Home » News » Studio18 » Screening for Diabetes related vision loss? Artificial Intelligence to the rescue

Screening for Diabetes related vision loss? Artificial Intelligence to the rescue

By: Studio18 Desk


Last Updated: September 20, 2022, 13:35 IST

Mumbai, India

Screening for Diabetes related vision loss? Artificial Intelligence to the rescue

Diabetes has become the fifth leading cause of blindness across the globe. Diabetic retinopathy is one of the major reasons for visual impairment and blindness among the people with diabetes, globally.

Did you know that India has the dubious honour of being the Diabetes Capital of the World?1. The estimates show that India’s diabetes burden is increasing, and it is doing so at a rapid clip. The International Diabetes Federation Atlas 2019 estimated that there are roughly 77 million cases of diabetes in the adult population of India as of 2019. It also predicts that this number will climb to 101 million in 2030 and to 134 million in 20452.

The disease burden of diabetes doesn’t come from diabetes alone, but the various complications that go hand in hand with it. Diabetes has become the fifth leading cause of blindness across the globe. Diabetic retinopathy is one of the major reasons for visual impairment and blindness among the people with diabetes, globally1. Diabetic Retinopathy is an eye related complication of diabetes which affects the retina, and while it is asymptomatic in the early stages, it can progress to permanent vision loss when left untreated.

The good news is that vision loss from DR is wholly preventable, provided it is caught early enough, and provided one follows the doctor’s advice to the last letter3. The first step though, is getting a diagnosis. DR can be diagnosed through a DR screening and eye test administered by an ophthalmologist4.

In India, however, getting a diagnosis can be a challenge in itself. There are several reasons why getting a diagnosis for DR becomes difficult5:
Location: If you’re in a small town or rural area, chances are, eye specialists are few and far between. Getting an appointment can involve significant wait time because of the doctor’s case load5.

Time: People with DR in the working age group may face certain issues. If you have flexible timings, or if your work allows you to take doctors appointments in the middle of the workday, great! If not, you’re probably putting it off… because honestly, who has the time to spend half a day in a doctor’s waiting room? Especially if you can’t afford the time off and the loss of pay that comes with it5.

Even if you have flexible hours, live in a metropolitan area, and can afford quality medical care, the ratio of trained ophthalmologists to people with diabetes is staggering. Especially considering that you need to test for DR annually, as it is a progressive disease, and one which carries greater risk the longer you’ve had diabetes6.

India has about 12,000 ophthalmologists (approximately 3500 trained retina specialists)1. As previously mentioned, India is expected to have more than 100 million people with diabetes by 20302. That’s just one ophthalmologist for every 8,333 people with diabetes. Even if all these people are located near their ophthalmologist, it is almost impossible for the doctor to see them all for their annual DR test each year.

According to Dr Manisha Agarwal, Joint Secretary, Retina Society of India, the medical profession is very aware of this gap, and has turned its collective gaze towards AI powered solutions that make it possible for them to screen more people, while spending their time only on those cases that actually need a specialist. These may sound like contradictory aims, but consider this: while DR screening needs a trained ophthalmologist, so does the actual diagnosis and treatment plan!

What if there was a way to filter out the cases where no DR is present, so doctors could focus their energies on those who really need their help? AI may be the answer here.

301 patients with type 2 diabetes underwent retinal photography with Remidio ‘Fundus on phone’ (FOP), a smartphone-based device, at a tertiary care diabetes centre in India. Retinal images of 296 patients were graded. DR was detected by the ophthalmologists in 191 (64.5%) and by the AI software in 203 (68.6%) patients while Sight Threatening DR was detected in 112 (37.8%) and 146 (49.3%) patients, respectively.7

The way the AI was programmed was that it flagged cases even when it suspected that DR was present. This is why the AI numbers are higher than those of the ophthalmologists. This is because the AI aims to filter out only the obvious cases. In case of doubt, it passes the case on to the ophthalmologist.

According to Rito Maitra, co-founder of Radical Health, “What Radical Health builds and what we aim to propagate is the ability to read that image using artificial intelligence, so that every single image that is read produces a result right then and there without the need to have a retina specialist at every corner. There are diabetologists, family physicians, primary care clinics, government setups, district hospitals… this is something that can be done anywhere and everywhere.” Radical Health’s turnkey AI solution is already in use by several healthcare providers.

AI solutions have several advantages8. No more lengthy wait times at your doctor because now that the AI can give you a preliminary result, you’ll only see the doctor if you actually need to. Moreover, the test can also be deployed in rural areas that are too remote to be a part of an eye specialists’ rotation. Trained technicians can administer the test, and based on the result, can refer people to the ophthalmologist in the nearest town or city, for further treatment.


DR is called a silent killer of sight, but it doesn’t need to be. The gap is one of awareness among the general public. After all, if every person with diabetes knows they have to get tested for DR annually, there’s no reason why it can’t be relegated to the past, just like we did with several other diseases we no longer remember.

With this lofty aim in mind, and to remedy the lack of awareness about the importance of Diabetic Retinopathy screening, Network18 has launched the Netra Suraksha initiative in association with Novartis. This is the second season of the initiative and it aims to further increase awareness around DR, dispel myths and promote preventive eye check ups.

Visit the Netra Suraksha initiative website to learn more about Diabetic Retinopathy, and how to prevent vision loss arising from it.


  1. Pandey SK, Sharma V. World diabetes day 2018: Battling the Emerging Epidemic of Diabetic Retinopathy. Indian J Ophthalmol. 2018 Nov;66(11):1652-1653. Available at: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6213704/ [Accessed 4 Aug 2022]
  2. IDF Atlas, International Diabetes Federation, 9th edition, 2019. Available at: https://diabetesatlas.org/atlas/ninth-edition/ [Accessed 4 Aug 2022]
  3. Abràmoff MD, Reinhardt JM, Russell SR, Folk JC, Mahajan VB, Niemeijer M, Quellec G. Automated early detection of diabetic retinopathy. Ophthalmology. 2010 Jun;117(6):1147-54. Available at: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2881172/ [Accessed 4 Aug 2022]
  4. Complications of Diabetes. Available at: https://www.diabetes.org.uk/guide-to-diabetes/complications [Accessed 25 Aug 2022]
  5. Kumar S, Kumar G, Velu S, et al, Patient and provider perspectives on barriers to screening for diabetic retinopathy: an exploratory study from southern India. BMJ Open 2020;10:e037277. doi: 10.1136/bmjopen-2020-037277. Available at https://bmjopen.bmj.com/content/10/12/e037277 [Accessed on 6 Sep 2022]
  6. Ramachandran Rajalakshmi, Umesh C Behera, Harsha Bhattacharjee, Taraprasad Das, Clare Gilbert, G V S Murthy, Hira B Pant, Rajan Shukla, SPEED Study group. Spectrum of eye disorders in diabetes (SPEED) in India. Report # 2. Diabetic retinopathy and risk factors for sight threatening diabetic retinopathy in people with type 2 diabetes in India. Indian J Ophthalmol. 2020 Feb;68(Suppl 1):S21-S26.. Available at https://pubmed.ncbi.nlm.nih.gov/31937724/ [Accessed on 25 Aug 2022]
  7. Rajalakshmi R, Subashini R, Anjana RM, Mohan V. Automated diabetic retinopathy detection in smartphone-based fundus photography using artificial intelligence. Eye (Lond). 2018 Jun;32(6):1138-1144. Available at: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5997766/ [Accessed 4 Aug 2022]
  8. Revelo AI Homepage. Available at https://revelo.care/ [Accessed 6 Sep 2022]

This is a partnered post. 

Read the Latest News and Breaking News here

first published:September 20, 2022, 13:35 IST
last updated:September 20, 2022, 13:35 IST