Work

A call for clinical evaluation of open-source algorithms in radiology

Year: 2025

Type: article

Abstract: • The radiology AI literature is dominated by retrospective, technical model development. • A critical gap exists for clinical validation, especially for the plethora of available open-source models. • Open-source models, despite their abundance, are overwhelmingly untested in real clinical settings. • A paradigm shift towards clinically meaningful evaluation of open-source AI is urgently needed

Source: European Journal of Radiology Artificial Intelligence

DOI: 10.1016/j.ejrai.2025.100068

Authors: Adrien Jayet, Guillaume Fahrni

Institutions: Centre Hospitalier Universitaire Vaudois, University of Lausanne

Language: English

Topic: Artificial Intelligence in Healthcare and Education

Subfield: Health Informatics

Field: Medicine

Domain: Health Sciences

SDG: Good health and well-being

Open Access status: gold

Estimated APC paid: $2,900