用VAE统一处理血糖数据缺失和预测，减少人工预处理依赖。
A Multitask VAE for Time Series Preprocessing and Prediction of Blood Glucose Level
- 构建多任务变分自编码器，学习时间序列的预处理隐空间。
- 在糖尿病患者远程监测数据上，预测精度优于现有方法。
- 适合医疗时序数据建模，尤其适用于有缺失值的临床数据。
时序数据分析中，数据预处理至关重要。来自联网医疗设备的数据常存在缺失或异常值，处理此类问题需额外假设与领域知识，耗时且易引入偏差，影响预测模型准确性及医学解读。为此，我们提出一种新型深度学习模型，以减少预处理假设。该模型基于变分自编码器（VAE）生成预处理隐空间，并采用循环变分自编码器（RVAE）保留数据的时间动态特性。我们在远程监测数据上验证了该架构的有效性，用于预测糖尿病患者的血糖水平。结果表明，相比现有最先进方法与模型架构，该模型在预测精度上有所提升。
原文摘要 · Abstract (English)
Data preprocessing is a critical part of time series data analysis. Data from connected medical devices often have missing or abnormal values during acquisition. Handling such situations requires additional assumptions and domain knowledge. This can be time-consuming, and can introduce a significant bias affecting predictive model accuracy and thus, medical interpretation. To overcome this issue, we propose a new deep learning model to mitigate the preprocessing assumptions. The model architecture relies on a variational auto-encoder (VAE) to produce a preprocessing latent space, and a recurrent VAE to preserve the temporal dynamics of the data. We demonstrate the effectiveness of such an architecture on telemonitoring data to forecast glucose-level of diabetic patients. Our results show an improvement in terms of accuracy with respect of existing state-of-the-art methods and architectures.
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。