AI systems in smartphones may help detect eye diseases: study

A recent study published in the European Journal of Ophthalmology has revealed that a smartphone-based AI system can accurately detect major eye diseases such as diabetic retinopathy, age-related macular degeneration, and glaucoma, according to a press release. Conducted by doctors from the NIO Super Specialty Hospital in Pune, the prospective, cross-sectional study involved 193 adults aged 18 and above, examining 371 eyes.

The research utilized a Remidio Fundus on Phone platform with Medios AI multi-disease software, an offline AI system approved by the Central Drugs Standard Control Organisation for clinical use. The platform operated entirely offline, with dilated fundus imaging performed using Remidio Fundus on Phone and Zeiss Clarus 500 cameras.

Ungradable images were excluded from the analysis. The offline MAI algorithm generated disease-specific reports, which were compared to masked grading performed by two ophthalmologists fellowship-trained in the field. The study's findings showed high diagnostic accuracy: for glaucoma, sensitivity was 98.2% and specificity was 99.0%; for AMD, sensitivity was 88.9% and specificity was 97.5%; and for DR, sensitivity was 84.6% and specificity was 99.0%.

The researchers concluded that the system showed promise for scalable, point-of-care retinal screening in resource-limited settings.