Artificial Intelligence (AI) may soon play a key role in the diagnosis of infectious keratitis (IK), a leading cause of corneal blindness worldwide.

Corneal blindness is a broad term for a group of eye conditions caused by lesions on the cornea, leading to vision loss or blindness.

A recent study found that AI models, particularly deep learning (DL) models, were as accurate as eye experts in identifying infections.

The study, led by Dr. Darren Ting of the University of Birmingham, reviewed 35 studies that used the DL model to diagnose infectious keratitis.

Published in eClinicalMedicine, the research showed that the AI ​​had a diagnostic sensitivity of 89.2% and specificity of 93.2%.

In comparison, ophthalmologists demonstrated a sensitivity of 82.2% and specificity of 89.6%. The AI ​​models analyzed more than 1,36,000 corneal images, proving their ability to assist in medical settings.

Dr. Ting said, “Our study shows that AI has the potential to provide rapid, reliable diagnosis, which could revolutionize how corneal infections are managed globally, especially in areas where eye care specialists are not available. Access is limited. This may reduce the cases of preventable blindness.”

The AI ​​model not only accurately identified infections, but also distinguished between healthy eyes and different types of IK, such as bacterial and fungal infections.

Although the results are promising, the study authors highlighted the need for more diverse data and further testing to ensure reliability in clinical practice.

Infectious keratitis affects millions of people, particularly in low- and middle-income countries where there is limited access to specialized care.

The study authors said that as AI continues to develop, it could become a powerful tool in preventing corneal blindness around the world.