EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hybrid Machine Learning Approach to Zero-Inflated Data Improves Accuracy of Dengue Prediction

Micanaldo Ernesto Francisco, Thaddeus M Carvajal, Kozo Watanabe iD

PLOS Neglected Tropical Diseases · 21.10.2024 · 18 (10) · e0012599

DOI: 10.1371/journal.pntd.0012599 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Neglected Tropical Diseases, online erschienen am 21.10.2024. Verfasst von Micanaldo Ernesto Francisco und 2 weiteren Autor:innen. Beteiligte Einrichtung: Center for Marine Environmental Studies (CMES), Ehime University, Matsuyama, Japan. Hauptthemen laut MEDLINE: Dengue, Machine Learning. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science (JSPS), Japan Society for the Promotion of Science (JSPS) Grant-in-Aid Fund for the Promotion of Joint International Research (Fostering Joint International Research, JSPS Grant-in-Aid for Scientific Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background Spatiotemporal dengue forecasting using machine learning (ML) can contribute to the development of prevention and control strategies for impending dengue outbreaks. However, training data for dengue incidence may be inflated with frequent zero values because of the rarity of cases, which lowers the prediction accuracy. This study aimed to understand the influence of spatiotemporal resolutions of data on the accuracy of dengue incidence prediction using ML models, to understand how the influence of spatiotemporal resolution differs between quantitative and qualitative predictions of dengue incidence, and to improve the accuracy of dengue incidence prediction with zero-inflated data. Methodology We predicted dengue incidence at six spatiotemporal resolutions and compared their prediction accuracy. Six ML algorithms were compared: generalized additive models, random forests, conditional inference forest, artificial neural networks, support vector machines and regression, and extreme gradient boosting. Data from 2009 to 2012 were used for training, and data from 2013 were used for model validation with quantitative and qualitative dengue variables. To address the inaccuracy in the quantitative prediction of dengue incidence due to zero-inflated data at fine spatiotemporal scales, we developed a hybrid approach in which the second-stage quantitative prediction is performed only when/where the first-stage qualitative model predicts the occurrence of dengue cases. Principal findings At higher resolutions, the dengue incidence data were zero-inflated, which was insufficient for quantitative pattern extraction of relationships between dengue incidence and environmental variables by ML. Qualitative models, used as binary variables, eased the effect of data distribution. Our novel hybrid approach of combining qualitative and quantitative predictions demonstrated high potential for predicting zero-inflated or rare phenomena, such as dengue. Significance Our research contributes valuable insights to the field of spatiotemporal dengue prediction and provides an alternative solution to enhance prediction accuracy in zero-inflated data where hurdle or zero-inflated models cannot be applied.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

DengueMachine LearningHumansIncidenceForecastingSpatio-Temporal AnalysisModels, StatisticalAlgorithmsDisease Outbreaks

Autor:innen und Institutionen

  • Center for Marine Environmental Studies (CMES), Ehime University, Matsuyama, Japan.
  • Graduate School of Science and Engineering, Ehime University, Matsuyama, Ehime, Japan.
  • Faculty of Architecture and Physical Planning (FAPF), Lurio University, Nampula, Mozambique.
  • Department of Biology De La Salle University, Taft Ave Manila, Philippines.

ORCID-Profile: Kozo Watanabe

Förderung

  • Japan Society for the Promotion of Science (JSPS)
  • Japan Society for the Promotion of Science (JSPS) Grant-in-Aid Fund for the Promotion of Joint International Research (Fostering Joint International Research
  • JSPS Grant-in-Aid for Scientific Research
  • JSPS Core-to-Core Program B. Asia-Africa Science Platforms,
  • Endowed Chair Program of the Sumitomo Electric Industries Group Corporate Social Responsibility Foundation

Zitieren

APA

Francisco, M. E., Carvajal, T. M., & Watanabe, K. (2024). Hybrid Machine Learning Approach to Zero-Inflated Data Improves Accuracy of Dengue Prediction. PLOS Neglected Tropical Diseases, 18(10), e0012599. https://doi.org/10.1371/journal.pntd.0012599

Vancouver

Francisco ME, Carvajal TM, Watanabe K. Hybrid Machine Learning Approach to Zero-Inflated Data Improves Accuracy of Dengue Prediction. PLOS Neglected Tropical Diseases. 2024;18(10):e0012599. doi:10.1371/journal.pntd.0012599

BibTeX
@article{Francisco2024,
  author = {Francisco, Micanaldo Ernesto and Carvajal, Thaddeus M and Watanabe, Kozo},
  title = {Hybrid Machine Learning Approach to Zero-Inflated Data Improves Accuracy of Dengue Prediction},
  journal = {PLOS Neglected Tropical Diseases},
  year = {2024},
  volume = {18},
  number = {10},
  pages = {e0012599},
  doi = {10.1371/journal.pntd.0012599}
}
Kostenlos starten →