保护隐私、提高可及性并降低成本：一种用于医疗转录与病历生成的端侧人工智能模型
Preserving Privacy, Increasing Accessibility, and Reducing Cost: An On-Device Artificial Intelligence Model for Medical Transcription and Note Generation
AI总结：
本文提出并评估了一种基于微调Llama 3.2 1B的端侧医疗转录系统，通过LoRA在浏览器内实现隐私保护的结构化病历生成，显著提升ROUGE等指标并减少幻觉。
摘要：
背景：临床文档记录给医疗服务提供者带来了沉重负担，医生每天在行政事务上花费的时间多达2小时。大语言模型（LLMs）的最新进展提供了有前景的解决方案，但隐私问题和计算需求限制了它们在医疗环境中的采用。目的：开发并评估一个保护隐私的端侧医疗转录系统，该系统使用经过微调的Llama 3.2 1B模型，能够从医疗转录内容中生成结构化医疗记录，同时在浏览器中完全保持数据主权。方法：我们使用参数高效微调（PEFT）和LoRA方法，在1,500对合成的医疗转录到结构化记录数据上对Llama 3.2 1B模型进行了微调。该模型在两个数据集上与基础版Llama 3.2 1B进行了评估：100份内分泌科转录记录和140个修改后的ACI基准测试案例。评估同时采用了统计指标（ROUGE、BERTScore、BLEURT）和跨多个临床质量维度的LLM-as-judge评估。结果：微调后的OnDevice模型相比基础模型表现出显著改进。在ACI基准测试上，ROUGE-1分数从0.346提高到0.496，而BERTScore F1从0.832提高到0.866。临床质量评估显示重大幻觉明显减少（从85例降至35例），事实正确性增强（5分制评分从2.81提高到3.54）。在内部评估数据集上也观察到类似改进，综合得分从3.13提高到4.43（+41.5%）。结论：对紧凑型LLMs进行医疗转录微调能够带来具有临床意义的改进，同时实现完全的端侧浏览器部署。该方法解决了医疗领域采用AI的关键障碍：隐私保护、成本降低以及资源受限环境下的可及性。
英文摘要：
Background: Clinical documentation represents a significant burden for healthcare providers, with physicians spending up to 2 hours daily on administrative tasks. Recent advances in large language models (LLMs) offer promising solutions, but privacy concerns and computational requirements limit their adoption in healthcare settings. Objective: To develop and evaluate a privacy-preserving, on-device medical transcription system using a fine-tuned Llama 3.2 1B model capable of generating structured medical notes from medical transcriptions while maintaining complete data sovereignty entirely in the browser. Methods: We fine-tuned a Llama 3.2 1B model using Parameter-Efficient Fine-Tuning (PEFT) with LoRA on 1,500 synthetic medical transcription-to-structured note pairs. The model was evaluated against the base Llama 3.2 1B on two datasets: 100 endocrinology transcripts and 140 modified ACI benchmark cases. Evaluation employed both statistical metrics (ROUGE, BERTScore, BLEURT) and LLM-as-judge assessments across multiple clinical quality dimensions. Results: The fine-tuned OnDevice model demonstrated substantial improvements over the base model. On the ACI benchmark, ROUGE-1 scores increased from 0.346 to 0.496, while BERTScore F1 improved from 0.832 to 0.866. Clinical quality assessments showed marked reduction in major hallucinations (from 85 to 35 cases) and enhanced factual correctness (2.81 to 3.54 on 5-point scale). Similar improvements were observed on the internal evaluation dataset, with composite scores increasing from 3.13 to 4.43 (+41.5%). Conclusions: Fine-tuning compact LLMs for medical transcription yields clinically meaningful improvements while enabling complete on-device browser deployment. This approach addresses key barriers to AI adoption in healthcare: privacy preservation, cost reduction, and accessibility for resource-constrained environments.
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。
