Prospective Prediction of Match Outcomes in Integrated Plastic Surgery: A Novel, Mixed-Methods Approach Incorporating Holistic Applicant Review.

Abstract

Applying to an integrated plastic surgery program is among the most competitive processes in graduate medical education. Prior studies have highlighted the role of objective metrics in application selection. However, no studies have incorporated the qualitative content and authorship characteristics of letters of recommendation (LOR). The purpose of this study is to develop and validate a model integrating both quantitative and qualitative application data-including LOR content and authorship characteristics-to predict match outcomes in integrated plastic surgery. A retrospective review was conducted on all US MD applicants to integrated plastic surgery programs during the 2023 to 2024 and 2024 to 2025 cycles. Data collected included applicant demographics, academic metrics, research productivity, narrative LOR, and standardized LOR rankings. Letter writer characteristics were also extracted. Narrative LOR underwent linguistic analysis using LIWC-22 with a customized dictionary. A multivariable logistic model was developed using Least Absolute Shrinkage and Selection Operator on the 2023 to 2024 cohort and prospectively applied to the 2024 to 2025 cohort. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC). A total of 169 applicants were included from the 2023 to 2024 cohort. The final model identified higher step 2 scores, an increased number of podium presentations, a higher letter writer H-index, and "communal/likable" language in LORs as positive predictors of matching. A standardized LOR ranking of 5 to 10 was a negative predictor of matching. Prospective validation yielded an AUC of 0.7791. Our machine-learning-based statistical model accurately identified predictors of match success in integrated plastic surgery. As the residency selection landscape evolves, efforts to improve transparency, standardization, and evidence-based advising will be critical in promoting equity and optimizing match outcomes.