Association of Second-Opinion Strategies in the Histopathologic Diagnosis of Cutaneous Melanocytic Lesions with Diagnostic Accuracy and Population-Level Costs

Importance: Diagnostic variation among pathologists interpreting cutaneous melanocytic lesions could lead to suboptimal care. Objective: To estimate the potential association of second-opinion strategies in the histopathologic diagnosis of cutaneous melanocytic lesions with diagnostic accuracy and 1-year population-level costs in the US. Design, Setting, and Participants: Decision analysis with 1-year time horizon including melanocytic lesion diagnoses available from US pathologists participating in the Melanoma Pathology Study (M-Path) and from the study panel of reference pathologists who classified cases using the MPATH-Dx classification tool. M-Path data collection occurred from July 2013 through March 2015; analyses for the present study were performed between April 2015 and January 2021. Exposures: Various second-opinion strategies for interpretation of melanocytic cutaneous lesions. Main Outcomes and Measures: Estimated accuracy of pathologists' diagnoses, defined as concordance with the reference panel diagnoses, and 1-year postbiopsy medical costs under various second-opinion strategies. Expected percentage of concordant diagnoses, including percentages of overinterpretation and underinterpretation, and 1-year costs of medical care per 100000 in the US population. Results: Decision-analytic model parameters were based on diagnostic interpretations for 240 cases by 187 pathologists compared with reference panel diagnoses. Without second opinions, 83.2% of diagnoses in the US were estimated to be accurate - ie, concordant with the reference diagnosis; with overinterpretation (8.0%) or underinterpretation (8.8%), and 16850 misclassified diagnoses per 100000 biopsies. Accuracy increased under all second-opinion strategies. Accuracy (87.4% concordance with 3.6% overinterpretation and 9.1% underinterpretation) and cost (an increase of more than $10 million per 100000 biopsies per year) were highest when second opinions were universal (eg, performed on all biopsies), relative to no second opinions. A selective second-opinion strategy based on pathologists' desire or institutional requirements for a second opinion was most accurate (86.5% concordance; 4.4% overinterpretation; 9.1% underinterpretation) and would reduce costs by more than $1.9 million per 100000 skin biopsies relative to no second opinions. Improvements in diagnostic accuracy with all second-opinion strategies were associated with reductions in overinterpretation but not underinterpretation. Conclusions and Relevance: In this decision-analytic model, selective second-opinion strategies for interpretation of melanocytic skin lesions showed the potential to improve diagnostic accuracy and decrease costs relative to no second opinions or universal second opinions..