IoT Based Risk Level Prediction Model For Maternal Health Care In The Context Of Bangladesh

Internet of Things(IoT), a new paradigm has the extensive applicability including healthcare and numerous areas. In this research, a system has been developed for effective monitoring and predicting risk level of a pregnant women, in the context of Bangladesh. This system will analyzed the health data and risk factors of pregnant women to identify the risk intensity level. The United Nations goal is primarily concern about improving maternal health, reducing maternal and child mortality by 2030; however the rate is not declining up to the indication. This research intended to use respective analytical tools and machine learning algorithms for discovering the risk level on the basis of risk factors in pregnancy. In this research, a maternal health data set has been prepared from different sources (IoT device, Web portal, Hospitals in Bangladesh). This data set been also stored in the local server and as usual as in the cloud server as CSV(comma-separated value). For the analysis of risk factors, categorize and classifying approaches has been used according to the intensity of risk. After comparing among some groups of the machine learning algorithm, in case of classification and prediction of the risk level shows that Modified Decision Tree Algorithm gives the highest accuracy and the numeric value of this accuracy is 97%. A web application has also been developed as a crowdsourced platform to get feedback on different important suggestions and recommendations from corresponding stakeholders, which can also create as test data for further use.