2026-10-11T13:18:27Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33956136 2026-09-21T17:28:33Z category_7 category_12 category_21 category_45 category_734 category_64 category_132 portal_5 item_type_3 month_year_09_2026

<p>Machine learning model performance matrix.</p> Jakia Sultana Mim (25084530) Md. Shihab Mostafa (25084533) Bodrunnahar Barna (25084536) Ahmed Nuzat Sadia (25084539) Raisul Islam (4016498) Abdullah Al Islam (25084542) Medicine Cell Biology Biotechnology Sociology Biological Sciences not elsewhere classified Cancer Infectious Diseases targeted interventions focusing random forest achieved nationally representative cross improves classification performance identify significant determinants identify key socioeconomic highest numerical accuracy binary logistic regression additional classification framework achieved notable progress 72 &# 8211 47 &# 8211 11 &# 8211 skilled birth attendants antenatal care utilization cultural factors rather xlink "> data key factors associated 94 &# 8211 sba utilization compared greater sba utilization substantially higher odds xlink "> education xlink "> bangladesh 2022 bangladesh demographic machine learning models higher maternal education xlink "> learning models associated factors higher odds attendants provided higher education anc utilization significantly associated lower odds bangladesh using using sba use sba classify sba square tests sectional survey rural populations richest households poorest households partly due outcome variable <div> <p>Background</p><p>Bangladesh has achieved notable progress in maternal and child health; however, maternal and neonatal mortality remain high, partly due to inadequate access to skilled birth attendants (SBA) during delivery. This study aims to identify key socioeconomic and demographic factors influencing SBA utilization in Bangladesh.</p> <p>Methods</p><p>Data were obtained from the 2022 Bangladesh Demographic and Health Survey (BDHS), a nationally representative cross-sectional survey which was conducted from June 27 to December 12, 2022. The outcome variable was skilled birth attendants during delivery, defined as attendants provided by a doctor, nurse, or midwife. Descriptive statistics and chi-square tests were used for initial analysis, followed by binary logistic regression to identify significant determinants. Additionally, the inclusion of machine learning models provides an additional classification framework that improves classification performance and helps identify important predictors, complementing traditional regression analysis.</p> <p>Results</p><p>From the study, 67.94% of women utilized skilled birth attendants during childbirth. Higher maternal education, household wealth, antenatal care utilization, and urban residence were significantly associated with greater SBA utilization. Women with higher education had substantially higher odds of using SBA than those with no education (AOR = 4.10, 95% CI: 1.94–8.66, p < 0.001), while rural women had lower odds than urban women (AOR = 0.64, 95% CI: 0.47–0.88, p = 0.006). Women who attended four or more ANC visits were also more likely to use SBA than those with no ANC visits (AOR = 2.92, 95% CI: 1.72–4.96, p < 0.001). Women from the richest households had higher odds of SBA utilization compared with those from the poorest households (AOR = 1.77, 95% CI: 1.11–2.81, p = 0.016). Among the machine-learning models, Random Forest achieved the highest numerical accuracy (0.82).</p> <p>Conclusion</p><p>Education, economic status, ANC utilization, and place of residence were identified as key factors associated with skilled birth attendants during delivery in Bangladesh using the binary logistic regression model. Moreover, the machine learning models were used separately to classify SBA. Targeted interventions focusing on disadvantaged and rural populations can help improve equitable access to maternal healthcare. However, differences related to religion and region should be interpreted cautiously, as they may reflect broader socioeconomic and cultural factors rather than direct effects.</p></div> 2026-09-21T17:28:24Z Dataset Dataset 10.1371/journal.pone.0358556.t003 https://figshare.com/articles/dataset/_p_Machine_learning_model_performance_matrix_p_/33956136 CC BY 4.0