Dataset for Maternal Health Risks Stratification (MHRS) in Tanzania

The dataset is a collection of clinical parameters of pregnant women from Chamwino District in Dodoma region within the Central Zone, Mkuranga District in Pwani region within the Coastal Zone, Meatu District in  Simiyu region within Lake Zone, Mbulu District in Manyara region within the Northern Zone and Kilolo District in Iringa region within Southern Highlands. To ensure diversity and the inclusion of underserved communities in the dataset, the studyinitially collected and stratified data from a cohort of at least 8,817 pregnant women attending maternity primary health facilities for over nine months. Following rigorous data cleaning procedures and the exclusion of incomplete records, a final sample of 7,982 participants remained.

This dataset was developed to support machine learning applications that stratify maternal health risks in underserved communities across Tanzania. It enables research and development of predictive models to identify high-risk pregnancies, inform timely interventions, and improve maternal and newborn health outcomes. The dataset can also be used for public health research, benchmarking maternal health indicators, and building educational tools for community and clinical settings.