left: Associate Professor Ponnudurai Kuperan, emeritus consultant at the department of haematology, Tan Tock Seng Hospital (TTSH); Mr David Chen, product manager, Asus; and Dr Eugene Fan, consultant at TTSH’s department of haematology. They were using the AI tool Blade on Wednesday for diagnosis of blood abnormalities. ST PHOTO: ONG WEE JIN
THE STRAITS TIMES (9 July 2022)
Developed by TTSH and Asus, AI-powered Blade software can halve the time for analysing blood
Diagnosing leukaemia as well as diseases such as malaria may soon be faster and more accurate, thanks to the use of artificial intelligence (AI).
An AI-powered software named Blade – developed by Tan Tock Seng Hospital (TTSH) and Taiwanese tech company Asus – can cut by half the time needed to analyse blood to detect these diseases, allowing for earlier clinical intervention for patients.
The current process requires a laboratory technologist to examine a patient’s blood, which is placed on a piece of film under a microscope, and perform a manual cell count.
Those blood films with abnormal features or an unclear diagnosis are sent to a reference lab or a haematologist for review.
This can leave the technologists fatigued, leading to a greater chance of error, said TTSH haematology department consultant Eugene Fan. He told reporters on Wednesday that the TTSH haematology lab – which operates 24 hours a day, seven days a week – handles up to 400 such blood films a day.
Blade allows for the procedure to be automated, enabling a technologist to load several blood films into a scanner that converts them into digital images.
The AI analyses the films and flags critical ones, such as possible cases of leukaemia.
Lab technologists need to only review the scans and correct misclassified cases, said Dr Fan, who is part of the team studying Blade.
The software was developed using a data set of 337,700 digital images of peripheral blood cells from the National Healthcare Group, which oversees TTSH.
Differential blood counts to check white blood cell levels – indicating the presence of infection and disease – are currently 91.4 per cent accurate, Asus and TTSH said in a media statement. Before the partnership with Asus, funding for the project came from sources such as Enterprise Singapore and a National Medical Research Council award.
Blade is now being evaluated at TTSH and other sites, with plans for it to gain regulatory approval in the next few years.
Hougang Polyclinic – which has its own lab where blood films are examined – is expected to get Blade this month.
Asus and TTSH are also looking at developing similar solutions in fields such as pathology and microbiology. On Thursday, the two formalised their collaboration by signing a three-year agreement.
Other projects in the works include those targeting breast and colon cancer detection.
“We believe that computer science can help a lot to improve healthcare quality,” said Asus chief technology officer and corporate vice-president Huang Tai-yi, noting that the company had deployed smart medical solutions at 20 hospitals in Taiwan.
Associate Professor Tan Cher Heng, assistant chairman of the medical board for clinical research and innovation at TTSH, said the adoption of technology such as AI will allow the hospital to reinvent its practice and improve care for the community.