In order to make discoveries, scientists and decision makers need data. These datasets are currently distributed across many different institutional, regional and national systems, making it impossible to leverage their collective power to make insights. The traditional approach of centralized “data sharing” – where datasets are combined by uploading and analyzing them in one place – is not suitable for sensitive datasets because co-locating data is inefficient, insecure, not scalable nor regulatory compliant, and does not empower data stewards to retain control over data. 

The technology developed throughout this project enables privacy-preserving “federated insights”, where insights can be derived across distributed datasets without moving them. All data remains in place and so, instead of “moving data to the question” this new approach “moves questions to the data”. This is more efficient, secure, scalable, compliant and empowers custodians to retain control over data. The CP4GPH is being used to train AI-powered models across federated networks of data in neuroscience, oncology, rare disease, infectious disease, health care, agriculture and beyond. 

This project democratized access to leading-edge technologies by creating a menu of new software and related services that can now be licensed to data generators (such as sequencing companies, hospitals, precision health initiatives, patient advocacy groups and funders) who want to increase the impact of their data, and to data consumers (such as health ministries and pharmaceutical companies) who want to extract insights from shared data. This open innovation ecosystem is helping to put Canada at the forefront of precision health: driving innovation, creating jobs, and fostering high-caliber research and discovery.