Yousefi 2018.

Study characteristics
Patient Sampling	Multicentre, retrospective, case‐control study. Corneal OCT images were collected from 12,242 eyes of 3162 people using SS‐1000 CASIA OCT Imaging Systems (Tomey, Japan) and other parameters from the electronic health record (EHR) system.
Patient characteristics and setting	All available data were collected without any preconditions. The investigators then selected a single visit from each eye and excluded eyes with missing ectasia status index (ESI). Eyes were grouped as follows according to ESI. Normal: ESI 0–4 Forme fruste keratoconus (or keratoconus suspect): ESI 5–29 Keratoconus: ESI ≥ 30 Using Casia labels, the data set included 1970 healthy eyes, 796 eyes with forme fruste keratoconus, and 390 eyes with keratoconus.
Index tests	The algorithm included 3 major steps, as follows. Principal component analysis (PCA) was used to linearly reduce the dimensionality of the input data from 420 to 8 significant principal components. Manifold learning was used to further reduce the selected principal components non‐linearly to 2 eigen parameters. Finally, a density‐based clustering was applied to the eigen parameters to identify eyes with keratoconus.
Target condition and reference standard(s)	The article does not state who made the diagnosis. All cases were diagnosed before the analysis.
Flow and timing	Unclear whether all participants were diagnosed by the same cornea specialists. Unclear if all cases included in the analysis.
Comparative	Not applicable
Notes	The study authors were funded by an unrestricted grant from Research to Prevent Blindness (RPB), New York, NY. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of 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?			Unclear
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?	Unclear
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?		Unclear 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?	Unclear
Were all patients included in the analysis?	Unclear
Could the patient flow have introduced bias?		Unclear risk
DOMAIN 5: Comparative