SAFECARD: Safety Assessment Framework for Evaluating Clinical AI in Realistic Decision-Making — Study Protocol v2.9

Read full text Summarise with VIRAT
Authors: Olaf Göing
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

SAFECARD (Safety Assessment Framework for Evaluating Clinical AI in Realistic Decision-Making) is a prospective paired-comparison evaluation framework for clinical AI safety assessment. The OCC-VIM framework operationalizes six safety dimensions: Omission (O), Commission (C), Confession/Calibration (C²), Values in Model (V), Anchoring Bias (A), and Gender Bias (G). Output: machine-readable JSON with traffic-light safety flags (GREEN/AMBER/RED). Designed for EU AI Act Art. 9/13/26 compliance. CRIMSON imaging substudy (CXR) included. Protocol version 2.9, March 2026. Scientific Coordinator: O. Göing. Principal Investigator: Prof. Dr. med. J. Brachmann, Sana Medical School Coburg.

Fields of Study & Subjects

Artificial Intelligence in Healthcare and Education Ethics and Social Impacts of AI Safety Systems Engineering in Autonomy

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
30 March 2026
Language
EN