Performance of a Large Language Model in Screening Citations

Key Points Question How accurate and efficient is a large language model (LLM) for screening titles and abstracts for article inclusion in a systematic review? Findings In this diagnostic study, LLM-assisted citation screening exhibited acceptable sensitivity and reasonably high specificity in evaluating 5 clinical questions, with post hoc prompt modifications further improving accuracy. The screening time for 100 studies was significantly reduced compared with that of conventional methods. Meaning These findings suggest that LLM-assisted citation screening could offer a reliable and time-efficient alternative to systematic review processes.