DeepAJM:面向不规则采样数据的深度联合模型
Get the story
2026年10月7日,研究者在 arXiv(Statistics Machine Learning)发布论文,提出面向不规则采样数据的深度关联联合模型 DeepAJM。该模型无需参数假设,可同时建模纵向与生存结局,并保留按纵向结局划分的可解释关联结构。其采用 encoder-decoder(sequence-to-sequence)架构,学习患者时变协变量轨迹的潜在结构;解码器输出的每个纵向结果在进入生存头风险评分前,由基线协变量重新调制。目前公开信息仅涉及该论文的方法描述,尚无后续验证或应用报道。
Generated from reports · updated 3 hr ago
Timeline
Follow the coverage from different angles.
- arXiv · Statistics Machine LearningDeepAJM:面向不规则采样数据的深度关联联合模型
研究者提出深度联合模型 DeepAJM,无需参数假设即可同时建模纵向与生存结局,并保留按纵向结局划分的可解释关联结构。模型采用 encoder-decoder(sequence-to-sequence)架构学习患者时变协变量轨迹的潜在结构,解码器输出的每个纵向结果在进入生存头风险评分前由基线协变量重新调制。
Heat trend
Current heat 9·Comparable peak 10(Oct 7)·Comparable change over 24 hours –
The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.