The value of deep learning in the diagnosis of diabetic retinopathy based on color fundus photographs: a meta-analysis_Chinese Journal of Evidence-Based Medicine

Authors：

HE Hongyue ¹ , LIU Jingxia ¹ , CHEN Jiao ¹ , LIU Lixin ¹ , YOU Wenli ¹ , LUO Wen ¹ ,  WANG Fang ²

1. Chengdu University of Traditional Chinese Medicine, Chengdu 610000, P. R. China;
2. Guang'an Hospital of Chinese Medicine, Guang'an 638400, P. R. China;

Corresponding?author：

WANG Fang, Email: 1697070757@qq.com

Keywords：

Deep learning; Diabetic retinopathy; Diagnostic test accuracy study; Meta-analysis

DOI：

10.7507/1672-2531.202504076

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To systematically review the value of deep learning (DL) on the diagnosis of diabetic retinopathy (DR) based on color fundus photographs. Methods The PubMed, Embase, Web of Science, Cochrane Library, IEEE, CNKI, VIP, WanFang Data databases were systematically searched to collect the studies on the use of DL in the diagnosis of DR from January 2019 to November 2024. Two reviewers independently screened literature, extracted data and assessed the risk of bias of the included studies. Meta-analysis was then performed by using RevMan 5.4.1, Meta-Disc 1.4 and Stata 16.0 software. Results A total of 16 literatures were included, involving 215 560 images. Meta-analysis results showed that the combined sensitivity of DL in diagnosing DR was 0.97 (95%CI 0.94 to 0.98), the specificity was 0.97 (95%CI 0.94 to 0.98), the AUC was 0.99 (95%CI 0.94 to 0.98), and the DOR was 852 (95%CI 403 to 1 803). Conclusion DL has a high diagnostic value for DR. However, there is a high degree of heterogeneity among different studies. In the future, more large-sample, high-quality studies can be included to confirm its clinical applicability.

1.	American Diabetes Association Professional Practice Committee. 2. Diagnosis and classification of diabetes: standards of care in diabetes-2025. Diabetes Care, 2025, 48(1 Suppl 1): S27-S49.
2.	Tan TE, Wong TY. Diabetic retinopathy: looking forward to 2030. Front Endocrinol (Lausanne), 2023, 13: 1077669.
3.	Cheung N, Mitchell P, Wong TY. Diabetic retinopathy. Lancet, 2010, 376(9735): 124-136.
4.	Diabetic retinopathy. Nature Reviews Disease Primers, 2016, 2(1): 16013.
5.	鄧宇軒, 葉雯青, 孫艷婷, 等. 中國糖尿病視網膜病變患病率的薈萃分析. 中華醫學雜志, 2020, 100(48): 3846-3852.
6.	張佳慧, 陳曉隆. 糖尿病視網膜病變的診斷和治療: 2016-2018年最新研究進展. 眼科新進展, 2018, 38(12): 1185-1190.
7.	Flaxel CJ, Adelman RA, Bailey ST, et al. Diabetic retinopathy preferred practice Pattern?. Ophthalmology, 2020, 127(1): P66-P145.
8.	Cole JB, Florez JC. Genetics of diabetes mellitus and diabetes complications. Nat Rev Nephrol, 2020, 16(7): 377-390.
9.	Dinpajhouh M, Seyyedsalehi SA. Automated detecting and severity grading of diabetic retinopathy using transfer learning and attention mechanism. Neural Comput Appl, 2023, 35(33): 23959-23971.
10.	孫石磊, 李明, 劉靜, 等. 深度學習在糖尿病視網膜病變分類領域的研究進展. 計算機工程與應用, 2024, 60(8): 16-30.
11.	Tsiknakis N, Theodoropoulos D, Manikis G, et al. Deep learning for diabetic retinopathy detection and classification based on fundus images: a review. Comput Biol Med, 2021, 135: 104599.
12.	Grauslund J. Diabetic retinopathy screening in the emerging era of artificial intelligence. Diabetologia, 2022, 65(9): 1415-1423.
13.	LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521(7553): 436-444.
14.	Jang HJ, Cho KO. Applications of deep learning for the analysis of medical data. Arch Pharm Res, 2019, 42(6): 492-504.
15.	康林, 劉喜, 程浩, 等. 深度學習在內鏡中識別萎縮性胃炎和腸上皮化生的診斷效能: 系統綜述和Meta分析. 海南醫學院學報, 2024, 30(17): 1335-1345.
16.	張倩, 曹云太, 王志潔, 等. 深度學習在早期胃癌內鏡圖像診斷中的研究進展. 實用醫學雜志, 2025, 41(14): 2160-2166.
17.	羅文斌, 鄭曄, 劉欣, 等. 基于DCE-MRI圖像深度學習模型鑒別診斷乳腺良惡性腫瘤的價值分析. 磁共振成像, 2024, 15(10): 22-29.
18.	宮阿娟, 潘天榮. 多病種眼底疾病診斷的深度學習策略討論. 計算機工程, 2024, 50(5): 363-372.
19.	Dong L, He W, Zhang R, et al. Artificial intelligence for screening of multiple retinal and optic nerve diseases. JAMA Netw Open, 2022, 5(5): e229960.
20.	McInnes MDF, Moher D, Thombs BD, et al. Preferred reporting items for a systematic review and meta-analysis of diagnostic test accuracy studies: the PRISMA-DTA statement. JAMA, 2018, 319(4): 388-396.
21.	Whiting PF, Rutjes AW, Westwood ME, et al. QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies. Ann Intern Med, 2011, 155(8): 529-536.
22.	Chetoui M, Akhloufi MA. Explainable end-to-end deep learning for diabetic retinopathy detection across multiple datasets. J Med Imaging (Bellingham), 2020, 7(4): 044503.
23.	Bodapati JD, Shaik NS, Naralasetti V. Composite deep neural network with gated-attention mechanism for diabetic retinopathy severity classification. J Ambient Intell Humaniz Comput, 2021, 12(10): 9825-9839.
24.	Mohammedhasan M, U?uz H. A new early stage diabetic retinopathy diagnosis model using deep convolutional neural networks and principal component analysis. Traitement du Signal, 2020, 37(5): 711-722.
25.	Sanjana S, Shadin NS, Farzana M. Automated diabetic retinopathy detection using transfer learning models. 2021 5th International Conference on Electrical Engineering and Information Communication Technology (ICEEICT), 2021: 1-6.
26.	Shakibania H, Raoufi S, Pourafkham B, et al. Dual branch deep learning network for detection and stage grading of diabetic retinopathy. Biomed Signal Process Control, 2024, 93: 106061.
27.	Sridhar S, Sanagavarapu S. Detection and prognosis evaluation of diabetic retinopathy using ensemble deep convolutional neural networks. Proceedings of the 2020 International Electronics Symposium (IES), 2020: F 29-30 Sept.
28.	Vives-Boix V, Ruiz-Fernández D. Diabetic retinopathy detection through convolutional neural networks with synaptic metaplasticity. Comput Methods Programs Biomed, 2021, 206: 106094.
29.	Zhang W, Zhong J, Yang S, et al. Automated identification and grading system of diabetic retinopathy using deep neural networks. Knowl Bas Sys, 2019, 175: 12-25.
30.	Kumar G, Chatterjee S, Chattopadhyay C. DRISTI: a hybrid deep neural network for diabetic retinopathy diagnosis. Signal Image Video Process, 2021, 15(8): 1679-1686.
31.	Nur-A-Alam M, Nasir MMK, Ahsan M, et al. A faster Rcnn-based diabetic retinopathy detection method using fused features from retina images. IEEE Access, 2023, 11: 124331-124349.
32.	Hu J, Wang H, Wang L, et al. Graph adversarial transfer learning for diabetic retinopathy classification. IEEE Access, 2022, 10: 119071-119083.
33.	Zhu D, Ge A, Chen X, et al. Supervised contrastive learning with angular margin for the detection and grading of diabetic retinopathy. Diagnostics (Basel), 2023, 13(14): 2389.
34.	朱小紅, 張云, 劉美玲, 等. GhostNet輕量級網絡在糖尿病視網膜病變診斷中的應用價值. 首都醫科大學學報, 2024, 45(4): 678-685.
35.	張子振, 劉明, 朱德江. 融合注意力機制和高效網絡的糖尿病視網膜病變識別與分類. 中國圖象圖形學報, 2020, 25(8): 1708-1718.
36.	高韶暉, 金學民, 趙朝霞, 等. 糖尿病視網膜病變人工智能機器人輔助診斷系統的建立及應用. 中華實驗眼科雜志, 2019, 37(8): 669-673.
37.	Teo ZL, Tham YC, Yu M, et al. Global prevalence of diabetic retinopathy and projection of burden through 2045: systematic review and meta-analysis. Ophthalmology, 2021, 128(11): 1580-1591.
38.	Zheng Y, Ley SH, Hu FB. Global aetiology and epidemiology of type 2 diabetes mellitus and its complications. Nat Rev Endocrinol, 2018, 14(2): 88-98.
39.	倪家遠. 基于決策樹的糖尿病診斷專家系統的研究與設計. 合肥: 安徽工業大學, 2016.
40.	Shan Y, Xu Y, Lin X, et al. Burden of vision loss due to diabetic retinopathy in China from 1990 to 2017: findings from the global burden of disease study. Acta Ophthalmol, 2021, 99(2): e267-e273.
41.	Gulshan V, Peng L, Coram M, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA, 2016, 316(22): 2402-2410.
42.	Raumviboonsuk P, Krause J, Chotcomwongse P, et al. Deep learning versus human graders for classifying diabetic retinopathy severity in a nationwide screening program. NPJ Digit Med, 2019, 2: 25.
43.	陳明惠, 王子昂, 李家昱, 等. 基于人工智能輔助糖尿病視網膜病變分類研究. 激光與光電子學進展, 2025, (12): 1-21.
44.	楊雨帆, 袁立明, 王珂, 等. 基于圖卷積網絡的糖尿病視網膜病變分級模型. 計算機科學, 2024, 51(S2): 461-465.
45.	郭瑩, 李紹杰. 基于小尺度跨層融合模型的糖尿病視網膜病變分類方法. 生物醫學工程學雜志, 2024, 41(5): 861-868.
46.	Ting DSW, Cheung CY, Lim G, et al. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA, 2017, 318(22): 2211-2223.
47.	Dai L, Wu L, Li H, et al. A deep learning system for detecting diabetic retinopathy across the disease spectrum. Nat Commun, 2021, 12(1): 3242.
48.	Arcadu F, Benmansour F, Maunz A, et al. Deep learning algorithm predicts diabetic retinopathy progression in individual patients. NPJ Digit Med, 2019, 2: 92.
49.	Dai L, Sheng B, Chen T, et al. A deep learning system for predicting time to progression of diabetic retinopathy. Nat Med, 2024, 30(2): 584-594.

1. American Diabetes Association Professional Practice Committee. 2. Diagnosis and classification of diabetes: standards of care in diabetes-2025. Diabetes Care, 2025, 48(1 Suppl 1): S27-S49.
2. Tan TE, Wong TY. Diabetic retinopathy: looking forward to 2030. Front Endocrinol (Lausanne), 2023, 13: 1077669.
3. Cheung N, Mitchell P, Wong TY. Diabetic retinopathy. Lancet, 2010, 376(9735): 124-136.
4. Diabetic retinopathy. Nature Reviews Disease Primers, 2016, 2(1): 16013.
5. 鄧宇軒, 葉雯青, 孫艷婷, 等. 中國糖尿病視網膜病變患病率的薈萃分析. 中華醫學雜志, 2020, 100(48): 3846-3852.
6. 張佳慧, 陳曉隆. 糖尿病視網膜病變的診斷和治療: 2016-2018年最新研究進展. 眼科新進展, 2018, 38(12): 1185-1190.
7. Flaxel CJ, Adelman RA, Bailey ST, et al. Diabetic retinopathy preferred practice Pattern?. Ophthalmology, 2020, 127(1): P66-P145.
8. Cole JB, Florez JC. Genetics of diabetes mellitus and diabetes complications. Nat Rev Nephrol, 2020, 16(7): 377-390.
9. Dinpajhouh M, Seyyedsalehi SA. Automated detecting and severity grading of diabetic retinopathy using transfer learning and attention mechanism. Neural Comput Appl, 2023, 35(33): 23959-23971.
10. 孫石磊, 李明, 劉靜, 等. 深度學習在糖尿病視網膜病變分類領域的研究進展. 計算機工程與應用, 2024, 60(8): 16-30.
11. Tsiknakis N, Theodoropoulos D, Manikis G, et al. Deep learning for diabetic retinopathy detection and classification based on fundus images: a review. Comput Biol Med, 2021, 135: 104599.
12. Grauslund J. Diabetic retinopathy screening in the emerging era of artificial intelligence. Diabetologia, 2022, 65(9): 1415-1423.
13. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521(7553): 436-444.
14. Jang HJ, Cho KO. Applications of deep learning for the analysis of medical data. Arch Pharm Res, 2019, 42(6): 492-504.
15. 康林, 劉喜, 程浩, 等. 深度學習在內鏡中識別萎縮性胃炎和腸上皮化生的診斷效能: 系統綜述和Meta分析. 海南醫學院學報, 2024, 30(17): 1335-1345.
16. 張倩, 曹云太, 王志潔, 等. 深度學習在早期胃癌內鏡圖像診斷中的研究進展. 實用醫學雜志, 2025, 41(14): 2160-2166.
17. 羅文斌, 鄭曄, 劉欣, 等. 基于DCE-MRI圖像深度學習模型鑒別診斷乳腺良惡性腫瘤的價值分析. 磁共振成像, 2024, 15(10): 22-29.
18. 宮阿娟, 潘天榮. 多病種眼底疾病診斷的深度學習策略討論. 計算機工程, 2024, 50(5): 363-372.
19. Dong L, He W, Zhang R, et al. Artificial intelligence for screening of multiple retinal and optic nerve diseases. JAMA Netw Open, 2022, 5(5): e229960.
20. McInnes MDF, Moher D, Thombs BD, et al. Preferred reporting items for a systematic review and meta-analysis of diagnostic test accuracy studies: the PRISMA-DTA statement. JAMA, 2018, 319(4): 388-396.
21. Whiting PF, Rutjes AW, Westwood ME, et al. QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies. Ann Intern Med, 2011, 155(8): 529-536.
22. Chetoui M, Akhloufi MA. Explainable end-to-end deep learning for diabetic retinopathy detection across multiple datasets. J Med Imaging (Bellingham), 2020, 7(4): 044503.
23. Bodapati JD, Shaik NS, Naralasetti V. Composite deep neural network with gated-attention mechanism for diabetic retinopathy severity classification. J Ambient Intell Humaniz Comput, 2021, 12(10): 9825-9839.
24. Mohammedhasan M, U?uz H. A new early stage diabetic retinopathy diagnosis model using deep convolutional neural networks and principal component analysis. Traitement du Signal, 2020, 37(5): 711-722.
25. Sanjana S, Shadin NS, Farzana M. Automated diabetic retinopathy detection using transfer learning models. 2021 5th International Conference on Electrical Engineering and Information Communication Technology (ICEEICT), 2021: 1-6.
26. Shakibania H, Raoufi S, Pourafkham B, et al. Dual branch deep learning network for detection and stage grading of diabetic retinopathy. Biomed Signal Process Control, 2024, 93: 106061.
27. Sridhar S, Sanagavarapu S. Detection and prognosis evaluation of diabetic retinopathy using ensemble deep convolutional neural networks. Proceedings of the 2020 International Electronics Symposium (IES), 2020: F 29-30 Sept.
28. Vives-Boix V, Ruiz-Fernández D. Diabetic retinopathy detection through convolutional neural networks with synaptic metaplasticity. Comput Methods Programs Biomed, 2021, 206: 106094.
29. Zhang W, Zhong J, Yang S, et al. Automated identification and grading system of diabetic retinopathy using deep neural networks. Knowl Bas Sys, 2019, 175: 12-25.
30. Kumar G, Chatterjee S, Chattopadhyay C. DRISTI: a hybrid deep neural network for diabetic retinopathy diagnosis. Signal Image Video Process, 2021, 15(8): 1679-1686.
31. Nur-A-Alam M, Nasir MMK, Ahsan M, et al. A faster Rcnn-based diabetic retinopathy detection method using fused features from retina images. IEEE Access, 2023, 11: 124331-124349.
32. Hu J, Wang H, Wang L, et al. Graph adversarial transfer learning for diabetic retinopathy classification. IEEE Access, 2022, 10: 119071-119083.
33. Zhu D, Ge A, Chen X, et al. Supervised contrastive learning with angular margin for the detection and grading of diabetic retinopathy. Diagnostics (Basel), 2023, 13(14): 2389.
34. 朱小紅, 張云, 劉美玲, 等. GhostNet輕量級網絡在糖尿病視網膜病變診斷中的應用價值. 首都醫科大學學報, 2024, 45(4): 678-685.
35. 張子振, 劉明, 朱德江. 融合注意力機制和高效網絡的糖尿病視網膜病變識別與分類. 中國圖象圖形學報, 2020, 25(8): 1708-1718.
36. 高韶暉, 金學民, 趙朝霞, 等. 糖尿病視網膜病變人工智能機器人輔助診斷系統的建立及應用. 中華實驗眼科雜志, 2019, 37(8): 669-673.
37. Teo ZL, Tham YC, Yu M, et al. Global prevalence of diabetic retinopathy and projection of burden through 2045: systematic review and meta-analysis. Ophthalmology, 2021, 128(11): 1580-1591.
38. Zheng Y, Ley SH, Hu FB. Global aetiology and epidemiology of type 2 diabetes mellitus and its complications. Nat Rev Endocrinol, 2018, 14(2): 88-98.
39. 倪家遠. 基于決策樹的糖尿病診斷專家系統的研究與設計. 合肥: 安徽工業大學, 2016.
40. Shan Y, Xu Y, Lin X, et al. Burden of vision loss due to diabetic retinopathy in China from 1990 to 2017: findings from the global burden of disease study. Acta Ophthalmol, 2021, 99(2): e267-e273.
41. Gulshan V, Peng L, Coram M, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA, 2016, 316(22): 2402-2410.
42. Raumviboonsuk P, Krause J, Chotcomwongse P, et al. Deep learning versus human graders for classifying diabetic retinopathy severity in a nationwide screening program. NPJ Digit Med, 2019, 2: 25.
43. 陳明惠, 王子昂, 李家昱, 等. 基于人工智能輔助糖尿病視網膜病變分類研究. 激光與光電子學進展, 2025, (12): 1-21.
44. 楊雨帆, 袁立明, 王珂, 等. 基于圖卷積網絡的糖尿病視網膜病變分級模型. 計算機科學, 2024, 51(S2): 461-465.
45. 郭瑩, 李紹杰. 基于小尺度跨層融合模型的糖尿病視網膜病變分類方法. 生物醫學工程學雜志, 2024, 41(5): 861-868.
46. Ting DSW, Cheung CY, Lim G, et al. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA, 2017, 318(22): 2211-2223.
47. Dai L, Wu L, Li H, et al. A deep learning system for detecting diabetic retinopathy across the disease spectrum. Nat Commun, 2021, 12(1): 3242.
48. Arcadu F, Benmansour F, Maunz A, et al. Deep learning algorithm predicts diabetic retinopathy progression in individual patients. NPJ Digit Med, 2019, 2: 92.
49. Dai L, Sheng B, Chen T, et al. A deep learning system for predicting time to progression of diabetic retinopathy. Nat Med, 2024, 30(2): 584-594.

Chinese Journal of Evidence-Based Medicine

Latest ArticlesThe value of deep learning in the diagnosis of diabetic retinopathy based on color fundus photographs: a meta-analysis

Abstract Full text Figures/Tables Video References Cited by

Format

Content