提出可解释的医疗领域自适应方法，提升预测准确率与透明度。
Exploring Accurate and Transparent Domain Adaptation in Predictive Healthcare via Concept-Grounded Orthogonal Inference
- 将患者表征分解为不变与变化成分，强制正交训练
- 在两个真实EHR数据集上表现优于多数特征对齐模型
- 通过医学概念映射实现人类可理解的解释，适合临床可信部署
基于电子健康记录（EHR）的深度学习临床事件预测模型在不同数据分布下常出现性能下降。尽管领域自适应（DA）方法可缓解分布偏移，但其“黑箱”特性难以满足临床实践中对透明性的要求。本文提出ExtraCare，将患者表征分解为不变与协变成分，并在训练中监督二者且强制正交，既保留标签信息，又暴露领域特异性差异，从而实现比多数特征对齐模型更精准的预测。更重要的是，该方法通过将稀疏隐层维度映射至医学概念，并利用定向消融量化其贡献，提供人类可理解的解释。在两个真实EHR数据集、多种领域划分设置下评估，结果表明其不仅预测更准确，且通过大量案例研究验证了解释能力的优越性。
原文摘要 · Abstract (English)
Deep learning models for clinical event prediction on electronic health records (EHR) often suffer performance degradation when deployed under different data distributions. While domain adaptation (DA) methods can mitigate such shifts, their "black-box" nature prevents widespread adoption in clinical practice where transparency is essential for trust and safety. We propose ExtraCare to decompose patient representations into invariant and covariant components. By supervising these two components and enforcing their orthogonality during training, our model preserves label information while exposing domain-specific variation at the same time for more accurate predictions than most feature alignment models. More importantly, it offers human-understandable explanations by mapping sparse latent dimensions to medical concepts and quantifying their contributions via targeted ablations. ExtraCare is evaluated on two real-world EHR datasets across multiple domain partition settings, demonstrating superior performance along with enhanced transparency, as evidenced by its accurate predictions and explanations from extensive case studies.
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。