{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T01:53:35Z","timestamp":1781488415654,"version":"3.54.1"},"reference-count":50,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T00:00:00Z","timestamp":1781308800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Medicina"],"abstract":"<jats:p>Background and Objectives: Type 2 diabetes mellitus (T2DM) causes retinal microvascular changes that precede clinically apparent diabetic retinopathy (DR). We aimed to identify which optical coherence tomography angiography (OCTA) biomarkers best distinguish eyes with T2DM without clinical DR from healthy controls and to evaluate machine learning classifiers trained on a comprehensive 68-parameter OCTA panel. Materials and Methods: In this prospective case\u2013control study, 80 patients with T2DM without clinical DR and 33 controls underwent 3 \u00d7 3 mm macular OCTA using an Optovue RTVue Avanti System. After outlier screening, 221 eyes (155 T2DM, 66 controls) were analyzed. Sixty-eight OCTA parameters were extracted, covering FAZ morphometry (including foveal density FD-300), SCP and DCP vessel density and layer thickness, outer-retina and choriocapillaris flow, and a full retinal-thickness map. Between-group comparisons used the Mann\u2013Whitney U test with Benjamini\u2013Hochberg FDR correction. Logistic regression, random forest, and XGBoost classifiers were evaluated with patient-grouped 10-fold cross-validation; feature importance was quantified via SHAP. Results: Forty-two of 68 parameters reached FDR significance (q &lt; 0.05). Deep capillary plexus vessel density was the most discriminative family (whole image rb = \u22120.66, q = 2.5 \u00d7 10\u221213; parafovea rb = \u22120.64). FD-300 was reduced in T2DM (median 47.55% vs. 51.86%; rb = \u22120.57; q = 1.0 \u00d7 10\u221210) and emerged as the top SHAP feature (mean |SHAP| = 0.81). FAZ circularity decreased without FAZ-area enlargement, and outer-retina flow was paradoxically elevated (rb = +0.39), consistent with a projection artifact. XGBoost using all 68 features achieved a patient-grouped cross-validated AUC of approximately 0.91, compared with 0.85 for conventional SCP + DCP whole-image density. No parameter correlated with current HbA1c in T2DM (all q &gt; 0.98), and the well-controlled (&lt;7%) and poorly controlled (\u22657%) subgroups were indistinguishable across five of six principal biomarkers, consistent with metabolic memory. FD-300 remained independent after adjustment for hypertension, hyperlipidemia, and age (OR = 0.76; 95% CI 0.69\u20130.84; p &lt; 0.001). Conclusions: A multi-compartment OCTA panel outperforms conventional two-layer vessel-density metrics in detecting preclinical diabetic microvasculopathy, although external validation is required before clinical use. FD-300 is the single most informative biomarker, while choriocapillaris and retinal thickness measures provide complementary, compartment-specific signals. Because the OCTA signature is decoupled from the current HbA1c, screening should not be deferred in well-controlled T2DM.<\/jats:p>","DOI":"10.3390\/medicina62061153","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:44:58Z","timestamp":1781484298000},"page":"1153","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Foveal Density and Multi-Domain OCTA Biomarkers May Help Identify Preclinical Diabetic Microvasculopathy in Type 2 Diabetes Mellitus"],"prefix":"10.3390","volume":"62","author":[{"given":"Marko","family":"Zlatanovi\u0107","sequence":"first","affiliation":[{"name":"Ophthalmology Clinic, University Clinical Center Ni\u0161, Bulevar Dr Zorana \u0110in\u0111i\u0107a 48, 18000 Nis, Serbia"},{"name":"Department of Ophthalmology, Faculty of Medicine, University of Ni\u0161, Bulevar Dr Zorana \u0110in\u0111i\u0107a 81, 18000 Nis, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maja L. J.","family":"\u017divkovi\u0107","sequence":"additional","affiliation":[{"name":"Ophthalmology Clinic, University Clinical Center Ni\u0161, Bulevar Dr Zorana \u0110in\u0111i\u0107a 48, 18000 Nis, Serbia"},{"name":"Department of Ophthalmology, Faculty of Medicine, University of Ni\u0161, Bulevar Dr Zorana \u0110in\u0111i\u0107a 81, 18000 Nis, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2064-9520","authenticated-orcid":false,"given":"Nevena","family":"Zlatanovi\u0107","sequence":"additional","affiliation":[{"name":"Community Health Center Ni\u0161 in Ni\u0161, Vojvode Tankosi\u0107a 15, 18000 Nis, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mladen","family":"Brzakovi\u0107","sequence":"additional","affiliation":[{"name":"Special Hospital for Ophthalmology \u201cClinic Maja\u201d, Vizantijski Bulevar 8, 18000 Nis, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mihailo","family":"Jovanovi\u0107","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Faculty of Medicine, University of Kragujevac, Svetozara Markovi\u0107a 69, 34000 Kragujevac, Serbia"},{"name":"Ophthalmology Clinic, University Clinical Center Kragujevac, Zmaj Jovina 30, 34000 Kragujevac, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"109119","DOI":"10.1016\/j.diabres.2021.109119","article-title":"IDF Diabetes Atlas: Global, regional and country-level diabetes prevalence estimates for 2021 and projections for 2045","volume":"183","author":"Sun","year":"2022","journal-title":"Diabetes Res. Clin. Pract."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1580","DOI":"10.1016\/j.ophtha.2021.04.027","article-title":"Global Prevalence of Diabetic Retinopathy and Projection of Burden through 2045: Systematic Review and Meta-analysis","volume":"128","author":"Teo","year":"2021","journal-title":"Ophthalmology"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1016\/S2213-8587(18)30128-1","article-title":"Incidence and progression of diabetic retinopathy: A systematic review","volume":"7","author":"Sabanayagam","year":"2019","journal-title":"Lancet Diabetes Endocrinol."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Tan, T.E., and Wong, T.Y. (2023). Diabetic retinopathy: Looking forward to 2030. Front. Endocrinol., 13.","DOI":"10.3389\/fendo.2022.1077669"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1038\/s41572-025-00646-x","article-title":"Diabetic retinal disease","volume":"11","author":"Sivaprasad","year":"2025","journal-title":"Nat. Rev. Dis. Prim."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhang, N., Lin, P., Xing, Y., and Yang, N. (2024). Recent advances in the treatment and delivery system of diabetic retinopathy. Front. Endocrinol., 15.","DOI":"10.3389\/fendo.2024.1347864"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"101799","DOI":"10.1016\/j.redox.2020.101799","article-title":"Oxidative stress and diabetic retinopathy: Molecular mechanisms, pathogenetic role and therapeutic implications","volume":"37","author":"Kang","year":"2020","journal-title":"Redox Biol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1677","DOI":"10.1016\/S0161-6420(03)00475-5","article-title":"Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales","volume":"110","author":"Wilkinson","year":"2003","journal-title":"Ophthalmology"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1016\/j.ophtha.2020.10.008","article-title":"Updating the Staging System for Diabetic Retinal Disease","volume":"128","author":"Sun","year":"2021","journal-title":"Ophthalmology"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2216","DOI":"10.2337\/dc20-3097","article-title":"Understanding Metabolic Memory: The Prolonged Influence of Glycemia During the Diabetes Control and Complications Trial (DCCT) on Future Risks of Complications During the Study of the Epidemiology of Diabetes Interventions and Complications (EDIC)","volume":"44","author":"Lachin","year":"2021","journal-title":"Diabetes Care"},{"key":"ref_11","first-page":"CD006127","article-title":"Blood pressure control for diabetic retinopathy","volume":"3","author":"Do","year":"2023","journal-title":"Cochrane Database Syst. Rev."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"441","DOI":"10.2337\/db18-0567","article-title":"Multiethnic Genome-Wide Association Study of Diabetic Retinopathy Using Liability Threshold Modeling of Duration of Diabetes and Glycemic Control","volume":"68","author":"Pollack","year":"2019","journal-title":"Diabetes"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"100228","DOI":"10.1016\/j.xops.2022.100228","article-title":"Artificial Intelligence Detection of Diabetic Retinopathy: Subgroup Comparison of the EyeArt System with Ophthalmologists\u2019 Dilated Examinations","volume":"3","author":"Lim","year":"2022","journal-title":"Ophthalmol. Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1038\/s41433-019-0566-0","article-title":"Artificial intelligence for diabetic retinopathy screening: A review","volume":"34","author":"Grzybowski","year":"2020","journal-title":"Eye"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.preteyeres.2017.11.003","article-title":"Optical coherence tomography angiography","volume":"64","author":"Spaide","year":"2018","journal-title":"Prog. Retin. Eye Res."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1038\/s41433-020-01233-y","article-title":"Optical coherence tomography angiography in diabetic retinopathy: An updated review","volume":"35","author":"Sun","year":"2021","journal-title":"Eye"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"OCT211","DOI":"10.1167\/iovs.15-18793","article-title":"Normative Data for Vascular Density in Superficial and Deep Capillary Plexuses of Healthy Adults Assessed by Optical Coherence Tomography Angiography","volume":"57","author":"Coscas","year":"2016","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/j.ajo.2019.01.012","article-title":"Earliest Evidence of Preclinical Diabetic Retinopathy Revealed Using Optical Coherence Tomography Angiography Perfused Capillary Density","volume":"203","author":"Rosen","year":"2019","journal-title":"Am. J. Ophthalmol."},{"key":"ref_19","first-page":"7043251","article-title":"The Determination of Type 2 Diabetes Mellitus\u2019s Impact on the Density of Retinal Blood Vessels and the Choriocapillaris: Optical Coherence Tomography Angiography Study","volume":"2021","year":"2021","journal-title":"J. Ophthalmol."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Strauss, I., and Gaw\u0119cki, M. (2026). Biomarkers of Preclinical Diabetic Retinopathy Detected by OCT Angiography-A Descriptive Review. Life, 16.","DOI":"10.3390\/life16030496"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1167\/iovs.65.14.21","article-title":"Early Diabetic Retinopathy Evaluation With OCTA: A Study on Vascular Branching and Fragmentation","volume":"65","author":"Yu","year":"2024","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1016\/j.jclinepi.2007.11.008","article-title":"The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement: Guidelines for reporting observational studies","volume":"61","author":"Altman","year":"2008","journal-title":"J. Clin. Epidemiol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1194","DOI":"10.1016\/j.oret.2022.05.028","article-title":"Deep Capillary Geometric Perfusion Deficits on OCT Angiography Detect Clinically Referable Eyes with Diabetic Retinopathy","volume":"6","author":"Nesper","year":"2022","journal-title":"Ophthalmol. Retin."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"826","DOI":"10.1016\/j.oret.2019.04.027","article-title":"OCT Angiography Biomarkers for Predicting Visual Outcomes after Ranibizumab Treatment for Diabetic Macular Edema","volume":"3","author":"Hsieh","year":"2019","journal-title":"Ophthalmol. Retin."},{"key":"ref_26","first-page":"1545","article-title":"Foveal avascular zone area and parafoveal vessel density measurements in different stages of diabetic retinopathy by optical coherence tomography angiography","volume":"10","author":"Mastropasqua","year":"2017","journal-title":"Int. J. Ophthalmol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1167\/iovs.62.1.9","article-title":"Diabetic Macular Ischemia: Influence of Optical Coherence Tomography Angiography Parameters on Changes in Functional Outcomes Over One Year","volume":"62","author":"Tsai","year":"2021","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1107","DOI":"10.2147\/OPTH.S248881","article-title":"Correlations Between Optical Coherence Tomography Angiography Parameters and the Visual Acuity in Patients with Diabetic Retinopathy","volume":"14","author":"Abdelshafy","year":"2020","journal-title":"Clin. Ophthalmol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/j.visres.2016.09.019","article-title":"Acircularity index and axis ratio of the foveal avascular zone in diabetic eyes and healthy controls measured by optical coherence tomography angiography","volume":"139","author":"Krawitz","year":"2017","journal-title":"Vis. Res."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2212","DOI":"10.1167\/iovs.17-23498","article-title":"Evaluation of Automatically Quantified Foveal Avascular Zone Metrics for Diagnosis of Diabetic Retinopathy Using Optical Coherence Tomography Angiography","volume":"59","author":"Lu","year":"2018","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1167\/tvst.9.7.10","article-title":"Optical Coherence Tomography Angiography Projection Artifact Removal: Impact on Capillary Density and Interaction with Diabetic Retinopathy Severity","volume":"9","author":"Ashraf","year":"2020","journal-title":"Transl. Vis. Sci. Technol."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"271","DOI":"10.18502\/jovr.v16i2.9091","article-title":"Artifacts in Optical Coherence Tomography Angiography","volume":"16","author":"Anvari","year":"2021","journal-title":"J. Ophthalmic Vis. Res."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1319","DOI":"10.1136\/bjophthalmol-2021-320704","article-title":"Choriocapillaris flow deficit and the risk of referable diabetic retinopathy: A longitudinal SS-OCTA study","volume":"107","author":"Wang","year":"2023","journal-title":"Br. J. Ophthalmol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.ajo.2022.11.018","article-title":"Choriocapillaris Flow Deficit as a Biomarker for Diabetic Retinopathy and Diabetic Macular Edema: 3-Year Longitudinal Cohort","volume":"248","author":"Chen","year":"2023","journal-title":"Am. J. Ophthalmol."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1186\/s40942-024-00611-y","article-title":"Choriocapillaris flow deficit is associated with disease duration in type 2 diabetic patients without retinopathy: A cross-sectional study","volume":"10","author":"Spissinger","year":"2024","journal-title":"Int. J. Retin. Vitr."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1016\/j.visres.2017.03.003","article-title":"Diabetic retinopathy is a neurodegenerative disorder","volume":"139","author":"Lynch","year":"2017","journal-title":"Vis. Res."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1240","DOI":"10.1038\/s41433-019-0401-7","article-title":"Macular OCT-angiography parameters to predict the clinical stage of nonproliferative diabetic retinopathy: An exploratory analysis","volume":"33","author":"Rodrigues","year":"2019","journal-title":"Eye"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"5982","DOI":"10.1364\/BOE.9.005982","article-title":"Within-subject assessment of foveal avascular zone enlargement in different stages of diabetic retinopathy using en face OCT reflectance and OCT angiography","volume":"9","author":"Lynch","year":"2018","journal-title":"Biomed. Opt. Express"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"2547216","DOI":"10.1155\/2019\/2547216","article-title":"Early Detection of Microvascular Changes in Patients with Diabetes Mellitus without and with Diabetic Retinopathy: Comparison between Different Swept-Source OCT-A Instruments","volume":"2019","author":"Vujosevic","year":"2019","journal-title":"J. Diabetes Res."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1111\/aos.13570","article-title":"Macular thinning in prediabetes or type 2 diabetes without diabetic retinopathy: The Maastricht Study","volume":"96","author":"Schouten","year":"2018","journal-title":"Acta Ophthalmol."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"9","DOI":"10.2337\/dc13-2112","article-title":"The diabetes control and complications trial\/epidemiology of diabetes interventions and complications study at 30 years: Overview","volume":"37","author":"Nathan","year":"2014","journal-title":"Diabetes Care"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.visres.2017.02.011","article-title":"Diabetic retinopathy, metabolic memory and epigenetic modifications","volume":"139","author":"Kowluru","year":"2017","journal-title":"Vis. Res."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Kowluru, R.A., and Alka, K. (2023). Mitochondrial Quality Control and Metabolic Memory Phenomenon Associated with Continued Progression of Diabetic Retinopathy. Int. J. Mol. Sci., 24.","DOI":"10.3390\/ijms24098076"},{"key":"ref_44","first-page":"9516059","article-title":"Continuous Glucose Monitoring-Derived Metrics and Capillary Vessel Density in Subjects with Type 1 Diabetes without Diabetic Retinopathy","volume":"2023","author":"Carnevali","year":"2023","journal-title":"J. Diabetes Res."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"2813","DOI":"10.1038\/s41433-024-03173-3","article-title":"Identification of diabetic retinopathy classification using machine learning algorithms on clinical data and optical coherence tomography angiography","volume":"38","author":"Li","year":"2024","journal-title":"Eye"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1167\/tvst.9.2.20","article-title":"Ensemble Deep Learning for Diabetic Retinopathy Detection Using Optical Coherence Tomography Angiography","volume":"9","author":"Heisler","year":"2020","journal-title":"Transl. Vis. Sci. Technol."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1167\/tvst.9.2.58","article-title":"OCTA Multilayer and Multisector Peripapillary Microvascular Modeling for Diagnosing and Staging of Glaucoma","volume":"9","author":"Fokkinga","year":"2020","journal-title":"Transl. Vis. Sci. Technol."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"102919","DOI":"10.1016\/j.dsx.2023.102919","article-title":"Predicting the risk of diabetic retinopathy using explainable machine learning algorithms","volume":"17","author":"Islam","year":"2023","journal-title":"Diabetes Metab. Syndr."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1186\/s40001-025-02442-5","article-title":"Predicting diabetic retinopathy based on routine laboratory tests by machine learning algorithms","volume":"30","author":"Wan","year":"2025","journal-title":"Eur. J. Med. Res."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"142","DOI":"10.2337\/cd23-0019","article-title":"Clinical Implementation of Autonomous Artificial Intelligence Systems for Diabetic Eye Exams: Considerations for Success","volume":"42","author":"Wolf","year":"2024","journal-title":"Clin. Diabetes"}],"container-title":["Medicina"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1648-9144\/62\/6\/1153\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T01:35:33Z","timestamp":1781487333000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1648-9144\/62\/6\/1153"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,13]]},"references-count":50,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["medicina62061153"],"URL":"https:\/\/doi.org\/10.3390\/medicina62061153","relation":{},"ISSN":["1648-9144"],"issn-type":[{"value":"1648-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,13]]}}}