Evaluation of Artificial Intelligence–Based Grading of Diabetic Retinopathy in Primary Care | Zendy

Yogesan Kanagasingam | Zendy; Di Xiao | Zendy; Janardhan Vignarajan | Zendy; Amita Preetham | Zendy; MeiLing TayKearney | Zendy; Ateev Mehrotra | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Evaluation of Artificial Intelligence–Based Grading of Diabetic Retinopathy in Primary Care

Author(s) -

Yogesan Kanagasingam,

Di Xiao,

Janardhan Vignarajan,

Amita Preetham,

MeiLing TayKearney,

Ateev Mehrotra

Publication year - 2018

Publication title -

jama network open

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 3.278

H-Index - 39

ISSN - 2574-3805

DOI - 10.1001/jamanetworkopen.2018.2665

Subject(s) - medicine , diabetic retinopathy , false positive paradox , referral , grading (engineering) , retinopathy , clinical practice , diabetes mellitus , disease , gold standard (test) , primary care , optometry , pediatrics , ophthalmology , artificial intelligence , family medicine , computer science , civil engineering , engineering , endocrinology

Key Points Question How will an artificial intelligence (AI)–based grading system for diabetic retinopathy perform in a real-world clinical setting? Findings In a diagnostic study evaluating 193 patients (386 images), the AI system judged 17 as having diabetic retinopathy of sufficient severity to require referral. While the system correctly identified the 2 patients with true disease (severe diabetic retinopathy), the positive predictive value was only 12%, with 15 patients misclassified as needing referral. Meaning Grading of diabetic retinopathy using AI has both potential benefits and challenges, and further study in real-world settings is needed.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research