融合序列与图像建模，提升不规则医疗时间序列分析精度
Integrating Sequence and Image Modeling in Irregular Medical Time Series Through Self-Supervised Learning
- 联合建模序列与图像表示，统一处理不规则医疗数据
- 在三个真实临床数据集上超越7个主流模型，分类性能更优
- 自监督学习增强鲁棒性，特别适合缺失数据场景
医疗时间序列常呈现不规则性且存在显著缺失，给数据分析和临床决策带来挑战。现有方法多采用单一建模视角，或将其视为序列，或转换为图像表示进行分类。本文提出一种联合学习框架，同时融合序列与图像表征，并设计三种自监督学习策略，以捕获更具泛化能力的联合表示。实验结果表明，该方法在三个代表性真实临床数据集上优于七种先进模型。通过留传感器法和留样本法模拟两类主要缺失模式，进一步验证了本方法的鲁棒性，在分类性能上显著优于基线模型。
原文摘要 · Abstract (English)
Medical time series are often irregular and face significant missingness, posing challenges for data analysis and clinical decision-making. Existing methods typically adopt a single modeling perspective, either treating series data as sequences or transforming them into image representations for further classification. In this paper, we propose a joint learning framework that incorporates both sequence and image representations. We also design three self-supervised learning strategies to facilitate the fusion of sequence and image representations, capturing a more generalizable joint representation. The results indicate that our approach outperforms seven other state-of-the-art models in three representative real-world clinical datasets. We further validate our approach by simulating two major types of real-world missingness through leave-sensors-out and leave-samples-out techniques. The results demonstrate that our approach is more robust and significantly surpasses other baselines in terms of classification performance.
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。