New artificial intelligence index based on Scheimpflug corneal tomography to distinguish subclinical keratoconus from healthy corneas

Detalhes bibliográficos
Autor(a) principal: Almeida, Gildásio Castello
Data de Publicação: 2022
Outros Autores: Guido, Rodrigo Capobianco [UNESP], Balarin Silva, Henrique Monteiro, Brandão, Cinara Cássia, De Mattos, Luiz Carlos, Lopes, Bernardo T., Machado, Aydano Pamponet, Ambrósio, Renato
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
DOI: 10.1097/j.jcrs.0000000000000946
Texto Completo: http://dx.doi.org/10.1097/j.jcrs.0000000000000946
http://hdl.handle.net/11449/247723
Resumo: Purpose: To assess the efficiency of an index derived from multiple logistic regression analysis (MLRA) to measure differences in corneal tomography findings between subclinical keratoconus (KC) in 1 eye, corneal ectasia, and healthy corneas. Setting: 2 private Brazilian ophthalmological centers. Design: Multicenter case-control study. Methods: This study included 187 eyes with very asymmetric ectasia and with normal corneal topography and tomography (VAE-NTT) in the VAE-NTT group, 2296 eyes with healthy corneas in the control group (CG), and 410 eyes with ectasia in the ectasia group. An index, termed as Boosted Ectasia Susceptibility Tomography Index (BESTi), was derived using MLRA to identify a cutoff point to distinguish patients in the 3 groups. The groups were divided into 2 subgroups with an equal number of patients: validation set and external validation (EV) set. Results:2893 patients with 2893 eyes were included. BESTi had an area under the curve (AUC) of 0.91 with 86.02% sensitivity (Se) and 83.97% specificity (Sp) between CG and the VAE-NTT group in the EV set, which was significantly greater than those of the Belin-Ambrósio Deviation Index (BAD-D) (AUC: 0.81; Se: 66.67%; Sp: 82.67%; P <.0001) and Pentacam random forest index (PRFI) (AUC: 0.87; Se: 78.49%; Sp: 79.88%; P =.021). Conclusions: BESTi facilitated early detection of ectasia in subclinical KC and demonstrated higher Se and Sp than PRFI and BAD-D for detecting subclinical KC.
id UNSP_4c75daa9121cd603c83fc4c731926a66
oai_identifier_str oai:repositorio.unesp.br:11449/247723
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling New artificial intelligence index based on Scheimpflug corneal tomography to distinguish subclinical keratoconus from healthy corneasPurpose: To assess the efficiency of an index derived from multiple logistic regression analysis (MLRA) to measure differences in corneal tomography findings between subclinical keratoconus (KC) in 1 eye, corneal ectasia, and healthy corneas. Setting: 2 private Brazilian ophthalmological centers. Design: Multicenter case-control study. Methods: This study included 187 eyes with very asymmetric ectasia and with normal corneal topography and tomography (VAE-NTT) in the VAE-NTT group, 2296 eyes with healthy corneas in the control group (CG), and 410 eyes with ectasia in the ectasia group. An index, termed as Boosted Ectasia Susceptibility Tomography Index (BESTi), was derived using MLRA to identify a cutoff point to distinguish patients in the 3 groups. The groups were divided into 2 subgroups with an equal number of patients: validation set and external validation (EV) set. Results:2893 patients with 2893 eyes were included. BESTi had an area under the curve (AUC) of 0.91 with 86.02% sensitivity (Se) and 83.97% specificity (Sp) between CG and the VAE-NTT group in the EV set, which was significantly greater than those of the Belin-Ambrósio Deviation Index (BAD-D) (AUC: 0.81; Se: 66.67%; Sp: 82.67%; P <.0001) and Pentacam random forest index (PRFI) (AUC: 0.87; Se: 78.49%; Sp: 79.88%; P =.021). Conclusions: BESTi facilitated early detection of ectasia in subclinical KC and demonstrated higher Se and Sp than PRFI and BAD-D for detecting subclinical KC.Faculty of Medicine of São José do Rio Preto, São José do Rio PretoBase Hospital of São José do Rio Preto, São José do Rio PretoVisum Eye Center, São José do Rio PretoDepartment of Computer Science and Statistics Institute of Biosciences Letters and Exact Sciences São Paulo State University at São José do Rio PretoRio Claro Eye Institute, Rio ClaroDepartment of Civil Engineering and Industrial Design School of Engineering University of LiverpoolDepartment of Ophthalmology Federal University of São PauloComputing Institute Federal University of AlagoasDepartment of Ophthalmology Federal University the State of Rio de JaneiroDepartment of Computer Science and Statistics Institute of Biosciences Letters and Exact Sciences São Paulo State University at São José do Rio PretoFaculty of Medicine of São José do Rio PretoBase Hospital of São José do Rio PretoVisum Eye CenterUniversidade Estadual Paulista (UNESP)Rio Claro Eye InstituteUniversity of LiverpoolUniversidade de São Paulo (USP)Federal University of AlagoasFederal University the State of Rio de JaneiroAlmeida, Gildásio CastelloGuido, Rodrigo Capobianco [UNESP]Balarin Silva, Henrique MonteiroBrandão, Cinara CássiaDe Mattos, Luiz CarlosLopes, Bernardo T.Machado, Aydano PamponetAmbrósio, Renato2023-07-29T13:24:01Z2023-07-29T13:24:01Z2022-10-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article1168-1174http://dx.doi.org/10.1097/j.jcrs.0000000000000946Journal of Cataract and Refractive Surgery, v. 48, n. 10, p. 1168-1174, 2022.1873-45020886-3350http://hdl.handle.net/11449/24772310.1097/j.jcrs.00000000000009462-s2.0-85139535442Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengJournal of Cataract and Refractive Surgeryinfo:eu-repo/semantics/openAccess2023-07-29T13:24:01Zoai:repositorio.unesp.br:11449/247723Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T17:58:07.586393Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv New artificial intelligence index based on Scheimpflug corneal tomography to distinguish subclinical keratoconus from healthy corneas
title New artificial intelligence index based on Scheimpflug corneal tomography to distinguish subclinical keratoconus from healthy corneas
spellingShingle New artificial intelligence index based on Scheimpflug corneal tomography to distinguish subclinical keratoconus from healthy corneas
New artificial intelligence index based on Scheimpflug corneal tomography to distinguish subclinical keratoconus from healthy corneas
Almeida, Gildásio Castello
Almeida, Gildásio Castello
title_short New artificial intelligence index based on Scheimpflug corneal tomography to distinguish subclinical keratoconus from healthy corneas
title_full New artificial intelligence index based on Scheimpflug corneal tomography to distinguish subclinical keratoconus from healthy corneas
title_fullStr New artificial intelligence index based on Scheimpflug corneal tomography to distinguish subclinical keratoconus from healthy corneas
New artificial intelligence index based on Scheimpflug corneal tomography to distinguish subclinical keratoconus from healthy corneas
title_full_unstemmed New artificial intelligence index based on Scheimpflug corneal tomography to distinguish subclinical keratoconus from healthy corneas
New artificial intelligence index based on Scheimpflug corneal tomography to distinguish subclinical keratoconus from healthy corneas
title_sort New artificial intelligence index based on Scheimpflug corneal tomography to distinguish subclinical keratoconus from healthy corneas
author Almeida, Gildásio Castello
author_facet Almeida, Gildásio Castello
Almeida, Gildásio Castello
Guido, Rodrigo Capobianco [UNESP]
Balarin Silva, Henrique Monteiro
Brandão, Cinara Cássia
De Mattos, Luiz Carlos
Lopes, Bernardo T.
Machado, Aydano Pamponet
Ambrósio, Renato
Guido, Rodrigo Capobianco [UNESP]
Balarin Silva, Henrique Monteiro
Brandão, Cinara Cássia
De Mattos, Luiz Carlos
Lopes, Bernardo T.
Machado, Aydano Pamponet
Ambrósio, Renato
author_role author
author2 Guido, Rodrigo Capobianco [UNESP]
Balarin Silva, Henrique Monteiro
Brandão, Cinara Cássia
De Mattos, Luiz Carlos
Lopes, Bernardo T.
Machado, Aydano Pamponet
Ambrósio, Renato
author2_role author
author
author
author
author
author
author
dc.contributor.none.fl_str_mv Faculty of Medicine of São José do Rio Preto
Base Hospital of São José do Rio Preto
Visum Eye Center
Universidade Estadual Paulista (UNESP)
Rio Claro Eye Institute
University of Liverpool
Universidade de São Paulo (USP)
Federal University of Alagoas
Federal University the State of Rio de Janeiro
dc.contributor.author.fl_str_mv Almeida, Gildásio Castello
Guido, Rodrigo Capobianco [UNESP]
Balarin Silva, Henrique Monteiro
Brandão, Cinara Cássia
De Mattos, Luiz Carlos
Lopes, Bernardo T.
Machado, Aydano Pamponet
Ambrósio, Renato
description Purpose: To assess the efficiency of an index derived from multiple logistic regression analysis (MLRA) to measure differences in corneal tomography findings between subclinical keratoconus (KC) in 1 eye, corneal ectasia, and healthy corneas. Setting: 2 private Brazilian ophthalmological centers. Design: Multicenter case-control study. Methods: This study included 187 eyes with very asymmetric ectasia and with normal corneal topography and tomography (VAE-NTT) in the VAE-NTT group, 2296 eyes with healthy corneas in the control group (CG), and 410 eyes with ectasia in the ectasia group. An index, termed as Boosted Ectasia Susceptibility Tomography Index (BESTi), was derived using MLRA to identify a cutoff point to distinguish patients in the 3 groups. The groups were divided into 2 subgroups with an equal number of patients: validation set and external validation (EV) set. Results:2893 patients with 2893 eyes were included. BESTi had an area under the curve (AUC) of 0.91 with 86.02% sensitivity (Se) and 83.97% specificity (Sp) between CG and the VAE-NTT group in the EV set, which was significantly greater than those of the Belin-Ambrósio Deviation Index (BAD-D) (AUC: 0.81; Se: 66.67%; Sp: 82.67%; P <.0001) and Pentacam random forest index (PRFI) (AUC: 0.87; Se: 78.49%; Sp: 79.88%; P =.021). Conclusions: BESTi facilitated early detection of ectasia in subclinical KC and demonstrated higher Se and Sp than PRFI and BAD-D for detecting subclinical KC.
publishDate 2022
dc.date.none.fl_str_mv 2022-10-01
2023-07-29T13:24:01Z
2023-07-29T13:24:01Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://dx.doi.org/10.1097/j.jcrs.0000000000000946
Journal of Cataract and Refractive Surgery, v. 48, n. 10, p. 1168-1174, 2022.
1873-4502
0886-3350
http://hdl.handle.net/11449/247723
10.1097/j.jcrs.0000000000000946
2-s2.0-85139535442
url http://dx.doi.org/10.1097/j.jcrs.0000000000000946
http://hdl.handle.net/11449/247723
identifier_str_mv Journal of Cataract and Refractive Surgery, v. 48, n. 10, p. 1168-1174, 2022.
1873-4502
0886-3350
10.1097/j.jcrs.0000000000000946
2-s2.0-85139535442
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Journal of Cataract and Refractive Surgery
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 1168-1174
dc.source.none.fl_str_mv Scopus
reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv
_version_ 1822182326558261248
dc.identifier.doi.none.fl_str_mv 10.1097/j.jcrs.0000000000000946