科研速览 · Science Skim继续刷下去 · Keep skimming →
◆ Frontiers in global women's health2026-01-01

Contraceptive ever-use among women of reproductive age in Northern Ghana: a comparative analysis of logistic regression, LASSO penalised regression, and random forest machine learning approaches.

Joseph Lasong, Mavis Kala, Torjim Salifu, Yula Salifu

一句话结论 · In one sentence

Random Forest provided better discrimination and may complement regression for prediction, though regression remains essential for interpretable effect estimates. Attitude change, education, and counselling quality are priority targets. The inverse wealth association warrants qualitative investigation, as polygyny, religiosity, and partner dynamics were unmeasured.

原始摘要(英文原文)· Original abstract
BACKGROUND: Contraceptive uptake in Northern Ghana remains low despite high awareness, suggesting barriers not fully captured by additive models. This study compared logistic regression, LASSO, and Random Forest to predict contraceptive ever-use and identify determinants among women in Tamale Metropolis. METHODS: A facility-based cross-sectional survey (January-April 2023) included 414 women aged 15-49 from three public health facilities. Outcome: contraceptive ever-use. Twelve predictors included knowledge/attitude scores, wealth tertile, education, parity, marital status, occupation, age, cultural barriers, health worker attitudes, and information source. Model discrimination was assessed via AUC with 95% CIs; LASSO used 10-fold cross-validation (λ.min=0.012); Random Forest used 500 trees. RESULTS: Random Forest achieved highest discrimination (AUC=0.865, 95% CI:0.83-0.90), outperforming logistic regression (AUC=0.727) and LASSO (AUC=0.723) (both p < 0.001); logistic and LASSO did not differ (p = 0.91). Logistic regression identified five independent predictors: positive attitudes (AOR=1.53), education above primary (AOR=2.72), parity (AOR=2.95), health worker as information source (AOR=2.07), and richest wealth tertile inversely associated (AOR=0.49). Knowledge was non-significant in regression but ranked second in Random Forest importance, suggesting non-linear/interaction effects. LASSO retained nine predictors, dropping cultural barriers, health worker attitudes, and age. CONCLUSIONS: Random Forest provided better discrimination and may complement regression for prediction, though regression remains essential for interpretable effect estimates. Attitude change, education, and counselling quality are priority targets. The inverse wealth association warrants qualitative investigation, as polygyny, religiosity, and partner dynamics were unmeasured.
读原文 · Read the paper ↗

AI 追问PRO

登录后使用 AI 追问

讨论区

登录后参与讨论

相关论文 · Related

Contraceptive ever-use among women of reproductive age in Northern Ghana: a comparative analysis of logistic regression, LASSO penalised regression, and random forest machine learning approaches. — 科研速览 Science Skim