Why Do Medical Students Choose to Become Neurologists? A Computational Linguistics Analysis of Residency Personal Statements (S39.001)

Objective: We sought to understand medical students’ motivations for choosing neurology, specifically investigating how applicants of different backgrounds conceptualize this field. This information can be used to foster further interest in neurology and develop educational programs to help future neurologists find gratifying career paths. Background: Applicants to neurology residencies submit personal statements via the Electronic Residency Application System (ERAS). Textual analysis of personal statements has been performed in internal medicine, but never before in neurology. By using computational linguistics software, key words can be assessed to study motivations, expectations, and themes present amongst neurology applicants. Design/Methods: 2,405 personal statements submitted over five years to our institution were de-identified and compiled into a database for evaluation through two computational linguistics software programs. We searched for term frequency (TF), utilized term weighting models, and calculated Term Frequency-Inverse Document Frequency (TF-IDF), to evaluate statistical differences among subgroups. Results: Specific disease states and subspecialties were often discussed in personal statements, with widely variable term frequency. For example, stroke (TF=2178), epilepsy (TF=970), dementia (TF=944) were referenced more often than ALS (TF=220) and carpal tunnel (TF=10). The most common proper names cited include Oliver Sacks (TF=94) and Sherlock Holmes (TF=41). Females commonly mentioned: health, stroke, brain, love, student, and family; males referenced: stroke, human, training, brain, and teach. Further linguistic analysis of gender differences showed females emphasized: grandmother, puzzle, language, dance, culture, mother, and support, while male counterparts highlighted: computer, technology, highlight, EEG, neurophysiology, benefit, and suffer. Conclusions: This first computational linguistic analysis of neurology personal statements provides an initial characterization of medical student motivations, highlighting interest in specific disease states and subspecialties. In gender subgroup analysis, there was large variation in language used by males and females. Ongoing subgroup and thematic analyses will inform neuro-educational strategies and enhance recruitment to our field. Disclosure: Dr. Cheung has nothing to disclose. Dr. Grzebinski has nothing to disclose. Dr. Sanky has received personal compensation in an editorial capacity for Associate Editor for AHEAD, the University of Michigan School of Social Work’s research magazine. Dr. Ouyang has nothing to disclose. Dr. Krieger has received personal compensation for consulting, serving on a scientific advisory board, speaking, or other activities with Acorda, Bayer, Biogen, Celgene, EMD Serono, Genentech, Genzyme, Mallinckrodt, MedDay, Novartis, Teva, and TG Therapeutics.