Yale Biomedical Informatics and Data Science (BIDS) is leading the way in developing innovative technologies that prioritize data privacy while driving advancements in genomics and health-related research. Under the leadership of Lucila Ohno-Machado, MD, MBA, PhD, Waldemar von Zedtwitz Professor of Medicine and department chair; faculty members Hyunghoon Cho, PhD, assistant professor of biomedical informatics & data science and of computer science; and Tsung-Ting Kuo, PhD, associate professor of biomedical informatics and data science are spearheading transformative initiatives aimed at redefining privacy preserving data sharing frameworks.
At the center of these efforts is Ohno-Machado, whose pioneering work emphasizes patient-centric approaches to electronic health record (EHR) sharing, integrating advanced privacy-preserving techniques to balance data accessibility with robust protections against re-identification. Ohno-Machado's influential contributions include several key publications including, “A Hierarchical Strategy to Minimize Privacy Risk When Linking ‘De-identified’ Data in Biomedical Research Consortia” (Journal of Biomedical Informatics), which proposes innovative methods for linking de-identified datasets while minimizing privacy risks; "VERTICOX: Vertically Distributed Cox Proportional Hazards Model Using the Alternating Direction Method of Multipliers" (IEEE Transactions on Knowledge and Data Engineering), which introduces a scalable algorithm for distributed survival analysis; “Privacy-Protecting, Reliable Response Data Discovery Using COVID-19 Patient Observations” (Journal of the American Medical Informatics Association), which discusses maintaining privacy while ensuring data reliability during the pandemic; "Privacy Challenges and Research Opportunities for Genomic Data Sharing” (Nature Genetics), a review exploring privacy challenges in genomic data sharing and suggesting areas for improvement.
Cho leads the Hoon Cho Lab, which focuses on developing computational methods for secure biomedical data sharing. Supported by an NIH DP5 grant, his team recently developed a novel algorithm for securely estimating genetic kinship across distributed genomic datasets. This algorithm, tested on data from UK Biobank and All of Us, achieves high accuracy in identifying relatives without compromising individual privacy. Recognized for its impactful contribution, the work titled “Secure Discovery of Genetic Relatives across Large-Scale and Distributed Genomic Datasets” earned Cho’s team the Best Student Paper award at the prestigious RECOMB conference.
Kuo addresses vulnerabilities in centralized data-sharing frameworks, such as single points of failure and data security risks. By leveraging blockchain technology, Kuo is designing decentralized systems that enable secure, immutable exchanges of biomedical data transactions. His recent publication, “The Evolving and Privacy and Security Concerns for Genomic Data Analysis and Sharing as Observed from the iDASH Competition” (Journal of the American Medical Informatics Association), highlights the transformative potential of blockchain for applications such as recording patients’ data-sharing consents for clinical research. Supported by an NIH R01 grant, Kuo's team also published, “Quorum-based Model Learning on a Blockchain Hierarchical Clinical Research Network Using Smart Contracts”, (International Journal of Medical Informatics), which introduces the combination of blockchain and federated learning to protect patients’ privacy without the need for a central server.
Together, our faculty members exemplify Yale BIDS' commitment to creating innovative privacy technologies that empower cross-institutional collaboration while safeguarding individual confidentiality. Their combined efforts mark a significant leap forward in the ethical and secure advancement of biomedical research.