Monitor this situation.
Unsubscribe anytime.
[SITUATION] · [QUIET] · [HEALTH]
2 clusters · 8 sources · 5 days · First seen · Last updated
Seoul National University cognitive health research
Overview
Researchers at Seoul National University have developed new methods to identify cognitive decline and dementia risk through non-invasive assessments.
One study focused on road safety by identifying a ‘silent risk group’ of elderly drivers. By analyzing cognitive performance on a ‘symbol connection test’ alongside education levels, researchers found they could identify high-risk drivers who may not realize their own declining abilities. The study noted these metrics are intended for precise ability assessments rather than restricting driving rights.
In a separate development, a research team at Seoul National University Hospital created an artificial intelligence model that uses retinal fundus photographs to screen for current dementia and predict future risk. Utilizing ‘explainable AI’ technology, the model uses heatmaps to visualize retinal areas influencing its decisions, offering a potential low-cost, non-invasive tool for early intervention during routine health checkups.
Entities
Seoul National University Hospital · Ximed · Han Ji-won · npj Digital Medicine · Kim Ki-woong
Timeline
-
15 days ago
[HEALTH] 4 sourcesSeoul National University Hospital develops AI to predict dementia via retinal photosResearchers at Seoul National University Hospital developed an AI model that predicts dementia risk using retinal photographs, offering a low-cost tool for early screening and clinical intervention.
-
19 days ago
[HEALTH] 5 sourcesSeoul National University researchers identify high-risk elderly driversResearchers have identified a way to detect high-risk elderly drivers through cognitive tests, specifically targeting a 'silent risk group' who report no prior accidents but show declining cognitive processing.
Sources
autotribune.co.kr · bosa.co.kr · healthmedia.co.kr · hin.company · joongboo.com · kormedi.com · sportschosun.com · zdnet.co.kr