用Transformer和霍克斯过程建模患者医疗轨迹，提升罕见高危事件预测能力。
Modeling Patient Care Trajectories with Transformer Hawkes Processes
- 结合Transformer与霍克斯过程，捕捉医疗事件的时间依赖性。
- 在真实数据上显著提升罕见事件预测敏感度，尤其对高危人群识别有效。
- 适合临床风险预测、个性化医疗决策支持场景使用。
患者医疗行为由不规则时间戳的事件构成，如门诊、住院和急诊，形成个体化治疗轨迹。建模这些轨迹对理解利用模式和预测未来需求至关重要，但受时间不规则性和严重类别不平衡影响而困难。本文基于Transformer霍克斯过程框架，在连续时间中建模患者轨迹。通过将Transformer历史编码与霍克斯过程动态结合，模型可捕捉事件依赖关系，并联合预测事件类型与时间至事件。为应对极端不平衡问题，引入基于反平方根的类别加权训练策略，提升对罕见但临床重要的事件的敏感性，且不改变数据分布。在真实数据上的实验表明模型性能提升，并提供具有临床意义的高风险人群识别洞察。
原文摘要 · Abstract (English)
Patient healthcare utilization consists of irregularly time-stamped events, such as outpatient visits, inpatient admissions, and emergency encounters, forming individualized care trajectories. Modeling these trajectories is crucial for understanding utilization patterns and predicting future care needs, but is challenging due to temporal irregularity and severe class imbalance. In this work, we build on the Transformer Hawkes Process framework to model patient trajectories in continuous time. By combining Transformer-based history encoding with Hawkes process dynamics, the model captures event dependencies and jointly predicts event type and time-to-event. To address extreme imbalance, we introduce an imbalance-aware training strategy using inverse square-root class weighting. This improves sensitivity to rare but clinically important events without altering the data distribution. Experiments on real-world data demonstrate improved performance and provide clinically meaningful insights for identifying high-risk patient populations.
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。