Development of a risk stratification tool for rapidly progressive diabetic retinopathy in type 2 diabetes - Takeaways - MDSpire

Development of a risk stratification tool for rapidly progressive diabetic retinopathy in type 2 diabetes

  • By

  • Aiping Gu

  • Zhichao Yan

  • Yi Wu

  • Yanying Li

  • Renlong Liang

  • Xiaodi Tang

  • Mengke Li

  • June 19, 2026

  • 0 min

Share

  • 1

    A nomogram was developed to predict rapidly progressive diabetic retinopathy (PDR) in type 2 diabetes mellitus (T2DM) using multiple clinical factors.

  • 2

    Key predictors included diabetes duration, HbA1c, urinary protein, GDF15, DRSS grade, and foveal avascular zone area.

  • 3

    The study involved 342 T2DM patients, divided into training (240) and validation (102) sets for model development and assessment.

  • 4

    Random Forest achieved the highest validation AUC of 0.780, outperforming Gradient Boosting Machine and multivariable logistic regression.

  • 5

    The nomogram demonstrated good calibration and clinical utility, aiding in the early identification of high-risk individuals for PDR.

Original Source(s)

Development of a risk stratification tool for rapidly progressive diabetic retinopathy in type 2 diabetes

  • by Aiping Gu, Zhichao Yan, Yi Wu, Yanying Li, Renlong Liang, Xiaodi Tang, Mengke Li

  • June 19, 2026

Related Content

Retinal Imaging Model Aids CAD Detection

Fundus-based model showed moderate-to-good accuracy and improved performance when combined with clinical risk factors in a high-risk cohort

Visual Impairment and Cardiovascular Risk Factors in Hispanic and Latino Adults

AI Tool May Cut Macular Edema Referrals

An artificial intelligence–based optical coherence tomography pathway met noninferiority criteria for false-positive diabetic macular edema referrals and was associated with fewer referral decisions in a randomized clinical trial.