EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predictive association between control measures and chikungunya fever incidence based on random forest and SHAP analysis

Fengling Chen, Jinsen He, Huihui Liu, Zhilin Wu, Jiwen Wu, Kunlu He, Hongjuan Wen, Xiaohua Li, Hongwei Wu, Lang Lang iD, Lijie Zhang iD

PLOS Neglected Tropical Diseases · 2026

DOI: 10.1371/journal.pntd.0014675 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Neglected Tropical Diseases, 2026. Verfasst von Fengling Chen und 10 weiteren Autor:innen. Beteiligte Einrichtung: Chancheng District Center for Disease Control and Prevention, Foshan, Guangdong, China. Hauptthemen laut MEDLINE: Chikungunya Fever. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Public Health Talent Training Support Program of the National Administration of Disease Prevention and Control, Special Public Health Personnel Training and Professional Technical Capacity Building Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background Using the 2025 Chikungunya fever (CHIK) outbreak in Chancheng District, Foshan City, this study applied a random forest (RF) regression model combined with SHapley Additive exPlanations (SHAP) to explore predictive associations, nonlinear relationships and potential thresholds between environmental–social factors and village/community-level cumulative incidence, to inform stratified control of mosquito-borne diseases. Methodology/principal findings In this cross-sectional ecological study of 143 villages/communities, the outcome was cumulative incidence, and nine candidate covariates were assessed, including the hospitalization isolation rate, construction-site density, and population density. Multicollinearity was checked using the variance inflation factor. Model fit was evaluated by the out-of-bag (OOB) R², RMSE, and MAE, and variable importance by %IncMSE. Robustness was tested with 100 repeated runs, bootstrap thresholds from SHAP dependence plots, and a sensitivity analysis excluding the endogenous isolation rate. On the log(1 + incidence) scale, the OOB R² was 0.206, with underestimation of high-incidence areas. The hospitalization isolation rate had the highest importance (%IncMSE = 18.43) and was negatively correlated with predictions (ρ = −0.749), but this likely reflects reverse causation and is predictive only. Construction-site density was strongly positive (ρ = 0.855), with a stable threshold near 12.8 sites/km²; it remained the most robust predictor after removing the isolation rate (%IncMSE = 8.54). Conclusions/significance Construction-site density was the most robust environmental predictor, whereas population density contributed little. These exploratory, predictive associations—not causal effects—should guide risk stratification and require prospective validation with time-matched longitudinal data.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Chikungunya FeverHumansIncidenceRandom ForestCross-Sectional StudiesAnimalsChinaMosquito-Borne DiseasesChikungunya virusDisease Outbreaks

Autor:innen und Institutionen

  • Chancheng District Center for Disease Control and Prevention, Foshan, Guangdong, China.
  • Chinese Field Epidemiology Training Program, Chinese Center for Disease Control and Prevention (Chinese Academy of Preventive Medicine), Beijing, China.
  • Shunyi District Center for Disease Control and Prevention, Beijing, China.
  • The Johns Hopkins University, Baltimore, Maryland, United States of America.

ORCID-Profile: Lang Lang, Lijie Zhang

Förderung

  • Public Health Talent Training Support Program of the National Administration of Disease Prevention and Control
  • Special Public Health Personnel Training and Professional Technical Capacity Building Program

Zitieren

APA

Chen, F., He, J., Liu, H., Wu, Z., Wu, J., He, K., Wen, H., Li, X., Wu, H., Lang, L., & Zhang, L. (2026). Predictive association between control measures and chikungunya fever incidence based on random forest and SHAP analysis. PLOS Neglected Tropical Diseases. https://doi.org/10.1371/journal.pntd.0014675

Vancouver

Chen F, He J, Liu H, Wu Z, Wu J, He K, et al. Predictive association between control measures and chikungunya fever incidence based on random forest and SHAP analysis. PLOS Neglected Tropical Diseases. 2026. doi:10.1371/journal.pntd.0014675

BibTeX
@article{Chen2026,
  author = {Chen, Fengling and He, Jinsen and Liu, Huihui and Wu, Zhilin and Wu, Jiwen and He, Kunlu and Wen, Hongjuan and Li, Xiaohua and Wu, Hongwei and Lang, Lang and Zhang, Lijie},
  title = {Predictive association between control measures and chikungunya fever incidence based on random forest and SHAP analysis},
  journal = {PLOS Neglected Tropical Diseases},
  year = {2026},
  doi = {10.1371/journal.pntd.0014675}
}
Kostenlos starten →