arXiv 2603.080722026-05-25cs.LG

混合量子神经网络用于多变量临床时间序列预测

Hybrid Quantum Neural Network for Multivariate Clinical Time Series Forecasting

Department of Diagnostics and Intervention, Radiation Physics, Biomedical Engineering, Umeå University, Sweden（诊断与介入部门，辐射物理，生物医学工程，乌梅大学，瑞典）；Department of Naval, Electrical, Electronics and Telecommunications Engineering, University of Genoa, Italy（海军、电气、电子与电信工程部门，热那亚大学，意大利）

Irene Iele, Floriano Caprio, Paolo Soda, Matteo Tortora

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出一种混合量子-经典架构，将变分量子电路集成到循环神经网络中，用于多变量生理时间序列的多步预测，在BIDMC数据集上表现出与基线相当的精度和更强的鲁棒性。

摘要：

预测生理信号可以通过预期患者状态的临界变化来支持主动监测和及时的临床干预。在这项工作中，我们通过联合预测心率、血氧饱和度、脉搏率和呼吸率在15、30和60秒的预测时域上，解决了生理时间序列的多变量多步预测问题。我们提出了一种混合量子-经典架构，将变分量子电路（VQC）集成到循环神经骨干中。GRU编码器将历史观察窗口总结为潜在表示，然后将其投影到用于参数化VQC的量子角度上。量子层作为可学习的非线性特征混合器，在最终预测阶段之前建模跨变量交互。我们在BIDMC PPG和呼吸数据集上采用留一患者方案评估了所提出的方法。结果显示，与经典和深度学习基线相比，该方法具有竞争性的精度，同时对噪声和缺失输入具有更强的鲁棒性。这些发现表明，混合量子层可以为小队列临床环境中的生理时间序列预测提供有用的归纳偏置。代码可在https://github.com/arco-group/quantum-ml获取。

英文摘要：

Forecasting physiological signals can support proactive monitoring and timely clinical intervention by anticipating critical changes in patient status. In this work, we address multivariate multi-horizon forecasting of physiological time series by jointly predicting heart rate, oxygen saturation, pulse rate, and respiratory rate at forecasting horizons of 15, 30, and 60 seconds. We propose a hybrid quantum-classical architecture that integrates a Variational Quantum Circuit (VQC) within a recurrent neural backbone. A GRU encoder summarizes the historical observation window into a latent representation, which is then projected into quantum angles used to parameterize the VQC. The quantum layer acts as a learnable non-linear feature mixer, modeling cross-variable interactions before the final prediction stage. We evaluate the proposed approach on the BIDMC PPG and Respiration dataset under a Leave-One-Patient-Out protocol. The results show competitive accuracy compared with classical and deep learning baselines, together with greater robustness to noise and missing inputs. These findings suggest that hybrid quantum layers can provide useful inductive biases for physiological time series forecasting in small-cohort clinical settings. The code is available at https://github.com/arco-group/quantum-ml.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。