Photo Credit: Monsitj
The following is a summary of “Deep learning model for extensive smartphone-based diagnosis and triage of cataracts and multiple corneal diseases,” published in the January 2024 issue of Ophthalmology by Ueno et al.
Researchers conducted a retrospective study to develop an artificial intelligence (AI) algorithm capable of diagnosing cataracts and corneal diseases from diverse conditions using smartphone-captured images.
They utilized 6,442 images obtained via a slit-lamp microscope (6,106 images) and smartphone (336 images). An AI algorithm was created using slit-lamp images to classify 36 major diseases (cataracts and corneal diseases) into 9 categories. For model validation, smartphone images constituted the testing dataset. AI performance, including sensitivity, specificity, and receiver operating characteristic (ROC) curve analysis, was conducted to assess disease diagnosis and triage.
The results showed that the AI algorithm achieved an area under the ROC curve of 0.998 (95% CI, 0.992 to 0.999) for normal eyes, 0.986 (95% CI, 0.978 to 0.997) for infectious keratitis, 0.960 (95% CI, 0.925 to 0.994) for immunological keratitis, 0.987 (95% CI, 0.978 to 0.996) for cornea scars, 0.997 (95% CI, 0.992 to 1.000) for ocular surface tumors, 0.993 (95% CI, 0.984 to 1.000) for corneal deposits, 1.000 (95% CI, 1.000 to 1.000) for acute angle-closure glaucoma, 0.992 (95% CI, 0.985 to 0.999) for cataracts, and 0.993 (95% CI, 0.985 to 1.000) for bullous keratopathy. Triage of referral suggestion using smartphone images demonstrated high performance, with sensitivity and specificity of 1.00 (95% CI, 0.478 to 1.00) and 1.00 (95% CI, 0.976 to 1.000) for ‘urgent,’ 0.867 (95% CI, 0.683 to 0.962) and 1.00 (95% CI, 0.971 to 1.000) for ‘semi-urgent’, 0.853 (95% CI, 0.689 to 0.950) and 0.983 (95% CI, 0.942 to 0.998) for ‘routine,’ and 1.00 (95% CI, 0.958 to 1.00) and 0.896 (95% CI, 0.797 to 0.957) for ‘observation.’
Investigators concluded that the AI system demonstrated promising diagnostic performance for cataracts and corneal diseases.
Source: bjo.bmj.com/content/early/2024/01/18/bjo-2023-324488