Checklist for Artificial Intelligence in Medical Imaging (CLAIM)
DSA ADS Course - 2021
Machine Learning, Artificial Intelligence, Medicine, Medical Imaging, Medical Devices
The advent of deep neural networks as a new artificial intelligence (AI) technique has engendered a large number of medical applications, particularly in medical imaging. Such applications of AI must remain grounded in the fundamental tenets of science and scientific publication. Scientific results must be reproducible, and a scientific publication must describe the authors’ work in sufficient detail to enable readers to determine the rigor, quality, and generalizability of the work, and potentially to reproduce the work’s results. A number of valuable manuscript checklists have come into widespread use, including the Standards for Reporting of Diagnostic Accuracy Studies (STARD), Strengthening the Reporting of Observational studies in Epidemiology (STROBE), and Consolidated Standards of Reporting Trials (CONSORT). A radiomics quality score has been proposed to assess the quality of radiomics studies.
Peer-reviewed medical journals have an opportunity to connect innovations in AI to clinical practice through rigorous validation. Various guidelines for reporting evaluation of machine learning models have been proposed. We have sought to codify these into a checklist in a format concordant with the EQUATOR Network guidelines that also incorporates general manuscript review criteria.