Repositori institucional URV
| Autor/es de la URV: | Puig Valls, Domènec Savi / Romero Aroca, Pedro / Valls Mateu, Aïda |
| Autor según el artículo: | Romero-Aroca, P; Verges-Puig, R; de la Torre, J; Valls, A; Relaño-Barambio, N; Puig, D; Baget-Bernaldiz, M |
| Direcció de correo del autor: | domenec.puig@urv.cat domenec.puig@urv.cat pedro.romero@urv.cat pedro.romero@urv.cat aida.valls@urv.cat aida.valls@urv.cat |
| Identificador del autor: | 0000-0002-0562-4205 0000-0002-0562-4205 0000-0002-7061-8987 0000-0002-7061-8987 0000-0003-3616-7809 0000-0003-3616-7809 |
| Año de publicación de la revista: | 2020-08-01 |
| Tipo de publicación: | Journal Publications |
| ISSN: | 15305627 |
| Referencia de l'ítem segons les normes APA: | Romero-Aroca, P; Verges-Puig, R; de la Torre, J; Valls, A; Relaño-Barambio, N; Puig, D; Baget-Bernaldiz, M (2020). Validation of a Deep Learning Algorithm for Diabetic Retinopathy. Telemedicine And E-Health, 26(8), 1001-1009. DOI: 10.1089/tmj.2019.0137 |
| Referencia al articulo segun fuente origial: | Telemedicine And E-Health. 26 (8): 1001-1009 |
| Resumen: | Background: To validate our deep learning algorithm (DLA) to read diabetic retinopathy (DR) retinographies. Introduction: Currently DR detection is made by retinography; due to its increasing diabetes mellitus incidence we need to find systems that help us to screen DR. Materials and Methods: The DLA was built and trained using 88,702 images from EyePACS, 1,748 from Messidor-2, and 19,230 from our own population. For validation a total of 38,339 retinographies from 17,669 patients (obtained from our DR screening databases) were read by a DLA and compared by four senior retina ophthalmologists for detecting any-DR and referable-DR. We determined the values of Cohen's weighted Kappa (CWK) index, sensitivity (S), specificity (SP), positive predictive value (PPV) and negative predictive value (NPV), and errors type I and II. Results: The results of the DLA to detect any-DR were: CWK = 0.886 +/- 0.004 (95% confidence interval [CI] 0.879-0.894), S = 0.967%, SP = 0.976%, PPV = 0.836%, and NPV = 0.996%. The error type I = 0.024, and the error type II = 0.004. Likewise, the referable-DR results were: CWK = 0.809 (95% CI 0.798-0.819), S = 0.998, SP = 0.968, PPV = 0.701, NPV = 0.928, error type I = 0.032, and error type II = 0.001. Discussion: Our DLA can be used as a high confidence diagnostic tool to help in DR screening, especially when it might be difficult for ophthalmologists or other professionals to identify. It can identify patients with any-DR and those that should be referred. Conclusions: The DLA can be valid to aid in screening of DR. |
| DOI del artículo: | 10.1089/tmj.2019.0137 |
| Departamento: | Enginyeria Informàtica i Matemàtiques |
| URL Documento de licencia: | https://repositori.urv.cat/ca/proteccio-de-dades/ |
| Áreas temáticas: | Medicine (miscellaneous) Health information management Health informatics Health care sciences & services General medicine Ciência da computação |
| Palabras clave: | System Sensitivity and specificity Screening of diabetic retinopathy Quality education Prevalence Ophthalmologists Mass screening Humans Guidelines Family physicians Diagnostic techniques, ophthalmological Diabetic retinopathy Diabetes mellitus Deep learning Convolutional neural network Algorithms Agreement diabetic retinopathy deep learning convolutional neural network |
| Entidad: | Universitat Rovira i Virgili |
| Fecha de alta del registro: | 2026-05-09 |
| Busca tu registro en: |  |
© 2011 Universitat Rovira i Virgili