用心脏科教材训练的文本嵌入模型，检索准确率超现有模型15.94个百分点。
CardioEmbed: Domain-Specialized Text Embeddings for Clinical Cardiology
- 基于七本心血管专著15万句文本，用对比学习训练专用嵌入模型
- 心脏专科语义检索准确率达99.60%，比当前最优模型高15.94个百分点
- 适合临床辅助诊断、医学知识问答等需精准心脏术语理解的场景
生物医学文本嵌入模型主要基于PubMed研究文献训练，但临床心脏病学实践依赖大量来自权威教材的程序性知识和专业术语，而非研究摘要。这一研究与实践的差距限制了现有嵌入模型在心脏病学临床应用中的效果。本研究基于Qwen3-Embedding-8B训练了CardioEmbed，采用对比学习方法，在去重后约15万句的心脏病学教科书语料上进行训练。模型使用InfoNCE损失函数并引入批次内负样本，实现心脏专科语义检索任务99.60%的检索准确率，较当前最优模型MedTE提升15.94个百分点。在MTEB医疗基准测试中，取得BIOSSES 0.77 Spearman相关系数和SciFact 0.61 NDCG@10，表明其在相关生物医学领域具有竞争力。结果表明，基于综合性临床教材的领域专用训练可实现近乎完美的心脏病学检索性能。
原文摘要 · Abstract (English)
Biomedical text embeddings have primarily been developed using research literature from PubMed, yet clinical cardiology practice relies heavily on procedural knowledge and specialized terminology found in comprehensive textbooks rather than research abstracts. This research practice gap limits the effectiveness of existing embedding models for clinical applications incardiology. This study trained CardioEmbed, a domain-specialized embedding model based on Qwen3-Embedding-8B, using contrastive learning on a curated corpus of seven comprehensive cardiology textbooks totaling approximately 150,000 sentences after deduplication. The model employs InfoNCE loss with in-batch negatives and achieves 99.60% retrieval accuracy on cardiac-specific semantic retrieval tasks, a +15.94 percentage point improvement over MedTE, the current state-of-the-art medical embedding model. On MTEB medical benchmarks, the model obtained BIOSSES 0.77 Spearman and SciFact 0.61 NDCG@10, indicating competitive performance on related biomedical domains. Domain-specialized training on comprehensive clinical textbooks yields near-perfect cardiology retrieval (99.60% Acc@1), improving over MedTE by +15.94 percentage points.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。