用简单Transformer精准预测30天再入院风险
PT: A Plain Transformer is Good Hospital Readmission Predictor
- 基于Transformer融合病历、影像和文本数据，直接处理原始信息
- 在仅用病历或仅用文本时仍保持高准确率，30天再入院预测效果更优
- 适合临床部署，对缺失时间信息不敏感，模型简洁可靠
医院再入院预测对临床决策支持至关重要，旨在识别出院后30天内可能返回的患者。高再入院率常反映治疗或出院后照护不足，因此高效预测模型对优化资源和改善预后意义重大。本文提出PT，一种基于Transformer的模型，整合电子健康记录（EHR）、医学影像和临床文本，用于预测30天内全因再入院。PT从原始数据中提取特征，并使用针对数据复杂性定制的Transformer模块。通过随机森林进行EHR特征选择并结合测试时集成技术，PT在准确性、可扩展性和鲁棒性方面表现优异，即使在缺乏时间信息的情况下也能稳定工作。主要贡献包括：(1) 简洁性：一个强大且高效的基准模型，在预测准确率上优于现有方法；(2) 可扩展性：灵活处理多模态数据，仅用临床文本或仅用EHR数据即可实现高性能；(3) 鲁棒性：在时间信息缺失或模糊时仍具备强预测能力。
原文摘要 · Abstract (English)
Hospital readmission prediction is critical for clinical decision support, aiming to identify patients at risk of returning within 30 days post-discharge. High readmission rates often indicate inadequate treatment or post-discharge care, making effective prediction models essential for optimizing resources and improving patient outcomes. We propose PT, a Transformer-based model that integrates Electronic Health Records (EHR), medical images, and clinical notes to predict 30-day all-cause hospital readmissions. PT extracts features from raw data and uses specialized Transformer blocks tailored to the data's complexity. Enhanced with Random Forest for EHR feature selection and test-time ensemble techniques, PT achieves superior accuracy, scalability, and robustness. It performs well even when temporal information is missing. Our main contributions are: (1)Simplicity: A powerful and efficient baseline model outperforming existing ones in prediction accuracy; (2)Scalability: Flexible handling of various features from different modalities, achieving high performance with just clinical notes or EHR data; (3)Robustness: Strong predictive performance even with missing or unclear temporal data.
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。