Human-Written vs AI-Generated Texts in Orthopedic Academic Literature: Comparative Qualitative Analysis

• DOI: 10.2196/52164
• Publication Date: 2023-12-13T05:32:51Z
• Authors: Hassan Tarek Hakam; Robert Prill; Lisa Korte; Bruno Lovreković; Marko Ostojić; Nikolai Ramadanov; Felix Muehlensiepen
• Keywords: Preprint; Rank (graph theory)

Background As large language models (LLMs) are becoming increasingly integrated into different aspects of health care, questions about the implications for medical academic literature have begun to emerge. Key such as authenticity in writing at stake with artificial intelligence (AI) generating highly linguistically accurate and grammatically sound texts. Objective The objective this study is compare human-written AI-generated scientific orthopedics sports medicine. Methods Five original abstracts were selected from PubMed database. These subsequently rewritten assistance 2 LLMs degrees proficiency. Subsequently, researchers varying expertise areas specialization asked rank according linguistic methodological parameters. Finally, had classify articles AI generated or human written. Results Neither nor AI-detection software could successfully identify Furthermore, criteria previously suggested did not correlate whether deemed a text be they judged article correctly based on these Conclusions primary finding was that unable distinguish between LLM-generated However, due small sample size, it possible generalize results study. case any tool used research, potential cause harm can mitigated by relying transparency integrity researchers. With stake, further research similar design should conducted determine magnitude issue.