Cohen 2022.

Study characteristics
Patient Sampling	Single centre, retrospective, case‐control study that evaluated 8526 corneal tomography examinations of 2525 participants obtained between November 2010 and July 2017 with the Galilei dual Scheimpflug/Placido disc analyzer system (software version 5.2.1; Ziemer Ophthalmic Systems, Port, Switzerland). Low‐quality samples were excluded.
Patient characteristics and setting	Of the 7104 included samples: 4088 were labelled as normal; 1299 were labelled as suspect irregular cornea; and 2614 were labelled as keratoconus. Label distribution was similar in train and test sets.
Index tests	Random forest; the model integrated keratoconus prediction indexes of the device in addition to the 94 instrument‐derived output parameters. The model was first trained and tested, then validated with a separate validation set.
Target condition and reference standard(s)	All images were graded by a single cornea specialist (D.V.). A normal cornea would have a regular spherical or spherocylindrical curvature, thinning toward the centre without epicentral posterior or anterior elevation, with relatively normal numerical values. A suspected irregular cornea describes an at‐risk cornea. Such a cornea may have subtle inconclusive signs like I‐S values outside the reference range or aberrant C‐shaped or mild posterior surface elevations. Alternatively, a suspected irregular cornea may have an unusual corneal thinning.
Flow and timing	All cases were included in reference standard and index test. All data were included in a 2 × 2 table.
Comparative	Not applicable
Notes	All study authors declared that they received no grant support or research funding for the study. All study authors certified that they had no affiliations with or involvement in any organization or entity with any financial interest (such as honoraria; educational grants; participation in speakers’ bureaus; membership, employment, consultancies, stock ownership, or other equity interest; and expert testimony or patent‐licensing arrangements), or non‐financial interest (such as personal or professional relationships, affiliations, knowledge or beliefs) in the subject matter or materials discussed in the manuscript.
Methodological quality
Item	Authors' judgement	Risk of bias	Applicability concerns
DOMAIN 1: Patient selection
Was a consecutive or random sample of patients enrolled?	Unclear
Was a case‐control design avoided?	No
Did the study avoid inappropriate exclusions?	Unclear
Could the selection of patients have introduced bias?		Unclear 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?	Unclear
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?		Unclear 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?	No
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?		High 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.
Are the proportions and reasons for missing data similar for all index tests?