Scholarlink

Background <p>Despite global progress, neonatal mortality remains a significant challenge in Ethiopia, with rates higher than the global average. Identifying key determinants is important for developing targeted interventions. This study aims to comprehensively examine socio-economic and demographic factors influencing neonatal mortality in Ethiopia.</p> Methods <p>Data from the 2019 Ethiopia Mini-Demographic and Health Survey was analyzed. Binary logistic regression, machine learning models (logistic regression, random forests, and support vector machines), and propensity score matching were used to identify determinants of neonatal mortality and estimate the causal effect of early childbearing age.</p> Results <p>The study population included 22,829 children, with 867 (4%) experiencing neonatal death. Significant determinants identified included primary education (AOR = 1.72, 95% CI: 1.15–2.56), large household size (AOR = 1.78, 95% CI: 1.51–2.11), female household head (AOR = 1.25, 95% CI: 1.02–1.53), and early childbearing age (AOR = 1.28, 95% CI: 1.11–1.47). First or second birth order (AOR = 0.76, 95% CI: 0.65–0.88) and Muslim religion (AOR = 0.78, 95% CI: 0.66–0.92) were protective factors. Notably, machine learning algorithms identified additional factors such as maternal age and wealth index. Additionally, propensity score matching showed that giving birth before age 20 was associated with a 2% absolute increase in neonatal mortality risk (ATT = -0.02, 95% CI: -0.03 to -0.002) compared with mothers aged 20 years or older.</p> Conclusion <p>This study identified key socio-economic and demographic determinants of neonatal mortality in Ethiopia including maternal education, household characteristics, and obstetric factors. Addressing these interrelated factors through comprehensive strategies involving education, economic empowerment, family planning, and improved obstetric care is important for reducing neonatal mortality and achieving child health goals.</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

A machine learning approach to identify key socio-economic and demographic factors associated with neonatal mortality in Ethiopia

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月14日

查看全文
  • Filippos Admasu,
  • Mahlet Sewinet

摘要

Background

Despite global progress, neonatal mortality remains a significant challenge in Ethiopia, with rates higher than the global average. Identifying key determinants is important for developing targeted interventions. This study aims to comprehensively examine socio-economic and demographic factors influencing neonatal mortality in Ethiopia.

Methods

Data from the 2019 Ethiopia Mini-Demographic and Health Survey was analyzed. Binary logistic regression, machine learning models (logistic regression, random forests, and support vector machines), and propensity score matching were used to identify determinants of neonatal mortality and estimate the causal effect of early childbearing age.

Results

The study population included 22,829 children, with 867 (4%) experiencing neonatal death. Significant determinants identified included primary education (AOR = 1.72, 95% CI: 1.15–2.56), large household size (AOR = 1.78, 95% CI: 1.51–2.11), female household head (AOR = 1.25, 95% CI: 1.02–1.53), and early childbearing age (AOR = 1.28, 95% CI: 1.11–1.47). First or second birth order (AOR = 0.76, 95% CI: 0.65–0.88) and Muslim religion (AOR = 0.78, 95% CI: 0.66–0.92) were protective factors. Notably, machine learning algorithms identified additional factors such as maternal age and wealth index. Additionally, propensity score matching showed that giving birth before age 20 was associated with a 2% absolute increase in neonatal mortality risk (ATT = -0.02, 95% CI: -0.03 to -0.002) compared with mothers aged 20 years or older.

Conclusion

This study identified key socio-economic and demographic determinants of neonatal mortality in Ethiopia including maternal education, household characteristics, and obstetric factors. Addressing these interrelated factors through comprehensive strategies involving education, economic empowerment, family planning, and improved obstetric care is important for reducing neonatal mortality and achieving child health goals.