Detection of Referable Diabetic Retinopathy using Machine Learning on Routine Clinical Data - Takeaways - MDSpire

Detection of Referable Diabetic Retinopathy using Machine Learning on Routine Clinical Data

  • By

  • Jeon, Young Joon

  • Song, Jae Shin

  • Borghare, Shubham

  • Lee, Youngju

  • Choi, Young Wook

  • Song, Junghan

  • Lim, Soo

  • Woo, Se Joon

  • April 13, 2026

  • 0 min

Share

  • 1

    A machine learning algorithm was developed to identify referable diabetic retinopathy (RDR) using standard clinical data.

  • 2

    The study involved 562 adults with diabetes, assessing their clinical and laboratory parameters for RDR prediction.

  • 3

    The random forest model achieved an AUROC of 0.932, indicating high efficacy in identifying RDR without imaging.

  • 4

    Fifteen predictors were identified, with age being the most significant factor influencing RDR risk.

  • 5

    This model can facilitate early RDR identification in resource-limited settings, enhancing clinical decision-making.

Original Source(s)

Detection of Referable Diabetic Retinopathy using Machine Learning on Routine Clinical Data

  • by Jeon, Young Joon , Song, Jae Shin , Borghare, Shubham , Lee, Youngju , Choi, Young Wook , Song, Junghan , Lim, Soo , Woo, Se Joon

  • April 13, 2026

Related Content

Could Wegovy Raise Optic Nerve Risk?

A pharmacovigilance analysis of FDA adverse event reports finds the strongest ischemic optic neuropathy reporting signal with high-dose semaglutide formulations, with higher adjusted odds reported in men.

Screening for Diabetic Retinopathy in a Rural High-Latitude Community in Northern Norway

Comparative study of the therapeutic effects of different medications on DM-associated dry eye syndrome after vitrectomy