Xie 2020.

Study characteristics
Patient Sampling	Retrospective, case‐control study, including people throughout China who wanted to undergo refractive surgery, had a primary diagnosis of keratoconus, and had stable postoperative refractive states. In total, 6465 corneal tomographic images from 1385 people were collected to develop the AI model.
Patient characteristics and setting	The following groups were included: normal cornea, suspected irregular cornea, early‐stage keratoconus, keratoconus, and myopic postoperative cornea. Normal cornea has a natural shape with all the indices within a normal range. Normal corneas included with‐the‐rule astigmatism and normally thin corneas. A suspected irregular cornea describes an at‐risk cornea. Such a cornea may have I‐S values outside the reference range or aberrant C‐shaped or round posterior surface elevations. Alternatively, a suspected irregular cornea may have an unusual pachymetric progression. Keratoconus and early‐stage keratoconus: comprehensive analysis of all the morphologic and characteristic indices according to an Asian database by 3 cornea specialists
Index tests	InceptionResNetV2 architecture in a convolutional neural network on the TensorFlow platform to create the AI model with transfer learning technique. The algorithm uses a deep learning algorithm with corneal tomographic imaging and divides the images into the previously mentioned groups. This model may aid in identifying at‐risk corneas and determining which people are unsuited to corneal refractive surgery, thereby assisting in surgery decision‐making.
Target condition and reference standard(s)	The expert team included 3 senior ophthalmologists with at least 5 years of practical experience in the refractive surgery centre of the study clinic. Each image was independently labelled by the 3 experts, none of whom knew the labels selected by the others. When the labels differed, that chosen by 2 of the 3 experts was selected as the standard.
Flow and timing	The data from all participants were checked by 3 ophthalmologists. The diagnosis was made before the analysis with the AI algorithm.
Comparative	Not applicable
Notes	The research received funding through grants 2018YFC0116500 from the National Key R&D Program of China, 31671000 from the Natural Science Foundation of China, 201804020007 from the Guangzhou Science and Technology Planning Project, 81822010 from the National Natural Science Foundation of China, 2018B010109008 from the Science and Technology Planning Projects of Guangdong Province, and 2017TX04R031 from the Guangdong Science and Technology Innovation Leading Talents.
Methodological quality
Item	Authors' judgement	Risk of bias	Applicability concerns
DOMAIN 1: Patient selection
Was a consecutive or random sample of patients enrolled?	No
Was a case‐control design avoided?	No
Did the study avoid inappropriate exclusions?	No
Could the selection of patients have introduced bias?		High risk
Are there concerns that the included patients and setting do not match the review question?			High
DOMAIN 2: Index test (All tests)
Were the index test results interpreted without knowledge of the results of the reference standard?	Yes
If a threshold was used, was it pre‐specified?	Unclear
Was the model designed in an appropriate manner?	Yes
Could the conduct or interpretation of the index test have introduced bias?		Low risk
Are there concerns that the index test, its conduct, or interpretation differ from the review question?			Low concern
DOMAIN 3: Reference standard
Is the reference standard likely to correctly classify the target condition?	Yes
Were the reference standard results interpreted without knowledge of the results of the index tests?	Yes
Could the reference standard, its conduct, or its interpretation have introduced bias?		Low risk
Are there concerns that the target condition as defined by the reference standard does not match the question?			Unclear
DOMAIN 4: Flow and timing
Did all patients receive the same reference standard?	Yes
Were all patients included in the analysis?	Yes
Could the patient flow have introduced bias?		Low risk
DOMAIN 5: Comparative