SERI researchers develop AI tools for kidney disease screening, age prediction using eye images

Researchers at the Singapore Eye Research Institute have developed two new AI-powered tools for screening chronic kidney disease and predicting a person’s biological age based on retinal images.

Both tools use AI deep learning algorithms to scan pictures of a person’s retina to assess their health status.

WHAT THEY DO

The kidney disease screening tool called RetiKid was developed in 2019 by SERI and the National University of Singapore’s School of Computing. The tool has been trained with more than 23,000 retinal images from nearly 12,000 participants in Singapore and China.

In a study, it was found to have an accuracy of 91% in an internal test and 73% and 83% accuracy in two external test sets. The screening tool has been licensed to health tech startup EyRIS for production and commercialization.

Both the retina and kidneys share a “close biological relationship,” according to Charumathi Sabanayagam, deputy head of SERI’s Ocular Epidemiology Research Group. “Problems with blood vessels in the retina can therefore indicate changes in renal blood vessels.”

RetiKid can be used as a preliminary screening test for detecting CKD in general populations and high-risk groups, such as those with diabetes. Once done, patients may be advised to continue with routine confirmatory blood and urine tests.

The other AI tool, RetiAge, was developed later in 2021 by SERI and Medi Whale, a healthcare startup in South Korea. It was tested in more than 129,000 images of the retina of more than 40,000 South Korean individuals. The tool was also evaluated for its ability to predict the 10-year risk of illness and death in 56,000 individuals in the UK Biobank database.

The blood vessels in a person’s retina can also show their aging process and the overall health of their blood and brains, said Cheng Ching-Yu, head of SERI’s Ocular Epidemiology Research Group and Data Science Research Platform. “The retina is a non-invasive window into a person’s biological age and systemic health status, and can tell us many things about a person’s morbidity and mortality risks”.

A person’s biological age, compared to their chronological age, can better capture the physiological changes associated with aging. Therefore, it can be used to assess their general health status. Cheng also argues that biological age is of greater interest to researchers, especially given the global aging of the population and the increasing incidence of chronic diseases.

WHY IT MATTER

Both RetiKid and RetiAge offer a non-invasive approach to health screening in clinics. Patients may find them more tolerable, potentially leading to greater acceptance and adherence to preliminary health screening.

Both tools also integrate with the Singapore Eye Lesion Analyzer Plus, a retina-based system developed by SERI and currently used by outpatient clinics across Singapore to screen for diabetic eye disease, glaucoma and age-related macular degeneration.

For RetiKid, the screening process is automated, enabling effective mass screening of at-risk patients. “Tools like RetiKid have [the] potential to be widely used in primary care to improve the current rate of CKD screening,” said Dr Cynthia Lim, a principal investigator of the RetiKid project.

In addition, RetiKid has the potential to be connected to smartphones, enabling diagnosis at the point of care. “Timely detection of CKD empowers clinicians and patients to intervene early and delay” [its] progression,” said Dr. Lim.

Currently in the validation phase, RetiKid will be used in a community program by SERI in conjunction with the National Kidney Foundation. The program, which will run from February 2022 to January 2024, will involve approximately 1,200 participants at high risk of developing CKD.

Meanwhile, researchers are currently working to refine the algorithms in RetiAge to optimize prediction performance in the local population. They are also looking at whether it could also be used to predict other age-related illnesses.

THE BIGGER TREND

The Singapore National Eye Center claims the Singaporean population is “uniquely vulnerable” to eye diseases and conditions at every stage of life. Nearsightedness or nearsightedness affects one in two children by age 12. Among working adults, diabetic retinopathy is a leading cause of vision loss. In addition, the risk of blindness increases 15-fold for Singaporeans aged 50 and older.

One of the recent eye health innovations in Singapore is a AI-based screening method for glaucoma developed by a team of scientists and clinicians from Nanyang Technological University and Tan Tock Seng Hospital.

To help broaden access to eye care in the country, Johnson & Johnson Vision has developed a three-year roadmap to develop an integrated eye health ecosystem, with a focus on data and digitization initiatives. Some key projects it plans to implement include an e-referral network for the eye health community, an AI-powered eye care service, and telehealth.