US-based computer technology firm Nvidia has rolled out Clara Holoscan MGX platform that enables medical device makers to develop and deploy real-time AI applications.

Clara Holoscan MGX succeeds its earlier generation Clara Holoscan platform, and provides an all-in-one, medical-grade reference architecture, along with long-term software support.

The new-generation platform comes with a hardware reference design, featuring Nvidia components and a long-term software support for 10 years.

Nvidia said that its Clara Holoscan MGX platform facilitates advancement of edge computing by processing high-throughput data streams for real-time insights.

Nvidia healthcare vice president Kimberly Powell said: “Deploying real-time AI in healthcare and life sciences is critical to enable the next frontiers in surgery, diagnostics and drug discovery.

“Clara Holoscan MGX, with its unique combination of AI, accelerated computing and advanced visualization, accelerates the productization of AI and provides software-as-a-service business models for the medical device industry.”

Clara Holoscan MGX combines the company’s Jetson AGX Orin Industrial module, RTX A6000 GPU and ConnectX-7 SmartNIC network adapter into a scalable AI platform.

The platform is capable of providing superior AI performance of up to 254 to 619 trillion operations per second.

Nvidia said that the medical device makers can directly embed its platform or connect to the existing medical devices, to advance AI deployment and regulatory approval.

Several embedded-computing manufacturers have sought to build products based on the Clara Holoscan MGX reference design, to serve the medical device industry.

The firms include ADLINK, Advantech, Dedicated Computing, Kontron, Leadtek, MBX Systems, Onyx Healthcare, Portwell, Prodrive Technologies, RYOYO Electro and Yuan High-Tech.

In a separate development, Nvidia has selected UK-based biotechnology company Alchemab Therapeutics to provide access to its Cambridge-1 supercomputer.

Alchemab is focused on the discovery and development of naturally-occurring protective antibodies and immune repertoire-based patient stratification tools.

The company would use Nvidia DGX SuperPOD supercomputing cluster, powered by NVIDIA DGX A100 systems, to get better understanding and insights from its neurology and oncology datasets.