EUVIMEDEUVIMED entdecken
Open Access · CC0

Application of machine learning approaches to develop predictive models for diabetes and hypertension among Bangladeshi Adults

Anwendung von Machine-Learning-Ansätzen zur Entwicklung prädiktiver Modelle für Diabetes und Hypertonie bei Erwachsenen in Bangladesch

Gulam Muhammed Al Kibria iD, James Ross O'Hagan, Golam Shariar iD, Tarina Khan iD, Mohammed Elfaramawi

PLOS Global Public Health · 17.02.2026 · 6 (2) · e0004797

DOI: 10.1371/journal.pgph.0004797 ↗

Auf einen Blick

Mit Daten der Bangladesh Demographic and Health Survey 2022 wurden ML-Modelle für Diabetes und Hypertonie bei 13.847 Erwachsenen entwickelt. Die Sensitivität war hoch, die Spezifität insgesamt niedrig.

Fragestellung

Wie gut können Machine-Learning-Modelle Diabetes und Hypertonie bei bangladeschischen Erwachsenen vorhersagen?

Methode

Querschnittsanalyse national repräsentativer Daten der Bangladesh Demographic and Health Survey 2022; 6 ML-Modelle wurden getestet.

Ergebnisse

13.847 Erwachsene; 55 % Frauen. Diabetes: Prävalenz 16,3 %, höchste AUC 0,699 (AdaBoost), höchste Accuracy 0,836 (SVM). Hypertonie: Prävalenz 20,5 %, höchste AUC 0,775 und Accuracy 0,799 (AdaBoost).

Einschränkungen

Die Spezifität war insgesamt niedrig, besonders für Diabetes, sodass Nicht-Fälle schlecht erkannt wurden.

Schlussfolgerung der Autor:innen

Die Analyse identifizierte eine bidirektionale Beziehung zwischen Hypertonie und Diabetes sowie weitere Prädiktoren und unterstreicht den Bedarf an integriertem Screening und Lebensstilinterventionen.

Kernaussagen

  • ML-Modelle mit hoher Sensitivität, aber niedriger Spezifität
  • Diabetes: höchste AUC 0,699; Hypertonie: höchste AUC 0,775
  • Wichtige Prädiktoren: Hypertonie, Übergewicht/Adipositas, Alter und Wohlstand

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Global Public Health, online erschienen am 17.02.2026. Verfasst von Gulam Muhammed Al Kibria und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of international Health, Johns Hopkins Bloomberg School of Public Health, Baltimore, Maryland, United States of America. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC0).

Auf einen BlickAbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With rapid urbanization, lifestyle changes, and an aging population, non-communicable diseases (NCDs), including hypertension and diabetes, pose significant public health challenges in Bangladesh and many other low- and middle-income countries. This study used machine learning (ML) approaches to develop predictive models for hypertension and diabetes among Bangladeshi adults. Bangladesh Demographic and Health Survey 2022, a nationally representative cross-sectional survey, data were analyzed. Hypertension was defined as systolic/diastolic blood pressure 140/90 mmHg (or more) or taking any antihypertensive medication. Diabetes was defined as having fasting plasma glucose ≥7.0 mmol/L or using any glucose-lowering drugs. Potential predictors included age, sex, education, wealth quintile, overweight/obesity, rural-urban residence, and division of residence. Descriptive analysis was conducted, and six ML models were applied: artificial neural network (ANN), random forest, adaptive boosting (AdaBoost), gradient boosting, XGBoost, and support vector machine (SVM). Models’ performance and feature importance were reported. We included 13,847 adults (females: 55%). Sensitivity was high across models (up to 0.96 and 0.90 for diabetes and hypertension, respectively). However, the overall specificity was low, particularly for diabetes. The prevalence of diabetes and hypertension was 16.3% and 20.5%, respectively. For diabetes, AdaBoost had the highest AUC (0.699), and SVM had the highest accuracy (0.836); for hypertension, AdaBoost had the greatest AUC (0.775) and accuracy (0.799). Hypertension was the most common diabetes predictor, while overweight/obesity was the most common predictor for hypertension, followed by age and diabetes. Wealth and sex were moderately influential, with education and geographic factors less so. Low specificity across models indicated challenges in identifying non-cases. This ML-driven analysis identified the bidirectional relationship of hypertension and diabetes along with several other predictors, including overweight/obesity, older age, and richer household wealth quintiles. Our findings underscore the need for integrated screening and lifestyle interventions targeting high-risk groups to mitigate future NCD burden.

Autor:innen und Institutionen

  • Department of international Health, Johns Hopkins Bloomberg School of Public Health, Baltimore, Maryland, United States of America.
  • US Census Bureau, Baltimore, Maryland, United States of America.
  • New York Institute of Technology College of Osteopathic Medicine, New York City, New York, United States of America.
  • University of Arkansas for Medical Sciences, Little Rock, Arkansas, United States of America.

ORCID-Profile: Gulam Muhammed Al Kibria, Golam Shariar, Tarina Khan

Zitieren

APA

Kibria, G. M. A., O'Hagan, J. R., Shariar, G., Khan, T., & Elfaramawi, M. (2026). Application of machine learning approaches to develop predictive models for diabetes and hypertension among Bangladeshi Adults. PLOS Global Public Health, 6(2), e0004797. https://doi.org/10.1371/journal.pgph.0004797

Vancouver

Kibria GMA, O'Hagan JR, Shariar G, Khan T, Elfaramawi M. Application of machine learning approaches to develop predictive models for diabetes and hypertension among Bangladeshi Adults. PLOS Global Public Health. 2026;6(2):e0004797. doi:10.1371/journal.pgph.0004797

BibTeX
@article{Kibria2026,
  author = {Kibria, Gulam Muhammed Al and O'Hagan, James Ross and Shariar, Golam and Khan, Tarina and Elfaramawi, Mohammed},
  title = {Application of machine learning approaches to develop predictive models for diabetes and hypertension among Bangladeshi Adults},
  journal = {PLOS Global Public Health},
  year = {2026},
  volume = {6},
  number = {2},
  pages = {e0004797},
  doi = {10.1371/journal.pgph.0004797}
}
Kostenlos starten →