研究人员开发了一个自动化系统，利用自然语言处理（NLP）和机器学习（ML）对精神疾病诊断进行分类。该研究在一个包含超过145,000份西班牙语精神病描述的数据集上，评估了包括e5_large、BioLORD和Llama-3-8B等经典模型和大型语言模型（LLM）在内的各种文本表示方法。研究结果表明，基于Transformer的嵌入方法显著优于传统方法，经过微调的e5_large模型达到了0.866的最高F1分数。这项工作强调了将LLM适应专业临床语言以实现准确诊断编码的重要性。 AI
影响 展示了LLM通过自动化复杂的诊断编码来减轻医疗保健领域行政负担的潜力。
排序理由 该集群包含一篇学术论文，详细介绍了特定AI应用的新方法和基准测试结果。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2605.21154v1 Announce Type: cross Abstract: Mental health has become a global priority, leading to a massive administrative burden in the coding of clinical diagnoses. This study proposes the automation of psychiatric diagnostic analysis by mapping free-text descriptions to…
Mental health has become a global priority, leading to a massive administrative burden in the coding of clinical diagnoses. This study proposes the automation of psychiatric diagnostic analysis by mapping free-text descriptions to the International Classification of Diseases (ICD…
Mental health has become a global priority, leading to a massive administrative burden in the coding of clinical diagnoses. This study proposes the automation of psychiatric diagnostic analysis by mapping free-text descriptions to the International Classification of Diseases (ICD…