Enhancing Machine Learning Algorithms for Prenatal Care through the Group Antenatal Care Model in Tanzania

Leveraging the group antenatal care (G‑ANC) model, this project collected homogeneous data from nearly 5,000 pregnant women in Tanzania to design and test machine learning algorithms for predicting adverse pregnancy outcomes. By using the government‑led Unified Community System (UCS), the initiative harnessed over 100,000 data points, focusing on women grouped by similar gestational age. The resulting ML algorithms successfully predict hypertensive disorders during pregnancy, demonstrating how patient‑centred care models can fuel AI‑driven clinical decision‑making and improve maternal health outcomes.