RESUMO
PURPOSE: The purpose of the study was to develop a model that predicts an individual applicant's probability of successful placement into a surgical subspecialty fellowship program. METHODS: Candidates who applied to surgical fellowships during a 3-year period were identified in a set of databases that included the electronic application materials. RESULTS: Of the 1281 applicants who were available for analysis, 951 applicants (74%) successfully placed into a colon and rectal surgery, thoracic surgery, vascular surgery, or pediatric surgery fellowship. The optimal final prediction model, which was based on a logistic regression, included 14 variables. This model, with a c statistic of 0.74, allowed for the determination of a useful estimate of the probability of placement for an individual candidate. CONCLUSIONS: Of the factors that are available at the time of fellowship application, 14 were used to predict accurately the proportion of applicants who will successfully gain a fellowship position.
