Rhino Health aims to enhance breastcancer prognosis by developing an advanced detection algorithm using Federated Learning. This algorithm will enable the development ofmore robust, personalized algorithms while maximizing patient privacy. Rhino Health is partnering with German Corredor Prada, PhD, MS, Assistant Professor from Emory University and Georgia Institute of Technology, as well as Assuta Medical Center and the Tel Aviv Sourasky Medical Center (“Ichilov”) to complete this project.
“Rhino Health is excited to partner with an innovative researcher such as Dr. Prada and our longtime partners at Assuta and Ichilov. This collaboration represents a groundbreaking step forward for precision medicine approaches to treating breast cancer,” said Daniel Feller, PhD, Rhino Health AI Program Lead. “We believe that the future of clinical risk modeling lies in multimodal data with both images and EHR data, and the Rhino platform can be used to build such models in a privacy- and governance-preserving federated setting.”
“This project and Rhino's federated computing capabilities enable me to take my research to the next level, as I have been able to validate and improve generalizability of algorithms by securely leveraging diverse data from across the world, all while maximizing privacy,” said Dr. Prada.
Implementing Federated Learning for breast cancer prognosis detection may face challenges such as standardizing data formats across institutions and ensuring data quality and consistency. Rhino Health’s mission, however, is to harness the power of federated computing to improve healthcare outcomes, by creating an activated, global network. Their FCP makes it possible to deploy code on data without ever needing to transfer those data. AI developers use the FCP to do harmonization, pre-processing, exploratory analysis, federated training / inference or even to build their own apps using their partners' data - all using their favorite tools (e.g. Jupyter Notebook, TensorFlow).
Beyond the model itself, another exciting outcome of this project will be the resulting dataset. The digital pathology slides used to train this model will be made available as Federated Datasets™ on Rhino Health’s platform, streamlining future collaborations with other researchers interested in working on these high-quality datasets tied to EHR records for future multi-modal AI development.
Find out more about Rhino Health and their work here and follow them on LinkedIn here!
More about the ELISE 2nd Open call and awarded companies is available here.
