EUVIMEDEUVIMED entdecken
Crossref

Topological data analysis for cluster-based dengue forecasting in Mexico

J A Martínez-Cadena

Spatial and Spatio-temporal Epidemiology · 2026

DOI: 10.1016/j.sste.2026.100784 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Spatial and Spatio-temporal Epidemiology, 2026. Verfasst von J A Martínez-Cadena. Beteiligte Einrichtung: Departamento de Matemáticas, Facultad de Ciencias, Universidad Nacional Autónoma de México, Circuito Exterior s/n, Ciudad Universitaria, 04510, Ciuda…. Hauptthemen laut MEDLINE: Dengue. Die Arbeit nennt 23 Literaturangaben. Gefördert von: SECIHTI.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Topological Data Analysis (TDA) offers shape-aware descriptions for complex epidemic patterns. We have created a clustered forecasting pipeline for weekly dengue incidence at the state level in Mexico. This pipeline integrates TDA, using persistence diagrams and persistence images (PI), into feature engineering, Gaussian-mixture clustering, and cluster-level count Generalized Linear Models (GLMs). We compare Poisson and Negative-Binomial (NB2) models using a rolling-origin evaluation with naïve and seasonal-naïve baselines. With three clusters, NB2 consistently performs better than Poisson in skill, showing improved Mean Absolute Error (MAE) across clusters. The results for NB2 are {0.264,0.475,0.604}, compared to {0.131,0.382,0.495} for Poisson. An analysis across the Baseline, +TDA, and +TDA+PI demonstrates that adding TDA/PI does not significantly alter one-week forecast skill. However, it enhances interpretability and stratification. The means of PI and differences between cluster and global PI highlight unique, cluster-specific dynamic patterns. The workflow is fully reproducible, including seeds, versions, and configuration, and it generates operational, cluster-based forecasts suitable for regional dengue surveillance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

DengueMexicoHumansForecastingCluster AnalysisData AnalyticsIncidenceClustering Algorithms

Stichwörter der Autor:innen

DengueNegative-binomial GLMPersistence imagesRolling-origin evaluationSpatial epidemiologySpatio-temporal modelingTopological data analysis

Autor:innen und Institutionen

  • Departamento de Matemáticas, Facultad de Ciencias, Universidad Nacional Autónoma de México, Circuito Exterior s/n, Ciudad Universitaria, 04510, Ciudad de México, Mexico. Electronic address: martinezcadenajuan@gmail.com.

Förderung

  • SECIHTI

Zitieren

APA

Martínez-Cadena, J. A. (2026). Topological data analysis for cluster-based dengue forecasting in Mexico. Spatial and Spatio-temporal Epidemiology. https://doi.org/10.1016/j.sste.2026.100784

Vancouver

Martínez-Cadena JA. Topological data analysis for cluster-based dengue forecasting in Mexico. Spatial and Spatio-temporal Epidemiology. 2026. doi:10.1016/j.sste.2026.100784

BibTeX
@article{MartnezCadena2026,
  author = {Martínez-Cadena, J A},
  title = {Topological data analysis for cluster-based dengue forecasting in Mexico},
  journal = {Spatial and Spatio-temporal Epidemiology},
  year = {2026},
  doi = {10.1016/j.sste.2026.100784}
}
Kostenlos starten →