Patients Largely Embrace Artificial Intelligence in Mammogram Analysis, Study Finds
Table of Contents
Most individuals are comfortable with the integration of artificial intelligence (AI) to assist in the interpretation of mammograms, according to new research published December 3 in Breast Cancer Research and Treatment. The findings suggest a growing acceptance of AI in healthcare, though disparities in trust exist across different patient populations.
A team led by researchers at the University of Texas Southwestern Medical Center (UT Southwestern) in Dallas sought to understand patient perspectives on AI’s role in breast cancer detection. The study, conducted between February 2023 and June 2024, surveyed 924 patients at both safety-net and academic hospital breast imaging clinics.
Broad Acceptance with Notable Variations
Overall, 74% of respondents expressed acceptance of AI being used either independently or as a “second reader” to support mammogram interpretation. However, the study revealed significant differences based on socioeconomic factors. Patients accessing care through safety-net hospitals were less likely to accept AI assistance, with an odds ratio of 0.71.
Interestingly, this same group demonstrated a greater willingness to request an AI review following initial findings of abnormalities identified by radiologists (odds ratio of 1.83). They also tended to rate AI as equally effective, or even superior, to radiologists in cancer detection (odds ratio of 1.54) and expressed heightened concerns about data privacy (odds ratio of 1.87).
Education and Demographics Influence Trust
The research highlighted the importance of patient education and awareness. Individuals with higher levels of education (odds ratio of 1.99) and self-reported knowledge of AI (odds ratio of 1.98) were significantly more likely to embrace the technology.
A concerning trend emerged regarding racial disparities. Respondents identifying as non-Hispanic Black race exhibited lower acceptance of AI use (odds ratio of 0.40), even after accounting for other influencing factors. This suggests a need for targeted outreach and culturally sensitive communication to address potential concerns within this community.
“As AI is increasingly used in breast imaging interpretation, attention should be paid to educate patients about the role of AI, obtain consent for its use, and provide safeguards to protect data privacy,” stated a lead author from UT Southwestern.
These findings underscore the critical need for healthcare providers to proactively engage patients in discussions about AI, ensuring transparency and addressing concerns to foster trust and equitable access to potentially life-saving technology.
