Mayo Clinic has announced the adoption of AI solutions in its clinical environments, integrating NVIDIA DGX SuperPOD with NVIDIA DGX A100 systems.
This advanced AI computing infrastructure is part of Mayo Clinic’s strategic initiative to innovate healthcare and improve patient outcomes through its ‘Bold. Forward.’ strategy.
The collaboration between Mayo Clinic and NVIDIA aims to quickly innovate and establish foundational models that support the former’s healthcare platform.
This includes advancements in digital pathology and generative AI solutions, which are set to offer new insights and drive improvements in patient care.
The NVIDIA Blackwell-driven DGX SuperPOD is specifically designed to process high-resolution imaging, which is crucial for training AI foundational models.
Its speed and scalability will allow Mayo Clinic to enhance pathology slide analysis and reduce the time required for foundation model development from four weeks to one.
In collaboration with Aignostics, Mayo Clinic has established the Atlas pathology foundation model, which has been trained on over 1.2 million histopathology whole-slide images.
Atlas enables researchers and clinical care providers to increase accuracy and reduce the burden of administrative work. The new computing capabilities will further expedite the establishment of clinical models.
Mayo Clinic Digital Pathology CEO Jim Rogers said: “This compute power, coupled with Mayo’s unparalleled clinical expertise and platform data of over 20 million digitised pathology slides, will allow Mayo to build on its existing foundation models.
“We’re transforming healthcare by quickly and safely developing innovative AI solutions that can improve patient outcomes and enable clinicians to dedicate more time to patient care while also accelerating commercial affiliations with other industry leaders.”
Last year, Mayo Clinic worked with Abridge and Epic to build an integrated generative AI ambient documentation solution aimed at enhancing the workflow for nurses.
“Mayo Clinic integrates NVIDIA’s AI infrastructure” was originally created and published by Hospital Management, a GlobalData owned brand.
The information on this site has been included in good faith for general informational purposes only. It is not intended to amount to advice on which you should rely, and we give no representation, warranty or guarantee, whether express or implied as to its accuracy or completeness. You must obtain professional or specialist advice before taking, or refraining from, any action on the basis of the content on our site.