Accepted for/Published in: JMIR Medical Informatics
Date Submitted: Jun 12, 2025
Date Accepted: Jan 27, 2026
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Consequences and mitigation of cognitive bias in the radiological interpretation of breast cancer imaging using Artificial Intelligence
ABSTRACT
The interpretation of radiological images is a critical component in the diagnostic pathway of breast cancer, directly impacting therapeutic decisions and patient outcomes. However, system-related, perceptual, and cognitive factors may lead to the detection of diagnostic errors, which undermine the accuracy. This paper provides a comprehensive overview of the sources and implications of diagnostic inaccuracies in breast imaging, focusing on the growing role of artificial intelligence (AI) as both a supportive and potentially bias-reducing tool. Recent prospective studies demonstrate the clinical safety and efficiency of AI-assisted mammography screening, showing improved cancer detection rates and reduced workload. Nonetheless, integrating AI without an appropriate knowledge of the consequences might introduce new cognitive biases, such as anchoring, automation, and confirmation bias, that may influence radiologists' decision-making and counteract the intended benefits. The paper also explores strategies to mitigate these errors, including targeted training, improved interdisciplinary communication, and reflective practice. A balanced and cautious integration of AI, supported by continuous education and robust validation studies, seems essential to enhance diagnostic accuracy while preserving radiologists’ critical reasoning.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.