Importanc: Large language models (LLMs) with retrieval-augmented generation (RAG) show promise for clinical decision support. However, their application is constrained by limited & outdated vector databases, suboptimal evidence retrieval and poor contextual continuity. Objective: To develop and evaluate a novel LLM-based agent that integrates Evidence-Based Medicine (EBM) principles and contextual conversation capabilities in answering clinical questions. Design, Setting and Participants: The agent for clinical decision making was developed and evaluated between July 1, 2024, and July 31, 2025. The system incorporated an EBM-enabled workflow, a memory module and Thought-Action-Observation (TAO) loops. Evaluation 1 assessed the system’s performance on 150 initial clinical questions across 15 cancer types. Evaluation 2 involved 45 multi-turn dialogue tasks (across 3 types). Baselines were state-of-the-art traditional RAG method and commercial LLMs with plugins. All generated responses across both evaluations were independently rated by 3 experts with over five years of clinical experience. The study was performed at West China Medical Center. Main Outcomes and Measures: Each response in evaluation 1 was classified into one of three predefined categories—correct, inaccurate, or wrong. As for evaluation 2, tasks were deemed successful when previous conversation is remembered and answer is correct, otherwise the task was considered unsuccessful. Results: In evaluation 1, EBMChat generated the highest proportion of accurate responses (89% vs 78% for the best baseline method). The superior performance of EBMChat was associated with its ability to retrieve optimal evidence, demonstrated by significantly higher evidence hierarchy (100% vs 17.5% RCT-level or above), stricter evidence timeliness (within 5 years vs from the 1980s onwards), and more comprehensive retrieval (median of 693 vs 267 items/question). Regarding evaluation 2, EBMChat successfully completed 93% of the tasks. In contrast, GPT-4.1 with plugins (Web Search) achieved a success rate of only 31%. This performance gap was attributed to EBM-enabled workflow, memory module and TAO loops, which ensure robust contextual conversation capabilities. Conclusion and Relevanc: EBMChat identifies appropriate evidence by effectively balancing timeliness, hierarchy, and relevance. Meanwhile, its enhanced conversational capabilities facilitate the preservation of contextual data, enabling users to explore clinical problems more deeply or comprehensively in multi-turn dialogues. Our findings underscore that the effective promotion of clinical practice by AI requires deeper integration of core medical principles into the technology itself, rather than direct application of general-purpose AI tools.

Background: To ensure smooth surgical procedures, patient safety, and quality of perioperative care, perceived perioperative competence (PPC) is a daily and urgent requirement for operating room (OR) nurses. Understanding the status of PPC among OR nurses and its associated factors is essential for OR nurses/people in charge/researchers to pinpoint weaknesses and formulate interventions. Therefore, we aim to investigate the status of PPC and its associated factors. Furthermore, we explore the relationship between PPC, self-efficacy, and job burnout among OR nurses. Methods: Tertiary-A hospitals in various districts of Chengdu, China, were recruited using a stratified convenience sampling method. A cross-sectional survey was then administered to OR nurses in the selected hospitals. Data analysis included descriptive analysis, T-tests, one-way analysis of variance (ANOVA), multiple linear regression analysis, correlation analysis, and mediation analysis. Results: A survey of 640 OR nurses across 18 hospitals (with a 98.00% valid response rate) revealed an average PPC score of 3.66 ± 1.12/124.55 ± 26.54. Marital status, OR specialty education, and age significantly influenced PPC levels (p < 0.05). Self-efficacy was positively correlated with PPC, while job burnout was negatively correlated with PPC. Self-efficacy fully mediated the relationship between these two variables. Conclusions: The performances of PPC among Chinese OR nurses were acceptable. Marital status, OR specialty education, and age significantly influenced PPC levels. Self-efficacy fully mediates the relationship between job burnout and PPC.

In recent years, the development of large language models (LLMs) has revolutionized various fields of natural science, yet their application in molecular data processing remains constrained due to the reliance on single-modality inputs and outputs. To bridge the gap between experimenters and computational tools, we introduce ChatMolData, a novel LLM-based multimodal agent designed to handle diverse molecular data forms, including molecular databases, images, structure-specific files and unstructured & structured documents. ChatMolData integrates the capabilities of LLMs (e.g., GPT-4 and GPT-3.5) with robust toolset that supports data retrieval, structuring, prediction, visualization, and search tasks. Our agent employs a systematic cycle of reasoning and action to efficiently process complex tasks in molecular science. The evaluation demonstrates that ChatMolData achieves over 90% accuracy for 128 diverse tasks, significantly lowering barriers for researchers without computer science background. Our findings highlight the agent's potential in advancing molecular research through improved data accessibility and usability.