Detection of Antenatal Health Risk Level Using Machine Learning

During delicate gestation, various complications such as high blood pressure, increased heart rate and elevated blood glucose levels can lead to high-risk pregnancies. Early detection and treatment of abnormal health parameters can significantly reduce maternal mortality and morbidity rates. This research explores the use of Machine Learning approaches to enhance the efficacy of healthcare infrastructure, making it more cost-effective and capable of early diagnosis of pregnancy-related risks and health issues. The main goal of this research is to identify the most successful algorithm for identifying risk levels during pregnancy. Additionally, it examines health statistics and associated pregnancy risks. The construction of this model aims to drop maternal mortality rates by utilizing a dataset available on Kaggle, which includes seven features: age, blood pressure, blood sugar, body temperature, heart rate, and risk level. Comparative performance analysis demonstrates that the proposed model, based on the Random Forest classifier, achieves a relatively high accuracy of 93% compared to other existing models.