用多模态注意力模型提升急诊分诊准确率
Multimodal Attention-based Deep Learning for Emergency Triage with Electronic Health Records
- 融合文本主诉与数值生命体征的多模态深度学习架构
- 相较基线模型准确率提升1.95%，F1-score提高2.49%
- 适合医疗AI研发者及急诊决策系统优化人员参考
准确的急诊分诊对避免临床恶化、发病率和死亡率至关重要。基于机器学习的分诊系统需处理文本形式的主要主诉和数值型生命体征数据，实现患者信息的自动化高效分析，以及时准确地优先分配医疗资源。然而，建模两类数据的复杂性需要深入理解其时间结构与依赖关系。因此，本研究提出一种多模态深度学习架构，可有效处理表格数据与文本数据。该模型利用自注意力机制捕捉特征间的局部与全局关联。研究使用来自马来西亚理科大学医院急诊科的11,102条分诊数据进行模型开发与验证。结果表明，相比基线模型，该方法在准确率上提升1.95%，F1-score提高2.49%，ROC AUC提升1.41%。实验结果证明了该模型在预测分诊决策方面的潜力。
原文摘要 · Abstract (English)
Accurate emergency triage decision is critical to avoid clinical deterioration, morbidity, and mortality. Machine learning-based triage system involves acquiring the main presenting complaint in text form and assessing vital signs in numerical data, enabling an automated and efficient analysis of patient information for timely and accurate prioritization of medical attention. However, modelling the intricacies of both data types requires a comprehensive understanding of the temporal structure and dependencies within the data. Thus, the aim of this study is to propose a multimodal deep learning architecture that can effectively handle both tabular and textual data. Furthermore, the proposed model exploits self-attention to to capture both local and global relationships between the features. A dataset consisting of 11,102 triage data collected from emergency department of Hospital Universiti Sains Malaysia is used for model development and validation. The proposed model demonstrated an increase of 1.95% in accuracy, 2.49% in F1-score, and 1.41% in ROC AUC compared to the baseline model. The experimental results demonstrated the potential of the proposed model in predicting triage decisions.
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。