Health AI Central
Share:
Peer-Reviewed Publication
AJR Am J Roentgenol2026;1-11.July 8, 2026Journal Article

Predicting the Value of Radiology Artificial Intelligence Applications: Large-Scale Predeployment Evaluation of a Portfolio of Models.

David B Larson1, Jason A Poff2, Sriyesh Krishnan2, Jerome Avondo3, Bonnie A Armstrong1, Hye Sun Na1, Akshay Chaudhari1, Nina Kottler2
1Department of Radiology, AI Development and Evaluation (AIDE) Lab, Stanford University School of Medicine, 453 Quarry Rd, Mail Code 5659, Stanford, CA 94304.
2Clinical Artificial Intelligence Team, Radiology Partners, Nashville, TN.
3Aidoc, Tel Aviv-Yafo, Israel.
PubMed DOI

Abstract

BACKGROUND. Real-world performance of radiology artificial intelligence (AI) applications frequently diverges from previously reported results, creating challenges in anticipating a model's clinical value and impact. OBJECTIVE. The purpose of this study was to develop a structured predeployment evaluation method for radiology AI models that combines standard performance metrics with new augmentati…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.