Diagnostic Accuracy of Artificial Intelligence-Assisted Radiology Assessment of Cancer- A Systematic Review

Main Objective Perform a systematic review and meta-analysis of studies using multi-reader multi-case (MRMC) study designs for cancer diagnosis with artificial intelligence (AI). Review diagnostic accuracy, study design and reporting. Material and Methods A search of several databases between 1 January 2014 and 28 February 2024 was performed. Diagnostic accuracy studies that compared radiologists with and without AI-assistance in cancer diagnostic tasks over all imaging modalities were included. Meta-analysis using Summary Receiver Operating Characteristics (SROC) curves were plotted for pooled sensitivity and specificity. Risk of bias was assessed by using the Quality Assessment of Diagnostic Accuracy Studies-Comparative (QUADAS-C) and the Checklist for Artificial intelligence in Medical Imaging (CLAIM). Results Thirty-four studies were included of which twenty-three were included in meta-analysis. Eight identified cancers on Chest X-rays, seventeen on CT, nine on MRI. Pooled sensitivity and specificity were 0.67 (95%CI 0.58-0.74) and 0.82 (95%CI 0.75-0.88) respectively for clinicians and 0.79 (95%CI 0.71-0.88) and 0.87 (95%CI 0.82-0.91) for AI-assistance. 17 of 34 studies (50%) had concern of bias with QUADAS-C. CLAIM assessment highlighted reporting issues in several domains of methodology in a proportion of studies. Conclusion Artificial intelligence assistance tools may benefit clinician diagnostic performance in cancer diagnosis. Updated reporting guidelines may help to overcome potential methodological limitations to clarify AI’s value in healthcare. Advances in Knowledge Previous reviews compare AI accuracy alone against a clinician. We focus on MRMC study designs to ass AI use in a clinical environment.