A Smart Pregnant Women Health Care System for Risk Level Prediction Using Machine Learning

Abstract

Pregnancy is essential for mother and child, thus it is important to keep an monitor on any health concerns to ensure a safe delivery. Given that it compromises the mother's health as the long-term development of the baby, early risk tagging is essential for maternal health. Mothers would receive additional treatment before during, and after pregnancies if high-risk pregnancies were assigned, which would lower the chance of difficulties. However, the lack of access to healthcare in developing countries makes it difficult to manage any possible health risks during pregnancy.  Medical systems can generate data-driven decision support models automatically with machine learning techniques, removing the requirement for explicit rule development by utilizing real-world data inputs.  In this analysis, A Smart Pregnant Women Health Care System for Risk Level Prediction Using Machine Learning is presented. The Support vector machine (SVM) is used to predict the risk levels and health condition of pregnant woman. This model predicts the risk levels into Low, Mid and High levels. The accuracy, precision, recall, and F1-score of the model is used to evaluate its performance. When a patient is in a high-risk, this system informs registered family members and medical professionals.