Estado del Arte y Tendencias Contemporáneas en la Modelación Predictiva del Dengue mediante Inteligencia Artificial
Ibero Ciencias - Revista Científica y Académica - ISSN 3072-7197 · 29.05.2026 · 5 (2) · 2522-2533
DOI: 10.63371/ic.v5.n2.a1165 ↗Kurz gefasst
Fachartikel in der Zeitschrift Ibero Ciencias - Revista Científica y Académica - ISSN 3072-7197, online erschienen am 29.05.2026. Verfasst von Roberto Rosario Cruz und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Dengue epidemiological surveillance faces structural limitations related to reporting delays, underreporting of cases, and low predictive capacity of traditional systems. This review analyzes the current state of dengue predictive modeling using artificial intelligence and machine learning, based on literature published between 2015 and 2026. Findings show a predominance of algorithms such as Random Forest, LSTM neural networks, XGBoost, and Support Vector Machines, applied primarily to time series of incidence, climate data, and clinical records. Reported predictive capacity reaches windows of 1 to 12 weeks before clinical detection of outbreaks, although significant methodological problems persist: lack of external validation, heterogeneous definitions of "outbreak," selection biases, and limited reproducibility. Artificial intelligence-based early warning systems show high sensitivity in controlled settings, but their performance decreases under real operational conditions. Contemporary trends identified include hybrid models (mechanistic-empirical), explicit uncertainty quantification, and One Health perspective integration. The main gap is not technological but institutional: the lack of integration between predictive developments and existing surveillance workflows limits public health impact. Reporting standards, open databases, and external validation studies are required to advance toward truly operational systems.
Zitieren
APA
Cruz, R. R., Galeana, N. I. P., Galeana, R. P., & Reyes, R. R. (2026). Estado del Arte y Tendencias Contemporáneas en la Modelación Predictiva del Dengue mediante Inteligencia Artificial. Ibero Ciencias - Revista Científica y Académica - ISSN 3072-7197, 5(2), 2522-2533. https://doi.org/10.63371/ic.v5.n2.a1165
Vancouver
Cruz RR, Galeana NIP, Galeana RP, Reyes RR. Estado del Arte y Tendencias Contemporáneas en la Modelación Predictiva del Dengue mediante Inteligencia Artificial. Ibero Ciencias - Revista Científica y Académica - ISSN 3072-7197. 2026;5(2):2522-2533. doi:10.63371/ic.v5.n2.a1165
BibTeX
@article{Cruz2026,
author = {Cruz, Roberto Rosario and Galeana, Norma Ivone Peña and Galeana, Ricardo Peña and Reyes, Roberto Rosario},
title = {Estado del Arte y Tendencias Contemporáneas en la Modelación Predictiva del Dengue mediante Inteligencia Artificial},
journal = {Ibero Ciencias - Revista Científica y Académica - ISSN 3072-7197},
year = {2026},
volume = {5},
number = {2},
pages = {2522--2533},
doi = {10.63371/ic.v5.n2.a1165}
}
EUVIMED