Home // eTELEMED 2025, The Seventeenth International Conference on eHealth, Telemedicine, and Social Medicine // View article

Method for Retrospective Analysis of Clinical Outcomes After Removal of Radiologist Assessment of AI-Positive Skeletal X-rays

Authors:
Kristian Malm-Nicolaisen
Rune Pedersen
Asbjørn Johansen Fagerlund

Keywords: artificial intelligence; diagnostic imaging; clinical workflow; patient outcomes.

Abstract:
This retrospective in-progress study presents a method for evaluating the clinical impact of removing routine radiologist assessments of AI-flagged (“AI-positive”) skeletal X-rays at Vestre Viken Health Trust, which recently implemented the BoneView AI system. Over a five-month period, orthopedic surgeons or radiologists prospectively identified False Positives (FPs), and comprehensive chart reviews assessed whether omitting radiologist input compromised patient safety or led to unnecessary interventions. In the current phase, an estimated 20-40 FP cases will be analyzed for treatment outcomes, resource utilization, and potential misdiagnoses. The findings will inform evidence-based strategies for integrating AI into radiological workflows, guiding institutions in balancing efficiency with the need for robust diagnostic oversight.

Pages: 18 to 21

Copyright: Copyright (c) IARIA, 2025

Publication date: May 18, 2025

Published in: conference

ISSN: 2308-4359

ISBN: 978-1-68558-270-8

Location: Nice, France

Dates: from May 18, 2025 to May 22, 2025