记忆与排序：提升大型语言模型用于临床诊断预测
Memorize and Rank: Elevating Large Language Models for Clinical Diagnosis Prediction
- University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
- Optum AI（奥普腾人工智能公司）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出MERA临床诊断预测模型，通过分层对比学习缓解庞大决策空间问题，并利用微调进行概念记忆以连接自然语言知识与医疗代码，在MIMIC-III和IV上实现了最先进的诊断预测性能。
AI中文摘要：
临床诊断预测模型在获取患者病史后，旨在早期发现潜在疾病，促进及时干预并改善预后。然而，患者数据固有的稀缺性和庞大的疾病候选空间，常为开发令人满意的模型带来挑战。利用大型语言模型（LLMs）封装临床决策过程的探索仍然有限。我们提出了MERA，一种临床诊断预测模型，它将自然语言知识与医疗实践相连接。我们在疾病候选排序列表上应用分层对比学习，以缓解庞大决策空间的问题。通过微调进行概念记忆，我们将自然语言临床知识与医疗代码相连接。在MIMIC-III和IV数据集上的实验结果表明，MERA实现了最先进的诊断预测性能，并显著提升了生成式LMs的诊断预测能力。
英文摘要：
Clinical diagnosis prediction models, when provided with a patient's medical history, aim to detect potential diseases early, facilitating timely intervention and improving prognostic outcomes. However, the inherent scarcity of patient data and large disease candidate space often pose challenges in developing satisfactory models for this intricate task. The exploration of leveraging Large Language Models (LLMs) for encapsulating clinical decision processes has been limited. We introduce MERA, a clinical diagnosis prediction model that bridges pertaining natural language knowledge with medical practice. We apply hierarchical contrastive learning on a disease candidate ranking list to alleviate the large decision space issue. With concept memorization through fine-tuning, we bridge the natural language clinical knowledge with medical codes. Experimental results on MIMIC-III and IV datasets show that MERA achieves the state-of-the-art diagnosis prediction performance and dramatically elevates the diagnosis prediction capabilities of generative LMs.
