-

Verily Accelerates Precision Health AI With NVIDIA

NVIDIA’s software and accelerated computing will be integrated across Verily’s Pre platform. NVIDIA NeMo, NVIDIA Parabricks, and NVIDIA CUDA-X Data Science are now available in Verily Workbench, with accelerated workflows powered by NVIDIA Blackwell.

The NVIDIA-enhanced Pre platform will be used in the NIH All of Us Researcher Workbench, which supports nearly 20K registered researchers.

DALLAS--(BUSINESS WIRE)--Verily, a precision health AI company, today announced a collaboration with NVIDIA to integrate NVIDIA’s AI technology stack into its Pre platform, which is used by health system, life science, payer, and government customers and partners to more efficiently develop and deploy AI across healthcare.

Verily has added NVIDIA’s GPU-accelerated libraries and frameworks, including NVIDIA NeMo, NVIDIA Parabricks, and NVIDIA CUDA-X Data Science within Workbench, Verily’s trusted research environment (TRE). Researchers also now have access to some of the latest GPUs including NVIDIA Blackwell and NVIDIA Hopper. This integration has shown to greatly accelerate analyses, from hours to minutes, when using Parabricks and B200 to process genomic data as compared to traditional, CPU-only methods.

This effort will accelerate analyses within the National Institutes of Health’s (NIH) All of Us Researcher Workbench, which will be powered by Pre through Verily’s partnership with Vanderbilt University Medical Center. The All of Us Researcher Workbench hosts one of the world’s largest genomics datasets and supports nearly 20,000 registered researchers globally.

In addition to the Workbench integration, Verily plans to make NVIDIA GPU-accelerated microservices, libraries, and frameworks available for use across other Pre solutions. This includes Refinery, a powerful curation engine that ingests, harmonizes, and enriches multimodal data, using a clinically informed, FHIR-native data model to transform unstructured data into structured data assets, and Exchange, a secure forum for sharing and accessing AI-ready datasets, models, and agents to advance precision research and care.

“This collaboration is an exciting moment as we partner with our customers to deliver on the promise of precision health,“ said Stephen Gillett, Verily CEO. “With NVIDIA's cutting-edge AI capabilities now available in our Pre platform, we are providing researchers with unparalleled tools to enhance the speed and efficiency of AI model development and omics analysis, ultimately accelerating the understanding of disease and advancing precision health for everyone."

"AI is a critical tool for advancing precision health,” said Trent Norris, Global Industry Leader for Digital Health at NVIDIA. “Integrating NVIDIA's accelerated infrastructure and software stack into Verily's Pre platform will empower researchers to unlock new insights and drive faster development of AI models — ultimately leading to more personalized medicine and earlier disease prediction."

As a demonstration of the power of the Pre platform enhanced with NVIDIA AI tools, Verily's researchers have developed the first multimodal foundation model using the NIH All of Us Research Program dataset. The model integrates electronic health records (EHR) and genomics through polygenic risk scores, moving beyond traditional EHR-only approaches to build a more holistic individual health profile, enabling new insights into disease prediction and proactive health management. Using NVIDIA NeMo Automodel and H100 GPUs Verily researchers were able to train the model 10x faster than previous approaches.

About Verily
Verily is a data platform and technology company purpose-built to power AI for precision health. Verily offers AI-enabled solutions that transform multimodal health data into insights and actions that accelerate research and improve care for individuals and communities. Verily is uniquely positioned at the intersection of technology, data science, and healthcare to create tools that accelerate evidence generation, enable more personalized care, and help manage disease at a population level. For more information about Verily please visit: verily.com.

Contacts

Steven Cooper
Head of Media Relations
sjcoop@verily.com

Verily


Release Versions

Contacts

Steven Cooper
Head of Media Relations
sjcoop@verily.com

Social Media Profiles
More News From Verily

Verily Launches a New Consumer Health App, Verily Me, at HLTH USA 2025

DALLAS--(BUSINESS WIRE)--Verily, a precision health AI company, today announced the launch of a new consumer health app, Verily Me, that will be featured at HLTH USA 2025. Verily Me is designed to close gaps in care and enable people to stay informed and engaged in their health journey over time. Within the app, users can: Get personalized recommendations from providers: Licensed clinicians review relevant patient records across multiple providers and health systems and provide health recommend...

Verily, UCHealth, University of Colorado Anschutz, and RefinedScience Launch Strategic Collaboration for AI-Powered Research and Care Transformation

DALLAS--(BUSINESS WIRE)--Verily today announced a multi-year strategic collaboration with UCHealth, the University of Colorado Anschutz, and RefinedScience to transform how data is used and care is delivered, supported by Verily’s deep domain expertise and built-for-purpose healthcare technology capabilities. The agreement is grounded in a joint commitment to transform patient care and precision medicine through the latest advancements in artificial intelligence, digital technology and medical...

Verily Awarded Research Grant From the Michael J. Fox Foundation to Generate One of the World’s Largest, High-Dimensional Molecular Datasets of Parkinson’s Patients

DALLAS--(BUSINESS WIRE)--Today Verily, an Alphabet health data platform and AI company, announced it has received a grant from The Michael J. Fox Foundation for Parkinson’s Research (MJFF) to generate a comprehensive molecular dataset to advance Parkinson’s disease research. Verily will use cutting-edge molecular profiling techniques to accompany clinical, imaging, and wearable-based behavioral and physiological data already collected over several years as part of the Personalized Parkinson’s P...
Back to Newsroom