| Study characteristics |
| Patient Sampling |
Prospective, single‐centre, case‐control study, including a data set of 777 images of 777 participants |
| Patient characteristics and setting |
Data set included data from a 777 people, distributed as follows.
411 healthy eyes (people undergoing LASIK or photorefractive keratectomy) 302 people with bilateral clinical keratoconus (KISA% index > 100% and ≥ 1 of the following biomicroscopic signs: Fleischer's ring, focal stromal thinning, Vogt's striae) 64 people with very asymmetric ectasia and with 1 healthy cornea and frank ectasia in the fellow eye.
|
| Index tests |
AI model based on Paraconsistent Feature Engineering (PFE) and Support Vector Machine (SVM), that received subsets of the 52 original Pentacam tomographic descriptors as input and produced, as output, the scalar value called Corneal Tomography Multivariate Index (CTMVI) |
| Target condition and reference standard(s) |
Classification was performed by only 1 cornea specialist, before the index test. |
| Flow and timing |
All cases were included in the reference standard and index. All data were included in a 2 × 2 table. |
| Comparative |
Not applicable |
| Notes |
Funding: CAPES (Coordination for Improvement of Higher‐education Personnel), FAPESP (São Paulo Research Foundation) process no. 2015/17226‐7 and process no. 2019/04475‐0, and CNPq (National Council for Scientific and Technological Development) process no. 306808/20018‐8. The study was supported by FAPESP [2015/17226‐ 7] to GCAJr and [2019/04475‐0] to RCG; CNPq (National Council for Scientific and Technological Development) [306808/20018‐8] to RCG; PIBIC‐CNPq to JSN. |
| 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? |
No |
|
|
| 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? |
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 |
