HealthSentry: Design and Development of Municipal Health Condition Monitoring Using Spatio-Temporal Analysis and Geo-Mapping

Abstract

To prevent the spread of communicable illnesses and improve general health conditions, it is essential to have a better understanding of the health status of the community. Using historical data from the Rural Health Unit, this project aimed to develop a mechanism for anticipating health concerns. By predicting health concerns, decision-makers may develop better plans and tactics to prevent unhealthy circumstances. This endeavor used data-driven methodology and machine learning and deep learning approaches to improve monitoring accuracy. Graph neural networks (GNNs) were used in this research to handle graph-based forms, which are more ideal for predicting health concerns than convolutional neural networks (CNN), and were previously used to represent the city as a grid. The main goal was to provide a system that is simple to deploy and that provides a framework for future enhancements to track municipality natality, mortality, and morbidity rates. Using spatiotemporal analysis and geospatial mapping, the Municipal Health Condition Monitoring and Forecasting System was developed to monitor and manage the health status of the municipality's residents. The Rapid Application Development (RAD) technique was used to design and create the system. HTML, CSS, Javascript, and Node.js were used in the system's development for the user interface, whereas Phyton 3, TensorFlow, Keras, NumPy, and Pandas were utilized for data analysis. The technology may be used by decisionmakers to keep track of geographic and temporal links, which are crucial for predicting health conditions and helping them take preemptive action to halt the spread of illnesses. Overall, this study is a valuable resource for those who want to build the same kind of study concept. Above all, this study could assist policymakers and medical experts in monitoring and anticipating rural health difficulties once they are implemented in their municipality.