EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An automated machine learning approach to predict glycaemic control in patients with type 2 diabetes in Burkina Faso

Cheick A. Ouattara, Bazoumana Coulibaly, Tiandiogo I. Traoré, Bakary Cissé, Carole G. Kyelem, Macaire S. Ouedraogo, Téné M. Yaméogo, Issiaka Sombié

Journal of Public Health in Africa · 17.11.2026 · 17 (1)

DOI: 10.4102/jphia.v17i1.2024 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Public Health in Africa, online erschienen am 17.11.2026. Verfasst von Cheick A. Ouattara und 7 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Machine learning offers opportunities to improve risk stratification in type 2 diabetes by capturing complex clinical and sociodemographic interactions.

Aim

To develop and evaluate machine learning models for predicting 1-year glycaemic control in patients with type 2 diabetes in Burkina Faso.

Setting

A tertiary hospital in Burkina Faso, including patients followed up between 2020 and 2025.

Methods

A retrospective cohort study included 424 patients. Glycaemic control was defined as glycated haemoglobin (HbA1c) < 7% at 1 year. Nine classifiers were trained using nested cross-validation. Performance was assessed using AUC-ROC, F1-score, recall, accuracy, precision and AUC-PR. Interpretability was assessed using SHAP (SHapley Additive exPlanations) with consensus feature importance ranking.

Results

Overall, 42.9% of patients achieved glycaemic control at 1 year. Performance was moderate, with AUC-ROC ranging from 0.633 to 0.676 and no significant pairwise differences. AdaBoost performed best (AUC-ROC: 0.676). SHAP consistently identified baseline HbA1c, diabetes duration, total cholesterol, hypertension history and oral antidiabetic therapy as the most influential predictors.

Conclusion

Machine learning models showed moderate, comparable performance, suggesting a ceiling imposed by routinely available data. Baseline HbA1c and diabetes duration were dominant predictors. Future research should prioritise external validation and longitudinal data integration. Contribution: This study provides evidence supporting machine learning for identifying key predictors of glycaemic control in West Africa, offering clinically actionable insights and highlighting the need for context-adapted decision-support tools in resource-limited settings.

Zitieren

APA

Ouattara, C. A., Coulibaly, B., Traoré, T. I., Cissé, B., Kyelem, C. G., Ouedraogo, M. S., Yaméogo, T. M., & Sombié, I. (2026). An automated machine learning approach to predict glycaemic control in patients with type 2 diabetes in Burkina Faso. Journal of Public Health in Africa, 17(1). https://doi.org/10.4102/jphia.v17i1.2024

Vancouver

Ouattara CA, Coulibaly B, Traoré TI, Cissé B, Kyelem CG, Ouedraogo MS, et al. An automated machine learning approach to predict glycaemic control in patients with type 2 diabetes in Burkina Faso. Journal of Public Health in Africa. 2026;17(1). doi:10.4102/jphia.v17i1.2024

BibTeX
@article{Ouattara2026,
  author = {Ouattara, Cheick A. and Coulibaly, Bazoumana and Traoré, Tiandiogo I. and Cissé, Bakary and Kyelem, Carole G. and Ouedraogo, Macaire S. and Yaméogo, Téné M. and Sombié, Issiaka},
  title = {An automated machine learning approach to predict glycaemic control in patients with type 2 diabetes in Burkina Faso},
  journal = {Journal of Public Health in Africa},
  year = {2026},
  volume = {17},
  number = {1},
  doi = {10.4102/jphia.v17i1.2024}
}
Kostenlos starten →