AI poised for a critical role in Ophthalmology

From the back of the eye to the front, Artificial Intelligence (AI) is expected to give ophthalmologists new automated tools for diagnosing and treating ocular diseases. This transformation is being driven in part by a recent surge in attention to AI’s medical potential from big players in the digital world like Google and IBM. But, in ophthalmic AI circles, computerized analytics are being viewed as the path toward more efficient and more objective ways to interpret the flood of images that modern eye care practices produce, according to ophthalmologists involved in these efforts.

The most immediately promising computer algorithms are in the field of retinal diseases. For instance, researchers from the Google Brain initiative reported in 2016 that their Deep Learning AI system had taught itself to accurately detect diabetic retinopathy (DR) and diabetic macular edema in fundus photographs.

“Telemedicine for DR helped lay the groundwork for AI”, said Michael F. Chiang, MD, at Oregon Health & Science University in Portland.

AI is being applied to other retinal conditions, including age-related macular degeneration (AMD), retinopathy of prematurity (ROP) and reticular pseudodrusen.

Researchers are developing AI-based systems to better detect or evaluate other ophthalmic conditions, including pediatric, cataract, glaucoma, keratoconus, corneal ectasia, and occuloplastic reconstruction.

There is a whole spectrum, all the way from screening to full management, where these algorithms can make things better and make things more objective. There are a lot of times when clinicians just disagree, but an AI system gives the same answer every time.

One of the most common concerns clinical ophthalmologists and other physicians express about AI is that it will replace them. But Renato Ambrósio Jr., MD, PhD, who has been working on a machine learning algorithm to predict the risk of ectasia after refractive surgery said that he encourages his colleagues to regard AI as just another tool in their diagnostic armamentarium.

“I use the tools developed by our group for enhanced ectasia susceptibility characterization in my daily practice”, “It has allowed me to improve not only the sensitivity to detect patients at risk but also the specificity, allowing me to proceed with surgery in patients who may have been considered at high risk by less sophisticated approaches”, said Dr. Ambrósio, at the Federal University of São Paulo in São Paulo, Brazil.

“When these tools are ready for widespread clinical use, physicians would not need to become AI experts, because the software is likeliest to reside within devices like optical coherence tomography (OCT) machines”, said Ursula Schmidt-Erfurth, MD, at the Medical University of Vienna in Vienna, Austria. Her group is working on several AMD-analyzing algorithms. “Their algorithm can predict the course of the disease. It can identify exactly which patients will develop which type of advanced disease, whether it may be wet or dry [AMD], and it allows them to identify at-risk patients”.

“An automated algorithm is just a software tool, and ours are all based on routine OCT images that are available in thousands and thousands of hospitals and private offices. “Ideally, this software would be built into each machine that is being sold”.

FDA’s proposed Software (AI) as a medical device follows the guidelines of the International Medical Device Regulators Forum (IMDRF).

Looking ahead

Many aspects of the regulatory processes for AI are still evolving and there are challenges both for planning of clinical trials and commercial development. In real world clinical situations there are fewer patients with sight threatening diabetic retinopathy (5-7%). This is a key challenge for the design of prospective AI studies. As a result, the accuracy of the diabetic retinopathy AI in sight threatening may be lower.

AI retinal screening tools can have a limited scope in identifying a specific disease process such as diabetic retinopathy but fail to comment or identify other pathology that could be clinically significant. However, as AI-enhanced screening tools become more widely utilized, it is also important to integrate screening for multiple disease processes.

For automated retinal image analysis to be practiced in India there is a need to consider government regulatory norms, licensure, and costs. For Indian teleophthalmology there is a need to embrace a culture change. Patients have to accept that an equipment with AI will diagnose the disease condition and the physician will have to accept that computer software programs will aid in diagnosis of ocular diseases. We do need to have further work on adopting standard guidelines for adopting automated retinal analysis – AI screening programs

The systems must meet national regulations and accepted standards of IT Act of India. Programs should consider interoperability options when selecting equipment and software. These systems also must have software security protocols to protect patient health information and identification of image data. All companies registered under technology or providing technology services are governed by the IT Act.

Despite these challenges, it is clear that AI will occupy an increasingly critical role in medicine and will be a valuable research tool.

Dr Chiang, who is helping to develop AI techniques to assess ROP, said that he believes automated systems can and should complement what physicians do.

“Machines can help the doctor make a better diagnosis, but they are not good at making medical decisions afterward, Doctors and patients make management decisions by working together to weigh the various risks and benefits and treatment alternatives. The role of the doctor will continue to involve the art of medicine which is a uniquely human process”, he said.

We need medical practitioners and engineers to collaborate and work toward developing and improving new technologies for artificial intelligence that will aid in disease identification and diagnosis.

Some of the quotes and subject relating to AI has been sourced from the American Academy of Ophthalmology.