Small language models: The big play for agentic artificial intelligence in orthopaedics.

Journal: Knee surgery, sports traumatology, arthroscopy : official journal of the ESSKA
Published Date: Oct 27, 2025

Abstract

While the integration of artificial intelligence in orthopedics is accelerating, the focus has largely been on powerful but resource-intensive Large Language Models (LLMs). This editorial argues for a strategic shift towards Small Language Models (SLMs) for many specialized clinical applications. SLMs offer a more efficient, cost-effective, and adaptable solution for the narrowly-scoped tasks common in orthopedics. We discuss their potential in surgical assistance, personalized patient management, and administrative automation, positing that the future of practical AI in our field lies in a diverse ecosystem of specialized SLMs. However, we also underscore that rigorous validation and the development of robust evaluation benchmarks are critical to ensure their safe and trustworthy integration into clinical practice.

Authors

  • Felix C Oettl
    Hospital for Special Surgery, New York, New York, USA.
  • James A Pruneski
    Department of Orthopedic Surgery, Boston Children's Hospital, Boston, MA, USA.
  • Balint Zsidai
    Department of Orthopaedics Institute of Clinical Sciences, The Sahlgrenska Academy University of Gothenburg Gothenburg Sweden.
  • Yinan Yu
    Department of Computer Science and Engineering, Chalmers University of Technology, Gothenburg, Sweden.
  • Michael T Hirschmann
    Department of Arthroplasty, Sports Medicine and Traumatology, Orthopaedic Hospital Lindenlohe, Lindenlohe 18, 92421, Schwandorf, Germany.
  • Kristian Samuelsson
    Department of Orthopaedics Institute of Clinical Sciences, The Sahlgrenska Academy University of Gothenburg Gothenburg Sweden.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals