Enhancing Mentorship in Plastic Surgery Through an Algorithmic, Team-Based Approach.

Abstract

Mentorship is a cornerstone of surgical education, fostering professional growth, research productivity, and career guidance. In plastic surgery, mentorship profoundly impacts career choices and professional development, yet structured one-on-one programs are notably limited. Challenges such as time constraints, mismatched expectations, and disparities in representation often hinder traditional mentorship models. To address these issues, we developed a computational algorithm to facilitate team-based mentorship in plastic surgery. This algorithm utilizes a weighted Jaccard similarity index and recursive stability optimization to optimize compatibility among participants by aligning career goals, clinical interests, and mentorship priorities. A survey of 171 Professional Resource Opportunities in Plastic and Reconstructive Surgery Education and Leadership (PROPEL) members informed the pilot matching process, resulting in 36 teams with a median pooled similarity score of 0.823. Our approach offers distinct advantages, including equitable opportunity, scalability, and reduced administrative burden. Future efforts should focus on integrating qualitative feedback, evaluating long-term outcomes, and exploring advanced technologies such as natural language processing to refine the model further.