A new study finds that discrepant AI results revealed in a mammography report can have a significant impact on patient confidence, anxiety levels, and follow-up intentions. This study suggests that providing context alongside AI findings may help maintain radiologist trust and reduce unnecessary worry.
Artificial intelligence in mammography is increasingly being used to support radiologists by flagging potential abnormalities. However, when AI findings contradict the radiologist’s assessment, the resulting uncertainty can influence patient behavior, highlighting the importance of how these results are communicated.
Study highlights growing concerns
Researchers studied 600 women undergoing routine mammography at two academic centers in Milan, Italy, between January 2023 and January 2024. Participants, with an average age of 55 years, were randomly assigned to one of four hypothetical scenarios: a standard radiologist’s report, an AI agreed with the radiologist, an AI flagged as inconsistent, or an AI flagged with an explanatory note. The study measured trust in radiologists, anxiety, intention to seek a second opinion, consideration of legal action, and acceptance of AI integration. They found that when the AI provided inconsistent results without context, confidence dropped sharply from 90.1 to 73.0 on a 100-point scale. Concern increased from 16% to 58%, requests for a second opinion jumped from 8.7% to 50%, and consideration of legal options increased from 38.7% to 60.7%.
Explaining AI improves patient understanding
Adding contextual explanations along with discordant AI results significantly reduced adverse reactions. Anxiety decreased to 25.3%, trust remained mostly the same, and respondents were less likely to seek a second opinion or consider litigation. Support for AI remained above 85% across all groups, suggesting that patients generally remain receptive to AI support if outcomes are clearly communicated.
Clinical significance of mammography
This finding highlights the need for a clear communication strategy in AI-integrated mammography. Providing context about the limitations and role of AI can prevent unnecessary anxiety, reduce the risk of unwarranted follow-up, and protect against potential medical problems.
Although this study focuses on hypothetical scenarios rather than real-world results, the insights provide practical guidance for radiologists and healthcare organizations implementing AI tools. Clear and contextual disclosure can serve as a simple but effective strategy for balancing technological innovation with patient trust and emotional well-being.
reference
Pesapan F et al. Should AI results be disclosed in mammography reports? A randomized research study of patient responses to concordant and discordant interpretations. Eur radiol. 2026;DOI:10.1007/s00330-026-12405-x
Featured image: Thumbnail from Adobe Stock
