Related Experiment Video
Updated: Jan 17, 2026
05:14
Comparison of Agreement and Accuracy using Binocular Wavefront Optometer with Autorefractor and Phoropter
Published on: September 16, 2025
574
Artificial intelligence applications in refractive error management: A systematic review and meta-analysis.
Josephine Ampong1, Sylvia Agyekum1, Werner Eisenbarth2
1Department of Optometry and Visual Science, College of Science, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana.
PLOS Digital Health
|September 25, 2025
Summary
Artificial intelligence (AI) shows high accuracy in diagnosing and predicting refractive errors (REs). Further research is needed to develop generalizable AI models for broader clinical use in eye care.
Area of Science:
- Ophthalmology and Artificial Intelligence (AI)
Background:
- AI is increasingly integrated into healthcare, with significant potential in eye care.
- Refractive errors (REs) represent a major global vision challenge.
- AI applications in RE management include diagnosis, detection, prediction, progression monitoring, and treatment.
Purpose of the Study:
- To systematically review and meta-analyze the effectiveness of AI techniques in the diagnosis, detection, prediction, progression, and treatment of refractive errors.
- To assess the diagnostic and predictive accuracy of AI models in managing REs.
Main Methods:
- Systematic review and meta-analysis adhering to PRISMA guidelines.
- Searched multiple databases (PubMed, Web of Science, Embase, Scopus, Cochrane Library, Google Scholar) from inception to January 2025.
- Included 45 studies, with 19 undergoing meta-analysis, utilizing deep learning (DL) and machine learning (ML) techniques.
- Assessed risk of bias using QUADAS-2 and performed meta-analysis using R software.
Main Results:
- AI demonstrated high pooled performance for detection/diagnosis: sensitivity 0.94, specificity 0.96, DOR 382.56, SROC 0.98.
- AI showed strong predictive accuracy for REs: sensitivity 0.87, specificity 0.96, DOR 159.94, SROC 0.96.
- Performance metrics for progression and treatment varied, with AUC ranging from 0.60-0.99 and MAE from 0.119D-0.54D.
Conclusions:
- AI, particularly DL and ML, achieves high diagnostic and predictive accuracy in refractive error management.
- Current AI applications show promise for improving eye care outcomes.
- Future research should prioritize developing generalizable AI models trained on diverse datasets for widespread clinical adoption.
Related Concept Videos
01:16Focusing of Light in the Eye
5.4K
Light rays enter the eye through the cornea, a transparent dome-shaped tissue that is the eye's outermost layer. The cornea bends or refracts, light rays traveling to the pupil. The shape of the cornea determines how much of the light is bent and whether the image will be focused correctly on the retina at the back of the eye. Once the light has passed through both refraction layers, it converges into a single focal point onto a small area. This is where photoreceptors start transforming...
5.4K
01:28Angle Closure Glaucoma: Treatment
1.2K
Angle-closure glaucoma, or closed-angle glaucoma, is an eye condition where the iris bulges out and blocks the iridocorneal angle, resulting in a buildup of aqueous humor and increased intraocular pressure. Immediate medical attention is necessary due to the sudden onset of symptoms. The treatment for angle-closure glaucoma includes short-term and long-term approaches. Short-term treatment involves using eye drops like pilocarpine to lower intraocular pressure by increasing aqueous humor...
1.2K