The advantages of ophthalmic Artificial Intelligence systems
New Orleans, La. — Two recent studies presented this week at the Association for Research in Vision and Ophthalmology’s (ARVO) 2023 Annual Meeting in New Orleans; La. exhibited the benefits of involving artificial intelligence (AI) in research and global health. There are advantages of having an AI robot support ophthalmologists and patients. Not to mention the potential of using retinal images to predict whether a patient could have cardiovascular issues within the near future.
The birth of an AI ophthalmologist and eye specialist
Glaucoma is a group of eye disorders that harm the optic nerve. It is crucial for people to get dilated eye exams because if it is not caught early, glaucoma can lead to permanent vision loss or blindness. Lead researcher Siamak Yousefi, PhD, and his team from the University of Tennessee Health Science Center in Memphis, Tenn. wanted to assist in the battle against glaucoma by building an artificial intelligence (AI) robot named Alborz that will have the capability to evaluate glaucoma details and eventually operate as a digital ophthalmologist and glaucoma expert.
Yousefi and his team programmed Alborz to recognize glaucoma from visual fields (VFs) and retinal images taken by fundus cameras. It was also configured to produce glaucoma information utilizing natural language generation (NLG), computer software being able to generate output in human language, and natural language processing (NLP), the capability of a computer software comprehending written and spoken human language.
Their results showed that Alborz was able to identify glaucoma from VFs, fundus photos, and VF/fundus data. It was able to engage with the team and respond to questions. Alborz continues to undergo further training. Yousefi commented, “We have developed and integrated artificial intelligence (AI) models into Alborz, a humanoid robot, to both assess glaucoma and interact with ophthalmologists as well as patients. Alborz may also be used for educational and research purposes for dissemination of AI applications in ophthalmology.”
- Abstract title: Introducing Alborz: an artificial intelligence (AI)-enabled humanoid robot with natural language processing and generation skills for assessing glaucoma
- Presentation start/end time: Sunday, April 23, 8:00 – 9:45am CT
- Location: Exhibit Hall
- Presentation number: C0239
Cardiovascular Disease prediction by retinal imaging
The layer of tissue that lines the back of the eye and is light-sensitive is known as the retina. The retina is an extremely essential part of vision. In the last few years, it has come to light that the retina can play more crucial roles outside the realm of vision. Thanks to the aid of artificial intelligence, the retina can provide information into an array of health disorders, especially cardiovascular diseases (CVDs), the leading cause of death worldwide.
Mark Chia, MBBS (Hons), MMed, and a team of scientists at University College London (UCL) Institute of Ophthalmology in London, United Kingdom studied whether it would be possible to predict cardiovascular events like heart attacks and strokes by creating a deep learning model using retinal optical coherence tomography (OCT). They were able to collect and analyze data from a large study that connected retinal images of patients seen at Moorfields Eye Hospital with systemic disease data from hospital admissions across England (the AlzEye project). They developed a model to predict major adverse cardiovascular events (MACE), including atrial fibrillation, heart failure, ischemic stroke, and myocardial infarction. The model performed reasonably well at predicting MACE within three years suggesting that expanding this work to other populations may have potential.
“The potential for using retinal scans to predict some of the biggest causes of death is exciting because eye scans are safe, affordable, and widely available.” said Chia, “We might one day reach a point where a patient can be identified as ‘high-risk’ during a routine glasses check, which could lead them to having the necessary treatments to prevent a heart attack or stroke.”
- Abstract title: Optical coherence tomography for the prediction of major adverse cardiovascular events in AlzEye
- Presentation start/end time: Sunday, April 23, 1:30 – 1:45pm CT
- Location: 356-357
- Presentation number: 547
The Association for Research in Vision and Ophthalmology (ARVO) is the largest eye and vision research organization in the world. Members include approximately 10,000 eye and vision researchers from over 75 countries. ARVO advances research worldwide into understanding the visual system and preventing, treating and curing its disorders. Learn more at ARVO.org.