Creative Commons source reading · Nutrition and supplementation
Generative artificial intelligence and large language models in sports medicine: a scoping review of applications, accuracy, and ethical implications
Ismail Dergaa; Mohamed Amine Dergaa; Mortadha Razzak; Halil İbrahim Ceylan; Valentina Stefanica; Raul Ioan Muntean; Noomen Guelmami
Originally published in Front Public Health · 2026-07-29
From the article
Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.
Abstract
BackgroundGenerative artificial intelligence (GenAI), particularly large language models (LLMs) such as ChatGPT, GPT-3.5, and GPT-4, is rapidly being integrated into sports medicine practice. These tools are increasingly used by health professionals, coaches, and athletes for training prescription, rehabilitation, nutrition, mental health support, injury prevention, and academic writing. However, their adoption has outpaced the development of robust evidence regarding their clinical utility, accuracy, and safety, and no comprehensive synthesis of this emerging field currently exists.AimThis scoping review aimed to map the current evidence on GenAI and LLM applications in sports medicine and athlete health, evaluate their accuracy and hallucination risks across domains, and synthesise reported ethical and governance concerns.MethodsThe…
Discussion
This scoping review provides the first comprehensive evidence map of GenAI and LLM applications across the full spectrum of sports medicine and athlete health. Thirty-two sources published between January 2023 and March 2026 document both genuine clinical potential and substantive risks in this transition. Three recurring tensions characterise the evidence base: the gap between LLM capability and LLM reliability; the gap between practitioner adoption and the development of governance frameworks; and the gap between the technical sophistication of these tools and the conceptual frameworks available to sports medicine for evaluating them.
Ethical implications and governance requirements
The six ethical concern categories identified in this review are interconnected and mutually reinforcing. Algorithmic bias stemming from the underrepresentation of female athletes, youth athletes, and non-Western populations in LLM training data is particularly consequential, as sports medicine practice is increasingly global and population-diverse, while LLM development remains concentrated in North American and East Asian technology ecosystems (12). Bias in training data generates systematic directional errors that favour populations already over-represented in digital health data. The systematic scoping review on AI ethics in sport found no consensus ethical framework addressing these dimensions specifically (12), a gap that professional sports medicine bodies are positioned to close. Based on limited simulation data, LLMs have…
Editorial reading guide
- Was the outcome a biological marker, subjective response or meaningful performance change?
- What dose, timing, population and setting bound the practical conclusion?
