Teton unveils 3D hospital digital twin using Denmark’s supercomputer

Denmark-based Teton, a company that offers an AI companion to help nurses monitor patients and optimize workflow, announced it created a real-time, live 3D reconstruction of a hospital room using Gefion, Denmark’s national supercomputer.

The aim is to help nurses recognize risks early, reduce paperwork and improve patient care.

Operated by the Danish Center for AI Innovation, Gefion is built on NVIDIA DGX systems. Teton uses NVIDIA DGX systems “to generate data for the digital twin.”

According to NVIDIA, DGX Station is a “high-performance NVIDIA Grace Blackwell desktop supercomputer powered by the NVIDIA Blackwell Ultra platform.” It enables AI developers, researchers, data scientists and students to prototype, fine-tune and inference large models on desktops. 

In addition, users can run the models locally or deploy them on NVIDIA DGX Cloud, any other accelerated cloud or another data center infrastructure.

The digital twin provides a real-time view of what is happening inside a care facility in 3D.

In a statement, the company explained that the Teton AI Gym is a simulation engine that makes true-to-life, 3D care environments of realistic patient and staff interactions utilizing synthetic data.

The company said that early pilots have shown that it can reduce night shift work by as much as 25%.

“Our system can understand what people are doing, how they are sleeping, their respiration rate, their lying position and their gait,”  Mikkel Wad Thorsen, cofounder and CEO of Teton, told MobiHealthNews.

“It can do all these things in real time and provide continuous metrics on patient health and the care they receive,” he said. “Operating in 3D is a game-changer for the TEO-2 model, and it has only been possible with access to the supercomputer. With all of these data points, we could significantly accelerate the iteration time and unlock a new scale for the next generation of our model, TEO-2.” 

THE LARGER TREND

Other companies involved in the 3D healthcare space include Restor3d, a 3D-printed orthopedic implant care company that raised $38 million in April. Summers Value Partners participated in the round, along with existing and new private investors.

Restor3d provides joint replacements and 3D printing of osseointegrative materials, AI-based planning and design automation tools. 

In 2024, Taiwan-based medtech company SURGLASSES announced it implemented its augmented reality-based surgical navigation system in Thailand. 

Thailand Veterans General Hospital and Chulalongkorn Hospital conducted their first AR-guided surgeries using the Caduceus S system.

Designed for spine surgery, the SURGLASSES system provides surgeons with 3D visualization to view the patient’s internal anatomical structures during procedures, including bones, tissues and organs. 

Another Taiwanese company, JelloX Biotech, collaborated with Mayo Clinic to bring its AI imaging solution for cancer diagnosis support to research and clinical practices. 

The organizations signed a know-how agreement to further develop and validate JelloX’s technology. The company offers a 3D pathology imaging solution that uses AI to provide spatial analysis of cancer tissue images. 

Denmark-based Teton, a company that offers an AI companion to help nurses monitor patients and optimize workflow, announced it created a real-time, live 3D reconstruction of a hospital room using Gefion, Denmark’s national supercomputer.

The aim is to help nurses recognize risks early, reduce paperwork and improve patient care.

Operated by the Danish Center for AI Innovation, Gefion is built on NVIDIA DGX systems. Teton uses NVIDIA DGX systems “to generate data for the digital twin.”

According to NVIDIA, DGX Station is a “high-performance NVIDIA Grace Blackwell desktop supercomputer powered by the NVIDIA Blackwell Ultra platform.” It enables AI developers, researchers, data scientists and students to prototype, fine-tune and inference large models on desktops. 

In addition, users can run the models locally or deploy them on NVIDIA DGX Cloud, any other accelerated cloud or another data center infrastructure.

The digital twin provides a real-time view of what is happening inside a care facility in 3D.

In a statement, the company explained that the Teton AI Gym is a simulation engine that makes true-to-life, 3D care environments of realistic patient and staff interactions utilizing synthetic data.

The company said that early pilots have shown that it can reduce night shift work by as much as 25%.

“Our system can understand what people are doing, how they are sleeping, their respiration rate, their lying position and their gait,”  Mikkel Wad Thorsen, cofounder and CEO of Teton, told MobiHealthNews.

“It can do all these things in real time and provide continuous metrics on patient health and the care they receive,” he said. “Operating in 3D is a game-changer for the TEO-2 model, and it has only been possible with access to the supercomputer. With all of these data points, we could significantly accelerate the iteration time and unlock a new scale for the next generation of our model, TEO-2.” 

THE LARGER TREND

Other companies involved in the 3D healthcare space include Restor3d, a 3D-printed orthopedic implant care company that raised $38 million in April. Summers Value Partners participated in the round, along with existing and new private investors.

Restor3d provides joint replacements and 3D printing of osseointegrative materials, AI-based planning and design automation tools. 

In 2024, Taiwan-based medtech company SURGLASSES announced it implemented its augmented reality-based surgical navigation system in Thailand. 

Thailand Veterans General Hospital and Chulalongkorn Hospital conducted their first AR-guided surgeries using the Caduceus S system.

Designed for spine surgery, the SURGLASSES system provides surgeons with 3D visualization to view the patient’s internal anatomical structures during procedures, including bones, tissues and organs. 

Another Taiwanese company, JelloX Biotech, collaborated with Mayo Clinic to bring its AI imaging solution for cancer diagnosis support to research and clinical practices. 

The organizations signed a know-how agreement to further develop and validate JelloX’s technology. The company offers a 3D pathology imaging solution that uses AI to provide spatial analysis of cancer tissue images.