Logo do repositório
 
Publicação

Deep learning system to predict the 5-year risk of high myopia using fundus imaging in children

2023-12Artigo científico Acesso aberto
Ver registo simples
dc.contributor.authorFoo, Li Lian
dc.contributor.authorLim, Gilbert Yong San
dc.contributor.authorLanca, Carla
dc.contributor.authorWong, Chee Wai
dc.contributor.authorHoang, Quan V.
dc.contributor.authorZhang, Xiu Juan
dc.contributor.authorYam, Jason C.
dc.contributor.authorSchmetterer, Leopold
dc.contributor.authorChia, Audrey
dc.contributor.authorWong, Tien Yin
dc.contributor.authorTing, Daniel S.W.
dc.contributor.authorSaw, Seang Mei
dc.contributor.authorAng, Marcus
dc.contributor.institutionComprehensive Health Research Centre (CHRC) - Pólo ENSP
dc.contributor.institutionCentro de Investigação em Saúde Pública (CISP/PHRC)
dc.contributor.institutionEscola Nacional de Saúde Pública (ENSP)
dc.contributor.pblNature Publishing Group
dc.date.accessioned2023-04-17T22:19:55Z
dc.date.available2023-04-17T22:19:55Z
dc.date.issued2023-12
dc.descriptionFunding Information: This work is supported by National Medical Research Council Individual Research Grant (NMRC/0975/2005), National Medical Research Council Center Grant (NMRC/CG/C010A/2017_SERI) and Nurturing Clinician Researcher Scheme Program Grant Award (05/FY2021/P2/11-A92). Publisher Copyright: © 2023, The Author(s).
dc.description.abstractOur 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 of 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 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 primary dataset, 0.97 versus 0.94 in test dataset; mixed model AUC 0.99 versus 0.97 in 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.en
dc.description.versionpublishersversion
dc.description.versionpublished
dc.format.extent1422114
dc.identifier.doi10.1038/s41746-023-00752-8
dc.identifier.otherPURE: 58501758
dc.identifier.otherPURE UUID: 06f3599e-4055-451e-ac9d-815d267bc412
dc.identifier.otherScopus: 85146884981
dc.identifier.otherWOS: 000920868800001
dc.identifier.otherPubMed: 36702878
dc.identifier.otherPubMedCentral: PMC9879938
dc.identifier.urihttp://hdl.handle.net/10362/151889
dc.identifier.urlhttps://www.scopus.com/pages/publications/85146884981
dc.language.isoeng
dc.peerreviewedyes
dc.subjectMedicine (miscellaneous)
dc.subjectHealth Informatics
dc.subjectComputer Science Applications
dc.subjectHealth Information Management
dc.titleDeep learning system to predict the 5-year risk of high myopia using fundus imaging in childrenen
dc.typejournal article
degois.publication.issue1
degois.publication.titlenpj Digital Medicine
degois.publication.volume6
dspace.entity.typePublication
rcaap.rightsopenAccess

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
Foo_NPJ_Dig_Med_2023_6_1_10.pdf
Tamanho:
1.36 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

Home collection (ENSP)