A machine learning model for diabetic retinopathy risk stratification using routine blood and urine parameters: insights into kidney-eye crosstalk - Scorecard - MDSpire

A machine learning model for diabetic retinopathy risk stratification using routine blood and urine parameters: insights into kidney-eye crosstalk

  • By

  • Yong Wang

  • Ling Yao

  • Tianpeng Chen

  • Qianyu Zhang

  • Xin Cao

  • Jiayi Gu

  • Sijie Bao

  • Xiaojuan Chen

  • Cheng Cao

  • June 17, 2026

  • 0 min

Share

Clinical Scorecard: Development and External Validation of a Machine Learning Model for Assessing Diabetic Retinopathy Risk Utilizing Standard Blood and Urine Biomarkers: Exploring Kidney-Eye Interactions

At a Glance

CategoryDetail
Condition
Key MechanismsChronic hyperglycemia-induced oxidative stress and inflammatory responses (source needed)
Target Population
Care SettingResource-constrained settings (source needed)

Key Highlights

  • Development of a machine learning model for DR risk stratification using routine clinical biomarkers
  • LightGBM algorithm achieved an AUC of 0.841 for external validation
  • Identification of 14 key predictors related to glycemic control, renal function, and lipid metabolism
  • Probabilistic dependency structure (source needed)
  • Framework provides a web-based clinical decision support system

Guideline-Based Recommendations

Diagnosis

    Management

    • Focus on early intervention to reduce severe vision loss risk (source needed)

    Monitoring & Follow-up

      Risks

        Patient & Prescribing Data

        Diabetic patients at risk for diabetic retinopathy

        Integration of predictive ML with clinical biomarkers for early screening

        Clinical Best Practices

        • Incorporate machine learning models in routine clinical practice for DR risk assessment (source needed)
        • Utilize accessible biomarkers for early detection and intervention strategies

        Related Resources & Content

        Original Source(s)

        A machine learning model for diabetic retinopathy risk stratification using routine blood and urine parameters: insights into kidney-eye crosstalk

        • by Yong Wang, Ling Yao, Tianpeng Chen, Qianyu Zhang, Xin Cao, Jiayi Gu, Sijie Bao, Xiaojuan Chen, Cheng Cao

        • June 17, 2026

        Related Content

        AACE 2026: AI moves from hype to reality in diabetes care

        "Right now, AI is more of a copilot, but the long-term vision is something much closer to autopilot."

        Widefield SS-OCTA-detected retinal vascular changes and their correlation with DME in diabetes

        AI Screening for Diabetic Retinopathy