The Singapore healthcare service, SingHealth, and the Singapore’s National Supercomputing Centre (NCSS) announced the acquisition of an Nvidia supercomputer during this week’s SupercomputingAsia (SCA22) conference.
“The collaborations work hand-in-hand to build a complete innovation environment that combines supercomputing infrastructure capabilities, the operating software and AI tools to power advanced research, and healthcare use cases for applying these capabilities and tools,” NCSS said in its announcement. “Beyond healthcare, these tools will also support a variety of research in other fields like climate science and data center operations.”
SingHealth and NSCC will deploy the system at SingHealth’s Singapore General Hospital (SGH) campus to support medical research and innovation efforts for the cluster and healthcare researchers from across Singapore. Nvidia will provide access to its software tools and pre-trained AI models. Partners also will be able to leverage NSCC’s Supercomputing Digital Sandbox environment, which makes it easier for researchers without HPC training to use NSCC’s supercomputer.
SingHealth will use the supercomputing infrastructure for its medical research .
“Supercomputing power is a very critical national resource that is crucial in enabling many research projects that impact the economy and society, now and for the future,” said Peter Ho, chairman of the NSCC Steering Committee. “NSCC is excited to work with partners like SingHealth and Nvidia to benefit local researchers in an important field like healthcare. We also hope that this will spur the many local and international organizations attending SCA22 to do likewise and find mutually beneficial partnerships that will help advance Singapore’s HPC community, and its related research fields.”
The partnership will support SingHealth’s AI for Transformation of Medicine Programme (AIMx), which aims to develop AI algorithms for the smart triaging of patients with cardiovascular disease. Using big data comprising clinical data, chest x-rays and retinal images of patients with symptoms of cardiovascular disease, the AI algorithms are designed to predict a patient’s risk of adverse cardiac events and perform a suitable triage. The tool could help clinicians prioritize patients with serious cardiac issues for urgent medical attention in emergency settings or identify patients with a higher risk of coronary artery disease in outpatient settings.
The benefits of the research include greater efficiency and improved accuracy in the identification of high-risk patients, facilitating timely and life-saving clinical intervention, as well as optimising the use of precious healthcare resources.
Nvidia will provide access to its software development kits and open-source pre-trained AI models. The company will also working with NSCC to provide access to its software tools and training to support HPC-enabled AI research.
