The National University Health System has developed a new AI tool that can detect cases of hypercalcemia in real-time.
WHAT IT DOES
Dubbed CalSense, the AI screens blood calcium level reports across the organisation to flag hypercalcemia cases, which are then shown in real time via a live dashboard.
It also checks on other investigative test results to identify underlying causes of patients’ hypercalcemia “more accurately.”
The AI is hosted within the NUHS Endeavour AI platform, which also displays other medical information of patients across the organisation.
WHY IT MATTERS
Hypercalcemia is a result of overactive parathyroid glands that control the body’s blood calcium level, according to NUHS. The condition can be caused by cancer, certain medical disorders, some medications, and excessive consumption of calcium and vitamin D supplements.
“CalSense allows us to automate a process that previously had to rely on doctors to run through blood test results when patients return for a clinical review,” NUHS CTO Associate Professor Ngiam Kee Yuan said.
“It flags out cases that require prompt interventions across our network of hospitals, national specialty centres, and polyclinics in real-time, reducing the administrative work of doctors and expediting medical care.”
CalSense can also potentially shorten the period of diagnosis and treatment of hypercalcemia, which takes four years on average, according to A/Prof Ngiam, citing global studies.
“If patients do not receive timely treatments, they may suffer complications from hypercalcemia, which may include osteoporosis and fractures, kidney stones, kidney failure, mental disorders and even potentially sudden cardiac death,” NUHS Assistant CTO Dr James Lee added.
NUHS said CalSense is able to flag 1,600 cases of abnormal blood calcium levels in 26,000 tests in a trial conducted from January to July this year.
THE LARGER TREND
NUHS is also trying out another AI project on Endeavour AI. Called Pathfinder, the AI provides real-time visibility of bed occupancy rates, wait times, and predictive insights into daily attendance at the National University Hospital ED.
Another AI in the NUHS pipeline will support scoliosis x-ray assessment by automatically measuring the degree of scoliosis.
