Background: Large language models (LLMs) can contribute to treatment options and outcomes by assisting physiotherapists for conditions like osteoarthritis. Aims: The objective of this early-stage cross-sectional study is to assess the alignment of large language models with physiotherapists in designing physiotherapy and rehabilitation programs for knee osteoarthritis. Methods: Forty patients diagnosed with knee osteoarthritis were assessed using standardized clinical criteria. For each patient, individualized rehabilitation programs were created by three physiotherapists and by ChatGPT-4o and Gemini Advanced using structured prompts. The presence or absence of 50 clinically relevant rehabilitation parameters was recorded for each program. Chi-square tests were used to evaluate agreement rates between the LLMs and the physiotherapist-generated Consensus programs. Results: ChatGPT-4o achieved a 74% agreement rate with the physiotherapists’ Consensus programs, while Gemini Advanced achieved 70%. Although both models showed high compatibility with general rehabilitation components, they demonstrated notable limitations in exercise specificity, including frequency, sets, and progression criteria. ChatGPT-4o performed as well as or better than Gemini in most phases, particularly in Phase 3, while Gemini showed lower consistency in balance and stabilization parameters. Conclusions: ChatGPT-4o and Gemini Advanced demonstrate promising potential in generating personalized rehabilitation programs for knee osteoarthritis. While their outputs generally align with expert recommendations, notable gaps remain in clinical reasoning and the provision of detailed exercise parameters. These findings underscore the importance of ongoing model refinement and the necessity of expert supervision for safe and effective clinical integration.
27 March 2019 in American Journal of Physical Medicine & Rehabilitation
Objective: The aim of the study was to compare the efficacy of steroid injection and kinesio taping (KT) in the treatment of lateral epicondylitis. Design: A total number of 84 patients were randomized into three groups. Group 1 was given steroid injection, group 2 received KT, and group 3 received both. Pain was measured using a visual analog scale, functional status was measured using a quick form of the Disabilities of Arm, Shoulder and Hand questionnaire, pain-free grip strength was measured using a dynamometer, and the pressure pain threshold was measured using an algometer. All evaluations were performed before treatment and at the third and twelfth weeks after the treatment. Results: Twenty-eight patients were included in each group. A statistically significant difference was found between the pretreatment and posttreatment evaluations of all groups in the third and twelfth weeks after treatment. When group 1 and group 2 were compared, there was a significant difference only in pain-free grip strength measured in the twelfth week. The results of treatment in group 3 patients were significantly better in almost all evaluation parameters compared with the other groups. Conclusion: In the treatment of lateral epicondylitis, KT alone was found to be as effective as steroid injection alone. However, co-administration of steroid injection and KT is more effective compared with each treatment alone.
1 January 2023 in TURKISH JOURNAL OF MEDICAL SCIENCES
Background/aim: The purpose of this study was to determine the effect of the presence, size, or type of calcaneal spurs on pain or the outcomes of extracorporeal shock wave therapy (ESWT) therapy in patients with plantar fasciitis. Materials and methods: Seventy-four patients with unilateral plantar fasciitis who had no pain in the contralateral foot, either currently or in the past, were included in the study. The length, base width, type, and presence of plantar calcaneal spurs in both heels of the patients were determined using radiography. A total of five sessions of ESWT (3 bar, 2000 shocks/session, 12 Hz frequency) with an interval of 3 days were performed on the painful sides of the patients. Symptom duration and numerical rating scale (NRS) scores were recorded pretreatment and 1 week and 12 weeks after treatment. Results: Spurs were detected in 85.1% of painful feet and 71.6% of painless feet, this difference was statistically significant (p = 0.046). There was no significant correlation between the type of the spurs and whether the foot was painful. Patients with spur sizes of >5 mm or with horizontal and hooked spurs had a higher NRS decrease than patients with spur sizes of ≤5 mm or with a vertical spur. Symptom duration, spur length, and base width were found to be correlated with pretreatment NRS scores. Conclusion: The presence and size of calcaneal spurs are associated with pain. However, it should be kept in mind that a high rate of spurs can also be found in painless feet, so spur is not the only factor that causes pain. Patients with a spur size of ≤5 mm or a vertical spur have less pain relief with ESWT.
Background: There is no Turkish version of the Postural Assessment Scale for Stroke patients (PASS). Objectives: To translate and make the cross-cultural adaptation of the PASS into the Turkish language and evaluate the reliability and validity of the Turkish version (PASS-Turk). Methods: Sixty patients with stroke who had survived the three-week acute period were included in the study. The first researcher applied the scale to the participants twice with 5-day intervals. The second researcher applied the scale once at the same time with the first researcher. The reliability of PASS-Turk and its subsections was evaluated using Cronbach’s alpha coefficient. In addition, item-total correlation and test-retest reliability were calculated. The interobserver agreement was assessed using the intraclass correlation coefficient. The construct validity of PASS-Turk was assessed using Pearson’s product-moment correlation and principal component analyses. The Berg Balance Scale (BBS) and motor subscale of the Functional Independence Measure (FIM) were used for validity. Results: The Cronbach’s alpha coefficients of the PASS-Turk scale were 0.903 for the subsection of “maintaining posture,” 0.940 for the subsection of “changing a posture,” and 0.953 for the total PASS-Turk scale. The first and second researcher evaluations were perfectly consistent with each other in terms of PASS-Turk total scores (ICC = 0.999, 95% CI: 0.998–0.999, and p < .001). A strong positive correlation was found between PASS-Turk and BBS and the motor subscale of FIM. Conclusion: PASS-Turk is a valid and reliable scale for the evaluation of posture and balance of patients with stroke.
1 January 2025 in Revista da Associação Médica Brasileira
OBJECTIVE: The aim of this study was to compare the efficacy of radial extracorporeal shock wave therapy administered at low vs. high pressures in patients with carpal tunnel syndrome.