Gangbuk Samsung Hospital, First Development of Algorithm

Kangbuk Samsung Hospital announced on the 15th that a research team consisting of Neurology professors Won-Tae Yoon and Su-Jeong Song from the Department of Ophthalmology, along with Ji-Tae Shin from the Department of Electronic and Electrical Engineering at Sungkyunkwan University, has developed an algorithm for the first time that measures brain nervous system dysfunction in patients with Parkinson's-related diseases through fundus photography.


Predicting Brain Neurofunctional Status of Parkinson's Patients Through Eye Analysis View original image

The research team analyzed ▲ brain function-related imaging ▲ brain nervous system motor function evaluation results ▲ fundus photographs of patients with Parkinson's-related diseases who visited the Neurology Department at Kangbuk Samsung Hospital between October 2020 and April 2021. Based on this information, they analyzed correlations with basic patient information such as age and gender to develop an artificial intelligence algorithm that predicts the motor function status of Parkinson's-related symptoms in the brain nervous system from fundus images.


When basic information such as fundus photographs, age, and gender are input into the algorithm, it can automatically predict the patient's Parkinson's-related brain nervous system motor function scales, including the H-Y scale and UPDRS score. Kangbuk Samsung Hospital explained that despite using a small amount of patient data, the algorithm demonstrated high accuracy close to 0.8 in predicting both neurological motor function indicators.


The retina of the eye has the advantage of allowing non-invasive direct observation of the body's blood vessels, leading to ongoing attempts to assess systemic vascular conditions through simple retinal examinations. Although many studies have used fundus photography to predict cardiovascular disease risks, research on brain diseases and the retina has been scarce and the results limited.



Professor Su-Jeong Song of the Department of Ophthalmology at Kangbuk Samsung Hospital stated, "The significance of this study lies in enabling various research on the relationship between Parkinson's-related diseases, a representative neurodegenerative disorder, and the eye through artificial intelligence methodologies," adding, "Fundus examinations can directly and indirectly confirm neurological brain nervous system functions, which is clinically important."


This content was produced with the assistance of AI translation services.

© The Asia Business Daily(www.asiae.co.kr). All rights reserved.

Today’s Briefing