Maternal health risk factors dataset: Clinical parameters and insights from rural Bangladesh

Pregnancy-related complications and their consequences pose significant public health challenges, particularly in rural and developing areas where healthcare resources are limited. Monitoring clinical parameters during pregnancy improves diagnosis, treatment, and maternal health prognosis. This database includes records of pregnant patients from Kurigram General Hospital, Bangladesh. It captures core health parameters such as age, blood pressure (systolic and diastolic), blood sugar levels, body temperature, BMI, current mental health status, pre-existing medical history, gestational diabetes status, and heart rate. The diversity of data collected in this dataset is essential for understanding potential health changes associated with pregnancy. It will aid in generating high-risk pregnancy evaluation and prediction models to support clinical management. This dataset is valuable for its potential to serve as a benchmark for comparing maternal health responses across different clinical conditions of patients, thereby contributing to a broader understanding of pregnancy-related complications. The study's preprocessing methods, which included data cleaning, normalization, and encoding, ensured high-quality data for statistical analysis. Initial findings used statistical tests to explore associations within the data. A Chi-Square test analyzed the relationship between preexisting diabetes and risk levels, revealing a significant association with a p-value of 4.85e-119. A Z-test was also conducted to compare clinical parameters between pregnant patients with and without diabetes, with a sample ratio of 337:811. This test showed a significant difference in BMI (body mass index), with a p-value of 2.23e-24, indicating that preexisting diabetes impacts BMI. A T-test for BMI revealed a significant difference, with a p-value of 1.405e-20. These findings further elucidate how specific age and body mass index details influence the risk levels associated with maternal clinical conditions. In summary, this database will be highly valued and a significant asset for research studies on maternal health in pregnant patients, public health strategies, and the enhancing diagnostic and treatment modalities for patients.