Mayo Clinic: New AI Computing Platform Will Advance Precision Medicine

One of the great aspirational challenges of artificial intelligence (AI) has been to meaningfully detect disease early enough to intervene. Of course, hospitals and health systems need the right data, advanced computing and storage capabilities to achieve this goal.

Mayo Clinic leaders recently said they are well on their way to integrating AI solutions in the clinical setting. The Rochester, Minnesota-based health system partnered with Nvidia to launch an AI computing platform designed to support the development of foundation models used in areas like digital pathology, drug discovery and precision medicine.

The deployment of Nvidia’s DGX SuperPOD powered by DGX B200 systems will provide the infrastructure to contribute to Mayo’s “Bold. Forward. Unbound.” strategy and support new innovations for generative AI solutions and digital pathology.

The advanced computing infrastructure initially will support foundation model development for pathomics, drug discovery and precision medicine.

The Nvidia Blackwell-powered SuperPOD is optimized for processing high-resolution imaging and is expected to sharply cut the time required to analyze pathology slides. Tasks that previously took four weeks now can be completed in one, according to Mayo Clinic.

Mayo Clinic's Atlas pathology foundation model, developed with the biomedical AI company Aignostics, is trained on a dataset of more than 1.2 million histopathology whole-slide images and used by clinicians and researchers to enhance accuracy.