Return to sport decision support with large language models after lower limb ligament injury
International Journal of Sports Science & Coaching · 16.11.2026
DOI: 10.1177/17479541261507302 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Sports Science & Coaching, online erschienen am 16.11.2026. Verfasst von Ömer Alperen Gürses und 4 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Patients and clinicians increasingly use large language models (LLMs) for return-to-sport decisions, but their reliability and the effect of structured clinical context remain uncertain. In this pre-registered, blinded, multi-model study, GPT-5, Gemini 2.5 Pro, Claude Sonnet 4.5, and DeepSeek-V3.2-Exp answered 12 fictional anterior cruciate ligament reconstruction or lateral ankle sprain vignettes under instruction-only (Prompt+) and guideline-derived context (Context+) conditions across two runs, generating 192 outputs. Three blinded domain experts scored six binary criteria. The primary outcome was a correct clinical claim supported by a valid DOI or PMID. Context + did not improve the primary outcome compared with Prompt + (OR 0.41, 95% CI 0.16–1.05; p = 0.065). GPT-5 was the only model whose point estimate favoured Context+, whereas the other three models favoured Prompt+. Claude Sonnet 4.5 showed a higher majority-vote Hallucination rate under Context + (22.7% vs 62.5%; Holm-adjusted p = 0.014); however, inter-rater agreement for Hallucination was poor (Fleiss’ κ < 0 in both domains), so this finding should be interpreted cautiously. Citation validity declined under Context + in three of the four models. Structured guideline-derived context did not reliably improve return-to-sport decision support in the models and conditions tested, and its effects varied between models. LLMs intended for clinical decision support should therefore undergo task- and model-specific evaluation before deployment.
Zitieren
APA
Gürses, Ö. A., Bizzini, M., Wikstrom, E. A., Forelli, F., & Fourchet, F. (2026). Return to sport decision support with large language models after lower limb ligament injury. International Journal of Sports Science & Coaching. https://doi.org/10.1177/17479541261507302
Vancouver
Gürses ÖA, Bizzini M, Wikstrom EA, Forelli F, Fourchet F. Return to sport decision support with large language models after lower limb ligament injury. International Journal of Sports Science & Coaching. 2026. doi:10.1177/17479541261507302
BibTeX
@article{Grses2026,
author = {Gürses, Ömer Alperen and Bizzini, Mario and Wikstrom, Erik A and Forelli, Florian and Fourchet, François},
title = {Return to sport decision support with large language models after lower limb ligament injury},
journal = {International Journal of Sports Science & Coaching},
year = {2026},
doi = {10.1177/17479541261507302}
}
EUVIMED