Accuracy of screening mammography interpretation by characteristics of radiologists

Abstract

Background: Radiologists differ in their ability to interpret screening mammograms accurately. We investigated the relationship of radiologist characteristics to actual performance from 1996 to 2001.

Methods: Screening mammograms (n = 469,512) interpreted by 124 radiologists were linked to cancer outcome data. The radiologists completed a survey that included questions on demographics, malpractice concerns, years of experience interpreting mammograms, and the number of mammograms read annually. We used receiver operating characteristics (ROC) analysis to analyze variables associated with sensitivity, specificity, and the combination of the two, adjusting for patient variables that affect performance. All P values are two-sided.

Results: Within 1 year of the mammogram, 2402 breast cancers were identified. Relative to low annual interpretive volume (< or =1000 mammograms), greater interpretive volume was associated with higher sensitivity (P = .001; odds ratio [OR] for moderate volume [1001-2000] = 1.68, 95% CI = 1.18 to 2.39; OR for high volume [>2000] = 1.89, 95% CI = 1.36 to 2.63). Specificity decreased with volume (OR for 1001-2000 = 0.65, 95% CI = 0.52 to 0.83; OR for more than 2000 = 0.76, 95% CI = 0.60 to 0.96), compared with 1000 or less (P = .002). Greater number of years of experience interpreting mammograms was associated with lower sensitivity (P = .001), but higher specificity (P = .003). ROC analysis using the ordinal BI-RADS interpretation showed an association between accuracy and both previous mammographic history (P = .012) and breast density (P<.001). No association was observed between accuracy and years interpreting mammograms (P = .34) or mammography volume (P = .94), after adjusting for variables that affect the threshold for calling a mammogram positive.

Conclusions: We found no evidence that greater volume or experience at interpreting mammograms is associated with better performance. However, they may affect sensitivity and specificity, possibly by determining the threshold for calling a mammogram positive. Increasing volume requirements is unlikely to improve overall mammography performance.

Fig. 1

True positive rate (sensitivity) of the 124 radiologists versus the false positive rate (1 – specificity). Rates not adjusted for patient variables.

Fig. 2

Empirical receiver operating characteristic curves for mammograms of radiologists who reported interpreting ≤1000 (solid circles), 1001–2000 (solid diamonds), or >2000 (solid squares) mammograms per year, not adjusted for patient variables.

Fig. 3

Empirical receiver operating characteristic curves for mammograms of radiologists who reported <10 years (solid circles), 10–19 years (solid diamonds), or ≥20 years (solid squares) of experience interpreting mammograms, not adjusted for patient variables.

Fig. 4

Modeled receiver operating characteristic curves by breast density adjusted for age, prior mammography, and mammography registry. Category 1 = almost entirely fatty, category 2 = scattered fibroglandular densities, category 3 = heterogeneously dense, and category 4 = extremely dense.