Optimizing patient transportation by applying cloud computing and big data analysis

In recent years, patient transportation demand has increased rapidly worldwide, especially in the Republic of Korea. Patient transportation requires high accuracy, arrangements, and reasonable allocation in time to the nearest healthcare facilities to support healthcare efficiency. Based on the emergency medical services system process, this research proposes a complete approach for collecting and processing data, and building the operating system, a web-app architecture using ReactJS, NodeJS, and Python to optimize patient transportation based on pathologies, distances, and corresponding specialized hospitals. Our system was designed to crawl data from a public information website of Busan City. After that, it automatically aggregated and stored these data in MongoDB before processing and input into our system. The concept of big data analysis was also built in here. This crawled data were analyzed and applied the API shortest direction of Naver Cloud to identify recommended hospitals with the most intelligent route and least cost. We built a web app connected to a server to visualize the research results and recommend decision-making for the operator and dispatcher in each area. The experiment results showed that the proposed method could recommend the nearest healthcare facilities and routes based on pathologies, optimal distances and times, and travel costs in an actual application, thereby helping solve patient congestion problems, allocate appropriate medical resources, and support healthcare efficiency to solve significant social problems.