This study investigates the impact of AI-assisted text simplification on the relationship between medical vocabulary knowledge and reading comprehension in English for Medical Purposes (EMP). Using a two-group design with 84 second-year medical students, the research compares performance on original and ChatGPT-simplified biochemistry texts. Findings show high vocabulary recognition (91%) and comprehension (84%), with a stronger vocabulary–comprehension correlation under simplified conditions (r = .74 vs. .56). Results suggest that AI-driven simplification reduces linguistic barriers, making lexical knowledge a more direct predictor of comprehension while preserving text-dependent variation. The study contributes to research on lexical coverage, L2 reading processes, and the pedagogical role of AI in specialized language learning. Note: this is a pre-print. The information will be updated when published.
Evgeni Stanchev (Thu,) studied this question.