Peter Jang
October 8, 2024 19:36
NVIDIA’s AI tools, including NIM microservices, are transforming the U.S. healthcare landscape and advancing research and clinical practice with cutting-edge AI technologies.
The U.S. healthcare sector is experiencing a technological transformation as digital health agents powered by artificial intelligence are integrated across various aspects from the laboratory to the clinical environment. This trend was highlighted at the NVIDIA AI Summit in Washington DC, where NVIDIA unveiled a suite of AI acceleration tools designed to improve healthcare capabilities.
AI Innovation at NVIDIA
Among the innovations on display are NVIDIA NIM, a suite of cloud-based microservices that facilitate AI model deployment and execution, and NIM Agent Blueprint, a catalog of pre-trained, custom workflows. These technologies are currently being utilized in the public sector to advance medical image analysis, support therapeutic research, and extract data from extensive PDF databases.
In fact, researchers at the National Cancer Institute, part of the National Institutes of Health (NIH), are using AI models developed with NVIDIA MONAI for medical imaging. These models include the VISTA-3D NIM-based model that helps segment and annotate 3D CT images. Additionally, NIH’s National Center for Advancing Translational Sciences (NCATS) uses the NIM Agent Blueprint for generative AI-based virtual screening to streamline the drug development process.
Wider applications and availability
NVIDIA’s NIM microservices and blueprints are accessible through a variety of cloud service providers and technology solutions, providing public sector healthcare researchers with the opportunity to adopt cutting-edge AI models. The tool is designed to be customizable to your organization’s data and can be improved through user feedback.
Using the NVIDIA AI Enterprise platform, developers have access to numerous NIM microservices and blueprints that can be deployed in production environments. Key blueprints include generative virtual screening in drug discovery, multimodal PDF data extraction, and creation of conversational AI-based avatars for customer service that can be applied to telemedicine and patient care.
Enhancing Drug Discovery
To accelerate drug discovery research, NCATS is actively evaluating the NIM Agent Blueprint for virtual screening leveraging NVIDIA’s RAPIDS software library. By using GPU-accelerated data science tools such as cuGraph and the cuDF library, researchers can efficiently map chemical reactions, significantly reducing processing time.
The Genetic and Rare Disease Information Center, managed by NCATS, is exploring AI tools for PDF data extraction to improve information retrieval in complex databases and assist in responding to inquiries from individuals with rare diseases.
Cooperation and future prospects
Startups and global integrators are integrating NVIDIA’s AI solutions into their platforms. Notable examples include Abridge, an NVIDIA Inception startup that signed a contract with the U.S. Department of Veterans Affairs to streamline clinical documentation through AI-powered transcription services. AWS HealthOmics and ConcertAI are also leveraging NVIDIA’s AI capabilities to advance drug discovery and oncology AI technologies, respectively.
Deloitte, a global systems integrator, is deploying the NIM Agent Blueprint for virtual testing to help federal health agencies adopt AI solutions for drug discovery. This collaboration highlights NVIDIA’s commitment to making AI tools widely available within the biomedical research community.
To learn more about NVIDIA’s healthcare AI innovations, visit the NVIDIA Blog.
Image source: Shutterstock