Hospitals around the world produce an average of 50 petabytes of data per year or a staggering 50 million GB of storage space. Research into modern medical technologies and applications that rely on tools such as Artificial Intelligence (AI), machine learning and automation, helps to make sense of the massive amounts of data to improve patient outcomes. The development of such tools can be exponentially enhanced using supercomputers as it allows medical researchers to build more complex AI models that can accommodate large amounts of data.
However, to run AI and machine learning at scale, requires massive amounts of computing power to train the models. Recently, NSCC (National Supercomputing Centre Singapore) and NUHS (National University Health System) inked a collaborative agreement, to build the national infrastructure for supercomputing to support AI programmes at public healthcare institutions by the middle of next year.
NUHS sees a large number of patients per day and generates large amounts of data that can be used to train AI models that improve the quality of care. Normally, these could take days to process but the new supercomputer could help to cut our training times down to hours allowing our medical and para-medical staff to optimise patient trajectories and to improve the quality of patient care.
– Professor Ngiam Kee Yuan, Group Chief Technology Officer, NUHS
Singapore is building its national supercomputer to advance research in COVID-19 and other areas in healthcare. The new supercomputer is so fast it is expected to train AI to predict a patient’s future disease condition – such as Covid-19 and kidney disease – within hours, instead of days as with standard computers. The past data of patients with specific diseases can be fed into the supercomputer to train the AI.
The training can be done more quickly because the supercomputer can carry out petascale computing. This means it can perform more than a quadrillion – or over a thousand trillion – calculations in a second. Other coronavirus research that can benefit from the supercomputer includes figuring out drug combinations for treating COVID-19 infections as well as discovering new drugs.
The five-year Research, Innovation and Enterprise 2020 (RIE2020) plan had allocated funds for research and development (R&D) in three high impact areas, including healthcare. Collaborating to provide the infrastructure and operational components respectively, the new system by NSCC and NUHS will benefit clinical researchers who will be able to train and run complex computations of healthcare models.
NUHS is entering into an agreement with Singtel to deploy a 5G indoor network with Multi-Access Edge Compute capabilities at NUH operating theatres and wards. This is a first for a public hospital. For NUHS, 5G is a key enabler of new services and technologies, such as mixed reality applications, robotics and the internet of things.
The high-speed connectivity of 5G would address current limitations in latencies and bandwidth, and open up possibilities for better healthcare experiences, such as smoother teleconsultations, augmented surgical navigation using mixed reality devices, and robot AI capabilities using cloud and edge computing.
As reported by OpenGov Asia, the National University Health System (NUHS) has embarked on a research and development programme within the academic healthcare cluster to explore the use of MR technology in clinical care.
The research programme aims to support the development of next-generation clinical applications and improve patient safety. This would augment clinical processes and enhance both undergraduate and postgraduate education. While the use of holographic technology in operating theatres is still nascent, NUHS hopes to apply it in multiple fields of surgery.
While holo-medicine is new in the field of medicine, it has become increasingly prominent in the past year. The technology leverages the concept of MR not only to augment the physical environment but permit interaction with virtual objects superimposed onto the real world. The virtual objects can also be manipulated relative to the real world using natural hand gestures.