用病历文本和表格数据提前预测诊断与治疗，提升医疗风险识别能力
Predictive Multimodal Modeling of Diagnoses and Treatments in EHR
- 融合临床文本与表格数据，通过跨模态注意力学习多模态表示
- 在住院早期即实现诊断与治疗的准确预测，性能超越现有最佳模型
- 适合医疗人工智能、临床决策支持系统研究者参考
尽管疾病编码分配问题已被广泛研究，但多数工作集中于出院后的文档分类。若能在患者入院初期就预测诊断与治疗信息，可助力健康风险识别、治疗建议优化及资源调度。为应对住院初期信息有限的挑战，本文提出一种多模态系统，融合电子病历中的临床文本与结构化事件数据。模型结合预训练编码器、特征池化与跨模态注意力机制，动态学习各模态的最优表示，并在每个时间点平衡其影响。此外，设计了一种加权时序损失函数，根据时间调整损失权重。实验表明，该策略显著提升早期预测性能，优于当前最先进方法。
原文摘要 · Abstract (English)
While the ICD code assignment problem has been widely studied, most works have focused on post-discharge document classification. Models for early forecasting of this information could be used for identifying health risks, suggesting effective treatments, or optimizing resource allocation. To address the challenge of predictive modeling using the limited information at the beginning of a patient stay, we propose a multimodal system to fuse clinical notes and tabular events captured in electronic health records. The model integrates pre-trained encoders, feature pooling, and cross-modal attention to learn optimal representations across modalities and balance their presence at every temporal point. Moreover, we present a weighted temporal loss that adjusts its contribution at each point in time. Experiments show that these strategies enhance the early prediction model, outperforming the current state-of-the-art systems.
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。