TrajGPT能处理不规则医疗时间序列，精准预测疾病发展轨迹。
TrajGPT: Irregular Time-Series Representation Learning for Health Trajectory Analysis
- 用自适应注意力机制动态筛选历史信息，捕捉连续健康变化规律。
- 在药物使用和疾病分类任务中表现优异，无需微调即可跨任务应用。
- 适合医疗轨迹预测、疾病风险推演等临床场景，可补全不完整病历数据。
在医疗等领域，时间序列常以不规则间隔采样，传统模型因要求等距数据难以适用。为此，我们提出新型时间序列Transformer——轨迹生成预训练模型（TrajGPT）。TrajGPT采用新颖的选定递归注意力（SRA）机制，基于上下文自适应地衰减无关历史信息。通过将TrajGPT解释为离散化的常微分方程（ODEs），其有效捕捉潜在连续动态，支持任意目标时间点的时序推理。实验表明，TrajGPT在轨迹预测、用药预测和表型分类任务中表现卓越，无需任务特定微调。通过演化学习到的连续动态，该模型可对部分观测的时间序列进行插值与外推，预测疾病风险轨迹。可视化显示，其能基于临床相关表型历史，预测未出现的疾病。
原文摘要 · Abstract (English)
In many domains, such as healthcare, time-series data is often irregularly sampled with varying intervals between observations. This poses challenges for classical time-series models that require equally spaced data. To address this, we propose a novel time-series Transformer called Trajectory Generative Pre-trained Transformer (TrajGPT). TrajGPT employs a novel Selective Recurrent Attention (SRA) mechanism, which utilizes a data-dependent decay to adaptively filter out irrelevant past information based on contexts. By interpreting TrajGPT as discretized ordinary differential equations (ODEs), it effectively captures the underlying continuous dynamics and enables time-specific inference for forecasting arbitrary target timesteps. Experimental results demonstrate that TrajGPT excels in trajectory forecasting, drug usage prediction, and phenotype classification without requiring task-specific fine-tuning. By evolving the learned continuous dynamics, TrajGPT can interpolate and extrapolate disease risk trajectories from partially-observed time series. The visualization of predicted health trajectories shows that TrajGPT forecasts unseen diseases based on the history of clinically relevant phenotypes (i.e., contexts).
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。