2026-10-13T13:17:40Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33904241 2026-09-17T17:32:14Z category_7 category_21 category_734 category_811 category_132 category_134 portal_5 item_type_3 month_year_09_2026

Evaluation metrics of ML and DL models. Shawrab Chandra (25037939) Md. Maeen Molla (20827041) Samiul Islam (16733804) Md. Matiur Rahaman (14784483) Mohammad Ali (73095) Md. Ayub Ali (7221854) Medicine Biotechnology Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Infectious Diseases Virology weighted logistic regression indicating greater sensitivity extreme gradient boosting 2 %&# 8211 square test suggests public health applications evaluated using accuracy major risk factors two dl models low recall limits important predictors among four ml models although wlr demonstrated deep learning models predict hypertension risk 2022 bangladesh demographic 981 ), auc 444 ), specificity 817 ), precision xlink "> hypertension bangladesh risk factors deep learning 751 ), test data health survey demographic determinants highest accuracy machine learning 357 ). 070 ). 05 ). wealth index variables included study examined significantly associated significant association sectional data random forest model performance leading cause layer perceptron included 14 <div> BackgroundHypertension is a leading cause of cardiovascular morbidity and mortality in Bangladesh. This study examined its prevalence, risk factors, and predictive modeling using machine learning (ML) and deep learning (DL) approaches. MethodWe analyzed cross-sectional data from the 2022 Bangladesh Demographic and Health Survey, which included 14,283 adults (≥18 years). Prevalence was estimated, chi-square tests assessed associations, and four ML models (weighted logistic regression, random forest, extreme gradient boosting, light gradient boosting machine) and two DL models (TabNet, and multi-layer perceptron) were applied to predict hypertension risk. Model performance was evaluated using accuracy, precision, recall, specificity, F1 score, and area under the receiver operating characteristics curve and precision-recall curve. ResultsOverall prevalence was 18.04% (95% CI: 17.2%–18.9%), higher among women (18.87%) than men (16.97%). The chi-square test suggests that hypertension was significantly associated with age, BMI, diabetes, wealth index, education, household size, and region (p < 0.05). Among the machine learning and deep learning models, weighted logistic regression (WLR) achieved the highest accuracy (0.817), precision (0.444), specificity (0.981), AUC-ROC (0.751), and AUC-PR (0.357). However, WLR exhibited low recall (0.070). In contrast, the random forest (RF) model achieved the highest recall (0.687) and F1-score (0.460) on the test data, indicating greater sensitivity in identifying individuals with hypertension. Additionally, age, BMI, sex, family size, and educational level were identified as the most important predictors among the variables included in the study. ConclusionHypertension is common in Bangladesh, with higher prevalence in women and significant association with socio-demographic determinants. Although WLR demonstrated the highest accuracy, precision, specificity, and AUC-PR, its low recall limits its utility for identifying individuals with hypertension. RF may be more suitable for public health applications because of its higher recall and F1-score; however, further external validation and assessment of its clinical utility are required before implementation.</div> 2026-09-17T17:32:00Z Dataset Dataset 10.1371/journal.pone.0358471.t004 https://figshare.com/articles/dataset/_p_Evaluation_metrics_of_ML_and_DL_models_p_/33904241 CC BY 4.0