June 25, 2019

Machine learning in Ophthalmology

Machine learning in Ophthalmology

New diagnostic and imaging techniques generate such an incredible amount of data that it is often a challenge to extract all information that could be possibly useful in clinical practice.

As population aging has become a major demographic trend around the world, patients suffering from eye diseases are expected to increase steeply. Early detection and appropriate treatment of eye diseases are of great significance to prevent vision loss and promote living quality.

Machine Learning techniques emerged as an objective tool to assist practitioners to diagnose certain conditions and take clinical decisions. In particular, Machine Learning techniques have repeatedly shown their usefulness to ophthalmologists.

The possible applications of this technology go much further than being used as a diagnostic tool, as it may also be used to grade the severity of a pathology, perform early disease detection, or predict the evolution of a condition.

Many ocular diseases leading to blindness can be halted or delayed when detected and treated at its earliest stages. With the recent developments in diagnostic devices, imaging and genomics, new sources of data for early disease detection and patients’ management are now available.

Machine learning techniques emerged in the biomedical sciences as clinical decision-support techniques to improve sensitivity and specificity of disease detection and monitoring, increasing objectively the clinical decision-making process.

These techniques allow creating homogeneous groups (unsupervised learning), or creating a classifier predicting group membership of new cases (supervised learning), when a group label is available for each case.

To ensure a good performance of the machine learning techniques in a given dataset, all possible sources of bias should be removed or minimized.

For that, the representativeness of the input dataset for the true population should be confirmed, the noise should be removed, the missing data should be treated and the data dimensionally (i.e., the number of parameters/features and the number of cases in the dataset) should be adjusted.

The application of machine learning techniques in ocular disease diagnosis and monitoring will be presented and discussed in the second section of this manuscript.

To show the clinical benefits of machine learning in clinical vision sciences, several examples will be presented in glaucoma, age-related macular degeneration, and diabetic retinopathy, these ocular pathologies being the major causes of irreversible visual impairment.

AI Application In Ophthalmology

Artificial Intelligence systems are available or in development for detecting several ophthalmic diseases, including Diabetic Retinopathy (DR), Wet Age-Related Macular Degeneration (AMD), cataract, and glaucoma.

These AI systems are tested for their ability to accurately detect disease, and this is typically assessed with measures called sensitivity and specificity. Sensitivity is a measure of how accurately the system catches all positive cases of the disease, and specificity shows a measure of how well the system avoids false positives. For each measure, the higher the value, the better the accuracy.

Diabetic Retinopathy
Recent studies show that diabetes affects over 415 million people worldwide, meaning 1 in every 11 adults is affected. DR, a chronic diabetic complication, is a vasculopathy that affects one-third of diabetic patients and can lead to irreversible blindness. Automated techniques for DR diagnosis have been explored to improve the management of patients with DR and alleviate the social burden. AI was used to predict DR risk and DR progression among diabetic patients to combat this worldwide disease.

Glaucoma, being the third-largest sight-threatening eye disease around the world, has a critical impact on global blindness. Glaucoma patients suffer from high intraocular pressure, damage of the optic nerve head (ONH), retina nerve fibre layer (RNFL) defect, and gradual vision loss. Automatically detecting features related to glaucoma have great significance in its timely diagnosis.

Age-Related Macular Degeneration
AMD is leading with the cause of irreversible blindness among old people in the developed world. Machine Learning algorithms automatically identify AMD-related lesions to improve AMD diagnosis and treatment. Detection of drusen, fluid, reticular pseudodrusen, and geographic atrophy from fundus images and SD-OCT using ML has been studied. The accuracy is usually over 80%, and the agreement between the models and retina specialists can reach 90%.

Cataract is a disease with cloudy lenses and has bothered millions of old people.
Early detection and treatment can bring light to cataract patients and improve their living quality. ML algorithms such as RF and SVM have been applied to diagnose and grading cataract from fundus images, ultrasounds images, and visible wavelength eye images.

The risk prediction model for posterior capsule opacification after phacoemulsification has also been built.

AI-assisted automated screening and diagnosis of common diseases in ophthalmology may eventually help maximize the doctors’ role at the clinic.
Outside the clinic,
AI platforms offer the patients more medical opportunities and reduce obstacles to access eye care where an ophthalmologist is not available.
To some extent, new technologies based on AI may reduce social inequalities. Looking further into the future, AI-assisted systems show the potential to relieve the overburdened healthcare system’s problems.


1.Simonite T. Google’s AI eye doctor gets ready to go to work in India. Wired Magazine. June 8, 2017. Accessed April 19, 2018.

2. van der Heijden AA, Abramoff MD, Verbraak F, et al. Validation of automated screening for referable diabetic retinopathy with the IDx-DR device in the Hoorn Diabetes Care System. Acta Ophthalmol. 2018;96:63-68.

3. FDA permits marketing of IDx-DR for automated detection of diabetic retinopathy in primary care [press release]. IDx. April 12, 2018. Accessed April 19, 2018.

4. BogunoviÄ H, Montuoro A, Baratsits M, et al. Machine learning of the progression of intermediate age-related macular degeneration based on OCT imaging. Invest Ophthalmol Vis Sci. 2017;58:BIO141-BIO150.

5. BogunoviÄ H, Waldstein SM, Schlelgl T, et al. Prediction of anti-VEGF treatment requirements in neovascular AMD using a machine learning approach. Invest Ophthalmol Vis Sci. 2017;58:3240-3248.

6. Schlegl T, Waldstein SM, Bogunovic H, et al. Fully automated detection and quantification of macular fluid in OCT using deep learning. Ophthalmology. 2018;125:549-558.

Alim Bidmus is a health tech enthusiast, data analyst and AI engineer who has been leveraging the leveraging the capabilities of tech in driving innovation in the Healthcare sector