MODEL FOR PREDICTING RISK LEVELS IN MATERNAL HEALTHCARE

Machine Learning

In the context of Bangladesh, a system has been built in this study for efficiently tracking and forecasting a pregnant woman's risk level. To determine the risk intensity level, this system will analyze the health information and risk factors of pregnant women. By 2030, the United Nations wants to improve maternal health and reduce mother and infant mortality; however, the rate is not decreasing as quickly as it should be. This study aimed to determine the risk level based on risk factors in pregnancy using appropriate analytical tools and machine learning algorithms. Data on maternal health were retrieved from the UCI machine learning repository for this study. According to the level of risk, categorization and classification methods have been utilized for the examination of risk variables. The AdaBoost Algorithm provides the highest AUC of 96%, when it comes to classification and prediction of the risk level, according to a comparison of certain groups of machine learning algorithms.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.