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.

Objectives: The aims to investigate the mediating effect of intertemporal decision-making on the association between personality traits and self-management among individuals with in Type 2 Diabetes (T2DM).Method: Patients with T2DM in the early stages of hospitalization at two tertiary hospitals in Shenyang and Jinzhou, Liaoning Province, May 2022 to January 2023. Questionnaires, including General Demographic, Self-Management, Big Five Personality, and Intertemporal Decision-Making, were administered. Pearson correlation analysis examined relationships between personality traits, intertemporal decision-making, and self-management. Hierarchical regression analysis identified self-management predictors. Mediation analysis used the PROCESS SPSS Macro version 3.3 model 4 to investigate intertemporal decision-making as mediator between personality traits and self-management.Results: Pearson correlation analysis revealed significant associations between self-management scores, personality traits, and intertemporal decision-making. Hierarchical regression revealed that Neuroticism and Conscientiousness accounted for 20.8% of the variance in self-management, while intertemporal decision-making explained 4.5% of the variance. Finally, using the Bootstrap method, the mediation analysis showed that intertemporal decision-making partially mediated the effect of personality traits on self-management.Conclusion: This study emphasizes the importance of intertemporal decision-making in improving self-management behaviors among patients with T2DM. Interventions targeted at modifying intertemporal decision-making preferences could be effective in enhancing self-management behaviors, leading to better health outcomes.

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