Public healthcare systems generate large amounts of heterogeneous data that can provide valuable insights to inform public policy design. However, extracting relevant information from extensive heterogeneous datasets might be challenging. To address this problem, in a government-academia collaboration, we are developing an interactive visual dashboard for large-scale data analysis based on the Brazilian National Health System (SUS) hospitalization data. Its software architecture enables integration with the Hospital Information System (SIH-SUS) datasets from any region of Brazil so that health professionals can use it in hundreds of different cities. We defined an architecture that tames code complexity and brings modularity to the system. The platform processes SIH-SUS data and stores it into a geolocated relational database. Expert users can then perform advanced queries on the data with composite filters. Results are then displayed via multiple map visualizations, graphs, and tables. We expect that this open-source platform will become a useful tool for science-based public health policy making, influencing Brazilian public managers in the future to adopt an evidence-based, data-driven approach to healthcare management.
