Minerva Studio - stock.adobe.com

NUHS taps LLM to boost productivity, patient care

Healthcare professionals at Singapore’s National University Health System can now summarise patient case notes and predict patient healthcare journeys using a large language model trained by a supercomputer

Singapore’s National University Health System (NUHS) is tapping a large language model (LLM) to help its doctors summarise patient case notes, write referral letters and predict patient healthcare journeys by analysing historical data.

Dubbed NUHS Russell-GPT, the LLM will allow NUHS staff to ask questions, such as those related to medical conditions and clinical practice guidelines, to aid them in their work. Plans are under way to progressively roll out the model throughout the healthcare cluster.

Research is also under way to use the model to predict the severity and trajectory of common conditions, such as urinary tract infections. The model was trained with NUHS’s onsite Prescience supercomputer that was deployed by the National Supercomputing Centre (NSCC) in December 2021.

Associate professor Ngiam Kee Yuan, group chief technology officer of NUHS, said the LLM that was trained with Prescience will benefit both healthcare workers and patients by synthesising local medical knowledge and reducing the administrative work of doctors and nurses.

Bernard Tan, director of strategy for planning and engagement at NSCC, added that the launch of the NUHS supercomputer was timely because of the heightened interest in generative artificial intelligence (AI).

“The Prescience supercomputer will significantly benefit Singapore’s healthcare research community and enable local healthcare professionals to develop tools that can increase the efficiency of healthcare delivery and accelerate healthcare innovations which ultimately benefit patients here,” he said.

Prescience is also being used to train two machine learning models – one using 3D dental scans, and the other using X-rays of the upper and lower jaw, in what is known as dental panoramic tomogram.

The 3D teeth charting model generates digital representations of the condition of teeth and their positions in the mouth, replacing manual tooth charting by dentists and facilitating enhanced visualisation. Instead of waiting for up to a day to get a dental cast done, it will take no more than five minutes for dentists to scan a patient’s teeth and collect information to initiate treatments.

Peter Yu, senior consultant from the department of prosthodontics at the National University Centre for Oral Health, Singapore (NUCOHS), said: “Dental treatments involve three-dimensional appreciation of facial structures, anatomy, reconstruction and a vision of what a patient’s teeth could be after treatments. This supercomputer, with its significant graphic capabilities, is particularly suited for this structural approach.”

To date, 400 3D dental scans of anonymised patients, from children to adults, have been collected to train the AI model. Another 200 dental panoramic tomograms of anonymised patients, the majority with gum problems, have also been collected.

Wilson Lu, consultant from the department of orthodontics at NUCOHS, said the AI tools can help dentists make objective clinical judgements on patients’ teeth and gum conditions, adding that the gum disease prediction model has the potential to be implemented on a population level so that a patient’s risk of developing gum disease can be classified into low, medium or high, and interventions recommended before the onset of disease.

Read more about AI in APAC

Read more on Artificial intelligence, automation and robotics

Data Center
Data Management