Assessing the performance of AI chatbots in answering patients' common questions about low back pain.

Journal: Annals of the rheumatic diseases
PMID:

Abstract

OBJECTIVES: The aim of this study was to assess the accuracy and readability of the answers generated by large language model (LLM)-chatbots to common patient questions about low back pain (LBP).

Authors

  • Simone P S Scaff
    Masters and Doctoral Programs in Physical Therapy, Universidade Cidade de Sao Paulo, Sao Paulo, Brazil. Electronic address: simone.pivaro@uol.com.br.
  • Felipe J J Reis
    Department of Physical Therapy, Federal Institute of Rio de Janeiro, Rio de Janeiro, Brazil; Pain in Motion Research Group, Department of Physical Therapy, Human Physiology and Anatomy, Faculty of Physical Education & Physiotherapy, Vrije Universiteit Brussel, Brussels, Belgium; School of Physical and Occupational Therapy, McGill University, Montreal, Canada. Electronic address: felipe.reis@ifrj.edu.br.
  • Giovanni E Ferreira
    Institute for Musculoskeletal Health, The University of Sydney and Sydney Local Health District, Sydney, Australia.
  • Maria Fernanda Jacob
    Masters and Doctoral Programs in Physical Therapy, Universidade Cidade de Sao Paulo, Sao Paulo, Brazil.
  • Bruno T Saragiotto
    Masters and Doctoral Programs in Physical Therapy, Universidade Cidade de Sao Paulo, Sao Paulo, Brazil; Discipline of Physiotherapy, Graduate School of Health, Faculty of Health, University of Technology, Sydney, New South Wales, Australia.