Assessing Resident Performance in Screening Mammography: Development of a Quantitative Algorithm

Rationale and Objectives: This study aims to provide objective performance data and feedback, including examination volumes, recall rates, and concordance with faculty interpretations, for residents performing independent interpretation of screening mammography examinations. Method and Materials: Residents (r) and faculty (f) interpret screening mammograms separately and identify non-callbacks (NCBs) and callbacks (CBs). Residents review all discordant results. The number of concordant interpretations (fCB-rCB and fNCB-rNCB) and discordant interpretations (fCB-rNCB and fNCB-rCB) are entered into a macro-driven spreadsheet. These macros weigh the data dependent on the perceived clinical impact of the resident's decision. Weighted outcomes are combined with volumes to generate a weighted mammography performance score. Rotation-specific goals are assigned for the weighted score, screening volumes, recall rate relative to faculty, and concordance rates. Residents receive one point for achieving each goal. Results: Between July 2013 and May 2017, 18,747 mammography examinations were reviewed by 31 residents, in 71 resident rotations, over 246 resident weeks. Mean resident recall rate was 9.9% and significantly decreased with resident level (R), R2 = 11.3% vs R3 = 9.4%, R4 = 9.2%. Mean resident-faculty discordance rate was 10% and significantly decreased from R2 = 12% to R4 = 9.6%. Weighted performance scores ranged from 1.1 to 2.0 (mean 1.6, standard deviation 0.17), but did not change with rotation experience. Residents had a mean goal achievement score of 2.6 (standard deviation 0.47). Conclusions: This method provides residents with easily accessible case-by-case individualized screening outcome data over the longitudinal period of their residency, and provides an objective method of assessing resident screening mammography performance.