Background: Large language models (LLMs) have garnered significant attention in the AI domain owing to their exemplary context recognition and response capabilities. However, the potential of LLMs in specific clinical scenarios, particularly in breast cancer diagnosis, treatment, and care, has not been fully explored. This study aimed to compare the performances of three major LLMs in the clinical context of breast cancer. Methods: In this study, clinical scenarios designed specifically for breast cancer were segmented into five pivotal domains (nine cases): assessment and diagnosis, treatment decision-making, postoperative care, psychosocial support, and prognosis and rehabilitation. The LLMs were used to generate feedback for various queries related to these domains. For each scenario, a panel of five breast cancer specialists, each with over a decade of experience, evaluated the feedback from LLMs. They assessed feedback concerning LLMs in terms of their quality, relevance, and applicability. Results: There was a moderate level of agreement among the raters (Fleiss’ kappa=0.345, P<0.05). Comparing the performance of different models regarding response length, GPT-4.0 and GPT-3.5 provided relatively longer feedback than Claude2. Furthermore, across the nine case analyses, GPT-4.0 significantly outperformed the other two models in average quality, relevance, and applicability. Within the five clinical areas, GPT-4.0 markedly surpassed GPT-3.5 in the quality of the other four areas and scored higher than Claude2 in tasks related to psychosocial support and treatment decision-making. Conclusion: This study revealed that in the realm of clinical applications for breast cancer, GPT-4.0 showcases not only superiority in terms of quality and relevance but also demonstrates exceptional capability in applicability, especially when compared to GPT-3.5. Relative to Claude2, GPT-4.0 holds advantages in specific domains. With the expanding use of LLMs in the clinical field, ongoing optimization and rigorous accuracy assessments are paramount.

Increasing evidence highlights a robust correlation between the gut microbiota and bone diseases; however, the existence of a causal relationship between them remains unclear. In this study, we thoroughly examined the correlation between gut microbiota and skeletal diseases using genome-wide association studies. Linkage disequilibrium score regression and Mendelian randomization were used to probe genetic causality. Furthermore, the potential mediating role of neuropsychological states (i.e., cognition, depression, and insomnia) between the gut microbiota and bone diseases was evaluated using mediation analysis, with genetic colocalization analysis revealing potential targets. These findings suggest a direct causal relationship between Ruminococcaceae and knee osteoarthritis (OA), which appears to be mediated by cognitive performance and insomnia. Similarly, a causal association was observed between Burkholderiales and lumbar pelvic fractures, mediated by cognitive performance. Colocalization analysis identified a shared causal variant (rs2352974) at the TRAF-interacting protein locus for cognitive ability and knee OA. This study provides compelling evidence that alterations in the gut microbiota can enhance cognitive ability, ameliorate insomnia, and potentially reduce the risk of site-specific fractures and OA. Therefore, strategies targeting gut microbiota optimization could serve as novel and effective preventive measures against fractures and OA.

An abstract is unavailable. This article is available as a PDF only.

An abstract is unavailable. This article is available as a PDF only.