Scholarlink

<p>In many developing countries, early motherhood is significantly associated with the risk to women’s health. Despite progress in women’s empowerment, healthcare, and education, early childbearing remains a persistent public health challenge in Bangladesh. This study investigates the associated socioeconomic and contextual factors of early motherhood in Bangladesh and categorizes them using a machine learning algorithm. The research employed a cross-sectional study design that incorporated data from the 2017–2018 Bangladesh Demographic and Health Survey (BDHS). From an initial target population of 20,127 ever-married women of reproductive age (15–49 years) residing in both urban and rural areas, a final analytical sample of 16,729 participants was established after excluding cases with incomplete information. The findings indicate that early childbearing is significantly associated with factors such as partner education, wealth status, living arrangements, educational attainment, and access to family planning services. Logistic regression, which outperformed other machine learning algorithms, was found to be the most reliable predictive model due to its superior Area Under the Curve (AUC = 0.8437). Based on these results, the government and non-governmental organizations should establish appropriate policies to delay reproductive age and anticipate future policy implications and fertility patterns, especially in emerging nations like Bangladesh.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Socioeconomic and contextual factors associated with age at first birth among married women in Bangladesh: analysis with machine learning (ML) algorithms

  • 期刊论文

  • 发表日期：

    2026年3月31日

查看全文
  • Arzo Ahmed,
  • Md. Mizanur Rahman,
  • Md. Mahfuj-Ur Rahman,
  • Taksina Kabir,
  • Nipu Kumar Bhoumik,
  • Tanjina Sultana

摘要

In many developing countries, early motherhood is significantly associated with the risk to women’s health. Despite progress in women’s empowerment, healthcare, and education, early childbearing remains a persistent public health challenge in Bangladesh. This study investigates the associated socioeconomic and contextual factors of early motherhood in Bangladesh and categorizes them using a machine learning algorithm. The research employed a cross-sectional study design that incorporated data from the 2017–2018 Bangladesh Demographic and Health Survey (BDHS). From an initial target population of 20,127 ever-married women of reproductive age (15–49 years) residing in both urban and rural areas, a final analytical sample of 16,729 participants was established after excluding cases with incomplete information. The findings indicate that early childbearing is significantly associated with factors such as partner education, wealth status, living arrangements, educational attainment, and access to family planning services. Logistic regression, which outperformed other machine learning algorithms, was found to be the most reliable predictive model due to its superior Area Under the Curve (AUC = 0.8437). Based on these results, the government and non-governmental organizations should establish appropriate policies to delay reproductive age and anticipate future policy implications and fertility patterns, especially in emerging nations like Bangladesh.