Artificial intelligence in breast cancer screening: primary care provider preferences

• Published in: Journal of the American Medical Informatics Association : JAMIA 2021-06, Vol.28 (6), p.1117-1124
• Main Authors: Hendrix, Nathaniel, Hauber, Brett, Lee, Christoph I, Bansal, Aasthaa, Veenstra, David L
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Attitude of Health Personnel; Attitude to Computers; Breast Neoplasms - diagnosis; Early Detection of Cancer - methods; Female; Humans; Male; Mammography - methods; Physicians, Primary Care; Primary Health Care; Radiographic Image Interpretation, Computer-Assisted; Research and Applications; Sensitivity and Specificity; United States
• ISSN: 1527-974X; 1067-5027; 1527-974X
• DOI: 10.1093/jamia/ocaa292

Abstract Background Artificial intelligence (AI) is increasingly being proposed for use in medicine, including breast cancer screening (BCS). Little is known, however, about referring primary care providers’ (PCPs’) preferences for this technology. Methods We identified the most important attributes of AI BCS for ordering PCPs using qualitative interviews: sensitivity, specificity, radiologist involvement, understandability of AI decision-making, supporting evidence, and diversity of training data. We invited US-based PCPs to participate in an internet-based experiment designed to force participants to trade off among the attributes of hypothetical AI BCS products. Responses were analyzed with random parameters logit and latent class models to assess how different attributes affect the choice to recommend AI-enhanced screening. Results Ninety-one PCPs participated. Sensitivity was most important, and most PCPs viewed radiologist participation in mammography interpretation as important. Other important attributes were specificity, understandability of AI decision-making, and diversity of data. We identified 3 classes of respondents: “Sensitivity First” (41%) found sensitivity to be more than twice as important as other attributes; “Against AI Autonomy” (24%) wanted radiologists to confirm every image; “Uncertain Trade-Offs” (35%) viewed most attributes as having similar importance. A majority (76%) accepted the use of AI in a “triage” role that would allow it to filter out likely negatives without radiologist confirmation. Conclusions and Relevance Sensitivity was the most important attribute overall, but other key attributes should be addressed to produce clinically acceptable products. We also found that most PCPs accept the use of AI to make determinations about likely negative mammograms without radiologist confirmation.