Kuo 2020.

Study characteristics
Patient Sampling	Retrospective, single‐centre (Taiwan), case‐control study. The investigators retrospectively collected corneal topographies (TMS‐4; Tomey Corporation, Nagoya, Japan) of the study group with clinically manifested keratoconus, the subclinical keratoconus group, and the control group with regular astigmatism (354 images of 206 participants).
Patient characteristics and setting	170 keratoconus pictures 28 subclinical keratoconus pictures (criteria based on topographic pattern and no slit‐lamp keratoconus findings) 156 normal topographic pictures (from candidates for refractive surgery without any previous manifestations and with regular astigmatism)
Index tests	3 convolutional neural network models
Target condition and reference standard(s)	The diagnosis of keratoconus was based on clinical signs (the existence of central protrusion of the cornea, Fleischer's ring, Vogt's striae, and focal corneal thinning on slit‐lamp examination) and topographic criteria (central K value > 47 D, I‐S value > 1.4 D, KISA% >100%, and asymmetric bowtie presentation). 4 corneas specialists classified the cases before the index test.
Flow and timing	All cases were included in the reference standard and index test. All data were included in a 2 × 2 table.
Comparative	Unclear whether different AI tests were developed and interpreted blind or independently and without knowledge of the results of each other. However, missing data and their causes were similar for each AI test.
Notes	Supported by Grants 107L891002 and 108L891002 from National Taiwan University.
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?	Unclear
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?			Low concern
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
Were different AI tests were developed and interpreted without knowledge of each other.	Unclear
Are the proportions and reasons for missing data similar for all index tests?	Yes
		Unclear risk