Answers are grounded in this paper and cite their sources.
Examines AI's effect on vocabulary and reading comprehension in medical students, suggesting improved alignment between the two.
This study examines how AI-assisted text simplification influences the relationship between domain-specific vocabulary knowledge and reading comprehension in English for Medical Purposes (EMP). Based on data from 84 second-year medical students, the findings show high levels of vocabulary recognition (91%) and reading comprehension (84%), with a strong positive correlation between the two (r = .74). Compared to an earlier phase using original texts (r = .56), the results suggest that simplified texts may strengthen the alignment between lexical knowledge and comprehension. Transfer-efficiency results (M = 0.92) indicate that learners generally apply their vocabulary knowledge effectively in reading tasks, though with notable individual variation. The findings suggest that AI-assisted simplification does not necessarily increase overall comprehension, but may shift the balance of factors underlying reading by reducing non-lexical complexity and making vocabulary knowledge a more central predictor. This contributes to research on specialized L2 reading, lexical coverage, and the role of AI in medical ESP pedagogy. Note: this is a pre-print. The information will be updated when published.
No takes yet. Share an insight, caveat, or question.
Evgeni Stanchev (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: