. Author manuscript; available in PMC: 2021 Aug 13.

Published in final edited form as: Asia Pac J Ophthalmol (Phila). 2021 Jul 1;10(3):268–281. doi: 10.1097/APO.0000000000000394

Table 2. Summary of the potential of artificial intelligence for various anterior segment diseases, based on data and various imaging modalities.

	Cornea	Refractive Surgery	Cataract
Clinical data	- Classification between fungal and bacterial keratitis⁴⁹ - Prediction of the need for keratoplasty in keratoconus⁶⁸	- Suggestion of nomogram for optimizing outcome of refractive surgery^99–101 - Intraocular lens power calculation^127–129	- Identifying cases at high risk of developing pediatric cataract.¹²⁵ - Prediction of complications after pediatric cataract surgery¹²⁴
SLP	- Differentiate between infectious and non-infectious keratitis, corneal dystrophies and surface neoplasms^50,55 - Distinguish bacterial and fungal keratitis⁵⁴		- Grading of cataract^{111, 112} - Detection and prediction of PCO^{120, 121} - Diagnosing pediatric cataract¹²³
AS-OCT	- Detection of localized or mild corneal edema⁷⁴ - Prediction of graft detachment and rebubbling after DMEK⁹⁰ - Diagnosis of graft detachment after DMEK⁸⁹ - Detecting early Fuchs endothelial dystrophy⁷⁵
CT	- Detection and grading of keratoconus^{67, 69} - Prediction of outcomes of intrastromal ring segments^{66, 73}	- Preoperative screening of CRS^{94, 97} - Identification of corneas with post-CRS and iatrogenic ectasia^{95, 96}
IVCM	- Correlating corneal nerve features to diagnose diabetic neuropathy and assess its severity^{80, 82} - Diagnosis of fungal keratitis^{51, 52}

SLP = Slit-lamp photography; AS-OCT = Anterior segment optical coherence tomography; CT = Corneal tomography / topography; IVCM = In vivo confocal microscopy; DMEK = Descemet membrane endothelial keratoplasty; CRS = Corneal refractive surgery; PCO = Posterior capsular opacification