Artificial intelligence and consistency in patient care: a large-scale longitudinal study of mammographic density assessment

Abstract

Objectives: To assess whether use of an artificial intelligence (AI) model for mammography could result in more longitudinally consistent breast density assessments compared with interpreting radiologists.

Methods: The AI model was evaluated retrospectively on a large mammography dataset including 50 sites across the United States from an outpatient radiology practice. Examinations were acquired on Hologic imaging systems between 2016 and 2021 and were interpreted by 39 radiologists (36% fellowship trained; years of experience: 2-37 years). Longitudinal patterns in 4-category breast density and binary breast density (non-dense vs. dense) were characterized for all women with at least 3 examinations (61 177 women; 214 158 examinations) as constant, descending, ascending, or bi-directional. Differences in longitudinal density patterns were assessed using paired proportion hypothesis testing.

Results: The AI model produced more constant (P < .001) and fewer bi-directional (P < .001) longitudinal density patterns compared to radiologists (AI: constant 81.0%, bi-directional 4.9%; radiologists: constant 56.8%, bi-directional 15.3%). The AI density model also produced more constant (P < .001) and fewer bi-directional (P < .001) longitudinal patterns for binary breast density. These findings held in various subset analyses, which minimize (1) change in breast density (post-menopausal women, women with stable image-based BMI), (2) inter-observer variability (same radiologist), and (3) variability by radiologist's training level (fellowship-trained radiologists).

Conclusions: AI produces more longitudinally consistent breast density assessments compared with interpreting radiologists.

Advances in knowledge: Our results extend the advantages of AI in breast density evaluation beyond automation and reproducibility, showing a potential path to improved longitudinal consistency and more consistent downstream care for screened women.

Keywords: artificial intelligence; breast cancer screening; breast density; longitudinal analysis; mammography.

Figure 1.

Flowchart shows inclusion and exclusion criteria for the cross-sectional screening sample analysed in our study.

Figure 2.

Longitudinal patterns in (A) 4-category breast density and (B) binary breast density (dense vs. non-dense).

Figure 3.

Consecutive craniocaudal mammographic views acquired in the year 2019 (top), 1 year later (middle), and 2 years later (bottom) of the same woman. An ascending longitudinal density pattern was produced by the interpreting radiologists due to inter/intra-observer variability who assigned BI-RADS density categories b, c, and d, respectively, whereas the AI density model assigned BI-RADS density category c to all 3 examinations, producing a constant longitudinal density pattern. Abbreviations: BI-RADS = Breast Imaging Reporting and Data System; AI = artificial intelligence.

Figure 4.

Consecutive craniocaudal mammographic views acquired in the year 2017 (top), 3 years later (middle), and 4 years later (bottom) of the same woman. The interpreting radiologists and the AI density model agreed on the same ascending longitudinal density pattern and assigned BI-RADS density categories b, b, and c, respectively, capturing potential weight loss between the last 2 years (as suggested by the reduction in compressed breast thickness of the left and right breasts from 4.9/5.0 cm to 3.1/3.1 cm). Abbreviations: AI = artificial intelligence; BI-RADS = Breast Imaging Reporting and Data System.

Figure 5.

Confusion matrices for longitudinal patterns in (A) 4-category breast density and (B) binary breast density (dense vs. non-dense).

Figure 6.

Sankey plots showing changes in 4-category breast density from women’s first to last screening examination, based on (left) the AI density model and (right) interpreting radiologists. Abbreviation: AI = artificial intelligence.