institute of Science Tokyo, Tokyo, Japan.
  • Department of Preventive Medicine, Nagoya University Graduate School of Medicine, Nagoya, Japan.

ORCID-Profile: Keiko Nakamura

Zitieren

APA

Eligado, A. A., Hasegawa, T., Hattori, Y., & Nakamura, K. (2026). Advancing outbreak detection: Hybridizing machine learning with wavelets for weekly dengue case forecasting. PLOS Neglected Tropical Diseases, 20(7), e0014444. https://doi.org/10.1371/journal.pntd.0014444

Vancouver

Eligado AA, Hasegawa T, Hattori Y, Nakamura K. Advancing outbreak detection: Hybridizing machine learning with wavelets for weekly dengue case forecasting. PLOS Neglected Tropical Diseases. 2026;20(7):e0014444. doi:10.1371/journal.pntd.0014444

BibTeX
@article{Eligado2026,
  author = {Eligado, Angelica Anne and Hasegawa, Takanori and Hattori, Yuta and Nakamura, Keiko},
  title = {Advancing outbreak detection: Hybridizing machine learning with wavelets for weekly dengue case forecasting},
  journal = {PLOS Neglected Tropical Diseases},
  year = {2026},
  volume = {20},
  number = {7},
  pages = {e0014444},
  doi = {10.1371/journal.pntd.0014444}
}
Kostenlos starten →