Bibliographic citations
Castillo, D., (2022). Algoritmo del sistema de aprendizaje profundo usando retinografía como método de diagnostico precoz de neuropatía óptica glaucomatosa basado en la relación Copa/Disco y la regla ISNT [Tesis, Universidad Privada Antenor Orrego - UPAO]. https://hdl.handle.net/20.500.12759/9814
Castillo, D., Algoritmo del sistema de aprendizaje profundo usando retinografía como método de diagnostico precoz de neuropatía óptica glaucomatosa basado en la relación Copa/Disco y la regla ISNT [Tesis]. PE: Universidad Privada Antenor Orrego - UPAO; 2022. https://hdl.handle.net/20.500.12759/9814
@misc{renati/371066,
title = "Algoritmo del sistema de aprendizaje profundo usando retinografía como método de diagnostico precoz de neuropatía óptica glaucomatosa basado en la relación Copa/Disco y la regla ISNT",
author = "Castillo Castillo, Diana Edith",
publisher = "Universidad Privada Antenor Orrego - UPAO",
year = "2022"
}
Glaucomatous optic neuropathy is considered one of the leading causes of blindness worldwide, and the leading cause irreversibly, it is caused by damage to the optic nerve of the eye. Objective: To determine the diagnostic accuracy of the Deep Learning System algorithm to detect glaucomatous optic neuropathy using retinography. Methods: A systematic review and meta-analysis was carried out in the following databases: Pubmed, Scopus, Web of Science, Ovid-Medline, Ovid-Embase. The selection criteria were applied in two phases respectively: first by title and abstract and then by full text. After this, the most relevant characteristics of each study were extracted and the bias analysis was performed using QUADAS-2, to finally meta-analyze the results using Stata v14 software. Results: 300 results were obtained when searching the 5 databases, finally including 8. In the bias analysis, the most affected domain in most studies was patient selection; followed by that of the index test. Finally, when combining the results, a sensitivity of 0.90 with a 95% CI ranging from 0.86 to 0.94 and a specificity ranging from 0.93 with a 95% CI ranging from 0.90 to 0.96 were obtained. Conclusions: The use of deep learning systems for the detection of GON offers acceptable sensitivity and specificity with respect to detection capacity of specialized ophthalmologists.
This item is licensed under a Creative Commons License