2026-10-13T14:51:33Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33979576 2026-09-24T04:35:03Z category_658 portal_316 item_type_3 month_year_09_2026

Data Sheet 1_Integration of ultra-widefield optical coherence tomography angiography images and clinical indicators for identifying early-stage diabetic retinopathy in type 2 diabetes.pdf Cong Zhang (582922) Li Wang (15202) Shimeng Huang (6590543) Ruoxuan Zheng (12729292) Jingjing Li (7654) Xiaotong Sun (6535064) Shuang Wu (148427) Tianpeng Zhang (706243) Xinyu Zhang (14029) Qian Xu (119888) Yangwen Chen (25102051) Chengye Xu (24714997) Hongyu Kuang (9774767) Cell Metabolism clinical factors diabetic retinopathy multimodal deep learning type 2 diabetes mellitus ultra-widefield optical coherence tomography angiography Background<p>Diabetic retinopathy (DR) is a common microvascular complication of diabetes and a leading cause of irreversible vision loss among working-age adults, making early detection essential for preventing permanent visual impairment. This study aimed to identify early-stage DR in patients with type 2 diabetes mellitus (T2DM) using a multimodal deep learning (DL) approach integrating ultra-widefield optical coherence tomography angiography (UW-OCTA) images with clinical factors.</p>Methods<p>This cross-sectional study enrolled patients with T2DM from an urban tertiary hospital and a community primary care setting between July 2024 and April 2026. Baseline demographic and laboratory data and 26 × 21 mm UW-OCTA images were obtained. Automatically segmented UW-OCTA slabs were compared to identify the most discriminative layer. Clinical variables were selected using between-group comparisons, XGBoost-based Shapley additive explanations (SHAP), and multivariable logistic regression. Selected clinical variables and UW-OCTA image features were integrated into a multimodal model. Performance was evaluated in internal test and external validation sets using receiver operating characteristic analysis. Gradient-weighted class activation mapping (Grad-CAM) was used for visualization.</p>Results<p>Overall, 1,676 patients were included: 1,047 and 453 tertiary-care patients formed the training and internal test sets, and 176 community-based patients formed the external validation set. Diabetes duration, glycated hemoglobin, low-density lipoprotein cholesterol and systolic blood pressure were independently associated with early-stage DR. The retinal slab showed the best image-only performance with AUCs of 0.906 (95%CI: 0.870-0.942) and 0.828 (95%CI: 0.725-0.931) in the internal and external sets. The multimodal model achieved AUCs of 0.921 (95%CI: 0.887-0.954) and 0.849 (95%CI: 0.760-0.953), outperforming image-only and clinical-only models. Grad-CAM highlighted macular and peripheral retinal regions.</p>Conclusion<p>Integrating UW-OCTA with clinical factors improved early-stage DR identification in T2DM and may support non-invasive risk assessment.</p> 2026-09-24T04:35:03Z Dataset Dataset 10.3389/fendo.2026.1941613.s001 https://figshare.com/articles/dataset/Data_Sheet_1_Integration_of_ultra-widefield_optical_coherence_tomography_angiography_images_and_clinical_indicators_for_identifying_early-stage_diabetic_retinopathy_in_type_2_diabetes_pdf/33979576 CC BY 4.0