Cargando…

The Clinical Influence after Implementation of Convolutional Neural Network-Based Software for Diabetic Retinopathy Detection in the Primary Care Setting

Deep learning-based software is developed to assist physicians in terms of diagnosis; however, its clinical application is still under investigation. We integrated deep-learning-based software for diabetic retinopathy (DR) grading into the clinical workflow of an endocrinology department where endoc...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Yu-Hsuan, Sheu, Wayne Huey-Herng, Chou, Chien-Chih, Lin, Chun-Hsien, Cheng, Yuan-Shao, Wang, Chun-Yuan, Wu, Chieh Liang, Lee, I.-Te
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8035657/
https://www.ncbi.nlm.nih.gov/pubmed/33807545
http://dx.doi.org/10.3390/life11030200
_version_ 1783676746309042176
author Li, Yu-Hsuan
Sheu, Wayne Huey-Herng
Chou, Chien-Chih
Lin, Chun-Hsien
Cheng, Yuan-Shao
Wang, Chun-Yuan
Wu, Chieh Liang
Lee, I.-Te
author_facet Li, Yu-Hsuan
Sheu, Wayne Huey-Herng
Chou, Chien-Chih
Lin, Chun-Hsien
Cheng, Yuan-Shao
Wang, Chun-Yuan
Wu, Chieh Liang
Lee, I.-Te
author_sort Li, Yu-Hsuan
collection PubMed
description Deep learning-based software is developed to assist physicians in terms of diagnosis; however, its clinical application is still under investigation. We integrated deep-learning-based software for diabetic retinopathy (DR) grading into the clinical workflow of an endocrinology department where endocrinologists grade for retinal images and evaluated the influence of its implementation. A total of 1432 images from 716 patients and 1400 images from 700 patients were collected before and after implementation, respectively. Using the grading by ophthalmologists as the reference standard, the sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) to detect referable DR (RDR) were 0.91 (0.87–0.96), 0.90 (0.87–0.92), and 0.90 (0.87–0.93) at the image level; and 0.91 (0.81–0.97), 0.84 (0.80–0.87), and 0.87 (0.83–0.91) at the patient level. The monthly RDR rate dropped from 55.1% to 43.0% after implementation. The monthly percentage of finishing grading within the allotted time increased from 66.8% to 77.6%. There was a wide range of agreement values between the software and endocrinologists after implementation (kappa values of 0.17–0.65). In conclusion, we observed the clinical influence of deep-learning-based software on graders without the retinal subspecialty. However, the validation using images from local datasets is recommended before clinical implementation.
format Online
Article
Text
id pubmed-8035657
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-80356572021-04-11 The Clinical Influence after Implementation of Convolutional Neural Network-Based Software for Diabetic Retinopathy Detection in the Primary Care Setting Li, Yu-Hsuan Sheu, Wayne Huey-Herng Chou, Chien-Chih Lin, Chun-Hsien Cheng, Yuan-Shao Wang, Chun-Yuan Wu, Chieh Liang Lee, I.-Te Life (Basel) Article Deep learning-based software is developed to assist physicians in terms of diagnosis; however, its clinical application is still under investigation. We integrated deep-learning-based software for diabetic retinopathy (DR) grading into the clinical workflow of an endocrinology department where endocrinologists grade for retinal images and evaluated the influence of its implementation. A total of 1432 images from 716 patients and 1400 images from 700 patients were collected before and after implementation, respectively. Using the grading by ophthalmologists as the reference standard, the sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) to detect referable DR (RDR) were 0.91 (0.87–0.96), 0.90 (0.87–0.92), and 0.90 (0.87–0.93) at the image level; and 0.91 (0.81–0.97), 0.84 (0.80–0.87), and 0.87 (0.83–0.91) at the patient level. The monthly RDR rate dropped from 55.1% to 43.0% after implementation. The monthly percentage of finishing grading within the allotted time increased from 66.8% to 77.6%. There was a wide range of agreement values between the software and endocrinologists after implementation (kappa values of 0.17–0.65). In conclusion, we observed the clinical influence of deep-learning-based software on graders without the retinal subspecialty. However, the validation using images from local datasets is recommended before clinical implementation. MDPI 2021-03-05 /pmc/articles/PMC8035657/ /pubmed/33807545 http://dx.doi.org/10.3390/life11030200 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) ).
spellingShingle Article
Li, Yu-Hsuan
Sheu, Wayne Huey-Herng
Chou, Chien-Chih
Lin, Chun-Hsien
Cheng, Yuan-Shao
Wang, Chun-Yuan
Wu, Chieh Liang
Lee, I.-Te
The Clinical Influence after Implementation of Convolutional Neural Network-Based Software for Diabetic Retinopathy Detection in the Primary Care Setting
title The Clinical Influence after Implementation of Convolutional Neural Network-Based Software for Diabetic Retinopathy Detection in the Primary Care Setting
title_full The Clinical Influence after Implementation of Convolutional Neural Network-Based Software for Diabetic Retinopathy Detection in the Primary Care Setting
title_fullStr The Clinical Influence after Implementation of Convolutional Neural Network-Based Software for Diabetic Retinopathy Detection in the Primary Care Setting
title_full_unstemmed The Clinical Influence after Implementation of Convolutional Neural Network-Based Software for Diabetic Retinopathy Detection in the Primary Care Setting
title_short The Clinical Influence after Implementation of Convolutional Neural Network-Based Software for Diabetic Retinopathy Detection in the Primary Care Setting
title_sort clinical influence after implementation of convolutional neural network-based software for diabetic retinopathy detection in the primary care setting
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8035657/
https://www.ncbi.nlm.nih.gov/pubmed/33807545
http://dx.doi.org/10.3390/life11030200
work_keys_str_mv AT liyuhsuan theclinicalinfluenceafterimplementationofconvolutionalneuralnetworkbasedsoftwarefordiabeticretinopathydetectionintheprimarycaresetting
AT sheuwaynehueyherng theclinicalinfluenceafterimplementationofconvolutionalneuralnetworkbasedsoftwarefordiabeticretinopathydetectionintheprimarycaresetting
AT chouchienchih theclinicalinfluenceafterimplementationofconvolutionalneuralnetworkbasedsoftwarefordiabeticretinopathydetectionintheprimarycaresetting
AT linchunhsien theclinicalinfluenceafterimplementationofconvolutionalneuralnetworkbasedsoftwarefordiabeticretinopathydetectionintheprimarycaresetting
AT chengyuanshao theclinicalinfluenceafterimplementationofconvolutionalneuralnetworkbasedsoftwarefordiabeticretinopathydetectionintheprimarycaresetting
AT wangchunyuan theclinicalinfluenceafterimplementationofconvolutionalneuralnetworkbasedsoftwarefordiabeticretinopathydetectionintheprimarycaresetting
AT wuchiehliang theclinicalinfluenceafterimplementationofconvolutionalneuralnetworkbasedsoftwarefordiabeticretinopathydetectionintheprimarycaresetting
AT leeite theclinicalinfluenceafterimplementationofconvolutionalneuralnetworkbasedsoftwarefordiabeticretinopathydetectionintheprimarycaresetting
AT liyuhsuan clinicalinfluenceafterimplementationofconvolutionalneuralnetworkbasedsoftwarefordiabeticretinopathydetectionintheprimarycaresetting
AT sheuwaynehueyherng clinicalinfluenceafterimplementationofconvolutionalneuralnetworkbasedsoftwarefordiabeticretinopathydetectionintheprimarycaresetting
AT chouchienchih clinicalinfluenceafterimplementationofconvolutionalneuralnetworkbasedsoftwarefordiabeticretinopathydetectionintheprimarycaresetting
AT linchunhsien clinicalinfluenceafterimplementationofconvolutionalneuralnetworkbasedsoftwarefordiabeticretinopathydetectionintheprimarycaresetting
AT chengyuanshao clinicalinfluenceafterimplementationofconvolutionalneuralnetworkbasedsoftwarefordiabeticretinopathydetectionintheprimarycaresetting
AT wangchunyuan clinicalinfluenceafterimplementationofconvolutionalneuralnetworkbasedsoftwarefordiabeticretinopathydetectionintheprimarycaresetting
AT wuchiehliang clinicalinfluenceafterimplementationofconvolutionalneuralnetworkbasedsoftwarefordiabeticretinopathydetectionintheprimarycaresetting
AT leeite clinicalinfluenceafterimplementationofconvolutionalneuralnetworkbasedsoftwarefordiabeticretinopathydetectionintheprimarycaresetting