Article

Evaluating medical AI models beyond predictive performance: a diabetic retinopathy screening case study

2026-06-11

Abstract excerpt

<title>Abstract</title> <p> Predictive metrics are widely used to evaluate artificial intelligence (AI)-based screening tools, yet their clinical reliability requires a more comprehensive assessment across multiple aspects, including robustness and calibration. Using diabetic retinopathy (DR) screening as an exemplar case study, we simulated a model development and update scenario to reflect realistic deployment...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 6b74fd03-d478-52b3-ae1a-d5f8ea3efd8c
DOI: 10.21203/rs.3.rs-9848475/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Evaluating medical AI models beyond predictive performance: a diabetic retinopathy screening case studyDOI 10.21203/rs.3.rs-9848475/v1Read

Real-World Diagnostic Accuracy of Fully Autonomous, FDA-Approved Artificial Intelligence Systems for Diabetic Retinopathy Screening in the United States: A Systematic Review and Meta-AnalysisSemantic proximity Read

Comparison of foundation models and transfer learning strategies for diabetic retinopathy classificationSemantic proximity Read

Artificial Intelligence for the Diagnosis of De Novo Diabetic Retinopathy: A Scoping Review of Global EvidenceSemantic proximity Read

How does AI detect diabetic retinopathy from retinal photos? A heatmap analysis of 54 deep learning modelsSemantic proximity Read

Autonomous Screening for Laser Photocoagulation in Fundus Images Using Deep LearningSemantic proximity Read

Metadata Insufficiency and Reporting Deficits in Medical AI Generalization: A Meta-Research Audit Using Non-Parametric Bootstrap ResamplingSemantic proximity Read

Diagnostic decisions of specialist optometrists exposed to ambiguous deep-learning outputsSemantic proximity Read

UWF-FM: A Foundation Model for Comprehensive Ultra-Widefield Retinal AssessmentSemantic proximity Read

Evaluating ChatGPT-4’s Role in Diagnosing and Grading Diabetic Retinopathy from Fundus ImagesSemantic proximity Read

AI-Augmented Fundus Disease Screening by Non-Ophthalmologist Physicians: A Paired Before–After StudySemantic proximity Read

Toward Personalized Diabetic Retinopathy Screening: Deep Learning Fundus Image Analysis and Clinical Risk FactorsSemantic proximity Read

Screening Diabetic Retinopathy Using an Automated Retinal Image Analysis System in Mexico: Independent and Assistive use CasesSemantic proximity Read