Maeda 1995b.

Study characteristics
Patient Sampling	Single‐centre, case‐control study. Corneal topographic maps of the TMS‐1 were drawn from the Louisiana State University Eye Center patient population.
Patient characteristics and setting	Participants were divided into the following 7 categories. Normal With‐the‐rule astigmatism Mild keratoconus Moderate keratoconus Advanced keratoconus Post‐photorefractive keratectomy Post‐keratoplasty The study excluded maps in which focusing or alignment were not properly achieved or that contained atypical topographic appearances. For this project, 183 eyes were selected. The maps were randomly divided into a training set (108 maps) and a test set (75 maps).
Index tests	Neural network constructed in 3 layers. The input layer consisted of 11 neurons equal to 11 topographic indices. There was 1 hidden layer of 18 neurons. The output layer consisted of 7 neurons, 1 for each topographic category.
Target condition and reference standard(s)	Topography images were made with the TMS‐1. All eyes were diagnosed by the 3 study authors and classified according to the topographic image and clinical records. The diagnosis was made before the images were analysed by the algorithm.
Flow and timing	All eyes received the same reference standard, and all data were included in a 2 × 2 table.
Comparative	Not applicable
Notes	Supported in part by US Public Health Service grant EY03311 and EY01377 from the National Eye Institute, National Institutes of Health (Bethesda, MD); Computed Anatomy (New York, NY); Menicon Co. Ltd. (Nagoya, Japan).
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?	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?	Yes
Were all patients included in the analysis?	Yes
Could the patient flow have introduced bias?		Low risk
DOMAIN 5: Comparative