The effectiveness of artificial intelligence-based automated grading and training system in education of manual detection of diabetic retinopathy
BackgroundThe purpose of this study is to develop an artificial intelligence (AI)-based automated diabetic retinopathy (DR) grading and training system from a real-world diabetic dataset of China, and in particular, to investigate its effectiveness as a learning tool of DR manual grading for medical...
Main Authors: | , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-11-01
|
Series: | Frontiers in Public Health |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fpubh.2022.1025271/full |
_version_ | 1811223260042362880 |
---|---|
author | Xu Qian Xu Qian Xu Qian Han Jingying Song Xian Zhao Yuqing Wu Lili Chu Baorui Guo Wei Zheng Yefeng Zhang Qiang Chu Chunyan Bian Cheng Ma Kai Qu Yi Qu Yi Qu Yi |
author_facet | Xu Qian Xu Qian Xu Qian Han Jingying Song Xian Zhao Yuqing Wu Lili Chu Baorui Guo Wei Zheng Yefeng Zhang Qiang Chu Chunyan Bian Cheng Ma Kai Qu Yi Qu Yi Qu Yi |
author_sort | Xu Qian |
collection | DOAJ |
description | BackgroundThe purpose of this study is to develop an artificial intelligence (AI)-based automated diabetic retinopathy (DR) grading and training system from a real-world diabetic dataset of China, and in particular, to investigate its effectiveness as a learning tool of DR manual grading for medical students.MethodsWe developed an automated DR grading and training system equipped with an AI-driven diagnosis algorithm to highlight highly prognostic related regions in the input image. Less experienced prospective physicians received pre- and post-training tests by the AI diagnosis platform. Then, changes in the diagnostic accuracy of the participants were evaluated.ResultsWe randomly selected 8,063 cases diagnosed with DR and 7,925 with non-DR fundus images from type 2 diabetes patients. The automated DR grading system we developed achieved accuracy, sensitivity/specificity, and AUC values of 0.965, 0.965/0.966, and 0.980 for moderate or worse DR (95 percent CI: 0.976–0.984). When the graders received assistance from the output of the AI system, the metrics were enhanced in varying degrees. The automated DR grading system helped to improve the accuracy of human graders, i.e., junior residents and medical students, from 0.947 and 0.915 to 0.978 and 0.954, respectively.ConclusionThe AI-based systemdemonstrated high diagnostic accuracy for the detection of DR on fundus images from real-world diabetics, and could be utilized as a training aid system for trainees lacking formal instruction on DR management. |
first_indexed | 2024-04-12T08:29:55Z |
format | Article |
id | doaj.art-b9f831a815a5442d93a69adc67ebab3e |
institution | Directory Open Access Journal |
issn | 2296-2565 |
language | English |
last_indexed | 2024-04-12T08:29:55Z |
publishDate | 2022-11-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Public Health |
spelling | doaj.art-b9f831a815a5442d93a69adc67ebab3e2022-12-22T03:40:14ZengFrontiers Media S.A.Frontiers in Public Health2296-25652022-11-011010.3389/fpubh.2022.10252711025271The effectiveness of artificial intelligence-based automated grading and training system in education of manual detection of diabetic retinopathyXu Qian0Xu Qian1Xu Qian2Han Jingying3Song Xian4Zhao Yuqing5Wu Lili6Chu Baorui7Guo Wei8Zheng Yefeng9Zhang Qiang10Chu Chunyan11Bian Cheng12Ma Kai13Qu Yi14Qu Yi15Qu Yi16Department of Geriatrics, Qilu Hospital of Shandong University, Jinan, ChinaKey Laboratory of Cardiovascular Proteomics of Shandong Province, Jinan, ChinaJinan Clinical Research Center for Geriatric Medicine (202132001), Jinan, ChinaSchool of Basic Medical Sciences, Shandong University, Jinan, ChinaDepartment of Geriatrics, Qilu Hospital of Shandong University, Jinan, ChinaDepartment of Geriatrics, Qilu Hospital of Shandong University, Jinan, ChinaDepartment of Geriatrics, Qilu Hospital of Shandong University, Jinan, ChinaDepartment of Geriatrics, Qilu Hospital of Shandong University, Jinan, ChinaLunan Eye Hospital, Linyi, ChinaTencent Healthcare, Shenzhen, ChinaTencent Healthcare, Shenzhen, ChinaTencent Healthcare, Shenzhen, ChinaTencent Healthcare, Shenzhen, ChinaTencent Healthcare, Shenzhen, ChinaDepartment of Geriatrics, Qilu Hospital of Shandong University, Jinan, ChinaKey Laboratory of Cardiovascular Proteomics of Shandong Province, Jinan, ChinaJinan Clinical Research Center for Geriatric Medicine (202132001), Jinan, ChinaBackgroundThe purpose of this study is to develop an artificial intelligence (AI)-based automated diabetic retinopathy (DR) grading and training system from a real-world diabetic dataset of China, and in particular, to investigate its effectiveness as a learning tool of DR manual grading for medical students.MethodsWe developed an automated DR grading and training system equipped with an AI-driven diagnosis algorithm to highlight highly prognostic related regions in the input image. Less experienced prospective physicians received pre- and post-training tests by the AI diagnosis platform. Then, changes in the diagnostic accuracy of the participants were evaluated.ResultsWe randomly selected 8,063 cases diagnosed with DR and 7,925 with non-DR fundus images from type 2 diabetes patients. The automated DR grading system we developed achieved accuracy, sensitivity/specificity, and AUC values of 0.965, 0.965/0.966, and 0.980 for moderate or worse DR (95 percent CI: 0.976–0.984). When the graders received assistance from the output of the AI system, the metrics were enhanced in varying degrees. The automated DR grading system helped to improve the accuracy of human graders, i.e., junior residents and medical students, from 0.947 and 0.915 to 0.978 and 0.954, respectively.ConclusionThe AI-based systemdemonstrated high diagnostic accuracy for the detection of DR on fundus images from real-world diabetics, and could be utilized as a training aid system for trainees lacking formal instruction on DR management.https://www.frontiersin.org/articles/10.3389/fpubh.2022.1025271/fullmedical image educationartificial intelligencediabetic retinopathymedical studentsdiagnosis |
spellingShingle | Xu Qian Xu Qian Xu Qian Han Jingying Song Xian Zhao Yuqing Wu Lili Chu Baorui Guo Wei Zheng Yefeng Zhang Qiang Chu Chunyan Bian Cheng Ma Kai Qu Yi Qu Yi Qu Yi The effectiveness of artificial intelligence-based automated grading and training system in education of manual detection of diabetic retinopathy Frontiers in Public Health medical image education artificial intelligence diabetic retinopathy medical students diagnosis |
title | The effectiveness of artificial intelligence-based automated grading and training system in education of manual detection of diabetic retinopathy |
title_full | The effectiveness of artificial intelligence-based automated grading and training system in education of manual detection of diabetic retinopathy |
title_fullStr | The effectiveness of artificial intelligence-based automated grading and training system in education of manual detection of diabetic retinopathy |
title_full_unstemmed | The effectiveness of artificial intelligence-based automated grading and training system in education of manual detection of diabetic retinopathy |
title_short | The effectiveness of artificial intelligence-based automated grading and training system in education of manual detection of diabetic retinopathy |
title_sort | effectiveness of artificial intelligence based automated grading and training system in education of manual detection of diabetic retinopathy |
topic | medical image education artificial intelligence diabetic retinopathy medical students diagnosis |
url | https://www.frontiersin.org/articles/10.3389/fpubh.2022.1025271/full |
work_keys_str_mv | AT xuqian theeffectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT xuqian theeffectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT xuqian theeffectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT hanjingying theeffectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT songxian theeffectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT zhaoyuqing theeffectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT wulili theeffectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT chubaorui theeffectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT guowei theeffectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT zhengyefeng theeffectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT zhangqiang theeffectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT chuchunyan theeffectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT biancheng theeffectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT makai theeffectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT quyi theeffectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT quyi theeffectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT quyi theeffectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT xuqian effectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT xuqian effectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT xuqian effectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT hanjingying effectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT songxian effectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT zhaoyuqing effectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT wulili effectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT chubaorui effectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT guowei effectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT zhengyefeng effectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT zhangqiang effectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT chuchunyan effectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT biancheng effectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT makai effectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT quyi effectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT quyi effectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy AT quyi effectivenessofartificialintelligencebasedautomatedgradingandtrainingsystemineducationofmanualdetectionofdiabeticretinopathy |