Physics-driven Spatiotemporal Regularization for High-dimensional Predictive Modeling: A Novel Approach to Solve the Inverse ECG Problem.

Physics-driven Spatiotemporal Regularization for High-dimensional Predictive Modeling: A Novel Approach to Solve the Inverse ECG Problem.
复制标题

物理驱动的时空正则化用于高维预测建模:一种解决反为ECG问题的新方法。

DOI:
10.1038/srep39012
复制
发表时间:
2016-12-14
期刊:
影响因子:
4.6
通讯作者:
Yang H
Yang H
中科院分区:
综合性期刊3区
文献类型:
--
作者:
Yao B;Yang H

文献摘要

参考文献

被引文献

相似文献

本文提出了一种新颖的物理驱动时空正则化(STRE)方法,用于复杂医疗系统中的高维预测建模。该模型不仅捕获了分布在空间中的时变解释变量和响应变量之间基于物理的相互关系,而且还解决了空间和时间正则化问题,以提高预测性能。 STRE 模型的实现是根据来自放置在身体表面的分布式传感器网络的心电图 (ECG) 数据来预测心脏表面电位随时间的变化分布。在模拟的双球体几何结构和真实的躯干心脏几何结构中对模型性能进行了评估和验证。实验结果表明,STRE模型显着优于当前实践中广泛使用的其他正则化模型,例如Tikhonov零阶、Tikhonov一阶和L1一阶正则化方法。
This paper presents a novel physics-driven spatiotemporal regularization (STRE) method for high-dimensional predictive modeling in complex healthcare systems. This model not only captures the physics-based interrelationship between time-varying explanatory and response variables that are distributed in the space, but also addresses the spatial and temporal regularizations to improve the prediction performance. The STRE model is implemented to predict the time-varying distribution of electric potentials on the heart surface based on the electrocardiogram (ECG) data from the distributed sensor network placed on the body surface. The model performance is evaluated and validated in both a simulated two-sphere geometry and a realistic torso-heart geometry. Experimental results show that the STRE model significantly outperforms other regularization models that are widely used in current practice such as Tikhonov zero-order, Tikhonov first-order and L1 first-order regularization methods.
DOI: 10.1109/tbme.1977.326201
发表时间: 1977-01-01
影响因子: 4.6
作者:
BARR, RC;RAMSEY, M;SPACH, MS
通讯作者: SPACH, MS
DOI: 10.1109/tase.2015.2459068
发表时间: 2016-01-01
影响因子: 5.6
作者:
Chen, Yun;Yang, Hui
通讯作者: Yang, Hui
DOI: 10.1109/tbme.2010.2063704
发表时间: 2011-02-01
影响因子: 4.6
作者:
Yang, Hui
通讯作者: Yang, Hui
DOI: 10.1016/s0022-0736(99)90025-0
发表时间: 1999-01-01
影响因子: 1.3
作者:
Rudy, Y
通讯作者: Rudy, Y
DOI: 10.1080/00401706.1970.10488634
发表时间: 1970-01-01
期刊: TECHNOMETRICS
影响因子: 2.5
作者:
HOERL, AE;KENNARD, RW
通讯作者: KENNARD, RW