Advancements in artificial intelligence (AI) and machine learning (ML) technology are democratizing health care in ophthalmology and eye care by making eye health services more accessible, affordable and personalized.
Algorithms can analyze retinal images for signs of eye diseases, enabling remote screening and diagnosis for those in rural or underserved areas. The eye is also being used to screen for chronic diseases like cardiovascular risk, diabetes and hypertension.
These technologies can then tailor the treatments to an individual’s specific needs based on their genetic makeup and medical history, and AI/ML algorithms can predict which patients are most likely to respond to a particular treatment.
Alexandra Murdoch, medical analyst at research firm GlobalData notes AI is revolutionizing many industries right now, and the medical industry is no exception.
“For some time, we heard a lot about AI usage in diagnostic imaging, patient monitoring, manufacturing devices and more,” she says. “More recently, we’re learning about AI usages in specific sectors, and ophthalmology is one of them.”
She adds what’s exciting is that there isn’t necessarily one specific use or outcome for AI in eye care, there can be several.
“We’re seeing AI improve ophthalmologic imaging and diagnostic tools, and it’s not only improving diagnoses related to the eyes, but can also help health care professionals find markers associated with cardiovascular health, stroke, and diabetes,” Murdoch says.
Ehsan Vaghefi president and CEO of AI-based diagnostic and screening tools provider Toku, explains retinal images are indeed obtained from millions of people daily, and he believes that the company’s technology can help identify individuals at risk of a major cardiac event.
The company recently received $8 million in Series A preferred financing to accelerate the development of its AI-powered technologies for retinal imaging.
“By analyzing retinal images, Toku’s technology can detect signs of cardiovascular disease, including hypertension and atherosclerosis, which are known risk factors for major cardiac events such as heart attacks and stroke,” he says. “This early detection and intervention can potentially save lives and improve the overall health outcomes of individuals.”
Vaghefi adds ML is playing a critical role in advancing eye care by expanding the scope of practice beyond traditional eye diseases.
“With the help of machine learning algorithms, eye care practitioners can now detect and monitor a wide range of health conditions that affect the eye, such as hypertension, diabetes, and even neurological disorders,” he notes.
Murdoch adds AI will help with imaging and diagnostics through machine and deep learning (ML and DL).
“AI helps automate the reading of diagnostic images at a much quicker rate than humans ever could,” she explains. “This will help to diagnose faster and can save radiologists some time.”
By identifying these conditions early, eye care practitioners can collaborate with other healthcare providers to provide precision medicine, tailoring treatments to the specific needs of each patient. Moreover, machine learning is also enabling eye care for a much wider population, including those from all socioeconomic backgrounds. ML in eye care will help in diagnoses as well.
“Because it can help quickly read images and identify abnormalities in scans, patients will be able to get imaging results faster,” Murdoch says.
She adds ML can also help in predicting abnormalities or disease rates–an important tool that will help healthcare professionals and researchers understand risk and incidence over time.
“By automating routine tasks and allowing for remote monitoring and screening, machine learning is making eye care more accessible and affordable,” Vaghefi says. “This is particularly important for individuals who live in rural or underserved areas, where access to eye care specialists can be limited.”
From Vaghefi’s perspective, the next major evolution in the use of AI technology for eye care is the use of generative AI, which goes beyond traditional machine learning algorithms to create new data based on existing data.
“This approach has the potential to revolutionize eye care by considering all aspects of a patient’s health, including medical records and clinicians’ subjective comments,” he explains.
By using generative AI, eye care practitioners can gain a more comprehensive understanding of each patient’s unique health needs, allowing for more personalized and effective treatments.
He adds generative AI can also help improve the accuracy of diagnosis and treatment recommendations by identifying subtle patterns and correlations within large datasets.
“This can help identify previously unrecognized risk factors for eye diseases and suggest new treatment approaches,” he says.
Murdoch points out that much today regarding AI in medical is quite new or even hypothetical.
“As these tools continue to be perfected in the near future, AI will dramatically change the diagnostic and treatment methods for several conditions like corneal ectasis, glaucoma, diabetic retinopathy, and more,” she says.
