Liu Zitao, Hauskrecht Milos
Computer Science Department, University of Pittsburgh, 210 South Bouquet Street, Pittsburgh, PA 15260, USA.
Computer Science Department, University of Pittsburgh, 210 South Bouquet Street, Pittsburgh, PA 15260, USA.
Artif Intell Med. 2015 Sep;65(1):5-18. doi: 10.1016/j.artmed.2014.10.005. Epub 2014 Nov 6.
Developing machine learning and data mining algorithms for building temporal models of clinical time series is important for understanding of the patient condition, the dynamics of a disease, effect of various patient management interventions and clinical decision making. In this work, we propose and develop a novel hierarchical framework for modeling clinical time series data of varied length and with irregularly sampled observations.
Our hierarchical dynamical system framework for modeling clinical time series combines advantages of the two temporal modeling approaches: the linear dynamical system and the Gaussian process. We model the irregularly sampled clinical time series by using multiple Gaussian process sequences in the lower level of our hierarchical framework and capture the transitions between Gaussian processes by utilizing the linear dynamical system. The experiments are conducted on the complete blood count (CBC) panel data of 1000 post-surgical cardiac patients during their hospitalization. Our framework is evaluated and compared to multiple baseline approaches in terms of the mean absolute prediction error and the absolute percentage error.
We tested our framework by first learning the time series model from data for the patients in the training set, and then using it to predict future time series values for the patients in the test set. We show that our model outperforms multiple existing models in terms of its predictive accuracy. Our method achieved a 3.13% average prediction accuracy improvement on ten CBC lab time series when it was compared against the best performing baseline. A 5.25% average accuracy improvement was observed when only short-term predictions were considered.
A new hierarchical dynamical system framework that lets us model irregularly sampled time series data is a promising new direction for modeling clinical time series and for improving their predictive performance.
开发机器学习和数据挖掘算法以构建临床时间序列的时间模型，对于理解患者病情、疾病动态、各种患者管理干预措施的效果以及临床决策至关重要。在这项工作中，我们提出并开发了一种新颖的分层框架，用于对长度各异且具有不规则采样观测值的临床时间序列数据进行建模。
我们用于对临床时间序列进行建模的分层动态系统框架结合了两种时间建模方法的优点：线性动态系统和高斯过程。我们通过在分层框架的较低层级使用多个高斯过程序列对不规则采样的临床时间序列进行建模，并利用线性动态系统捕捉高斯过程之间的转换。实验是在1000名心脏手术后住院患者的全血细胞计数（CBC）面板数据上进行的。我们的框架在平均绝对预测误差和绝对百分比误差方面进行了评估，并与多种基线方法进行了比较。
我们首先从训练集中患者的数据学习时间序列模型，然后使用该模型预测测试集中患者未来的时间序列值，以此对我们的框架进行测试。我们表明，我们的模型在预测准确性方面优于多个现有模型。与表现最佳的基线相比，我们的方法在十个CBC实验室时间序列上平均预测准确率提高了3.13%。在仅考虑短期预测时，观察到平均准确率提高了5.25%。
一种新的分层动态系统框架，使我们能够对不规则采样的时间序列数据进行建模，这是临床时间序列建模以及提高其预测性能的一个有前景的新方向。
