Authors
Petrachkov D.V.1, Altemirova Kh.Kh.1, Gorkavenko F.V.2, 3, Zenkin N.S.1, Pavlov V.G.1, Sidamonidze A.L.1, Khanova A.N.1, Chizhonkova E.A.1
1 M.M. Krasnov Research Institute of Eye Diseases, Moscow
2 Center for Healthcare Quality Assessment and Control, Moscow
3 Russian Medical Academy of Continuous Professional, Moscow
Abstract
Background. Diabetic retinopathy is now regarded as a disease of the retinal neurovascular unit in which microangiopathy, neurodegeneration and glial activation develop in an interrelated manner, which justifies the term diabetic angioretinoneuropathy. Current classifications describe disease severity but do not identify patients at high risk of progression, and the pathogenetic differences between type 1 and type 2 diabetes are usually not taken into account in prognostic models.
Aim. To develop and validate predictive criteria for one-year progression of diabetic angioretinoneuropathy based on imaging and systemic biomarkers, separately for type 1 diabetes, type 2 diabetes and a combined cohort.
Material and methods. A total of 731 patients (731 eyes) without proliferative retinopathy were followed prospectively; optical coherence tomography, optical coherence tomography angiography and systemic parameters yielded 102 candidate predictors. Multivariable logistic regression models were built separately for each diabetes type and for the combined cohort with a 75%/25% training/validation split and class balancing; performance was assessed by macro-F-measure, sensitivity, specificity and negative predictive value, and the robustness of the predictors was verified with random forest models.
Results. On the validation samples the macro-F-measure was 0.96 in type 1 diabetes (sensitivity 100%, specificity 97.3%, negative predictive value 100%), 0.85 in type 2 diabetes (90.5, 87.8 and 97%, respectively) and 0.91 in the combined cohort (91.2, 94.6 and 97.9%). The predictors were hyperreflective foci, relative ganglion cell complex thickness and central retinal thickness in type 1 diabetes; the fractal dimension of the superficial capillary plexus, the thickness of the ganglion cell complex and of the ganglion cell layer with the inner plexiform layer, and the estimated glomerular filtration rate in type 2 diabetes; and hyperreflective foci, the thickness of the same neuronal layers and the estimated glomerular filtration rate in the combined model.
Conclusion. The models provide high accuracy of one-year progression prediction and reveal a type-specific architecture of predictive criteria: neurodegenerative and neuroinflammatory biomarkers predominate in type 1 diabetes, whereas a combination of neurodegenerative, microvascular and systemic indicators predominates in type 2 diabetes.
Keywords: diabetic angioretinoneuropathy, diabetic retinopathy, type 1 diabetes mellitus, type 2 diabetes mellitus, predictive criteria, biomarkers, optical coherence tomography, optical coherence tomography angiography, logistic regression, glomerular filtration rate.
References
1. Kropp M, Golubnitschaja O, Mazurakova A, et al. Diabetic retinopathy as the leading cause of blindness and early predictor of cascading complications-risks and mitigation. EPMA J. 2023; 14(1): 21-42. doi: 10.1007/s13167-023-00314-8.
2. 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. doi: 10.1016/j.ophtha.2021.04.027.
3. Neroev VV, Zaitseva OV, Mikhailova LA. Diabetic retinopathy prevalence in the Russian Federation according to all-Russia statistics. Russian Ophthalmological Journal. 2023; 16(3): 7-11. (In Russ.) doi: 10.21516/2072-0076-2023-16-3-7-11.
4. Antonetti DA, Klein R, Gardner TW. Diabetic retinopathy. N Engl J Med. 2012; 366(13): 1227-1239. doi: 10.1056/NEJMra1005073.
5. Velieva IA. On the causes of the diabetic retinopathy progression after panretinal laser photocoagulation. Ophthalmology. Eastern Europe. 2022; 12(2): 218-225. (In Russ.) doi: 10.34883/PI.2022.12.2.029.
6. Abcouwer SF, Gardner TW. Diabetic retinopathy: loss of neuroretinal adaptation tells the story. Ann N Y Acad Sci. 2014; 1311: 174-190. doi: 10.1111/nyas.12412.
7. Fayzrakhmanov RR, Shishkin MM, Saraeva SN. A modern perspective on the pathogenesis of proliferative diabetic retinopathy. Vestn Oftalmol. 2025; 141(1): 92-98. (In Russ.) doi: 10.17116/oftalma202514101192.
8. Wilkinson CP, Ferris FL 3rd, Klein RE, et al. Global Diabetic Retinopathy Project Group. Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales. Ophthalmology. 2003; 110(9): 1677-1682. doi: 10.1016/S0161-6420(03)00475-5.
9. Sun JK, Aiello LP, Abràmoff MD, et al. Updating the Staging System for Diabetic Retinal Disease. Ophthalmology. 2021; 128(4): 490-493. doi: 10.1016/j.ophtha.2020.10.008.
10. Petrachkov DV, Budzinskaya MV, Filippov VM, Gorkavenko FV. Prediction of Diabetic Retinopathy Progression Based on Logistic Regression Model. Ophthalmology in Russia. 2025; 22(4): 866-875. (In Russ.) doi: 10.18008/1816-5095-2025-4-866-875.
11. Midena E, Torresin T, Velotta E, et al. OCT Hyperreflective Retinal Foci in Diabetic Retinopathy: A Semi-Automatic Detection Comparative Study. Front Immunol. 2021; 12: 613051. doi: 10.3389/fimmu.2021.613051.
12. Gundogan FC, Akay F, Uzun S, et al. Early Neurodegeneration of the Inner Retinal Layers in Type 1 Diabetes Mellitus. Ophthalmologica. 2016; 235(3): 125-132. doi: 10.1159/000442826.
13. Gong X, Wang W, Li W, et al. Association between renal function and retinal neurodegeneration in Chinese patients with type 2 diabetes mellitus. Ann Transl Med. 2021; 9(7): 560. doi: 10.21037/atm-20-6957.
14. Bianco L, Arrigo A, Aragona E, et al. Neuroinflammation and neurodegeneration in diabetic retinopathy. Front Aging Neurosci. 2022; 14: 937999. doi: 10.3389/fnagi.2022.937999.
15. Shah J, Tan B, Wong D, et al. Evaluation of thickness of individual macular retinal layers in diabetic eyes from optical coherence tomography. Sci Rep. 2024; 14(1): 17909. doi: 10.1038/s41598-024-68552-y.
16. Hashmi S, Lopez J, Chiu B, et al. Fractal Dimension Analysis of OCTA Images of Diabetic Retinopathy Using Circular Mass-Radius Method. Ophthalmic Surg Lasers Imaging Retina. 2021; 52(3): 116-122. doi: 10.3928/23258160-20210302-01.
17. Sun Z, Tang F, Wong R, et al. OCT Angiography Metrics Predict Progression of Diabetic Retinopathy and Development of Diabetic Macular Edema: A Prospective Study. Ophthalmology. 2019; 126(12): 1675-1684. doi: 10.1016/j.ophtha.2019.06.016.
18. Park HC, Lee YK, Cho A, et al. Diabetic retinopathy is a prognostic factor for progression of chronic kidney disease in the patients with type 2 diabetes mellitus. PLoS One. 2019; 14(7): e0220506. doi: 10.1371/journal.pone.0220506.
19. Fursova AZh, Derbeneva AS, Vasilyeva MA, et al. Structural and microvascular changes in the retina and choroid in patients with chronic kidney disease. Vestn Oftalmol. 2021; 137(6): 99-108. (In Russ.) doi: 10.17116/oftalma202113706199.
20. Cho A, Park HC, Lee YK, et al. Progression of Diabetic Retinopathy and Declining Renal Function in Patients with Type 2 Diabetes. J Diabetes Res. 2020; 2020: 8784139. doi: 10.1155/2020/8784139.


