Return to sport decision support with large language models after lower limb ligament injury

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.

Authors

Institutions

Publication Details

Journal
International Journal of Sports Science & Coaching
Published
2026-11-16
DOI
https://doi.org/10.1177/17479541261507302
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Return to sport decision support with large language models after lower limb ligament injury

Ömer Alperen Gürses, Erik A. Wikstrom, Mario Bizzini, François Fourchet et al.
5 links
International Journal of Sports Science & Coaching
Artificial Intelligence in Healthcare and Education
article

Return to sport decision support with large language models after lower limb ligament injury

Ömer Alperen Gürses, Erik A. Wikstrom, Mario Bizzini, François Fourchet, Florian Forelli
article en

Abstract

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.

International Journal of Sports Science & Coaching
University of North Carolina at Chapel Hill (US), Ahi Evran University (TR), Schulthess-Klinik (CH), HES-SO Arc (CH), Laboratoire Interuniversitaire de Biologie de la Motricité (FR), Hôpital de la Tour (CH), Université Jean Monnet (FR), Université Savoie Mont Blanc (FR), Université Jean Monnet (FR)
Good health and well-being
Artificial Intelligence in Healthcare and Education
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon