arXiv：cs.LG（机器学习，全量分类）· Manar Aljohani, Brandon Ho, Kenneth McKinley, Dennis Ren, Xuan Wang·· 15 小时前AI 评分35
领域自适应小语言模型用于可靠临床分诊
Domain-Adapted Small Language Models for Reliable Clinical Triage
AI 导读
研究评估开源小语言模型能否作为隐私保护的临床分诊决策支持工具，发现 Qwen2.5-7B 在准确率、稳定性和计算效率上表现最均衡。经专家标注和银标准儿科分诊数据大规模领域自适应微调后，Qwen2.5-7B 显著降低不一致率和临床显著错误，优于所有基线 SLM 及 GPT-4o 等专有 LLM。
正文
Abstract: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.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2604.26766 [cs.CL] |
| (or arXiv:2604.26766v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2604.26766 arXiv-issued DOI via DataCite |
Submission history
From: Manar Aljohani [view email]
[v1]
Wed, 29 Apr 2026 15:00:09 UTC (657 KB)
[v2]
Thu, 1 Oct 2026 15:46:50 UTC (729 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org