Analytics infrastructure for aggregated data

Medical data aggregated at a national level can bring a large number of insights to medical researchers and pharmaceutical companies. Research on the aggregated data will allow improving patient care, improving preventive healthcare, and measuring the effectiveness of medications and medical treatment. Medworq has developed a solution that aggregates medical data at a regional level from different healthcare sources. The goal of this project is to design and implement a solution that will aggregate healthcare data at a national level. Due to the fact that medical data is highly sensitive information, the main challenge of the data aggregation is to preserve data privacy of individuals. This report describes a project to analyze the data aggregation process, its challenges and use cases within Medworq, and to design a system that provides the data aggregation functionality. An inventory and comparative analysis of existing data privacy preserving techniques are provided in the report. The main deliverable of this project is a system that provides the data aggregation functionality together with a configurable choice of data privacy preserving techniques. The system was verified based on real patient data. The report also gives recommendations for future improvements.