Researchers at the Singapore Eye Research Institute have developed two new AI-powered tools for screening for chronic kidney disease and predicting a person’s biological age from retinal photos.
Both tools use AI deep learning algorithms to scan a person’s retina to assess their health status.
What do they do?
The RetiKid Kidney Disease Screening Tool was developed in 2019 by SERI and the National University of Singapore’s School of Computing. The tool was trained with more than 23,000 retinal images of about 12,000 participants from Singapore and China.
In one study, an internal test showed 91% accuracy and two external test sets showed 73% and 83% accuracy. The screening tool is licensed to health technology startup EyRIS for production and commercialization.
According to Charumathi Sabanyagam, deputy head of the Ocular Epidemiology Research Group at SERI, both the retina and the kidneys have a “close biological relationship.” “Thus, problems with the blood vessels in the retina can lead to changes in the blood vessels in the kidneys.”
Reticid can be used as a preliminary screening test to detect CKD in the general population and in high-risk groups, such as diabetic patients. Once done, patients may be advised to proceed with regular confirmatory blood and urine tests.
Other AI tools, RetiAge, later SERI and Medi Whale, were created in 2021 by a healthcare startup in South Korea. It was tested on more than 129,000 retinal images from more than 40,000 South Koreans. The tool was also evaluated for its ability to predict disease and death risk over 10 years in 56,000 individuals in the UK Biobank database.
Cheng Ching-Yu, head of SERI’s Ocular Epidemiology Research Group and Data Science Research Platform, says a person’s retinal blood vessels can also show their aging process and the overall health of their blood and brain. “The retina is a non-invasive window into a person’s biological age and systemic health status, and it can tell us a lot about a person’s risk of illness and death.”
A person’s biological age can better capture the physiological changes associated with aging than his or her chronological age. Therefore, it can be used to assess their general health status. Cheng further claims that biological age is of greater interest to researchers, especially considering the global aging population and the growing incidence of chronic diseases.
Why it matters
Both RetiKid and RetiAge offer a non-invasive approach to screening health conditions in clinics. Patients may find these more tolerable, perhaps leading to greater acceptance and compliance with early health screening.
Both tools can be integrated with the Singapore Eye Lesson Analyzer Plus, a retinal image-based system developed by SERI, which is currently being used by polyclinics across Singapore to screen for diabetic eye disease, glaucoma and age-related macular degeneration.
For RetiKid, the screening process is automated, which allows for effective mass screening of at-risk patients. “There are tools like Reticid [the] CKD is likely to be widely used in primary care to improve the current rate of screening, ”said Dr. Cynthia Lim, a lead investigator in the Reticid project.
In addition, RetiKid has the potential to connect to smartphones, enabling point-of-care diagnosis. “Early detection of CKD allows physicians and patients to intervene and slow down quickly. [its] Progress, “said Dr. Lim.
At its current validation stage, RetiKid will be used by SERI in a community outreach program in partnership with the National Kidney Foundation. About 1,200 participants in the program, which runs from February 2022 to January 2024, are at high risk of developing CKD.
Meanwhile, researchers are currently working to refine algorithms in RetiAge to optimize its predictive effectiveness among local people. They are also looking at whether it can be used to predict other age-related diseases.
The Singapore National Eye Center claims that Singapore’s population is “uniquely at risk” for eye diseases and disorders at every stage of life. Myopia affects one in two children under the age of 12. In working adults, diabetic retinopathy is a major cause of vision loss. In addition, the risk of blindness for Singaporeans aged 50 and over is 15 times higher.
One of the recent innovations in eye health in Singapore The AI-based glaucoma screening procedure was developed by a team of scientists and physicians from Nanyang Technological University and Tan Tok Seng Hospital.
To help expand access to eye care in the country, Johnson & Johnson has created a three-year roadmap for developing an integrated eye health ecosystem, focusing on vision data and digitization initiatives. Some of the key projects it plans to implement include a community eye health e-referral network, an AI-powered eye care service and telehealth.