Newsie – NZ AI can predict diseases of the retina and eyes


The New Zealand-designed artificial intelligence framework, MedicMind, which enables the development and design of unencoded AI, was used to develop an advanced set of algorithms to detect a variety of common eye diseases.

The results are published in Clinical and Experimental Ophthalmology.

The Dunedin-based research was part of an initiative to combat aging populations and degenerative eye diseases, said oDocs Eye Care Director Dr. Hong Sheng Chiong.

A total of 4435 images were used to develop artificial intelligence and its underlying algorithm. The mean accuracy was 80%, with sensitivity of 75% and specificity of 89%. AI is able to detect common eye diseases such as diabetic retinopathy, age-related macular degeneration, glaucoma and retinal vessel disease.

Age-related degenerative diseases such as macular degeneration, glaucoma and diabetic retinopathy are increasing, causing large delays and delays to clinical appointments and clinical workload, Dr. Hong says.

"With an AI capable of screening and making initial predictive diagnoses, it would help clinicians with limited knowledge and experience in ophthalmology – eye care – to filter retinal photographs efficiently"

"This is a pilot study and its performance can be improved with a much larger data set. We are asking all New Zealand clinical and artificial intelligence scientists to join the movement to explore this field. "

The research and algorithm are not designed to replace more conventional approaches, such as a visit to an optometrist or ophthalmologist. It is just one way to improve the efficiency and safety of patient eye care. The scientific article is available here.

Dr. Hong is an ophthalmologist at Dunedin Hospital and is the CEO of oDocs Eye Care. He says he's on a mission to end avoidable blindness globally.

Earlier this year, ODocs Eye Care signed its first international partnership abroad with King Saud University, Riyadh, which is the largest medical university in the Arab world.


Source link