The broader impact/commercial potential of this Small Business Innovation Research (SBIR) project is to address information needs of the COVID-19 crisis by rapidly integrating research findings describing the chemistry of the virus and its treatment. The proposed project will deploy advanced computational methods at participating medical institutions to make patient records immediately available for study while maintaining institutional and patient privacy. While the initial focus is on ameliorating COVID-19, the proposed solution can be applied more generally to accelerate epidemiological studies, improving scientific knowledge and public health with faster timelines and lowered costs for personnel, computing capabilities, and data storage.
This SBIR Phase I project proposes to rapidly expand and accelerate the accessibility of clinical and computational data to improve understanding of COVID-19. The proposed innovation will use cryptographic techniques, notably multiparty computation, to facilitate privacy-preserving cross-institutional querying of COVID-19 medical records. Improved access to petabytes of computational (simulation and model) data will speed research by allowing researchers around the world to probe the data. The effort will adapt and deploy decentralized computation techniques to enable distributed storage of many petabytes of virus molecular dynamics simulation data across computers around the world, in a verifiable manner that enables data analysis at the data location. The proposed dashboard will allow for secure queries of a combined dataset of participating institutions to quickly yield insight about the effect of various pre-existing conditions and medications on COVID-19. The effort will include verification and validation.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
