Evaluation of the accuracy of ChatGPT's responses to and references for clinical questions in physical therapy.

[Purpose] This study evaluated the accuracy of ChatGPT's responses to and references for five clinical questions in physical therapy based on the Physical Therapy Guidelines and assessed this language model's potential as a tool for supporting clinical decision-making in the rehabilitation field. [Participants and Methods] Five clinical questions from the "Stroke", "Musculoskeletal disorders", and "Internal disorders" sections of the Physical Therapy Guidelines, released by the Japanese Society of Physical Therapy, were presented to ChatGPT. ChatGPT was instructed to provide responses in Japanese accompanied by references such as PubMed IDs or digital object identifiers. The accuracy of the generated content and references was evaluated by two assessors with expertise in their respective sections by using a 4-point scale, and comments were provided for point deductions. The inter-rater agreement was evaluated using weighted kappa coefficients. [Results] ChatGPT demonstrated adequate accuracy in generating content for clinical questions in physical therapy. However, the accuracy of the references was poor, with a significant number of references being non-existent or misinterpreted. [Conclusion] ChatGPT has limitations in reference selection and reliability. While ChatGPT can offer accurate responses to clinical questions in physical therapy, it should be used with caution because it is not a completely reliable model.

The Feasibility of a Newly Developed Local Network System for Cardiac Rehabilitation (the CR-GNet) in Disease Management and Physical Fitness after Acute Coronary Syndrome.

OBJECTIVE: To examine the Cardiac Rehabilitation Gifu Network (CR-GNet) feasibility in managing diseases and assisting patients in attaining physical fitness, and its impact on long-term outcomes after acute coronary syndrome (ACS). METHODS: In this prospective observational study, we enrolled 47 patients with ACS registered in the CR-GNet between February 2016 and September 2019. 37, 29, and 21 patients underwent follow-up assessments for exercise capacity (peak oxygen uptake) at 3 months, 6 months, and 1 year after discharge, respectively. Major adverse cardiac events (MACE) were compared with controls not registered in the CR-GNet. RESULTS: The coronary risk factors, except blood pressure, improved at 3 and 6 months, and 1 year after discharge. These risk factors in each patient significantly reduced from 2.9 at admission to 1.6, 1.4, and 1.9 at 3 months, 6 months, and 1 year after discharge (p<0.05), respectively. Peak oxygen uptake was significantly higher at 3 months (17.5±4.9 ml/kg/min), 6 months (17.9±5.1 ml/kg/min), and 1 year (17.5±5.5 ml/kg/min) after discharge than that at discharge (14.7±3.6 ml/kg/min) (p<0.05). During follow-up, there was no significant difference; MACE did not occur in any patients in the CR-GNet but occurred in controls. CONCLUSION: CR-GNet is a feasible option for the long-term management of ACS patients.