E-seminar: Developing high performance secure multi-party protocols for healthcare data analytics

On December 10, 2021, Dr. Xiao Dong gave a seminar on developing high performance secure multi-party protocols for healthcare data analytics. Xiao Dong recently joined Center for Translational Data Science (CTDS) as a data scientist, Prior to joining CTDS, he was a senior research specialist at the Center for Clinical and Translational Science at University of Illinois at Chicago. Xiao Dong received his PhD in Informatics from Indiana University at Bloomington in 2010. This seminar talks about Xiao’s main research works at UIC between 2019 and 2021.

Performing privacy-preserving data analytics across different healthcare institutions is both important and challenging. In this talk, we presented how state-of-the art cryptography techniques, such as multi-party secure computation and homomorphic encryption, can accomplish cross-institution data analytics using highly efficient and provably secure protocols. Use cases for these protocols include clinical trial cohort studies, comorbidity index calculation and high utilizer identification when patient’s records are spread across multiple institutions. This series of research has been presented several times at the American Medical Informatics Association’s Annual Symposium (2019) and Informatics Summit (2020, 2021).