Researchers have successfully used AI to predict which patients need treatment to stabilise their corneas and protect their eyesight.
The study was presented at the 43rd Congress of the European Society of Cataract and Refractive Surgeons (ESCRS).
The research focused on individuals with keratoconus, a visual impairment that typically develops in teenagers and young adults and tends to worsen in later adult years.
It affects up to 1 in 350 people. In some cases, the condition can be managed with contact lenses, but in others, it deteriorates rapidly. If untreated, patients may need a corneal transplant. Currently, the only way to determine who requires treatment is to monitor patients over time.
The researchers utilised AI to evaluate images of patients’ eyes, combined with other data, and accurately predict which patients required immediate treatment and which could be monitored under observation.
The study was conducted by Dr Shafi Balal and colleagues at Moorfields Eye Hospital NHS Foundation Trust, London, and University College London (UCL), UK.
He said: “In people with keratoconus, the cornea bulges outward. Keratoconus causes visual impairment in young, working-age patients and is the most common reason for corneal transplantation in the Western world.
‘A single treatment called cross-linking can stop the disease from progressing. When performed before permanent scarring develops, cross-linking often prevents the need for corneal transplantation. However, doctors cannot currently predict which patients will progress and require treatment, and which will remain stable with monitoring alone. This means patients need frequent monitoring over many years, with cross-linking typically performed after progression has already occurred.’
The study involved patients referred to Moorfields Eye Hospital NHS Foundation Trust for keratoconus assessment and monitoring, including scanning the front of the eye with optical coherence tomography (OCT) to examine its shape.
Researchers used AI to analyse 36,673 OCT images from 6,684 patients, along with other patient data.
The AI algorithm could accurately predict whether a patient’s condition would worsen or stay stable using images and data from the first visit alone.
By using AI, the researchers were able to classify two-thirds of patients as low-risk, who did not require treatment, and the remaining third as high-risk, who needed prompt cross-linking treatment.
When data from a second hospital visit was included, the algorithm could successfully categorise up to 90% of patients.
Cross-linking treatment uses ultraviolet light and vitamin B2 (riboflavin) drops to strengthen the cornea, and it is successful in over 95% of cases.
Dr Balal said: ‘Our research demonstrates that we can use AI to predict which patients need treatment and which can be safely monitored. This is the first study of its kind to achieve this level of accuracy in predicting keratoconus progression through a combination of scans and patient data, and it involves a large cohort monitored over more than two years. Although this study utilised one specific OCT device, the methods and AI algorithm can be applied to other devices. The algorithm will now undergo further safety testing before being used in clinics.
‘Our findings could mean that patients with high-risk keratoconus could receive preventive treatment before their condition worsens. This could prevent vision loss and avoid the need for corneal transplant surgery with its associated risks and recovery time. Low-risk patients would also benefit, as they could avoid unnecessary frequent monitoring, thereby saving healthcare resources. Properly sorting patients with the algorithm will allow specialists to focus on areas with the greatest need.’
The researchers are now developing a more advanced AI algorithm trained on millions of eye scans that can be tailored for specific tasks, including predicting keratoconus progression, as well as detecting eye infections and inherited eye conditions.
Dr José Luis Güell, ESCRS Trustee and Head of the Cornea, Cataract and Refractive Surgery Department at the Instituto de Microcirugía Ocular, Barcelona, Spain, who was not involved in the research, said: ‘Keratoconus is a manageable condition, but knowing who to treat, and when and how to give treatment is challenging. Unfortunately, this can lead to delays, with many patients experiencing vision loss and requiring invasive surgery such as implants or transplants.
‘This research suggests that AI can help predict who will experience progression, even from their first routine consultation, enabling early treatment before secondary changes happen. Equally, it can reduce unnecessary monitoring of stable patients. If it consistently proves effective, this technology could ultimately prevent vision loss and the need for more complex management strategies in young, working-age patients.’
