Your browser doesn't support javascript.
loading
Diabetic Retinopathy Screening Using Artificial Intelligence and Handheld Smartphone-Based Retinal Camera.
Malerbi, Fernando Korn; Andrade, Rafael Ernane; Morales, Paulo Henrique; Stuchi, José Augusto; Lencione, Diego; de Paulo, Jean Vitor; Carvalho, Mayana Pereira; Nunes, Fabrícia Silva; Rocha, Roseanne Montargil; Ferraz, Daniel A; Belfort, Rubens.
Afiliação
  • Malerbi FK; Department of Ophthalmology and Visual Sciences, Federal University of São Paulo, São Paulo, Brazil.
  • Andrade RE; Instituto Paulista de Estudos e Pesquisas em Oftalmologia, IPEPO, Vision Institute, São Paulo, Brazil.
  • Morales PH; Department of Ophthalmology and Visual Sciences, Federal University of São Paulo, São Paulo, Brazil.
  • Stuchi JA; Hospital de Olhos Beira Rio, Itabuna, BA, Brazil.
  • Lencione D; Department of Ophthalmology and Visual Sciences, Federal University of São Paulo, São Paulo, Brazil.
  • de Paulo JV; Instituto Paulista de Estudos e Pesquisas em Oftalmologia, IPEPO, Vision Institute, São Paulo, Brazil.
  • Carvalho MP; Phelcom Technologies, São Carlos, Brazil.
  • Nunes FS; Phelcom Technologies, São Carlos, Brazil.
  • Rocha RM; Phelcom Technologies, São Carlos, Brazil.
  • Ferraz DA; State University of Santa Cruz, Ilhéus, BA, Brazil.
  • Belfort R; State University of Santa Cruz, Ilhéus, BA, Brazil.
J Diabetes Sci Technol ; 16(3): 716-723, 2022 05.
Article em En | MEDLINE | ID: mdl-33435711
BACKGROUND: Portable retinal cameras and deep learning (DL) algorithms are novel tools adopted by diabetic retinopathy (DR) screening programs. Our objective is to evaluate the diagnostic accuracy of a DL algorithm and the performance of portable handheld retinal cameras in the detection of DR in a large and heterogenous type 2 diabetes population in a real-world, high burden setting. METHOD: Participants underwent fundus photographs of both eyes with a portable retinal camera (Phelcom Eyer). Classification of DR was performed by human reading and a DL algorithm (PhelcomNet), consisting of a convolutional neural network trained on a dataset of fundus images captured exclusively with the portable device; both methods were compared. We calculated the area under the curve (AUC), sensitivity, and specificity for more than mild DR. RESULTS: A total of 824 individuals with type 2 diabetes were enrolled at Itabuna Diabetes Campaign, a subset of 679 (82.4%) of whom could be fully assessed. The algorithm sensitivity/specificity was 97.8 % (95% CI 96.7-98.9)/61.4 % (95% CI 57.7-65.1); AUC was 0·89. All false negative cases were classified as moderate non-proliferative diabetic retinopathy (NPDR) by human grading. CONCLUSIONS: The DL algorithm reached a good diagnostic accuracy for more than mild DR in a real-world, high burden setting. The performance of the handheld portable retinal camera was adequate, with over 80% of individuals presenting with images of sufficient quality. Portable devices and artificial intelligence tools may increase coverage of DR screening programs.
Assuntos
Palavras-chave
Texto completo
Adicionar na Minha BVS
Imprimir
XML
PubMed Links
Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Diabetes Mellitus Tipo 2 / Retinopatia Diabética Tipo de estudo: Diagnostic_studies / Prognostic_studies / Screening_studies Limite: Humans Idioma: En Revista: J Diabetes Sci Technol Assunto da revista: ENDOCRINOLOGIA Ano de publicação: 2022 Tipo de documento: Article País de afiliação: Brasil País de publicação: Estados Unidos
Texto completo
Adicionar na Minha BVS
Imprimir
XML
PubMed Links
Buscar no Google

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Diabetes Mellitus Tipo 2 / Retinopatia Diabética Tipo de estudo: Diagnostic_studies / Prognostic_studies / Screening_studies Limite: Humans Idioma: En Revista: J Diabetes Sci Technol Assunto da revista: ENDOCRINOLOGIA Ano de publicação: 2022 Tipo de documento: Article País de afiliação: Brasil País de publicação: Estados Unidos