Al‐Timemy 2021.

Study characteristics
Patient Sampling	The study design is unclear, it seems to be case‐control study. 3794 Pentacam (Oculus GmbH, Wetzlar, Germany) corneal images from University of Sao Paulo were included and an independent validation subset with 1050 images was collected from 150 eyes of 85 subjects from a separate centre in Brazil.
Patient characteristics and setting	The criteria for keratoconus diagnosis are unclear. People with manifest keratoconus, suspected keratoconus and normal eyes were included.
Index tests	A hybrid deep learning model which integrates multiple convolutional neural network (CNN) models for detecting keratoconus based on corneal topographic maps.
Target condition and reference standard(s)	The criteria for keratoconus diagnosis are unclear. Eyes were labelled as keratoconus suspects if corneal topography included atypical, localized steepening or an asymmetrical bowtie pattern; the keratometric curvature was > 47.00 D, the oblique cylinder was > 1.50 D, the central corneal thickness was < 500 μm, BAD‐D was between 1.6 and 3.0. 3 corneal specialists performed the eye classification, before the analysis with the algorithm.
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	Supported by National Institute of Health (NIH), National Eye Institute (NEI), and Bright Focus Foundation.
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?	Unclear
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?	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