Follow Us











Startup Sectors

Women in tech







Art & Culture

Travel & Leisure

Curtain Raiser

Wine and Food


This is a user generated content for MyStory, a YourStory initiative to enable its community to contribute and have their voices heard. The views and writings here reflect that of the author and not of YourStory.

How Artificial Intelligence Has Transformed Eyecare

How Artificial Intelligence Has Transformed Eyecare

Thursday June 27, 2019,

4 min Read


Artificial intelligence is not a new term, it is an old concept now that has been revolving around since a very long time. But it was not this common as it is today. Over a decade this idea has grown immensely in every filed. It promises to give an amazing boost to technology today as well as in the future in every industry. So, does its application can be seen in health care, including eye care-optometry and ophthalmology.

What is Artificial intelligence

Artificial intelligence is the science that uses complex sets of computers algorithms, codes, and programs to act like the human nervous system to learn, identify, analyze and interpret data like images, audios, videos, text, speech and anything to everything.

Technologists and computer scientists have done many experiments and gave us many results on AI, but there is yet much more to explore. Now the question is, is AI helpful for eye care? If, yes then how it can transform eye care.

Use of AI in Eye Care

As per studies and experiments, AI will play a vital role in eye care and diagnosis and treatment of ophthalmic disease. Besides this big picture, a very small benefit is to online eye care business. For instance, today you can easily buy glasses online by just a click and even try them on the website to get the look and feel of it before you purchase.

  • Identify Diabetic Retinopathy

Getting back to the role of AI in the screening and treatment of eye diseases. Researchers tried AI to diagnose diabetic retinopathy and found that it was not only the same as expert performance but in fact exceeded in identifying the disease and criticality of condition. Not even this, it recognized the features from images that hinted of the disease, though it was not programmed to do so. AI amazingly learned and figured it out on its own by simply looking thousands of diseased and healthy eyes.

Well, this description falls in the category of supervised deep learning where the machine was provided with a predefined set of data that is studies and interpreted step by step, layer by layer to give precise results. In unsupervised learning, the ladled data is combined with data from experiments, experiences, memory, and observations and then the machine is put live to give improved results. Well, there are other levels of deep learning that are used in experimentation.

  • Glaucoma Detection and VF Loss

Another test that was conducted was to detect glaucoma with a visual field analysis. AI was used to analyze glaucoma detection and growth using visual field (VF) patterns to identify VF loss at an early stage with more precision and accuracy. The anatomical changes that can be detected through photographs occur too late in the disease process, if this can be detected early, it will be useful to prevent vision loss in glaucoma. Though several metrics are used to analyse the growth of VF loss in glaucoma, AI-based system was also launched recently to identify patterns of VF changes to improve accuracy and reduce the time to identify. The algorithm spotted patterns of VF loss from the early and late glaucoma cohorts in a known VF database.

This machine learning–based pattern was significantly faster in identifying 25%-50% of the eyes showing VF loss than other methods and protocols. It turned out to be more effective and accurate.


Machine learning and AI is a strong approach to detect and treat diseases. Use of AI and machine learning can show quality results in terms of eye care or health care without much potential for criticism in terms of replacing comprehensive care with shortcuts, which may threaten overall quality.

But the biggest challenge is to convince people that the computers’ diagnostic conclusions are reliable. We have examples like Google Home, Siri, Amazon’s Alexa and many more. But when it comes to dealing with health, diseases, and treatment it does require more proven-results. Till now there is no conclusion that whether these machines can be used as a supplement or complete replacement of traditional clinical care.