EUVIMEDEUVIMED entdecken
BeobachtungsstudieOpen Access · CC BY 4.0

Predictive modeling and spatiotemporal analysis of TB in Argentina: Advancing control efforts through machine learning

Ignacio Garcia, Leonardo Giovanini, Leonardo López

Public Health · 2026-03 · 252 · 106151

DOI: 10.1016/j.puhe.2026.106151 ↗

Kurz gefasst

Beobachtungsstudie in der Zeitschrift Public Health, 2026-03. Verfasst von Ignacio Garcia und 2 weiteren Autor:innen. Beteiligte Einrichtung: University of Barcelona (UB), Facultat de Matemàtiquesi Informàtica, Barcelona, 08007, Barcelona, Spain; Barcelona Institute for Global Health, Dr Ai…. Hauptthemen laut MEDLINE: Machine Learning, Spatio-Temporal Analysis, Tuberculosis. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVES: To improve prediction and understanding of TB dynamics in Argentina, identifying key risk factors and high-incidence areas to inform surveillance and public health control strategies. STUDY DESIGN: Retrospective observational study. METHODS: We applied (i) machine learning models (Histogram-Based Gradient Boosting, XGBoost, Random Forest, and Logistic Regression) to predict treatment outcomes, (ii) time series models (ARIMA, SARIMAX, and LSTM) to forecast weekly TB case counts, and (iii) spatial analysis tools (LISA, Moran's I) to identify high-incidence clusters. RESULTS: ), with LISA revealing two significant clusters (p < 0.05). HGB predicted treatment outcomes (ROC-AUC = 0.86; top predictors: HIV, treatment duration, age). LSTM outperformed SARIMAX (RMSE 3.50 → 2.88 in Salta-Jujuy; 3.82 → 0.89 in Autonomous City of Buenos Aires (CABA)-Buenos Aires; -18 %/-77 %). A sex-difference test indicated higher infection among men (p < 0.05). CONCLUSIONS: Combining ML and spatial tools enhances TB monitoring by supporting early identification of high-risk areas, improving epidemiological surveillance, and enabling targeted, data-driven public health interventions in Argentina.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningSpatio-Temporal AnalysisTuberculosisHumansArgentinaBoosting Machine Learning AlgorithmsIncidencePrediction AlgorithmsPredictive Learning ModelsRandom ForestRetrospective StudiesRisk Factors

Stichwörter der Autor:innen

ArgentinaEpidemiologyMachine learning (ML)Predictive modelingPublic healthTuberculosis (TB)

Autor:innen und Institutionen

  • University of Barcelona (UB), Facultat de Matemàtiquesi Informàtica, Barcelona, 08007, Barcelona, Spain; Barcelona Institute for Global Health, Dr Aiguader, 88, Barcelona, 08003, Spain.
  • Research Institute for Signals, Systems and Computational Intelligence, Litoral National University, Santa Fe, 3000, Santa Fe, Argentina.
  • Barcelona Institute for Global Health, Dr Aiguader, 88, Barcelona, 08003, Spain. Electronic address: leonardorafael.lopez@isglobal.org.

Zitieren

APA

Garcia, I., Giovanini, L., & López, L. (2026). Predictive modeling and spatiotemporal analysis of TB in Argentina: Advancing control efforts through machine learning. Public Health, 252, 106151. https://doi.org/10.1016/j.puhe.2026.106151

Vancouver

Garcia I, Giovanini L, López L. Predictive modeling and spatiotemporal analysis of TB in Argentina: Advancing control efforts through machine learning. Public Health. 2026;252:106151. doi:10.1016/j.puhe.2026.106151

BibTeX
@article{Garcia2026,
  author = {Garcia, Ignacio and Giovanini, Leonardo and López, Leonardo},
  title = {Predictive modeling and spatiotemporal analysis of TB in Argentina: Advancing control efforts through machine learning},
  journal = {Public Health},
  year = {2026},
  volume = {252},
  pages = {106151},
  doi = {10.1016/j.puhe.2026.106151}
}
Kostenlos starten →