Search reports, ask a question, or jump to a page.
The problem
Intervention: Two parity-stratified clinical prediction models using maternal and clinical risk factors to predict risk of low 5-minute Apgar scores
Who it was tested with: 124,376 singleton births at or beyond 28 weeks of gestation across 16 hospitals in Benin, Malawi, Tanzania and Uganda (July 2021 - December 2023).
Experience from people who deliver programmes: stories, case studies and lessons learned. Valuable for understanding how and why, and for spotting what to test next, but not a measure of effect.
"Model predictors were selected using a knowledge-based approach, and multivariable logistic regression was performed. Model performance was assessed through calibration and discrimination with internal validation conducted using bootstrapping." The models showed moderate discriminative ability with excellent calibration in the development dataset, but without external validation or evidence of improved clinical outcomes, the true effectiveness is inconclusive.
Study only reports internal validation; external validation in different populations required to assess generalisability. Clinical utility and whether using these models improves actual patient outcomes or care delivery remain undemonstrated.
Across countries and designs
1 study · 4 countries
