Artificial intelligence (AI) has shown similar levels of accuracy to ophthalmologists in diagnosing infectious keratitis (IK), a meta-analysis study has found.
AI models in the study matched the diagnostic accuracy of ophthalmologists, exhibiting a sensitivity of 89.2% and specificity of 93.2%, compared to ophthalmologists’ 82.2% sensitivity and 89.6% specificity.1
The models in the study had analysed over 136,000 corneal images combined, and the authors said the results further demonstrate the potential use of AI in clinical settings.
“Our study shows that AI has the potential to provide fast, reliable diagnoses, which could revolutionise how we manage corneal infections globally. This is particularly promising for regions where access to specialist eye care is limited and can help to reduce the burden of preventable blindness worldwide,” said senior author Dr Darren Ting, from the University of Birmingham.
The AI models also proved effective at differentiating between healthy eyes, infected corneas, and the various underlying causes of IK
The AI models also proved effective at differentiating between healthy eyes, infected corneas, and the various underlying causes of IK, such as bacterial or fungal infections.
The study’s authors emphasised the need for more diverse data and further external validation to increase the reliability of these models for clinical use.
Infectious keratitis, an inflammation of the cornea, affects millions of people, particularly in low- and middle-income countries where access to specialist eye care is limited.
Reference
1. Ong ZZ, Sadek Y, Ting DSJ, et al. Diagnostic performance of deep learning for infectious keratitis: a systematic review and meta-analysis, eClinicalMedicine, Nov 2024; 77:102887.
