A comparison of performance of DeepSeek-R1 model-generated responses to musculoskeletal radiology queries against ChatGPT-4 and ChatGPT-4o - A feasibility study.

Journal: Clinical imaging
Published Date: May 12, 2025

Abstract

OBJECTIVE: Artificial Intelligence (AI) has transformed society and chatbots using Large Language Models (LLM) are playing an increasing role in scientific research. This study aims to assess and compare the efficacy of newer DeepSeek R1 and ChatGPT-4 and 4o models in answering scientific questions about recent research.

Authors

  • Hasaam Uldin
    Department of Musculoskeletal Radiology, Royal Orthopedic Hospital, Birmingham, UK.
  • Sonal Saran
    Department of Musculoskeletal Radiology, AIIMS, Rishikesh, India.
  • Girish Gandikota
    Department of Radiology, University of Michigan, Ann Arbor, MI, USA.
  • Karthikeyan P Iyengar
    Department of Orthopedics, Southport and Ormskirk Hospital, Southport, UK.
  • Raju Vaishya
    Department of Orthopaedics, Indraprastha Apollo Hospital, SaritaVihar, Mathura Road, 110076, New Delhi, India. Electronic address: raju.vaishya@gmail.com.
  • Yogesh Parmar
    Sport Medicine Physiotherapist, The Board of Control for Cricket in India, Mumbai, India.
  • Fahid Rasul
    Department of Spinal Surgery, University Hospitals Coventry and Warwickshire, Coventry, UK.
  • Rajesh Botchu
    Department of Radiology, Royal Orthopedic Hospital, Birmingham, UK.

Keywords

External Resources

Popular Topics
Recent Journals