AI out performs human doctors in predicting AMD progression

Published on

Posted by Erik van Dijk

Erik has previously worked for 10 years at Philips in various parts of the business and in different roles, most recently at Philips Healthcare in R&D management. Since his start at EasyScan in 2015 he headed the operations (supply chain/technical support) and R&D team. In 2017, Erik became the CEO. Erik has a PhD in Physics from the University of Twente.

AI out performs human doctors in predicting AMD progression

Researchers from Google Health, Deepmind and Moorfields Eye Hospital have recently presented results in Nature Medicine of a deep-learning algorithm trained to predict the progression of Age-related Macula Degeneration (AMD) in patients. AMD is a serious, progressive eye diseases which is the leading cause of blindness in the developed world. The researches showed that for patients that had already Wet-AMD (the most serious state of AMD) in one eye, their algorithm was more sensitive and specific in predicting the onset of Wet-AMD in the other eye than human experts.

This research is focusing on the treatment of the treatment of already seriously effected patients which have already significant visual impairment. There is no treatment to recover the lose of vision caused by AMD, all interventions are targeted to slowing down the progression. Early detection is therefore key. The EasyScan retinal scanner is an excellent tool to quickly screen patients or customers in optician store and detect the first signs of AMD even before there the vision is impacted. Read more about the use of the EasyScan as an AMD screening tool in this white paper. Early detection of at risk people allows prevention of vision lose by advising lifestyle changes and (optionally) the use of supplements.

Get our news directly in your mailbox:

Don’t miss our upcoming events: