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

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

AdaBoost · Artificial neural network · Blood pressure · Boosting (machine learning) · Diabetes mellitus · Gradient boosting · Random forest · Support vector machine · Artificial Intelligence in Healthcare · Diabetes, Cardiovascular Risks, and Lipoproteins · Machine Learning in Healthcare

• Global, regional, and national age-sex-specific mortality for 282 causes of death in 195 countries and territories, 1980–2017

  Open Access•Gregory A Roth, D Abate et al.•The Lancet•2018

  Add to list

• Burden of Undiagnosed Hypertension in Sub-Saharan Africa

  Feven Ataklte, Sebhat Erqou et al.•Hypertension•2015

  Add to list

• Global Burden of Hypertension and Systolic Blood Pressure of at Least 110 to 115 mm Hg, 1990-2015

  Mohammad H Forouzanfar, Patrick Liu et al.•JAMA•2017

  Add to list

• Clustering of hypertension, diabetes and overweight/obesity according to socioeconomic status among Bangladeshi adults

  Open Access•Gulam Muhammed Al Kibria, Mohammad Rashidul Hashan et al.•Journal of Biosocial Science•2021

  Add to list

• Clustering of chronic non-communicable disease risk factors among selected Asian populations

  Open Access•Sayed M Ahmed, Syed Masud Ahmed et al.•Global Health Action•2009

  Add to list

• Type 2 diabetes and its correlates among adults in Bangladesh

  Open Access•Muhammad Abdul Baker Chowdhury, Md Jamal Uddin et al.•BMC Public Health•2015

  Add to list