Friday, April 26, 2024
HomeHealthcareHospital and illnessAn AI method for identifying high myopia in kids

An AI method for identifying high myopia in kids

-

Singapore  (Commonwealth Union)_Singapore Researchers have invented a new artificial intelligence (AI) tool that can assist in the evaluation of youngsters at risk of acquiring high myopia, a condition that can result in potentially vision-threatening eye illnesses in later stages of life. The AI technology, which was created by the Singapore National Eye Centre (SNEC) and Singapore Eye Research Institute (SERI), employs deep learning algorithms to detect high-risk youngsters and can aid physicians in the early treatment and control of myopia.

Image Credit:

According to the SNEC, myopia advances fast in children between the ages of five and fifteen, before stabilizing in the early twenties. This indicates that the earlier a kid develops myopia, the greater the probability of getting extreme myopia as a teenager or adult. High myopia is described as serious short-sightedness of greater than 500 degrees. As the eye disease is irreversible, the researchers of the AI tool expect that early identification and treatment would minimize the prevalence of severe myopia among Singaporeans and the danger of its consequences.


Image Credit:

According to Associate Professor Marcus Ang, the primary investigator of the technology, “We are so concerned about preventing high myopia in childhood because it is irreversible”. He added, “Once a child or a teenager develops high myopia, the sight-threatening complications only occur later on in life”. High myopia dramatically raises the risk of vision-threatening conditions such as glaucoma, cataracts, myopic maculopathy, and retinal detachment in adulthood. The AI tool was created in response to an alarming national trend that has gained the attention of physicians. Singapore has one of the world’s highest rates of myopia.

According to the SNEC, the prevalence of the eye ailment and the steady rise in patient numbers have fueled fears that visual impairment due to extreme myopia may become a serious public health concern in the future. In 2021, the Ministry of Health (MOH) data revealed that over 65 percent of Singaporean youngsters become myopic by the end of Primary 6, and more than eighty percent of young adults suffer from myopia. The number of visitors to the Myopia Center at the SNEC has also increased over the past several years. In 2018, it had over 6,000 patient visits, more than three times that of 2019. Approximately 30% of its patients suffer from myopia.

The new AI tool is anticipated to help reduce these figures by targeting young Singaporeans, especially those in the age group where myopia growth is fast. Current assessments of near-sightedness by doctors are subjective and might be confused by a patient’s memory. According to Assoc Prof Ang, who is also a consultant at the SNEC Myopia Centre, “When did the child start wearing glasses? That can be limited by recall bias. Do your parents have myopia? Sometimes children, or even parents themselves, don’t even know their own prescriptions”. He added, “The AI tool is completely objective, and does not need subjective input from patients.”

The tool will also expedite the operation due to its reliance on a single baseline evaluation, as opposed to the current approach in which youngsters are evaluated by eye specialists in many sessions prior to diagnosis and treatment. It employs deep learning algorithms to analyze retinal scans and clinical data of children between the ages of six and twelve, and calculates the chance of them acquiring high myopia later during their adolescents. According to the SNEC, this first-of-its-kind breakthrough technology can detect with 90% accuracy. Currently, researchers are conducting a prospective study and evaluating the applicability of the AI algorithm in the real world.

spot_img

LEAVE A REPLY

Please enter your comment!
Please enter your name here

LATEST POSTS

Follow us

51,000FansLike
50FollowersFollow
428SubscribersSubscribe
spot_img