Deep learning system to predict the 5-year risk of high myopia using fundus imaging in children
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , , , , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.21/15482 |
Resumo: | Our study aims to identify children at risk of developing high myopia for timely assessment and intervention, preventing myopia progression and complications in adulthood through the development of a deep learning system (DLS). Using a school-based cohort in Singapore comprising 998 children (aged 6-12 years old), we train and perform primary validation of the DLS using 7456 baseline fundus images of 1878 eyes; with external validation using an independent test dataset of 821 baseline fundus images of 189 eyes together with clinical data (age, gender, race, parental myopia, and baseline spherical equivalent (SE)). We derive three distinct algorithms - image, clinical, and mix (image + clinical) models to predict high myopia development (SE ≤ -6.00 diopter) during teenage years (5 years later, age 11-17). Model performance is evaluated using the area under the receiver operating curve (AUC). Our image models (Primary dataset AUC 0.93-0.95; Test dataset 0.91-0.93), clinical models (Primary dataset AUC 0.90-0.97; Test dataset 0.93-0.94) and mixed (image + clinical) models (Primary dataset AUC 0.97; Test dataset 0.97-0.98) achieve clinically acceptable performance. The addition of 1 year SE progression variable has minimal impact on the DLS performance (clinical model AUC 0.98 versus 0.97 in the primary dataset, 0.97 versus 0.94 in the test dataset; mixed model AUC 0.99 versus 0.97 in the primary dataset, 0.95 versus 0.98 in test dataset). Thus, our DLS allows prediction of the development of high myopia by teenage years amongst school-going children. This has potential utility as a clinical decision support tool to identify "at-risk" children for early intervention. |
id |
RCAP_b8128ff236ed2397245aa0adcdf80a86 |
---|---|
oai_identifier_str |
oai:repositorio.ipl.pt:10400.21/15482 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Deep learning system to predict the 5-year risk of high myopia using fundus imaging in childrenOrthopticsMyopiaChildrenFundus imagingOur study aims to identify children at risk of developing high myopia for timely assessment and intervention, preventing myopia progression and complications in adulthood through the development of a deep learning system (DLS). Using a school-based cohort in Singapore comprising 998 children (aged 6-12 years old), we train and perform primary validation of the DLS using 7456 baseline fundus images of 1878 eyes; with external validation using an independent test dataset of 821 baseline fundus images of 189 eyes together with clinical data (age, gender, race, parental myopia, and baseline spherical equivalent (SE)). We derive three distinct algorithms - image, clinical, and mix (image + clinical) models to predict high myopia development (SE ≤ -6.00 diopter) during teenage years (5 years later, age 11-17). Model performance is evaluated using the area under the receiver operating curve (AUC). Our image models (Primary dataset AUC 0.93-0.95; Test dataset 0.91-0.93), clinical models (Primary dataset AUC 0.90-0.97; Test dataset 0.93-0.94) and mixed (image + clinical) models (Primary dataset AUC 0.97; Test dataset 0.97-0.98) achieve clinically acceptable performance. The addition of 1 year SE progression variable has minimal impact on the DLS performance (clinical model AUC 0.98 versus 0.97 in the primary dataset, 0.97 versus 0.94 in the test dataset; mixed model AUC 0.99 versus 0.97 in the primary dataset, 0.95 versus 0.98 in test dataset). Thus, our DLS allows prediction of the development of high myopia by teenage years amongst school-going children. This has potential utility as a clinical decision support tool to identify "at-risk" children for early intervention.Springer NatureRCIPLFoo, Li LianLim, Gilbert Yong SanLança, CarlaWong, Chee WaiHoang, Quan V.Zhang, Xiu JuanYam, Jason C.Schmetterer, LeopoldChia, AudreyWong, Tien YinTing, Daniel S. W.Saw, Seang-MeiAng, Marcus2023-02-03T16:35:18Z2023-012023-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.21/15482engFoo LL, Lim GY, Lança C, Wong CW, Hoang QV, Zhang XJ, et al. Deep learning system to predict the 5-year risk of high myopia using fundus imaging in children. NPJ Digit Med. 2023;6(1):10.10.1038/s41746-023-00752-8info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-08-03T10:13:04Zoai:repositorio.ipl.pt:10400.21/15482Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T20:23:08.849276Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Deep learning system to predict the 5-year risk of high myopia using fundus imaging in children |
title |
Deep learning system to predict the 5-year risk of high myopia using fundus imaging in children |
spellingShingle |
Deep learning system to predict the 5-year risk of high myopia using fundus imaging in children Foo, Li Lian Orthoptics Myopia Children Fundus imaging |
title_short |
Deep learning system to predict the 5-year risk of high myopia using fundus imaging in children |
title_full |
Deep learning system to predict the 5-year risk of high myopia using fundus imaging in children |
title_fullStr |
Deep learning system to predict the 5-year risk of high myopia using fundus imaging in children |
title_full_unstemmed |
Deep learning system to predict the 5-year risk of high myopia using fundus imaging in children |
title_sort |
Deep learning system to predict the 5-year risk of high myopia using fundus imaging in children |
author |
Foo, Li Lian |
author_facet |
Foo, Li Lian Lim, Gilbert Yong San Lança, Carla Wong, Chee Wai Hoang, Quan V. Zhang, Xiu Juan Yam, Jason C. Schmetterer, Leopold Chia, Audrey Wong, Tien Yin Ting, Daniel S. W. Saw, Seang-Mei Ang, Marcus |
author_role |
author |
author2 |
Lim, Gilbert Yong San Lança, Carla Wong, Chee Wai Hoang, Quan V. Zhang, Xiu Juan Yam, Jason C. Schmetterer, Leopold Chia, Audrey Wong, Tien Yin Ting, Daniel S. W. Saw, Seang-Mei Ang, Marcus |
author2_role |
author author author author author author author author author author author author |
dc.contributor.none.fl_str_mv |
RCIPL |
dc.contributor.author.fl_str_mv |
Foo, Li Lian Lim, Gilbert Yong San Lança, Carla Wong, Chee Wai Hoang, Quan V. Zhang, Xiu Juan Yam, Jason C. Schmetterer, Leopold Chia, Audrey Wong, Tien Yin Ting, Daniel S. W. Saw, Seang-Mei Ang, Marcus |
dc.subject.por.fl_str_mv |
Orthoptics Myopia Children Fundus imaging |
topic |
Orthoptics Myopia Children Fundus imaging |
description |
Our study aims to identify children at risk of developing high myopia for timely assessment and intervention, preventing myopia progression and complications in adulthood through the development of a deep learning system (DLS). Using a school-based cohort in Singapore comprising 998 children (aged 6-12 years old), we train and perform primary validation of the DLS using 7456 baseline fundus images of 1878 eyes; with external validation using an independent test dataset of 821 baseline fundus images of 189 eyes together with clinical data (age, gender, race, parental myopia, and baseline spherical equivalent (SE)). We derive three distinct algorithms - image, clinical, and mix (image + clinical) models to predict high myopia development (SE ≤ -6.00 diopter) during teenage years (5 years later, age 11-17). Model performance is evaluated using the area under the receiver operating curve (AUC). Our image models (Primary dataset AUC 0.93-0.95; Test dataset 0.91-0.93), clinical models (Primary dataset AUC 0.90-0.97; Test dataset 0.93-0.94) and mixed (image + clinical) models (Primary dataset AUC 0.97; Test dataset 0.97-0.98) achieve clinically acceptable performance. The addition of 1 year SE progression variable has minimal impact on the DLS performance (clinical model AUC 0.98 versus 0.97 in the primary dataset, 0.97 versus 0.94 in the test dataset; mixed model AUC 0.99 versus 0.97 in the primary dataset, 0.95 versus 0.98 in test dataset). Thus, our DLS allows prediction of the development of high myopia by teenage years amongst school-going children. This has potential utility as a clinical decision support tool to identify "at-risk" children for early intervention. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-02-03T16:35:18Z 2023-01 2023-01-01T00:00:00Z |
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://hdl.handle.net/10400.21/15482 |
url |
http://hdl.handle.net/10400.21/15482 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Foo LL, Lim GY, Lança C, Wong CW, Hoang QV, Zhang XJ, et al. Deep learning system to predict the 5-year risk of high myopia using fundus imaging in children. NPJ Digit Med. 2023;6(1):10. 10.1038/s41746-023-00752-8 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Springer Nature |
publisher.none.fl_str_mv |
Springer Nature |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799133504391348224 |