Search reports, ask a question, or jump to a page.
The problem
Intervention: Machine learning model (LightGBM) deployed in a mobile application to predict fetal nutritional status based on maternal and clinical variables
Who it was tested with: Pregnant women in Tanzania (training data from 11,703 women).
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.
"the model was deployed within a mobile application to provide accessible, real-time predictions that support prompt clinical and behavioral responses." The study demonstrates development and user satisfaction with a predictive tool but lacks evidence of actual implementation effectiveness or impact on child health outcomes.
No actual clinical outcome data reported; only user satisfaction measured. No comparison group or randomized trial; no evidence that predictions led to interventions or improved child nutritional status. Accuracy metrics not provided.
Across countries and designs
1 study · 1 country
