领域适应的小语言模型用于可靠的临床分诊
Domain-Adapted Small Language Models for Reliable Clinical Triage
AI总结：
本文研究了小语言模型在急诊分诊中的应用，发现通过领域适应可显著降低误诊率，Qwen2.5-7B模型在准确性和效率上表现最佳。
摘要：
准确且一致的急诊严重指数（ESI）分配仍然是急诊科的持续挑战，其中高度变化的自由文本分诊记录导致误诊和流程低效。本研究评估了开源小语言模型（SLMs）是否能作为可靠的、隐私保护的决策支持工具用于临床分诊。我们系统比较了多个SLMs在多样提示管道中的表现，发现临床情景摘要，即简短的分诊叙述总结，产生了最准确的预测。SLM Qwen2.5-7B在准确性、稳定性和计算效率方面表现最强。通过大规模领域适应使用专家编纂和银标准儿科分诊数据，微调的Qwen2.5-7B模型显著降低了不一致性和临床显著性错误，优于所有基线SLMs和先进的专有大语言模型（LLMs，例如GPT-4o）。这些发现突显了机构特定SLMs在可靠、隐私保护的ESI决策支持中的可行性，并强调了有针对性的微调优于更复杂的推理策略的重要性。
英文摘要：
Accurate and consistent Emergency Severity Index (ESI) assignment remains a persistent challenge in emergency departments, where highly variable free-text triage documentation contributes to mistriage and workflow inefficiencies. This study evaluates whether open-source small language models (SLMs) can serve as reliable, privacy-preserving decision-support tools for clinical triage. We systematically compared multiple SLMs across diverse prompting pipelines and found that clinical vignettes, concise summaries of triage narratives, yielded the most accurate predictions. The SLM, Qwen2.5-7B, demonstrated the strongest balance of accuracy, stability, and computational efficiency. Through large-scale domain adaptation using expert-curated and silver-standard pediatric triage data, fine-tuned Qwen2.5-7B models substantially reduced discordance and clinically significant errors, outperforming all baseline SLMs and advanced proprietary large language models (LLMs, e.g., GPT-4o). These findings highlight the feasibility of institution-specific SLMs for reliable, privacy-preserving ESI decision support and underscore the importance of targeted fine-tuning over more complex inference strategies.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
