Jakub Jirsák - stock.adobe.com

SingHealth researchers to get new supercomputer

Healthcare researchers at SingHealth can look forward to a new supercomputer to support their work

Healthcare researchers at SingHealth can look forward to a new supercomputer to support their medical research in areas such as personalised cancer therapies and triaging heart disease patients.

Built by SingHealth and the National Supercomputing Centre (NSCC), the supercomputer, to be located on the Singapore General Hospital campus, will also support research in other fields such as climate science and datacentre operations.

Through its digital sandbox environment, NSCC said researchers who are not trained in high-performance computing can also tap the new supercomputing resources. Software tools and pre-trained artificial intelligence (AI) models will be supplied by Nvidia.

“The adoption of emerging technologies is a game-changer in helping us enhance care delivery and optimise healthcare resources with the goal to improve clinical outcomes and the experience for patients,” said Kenneth Kwek, deputy group CEO for innovation and informatics at SingHealth.

“Through this exciting collaboration with NSCC and Nvidia, supercomputers and software specialised for AI and deep learning will be made readily available and accessible to our colleagues, to aid them in doing breakthrough research and developing new innovations that will transform and shape the future of healthcare.”

One of the healthcare projects the supercomputer is expected to support is SingHealth’s AI for Transformation of Medicine Programme, which aims to develop AI algorithms for the smart triaging of patients with heart 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.

Read more about high performance computing in APAC

This could help clinicians to prioritise 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 identifying high-risk patients, facilitating timely and life-saving clinical intervention, and optimising the use of healthcare resources.

Besides SingHealth, the National University Health System (NUHS) is also building a supercomputer to reduce the time it takes to train AI models from days to hours. It will reside at NUHS’s premises to address data privacy and security requirements.

When ready by the middle of this year, the petabyte-scale supercomputer can be used to predict patient health trajectories and train conversational chatbots that can converse with people in a more natural way, among other uses.

Read more on Clustering for high availability and HPC

Data Center
Data Management