Data Visualization and Predictive Analysis for Smart Healthcare: Tool for a Hospital

The healthcare industry is one of the most significant sources of Big Data. It is not feasible to manually interpret and understand the huge amounts of data generated by hospitals accurately. This creates the need for a data analytics and visualization tool. Visualizations are intuitive and help interpret the data easily. It would help the hospital to get insights from the data and to provide better service to the society. The aim of this project was to develop a data analysis and visualization tool for a hospital. This was implemented as a web application. The web application is developed using Django, which is a Python-based free and open-source web framework. For the visualizations embedded in the application, the Python library Altair was used. The application supports the upload of files that are the source for the visualizations and provides interactive visualizations based on the analysis performed. The visualizations can be exported as images using the application. Generating visualizations of choice becomes easier using navigation by menu bars in the application rather than writing complicated queries to the database. The tool ultimately attempts to help the hospital optimize time and resources effectively. Prediction using Long Short Term Memory (LSTM) for pharmacy orders and number of orders per patient will further help the hospital predict trends, patterns and outliers. Analysis tools will help analysing past, current and predict future pharmacy and diagnostics in a hospital which ultimately lead to better quality, efficient smart healthcare.