ABSTRACT
Objective: This research explores the performance of ChatGPT, compared to human doctors, in bilingual, Mandarin Chinese and English, medical specialty exam in Nuclear Medicine in Taiwan. Methods: The study employed generative pre-trained transformer (GPT-4) and integrated chain-of-thoughts (COT) method to enhance performance by triggering and explaining the thinking process to answer the question in a coherent and logical manner. Questions from the Taiwanese Nuclear Medicine Specialty Exam served as the basis for testing. The research analyzed the correctness of AI responses in different sections of the exam and explored the influence of question length and language proportion on accuracy. Results: AI, especially ChatGPT with COT, exhibited exceptional capabilities in theoretical knowledge, clinical medicine, and handling integrated questions, often surpassing, or matching human doctor performance. However, AI struggled with questions related to medical regulations. The analysis of question length showed that questions within the 109-163 words range yielded the highest accuracy. Moreover, an increase in the proportion of English words in questions improved both AI and human accuracy. Conclusions: This research highlights the potential and challenges of AI in the medical field. ChatGPT demonstrates significant competence in various aspects of medical knowledge. However, areas like medical regulations require improvement. The study also suggests that AI may help in evaluating exam question difficulty and maintaining fairness in examinations. These findings shed light on AI role in the medical field, with potential applications in healthcare education, exam preparation, and multilingual environments. Ongoing AI advancements are expected to further enhance AI utility in the medical domain.
ABSTRACT
BACKGROUND: Tai chi has been increasingly applied in osteoporosis patients. However, systematic reviews of the efficacy of this practice have been few and of limited scope. PURPOSE: This study reviews previous experimental research work using tai chi as an intervention in postmenopausal women with osteoporosis and to appraise the reported research designs used, tai chi methods used, and outcomes. METHODS: A systematic review method was used to search 14 databases for articles published between January 1980 and July 2013. Searched keywords included: "tai chi," "osteoporosis," and "postmenopausal women". The 2,458 articles initially identified were reduced to 4 valid articles based on considerations of criteria and repeatability. The 4 valid articles used either a randomized clinical trial (RCT) or a controlled clinical trial (CCT). They were further analyzed and synthesized in terms of common variables such as balance, muscle strength, and quality of life. RESULT: Three of the 4 studies identified significant pretest / posttest differences in physiological aspects of quality of life in participants but did not obtain consistent results in terms of the psychological aspects. While reports identified a significant and positive tai chi effect on balance, they all used different measurements to do so. Only one of the four studies identified significant improvement in muscle strength. Therefore, this review could not identify clear support for the effectiveness of tai chi on balance or muscle strength. CONCLUSIONS: This review did not definitively support the positive effects of tai chi on balance, muscle strength, and quality of life in postmenopausal women with osteoporosis. The designs used in the tai chi interventions may be referenced for future studies. We suggest that future studies use data triangulation rather than a single-item tool to validate the research in order to cross-verify the same information. This may strengthen the research and increase the credibility and the validity of related findings.