However, perceptions varied between women seen in safety-net clinics versus academic medical center clinics
TUESDAY, Jan. 27, 2026 (HealthDay News) — Most patients are comfortable with artificial intelligence (AI) use to support mammogram interpretation, according to a study published online Dec. 3 in Breast Cancer Research and Treatment.
Jenifer Chisom Ogu, M.D., from University of Texas Southwestern Medical Center (UT Southwestern) in Dallas, and colleagues surveyed 924 patients visiting safety-net and academic hospital breast imaging clinics (April to June 2024 and February to August 2023, respectively) to understand patient perceptions of AI use in mammogram interpretation.
The researchers found that use of AI alone or as a second reader was accepted by 74 percent of respondents overall, with safety-net participants less likely to accept it (odds ratio [OR], 0.71). However, safety-net participants were more likely to request a reading by AI following radiologist-interpreted abnormalities (OR, 1.83), rate AI as the same or better than a radiologist at detecting cancer (OR, 1.54), and have higher concern regarding data privacy (OR, 1.87). There were associations for higher education (OR, 1.99) and self-reported AI knowledge (OR, 1.98) with higher acceptance of AI use. Respondents of non-Hispanic Black race had lower acceptance (OR, 0.40) of AI use, when controlling for other covariates.
“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,” lead author Emily Knippa, M.D., also from UT Southwestern, said in a statement.
Abstract/Full Text (subscription or payment may be required)
Study IDs Gaps in Hereditary Breast Cancer Risk Assessment Before Gender-Affirming Mastectomy
Family History Drives Cancer Risk in BRCA Test Groups
Global Findings Indicate Breast Cancer and A-Fib Incidence Frequently Overlap
Recurrence Score Elevated for Breast Cancer Diagnosed Within First Year Postpartum
Achieving PSA <0.2 ng/mL Improves Survival in Metastatic Castration-Sensitive Prostate Cancer
Enfortumab Vedotin-Pembrolizumab More Effective for MIBC Than Cisplatin-Gemcitabine
Lung Transplant Can Prolong Survival in Stage IV NSCLC
KRAS ctDNA Linked to Worse Overall Survival in Localized Pancreatic Cancer