AI can now detect glaucoma from a fundus photograph with a sensitivity of over 90% — but the more important question is whether earlier detection translates into less blindness. Early detection, when coupled with early, consistent care can save sight. As Dr Shibal Bhartiya asked in a widely-read LinkedIn article on the subject: can AI reduce glaucoma blindness, or does it simply document it earlier?
That question sits at the heart of how AI must be evaluated in clinical practice.
Dr Shibal Bhartiya is a fellowship-trained glaucoma specialist and Mayo Clinic Research Collaborator with over 25 years of experience. Her approach focuses on identifying risk before damage is irreversible, simplifying treatment decisions, and protecting vision long-term. Emphasis on early detection, risk assessment, and continuity of care. She is rated 5 stars across 1,500+ patient reviews on Google.
She has written on AI in glaucoma screening in the Journal of Current Glaucoma Practice (PMID 36128081) and examined the integration of AI into glaucoma management in a 2025 narrative review in the Indian Journal of Ophthalmology (PMID 39982079). Dr Bhartiya also co-authored a foundational paper on target IOP and precision medicine, and in the TNOA Journal of Ophthalmic Science and Research’s 2025 review on personalised glaucoma care.
Why AI in Glaucoma Matters
Glaucoma is the leading cause of irreversible blindness worldwide. It causes no pain and no early symptoms. Most patients lose 40% of nerve fibres before they notice anything wrong. By that point, damage is permanent.
The challenge has always been detection: reaching the right patients, early enough, at scale. This is where AI offers genuine promise.
What AI Can Do in Glaucoma Today
Screening from fundus images
Deep learning models analyse retinal photographs to identify structural signs of glaucoma. These include optic disc cupping, nerve fibre layer defects, and haemorrhages. A meta-analysis published in the Journal of Glaucoma found that AI tools achieved a pooled area under the ROC curve of 96.3%, with sensitivity of 92% and specificity of 94% across 79 studies. Lippincott Williams & Wilkins
Dr Bhartiya raised a critical question about these numbers in her Journal of Current Glaucoma Practice editorial: high accuracy in controlled datasets does not automatically translate to clinical utility. The question is what happens after the algorithm flags a patient.
Progression monitoring
AI platforms can analyse longitudinal data and alert clinicians about rapid disease progression MDPI — a task that is difficult for human reviewers managing hundreds of visual field tests. This is clinically meaningful. Progression often goes undetected between annual visits, and irreversible damage accumulates silently.
Personalised target IOP
This is where AI’s most important future role lies. Glaucoma management is not one-size-fits-all. The paradigm for defining target IOP has shifted from a population-based threshold to a fluid, individualised estimate integrating multiple clinical and personal factors. AI is central to making that individualisation scalable.
Dr Bhartiya co-authored the foundational paper on this shift — New Perspectives on Target Intraocular Pressure (Clement, Bhartiya, Shaarawy; Survey of Ophthalmology 2014, PMID 25081325), which established that no current method for setting target IOP has been formally validated, and that IOP fluctuation and lamina cribrosa pressures are routinely excluded from clinical calculations. AI offers a path to closing that gap.
AI in education and training
Dr Bhartiya’s recent work on ophthalmology pedagogy highlights a parallel transformation. AI is reshaping how future glaucoma specialists learn: through personalised learning platforms, surgical simulation, and performance tracking. She argues that despite these advances, human mentorship and ethical reasoning remain irreplaceable. The same logic applies to clinical AI: the algorithm assists; the specialist decides.
What AI Cannot Do
AI cannot examine a patient. It cannot assess compliance, understand a patient’s fear of surgery, or weigh quality-of-life preferences against IOP targets. It cannot perform the slit-lamp examination that catches angle closure before it becomes an emergency.
Dr Bhartiya’s 2025 Indian Journal of Ophthalmology review notes that integration of telemedicine and artificial intelligence in glaucoma management “may revolutionize current glaucoma practice”, but only alongside pharmacological, surgical, and lifestyle interventions, and community-based access to care.
The word “alongside” is doing a lot of work there. AI without a clinical pathway is documentation, not prevention.
The Indian Context
India carries a disproportionate burden of glaucoma blindness. Most patients present late. Screening infrastructure is limited outside urban centres. AI-based triage using smartphone-compatible fundus cameras could extend specialist reach to primary care settings, rural camps, and community clinics. This is not theoretical, it is already being piloted.
Dr Bhartiya’s Vision Unlimited programme, which has served over 15,000 children and 5000 adults in urban underserved communities in Gurugram in 2025, reflects the same philosophy: expert-level care and early intervention must reach the people who need it most, not just those who can access a tertiary centre.
The Bottom Line
AI is a powerful tool for glaucoma screening, progression monitoring, and personalised care. Used well, it can help specialists detect disease earlier and adjust treatment more precisely. But it works only when connected to a specialist who can act on what the algorithm finds. Detection without treatment does not prevent blindness.
If you have a family history of glaucoma, are over 40, or have never had a comprehensive eye check, do not wait for AI to find you. See a glaucoma specialist now.
FAQs
Can AI replace a glaucoma specialist?
No. AI can screen and flag, but it cannot examine, treat, or make nuanced clinical decisions. A glaucoma specialist interprets AI findings alongside your full clinical picture.
How accurate is AI at detecting glaucoma?
In controlled studies, AI tools reach over 90% sensitivity for glaucoma detection from fundus images. Real-world performance is lower, and accuracy varies by image quality, population, and algorithm.
Is AI glaucoma screening available in India?
AI-assisted glaucoma screening programmes are being piloted in India, including smartphone-based models suitable for primary care and camp settings. Ask your eye specialist whether it is available in your area.
What is personalised target IOP?
Target IOP is the pressure level your specialist aims for to stop your glaucoma from getting worse. AI is helping make this target more precise: based on your individual risk, rate of progression, and optic nerve status.
Read the research articles
This article was written by Dr Shibal Bhartiya, fellowship-trained glaucoma specialist and Mayo Clinic Research Collaborator, Clinical Director at Marengo Asia Hospitals, Gurugram, known for ethical, patient-centred glaucoma care and independent glaucoma second opinions. She is also the Program Director for Community Outreach & Wellness; and for the Marengo Asia International Institute of Neuro and Spine.
She has published peer-reviewed research on glaucoma management, examining how treatment decisions should balance medical evidence, patient preferences, and long-term vision outcomes.
As Editor-in-Chief of Clinical and Experimental Vision and Eye Research and Executive Editor of the Journal of Current Glaucoma Practice (Pubmed Indexed, official journal of the International Society of Glaucoma Surgery), Dr Shibal Bhartiya brings editorial and research depth to every clinical decision. Her 200+ publications, including 90+ PubMed-indexed publications and 28 edited textbooks span glaucoma biology, surgical outcomes, health equity, and emerging diagnostics.
Access her work on Pubmed, Google Scholar, ResearchGate and ORCID.
Dr Shibal Bhartiya
Glaucoma • Second Opinion • Advanced Care
www.drshibalbhartiya.com
+91 88826 38735
1500+ Five Star Patient Reviews Google Business Profile
Upload your reports for a structured review.
If you are unable to come to Dr Bhartiya’s clinic: Read more about teleconsultation for glaucoma
