New Delhi, October 22 (IANS). A research has revealed that Artificial Intelligence is capable of detecting keratitis infection (IK) just like ophthalmologists.
The study has confirmed the potential of AI and deep learning models in promoting healthcare.
Keratitis infection is commonly known as corneal infection. The disease causes approximately 5 million cases of blindness worldwide and approximately 2 million cases of monocular blindness each year. It has particularly affected people in low- and middle-income countries.
U.K. Researchers at the University of Birmingham conducted a meta-analysis of 35 studies looking at keratitis infection.
Their findings, published in Clinical Medicine, showed that the AI models matched the work of ophthalmologists. The AI model demonstrated 89.2 percent sensitivity and 93.2 percent specificity, compared to ophthalmologists’ 82.2 percent sensitivity and 89.6 percent specificity.
Dr Darren Ting, an ophthalmologist at the University of Birmingham, said: “Our research shows that AI has the potential to detect disease rapidly and reliably and could be a game-changer in the treatment of corneal infections.”
Ting said AI-powered models could bring significant benefits in areas where access to specialist eye care is limited and could help reduce the burden of preventable blindness around the world.
Ting said artificial intelligence (AI) models could provide significant benefits in areas where access to eye specialists is limited and could help reduce the burden of preventable blindness around the world.
The AI models also proved effective in differentiating between infected corneas of healthy eyes and those with different causes of IK, such as bacterial or fungal infections.
Although the researchers called for the results to be interpreted with caution,
They stressed the need for more diverse data and external validation to increase the reliability of these models for clinical use.
–IANS
MKS/CBT