Patient-adaptable intracranial pressure morphology analysis using a probabilistic model-based approach.
Patient-adaptable intracranial pressure morphology analysis using a probabilistic model-based approach.
复制标题
DOI：
10.1088/1361-6579/abbcbb
复制
发表时间：
2020-11-06
影响因子：
3.2
通讯作者：
Russell S
中科院分区：
文献类型：
--
作者：
Rashidinejad P;Hu X;Russell S
我们提出了一个分析颅内压（ICP）形态的框架。分析ICP信号是具有挑战性的，这是由于信号动态的非线性和非高斯特性、不可避免的噪声和伪影破坏以及具有不同神经状况的个体之间ICP脉冲形态的变化。现有的框架对ICP动态做出了不切实际的假设，并且没有针对个体患者进行调整。我们提出了一个动态贝叶斯网络（DBN）的三个主要的ICP脉动成分的自动检测。所提出的模型捕获ICP形态的非线性和非高斯动态，并进一步适应于患者，因为接收到个体的ICP测量结果。为了使该方法更加鲁棒，我们利用证据反转，并提出了一种推理算法，以获得脉动分量位置的后验分布。我们在包含66名神经系统患者超过700小时记录的数据集上评估了我们的方法，其中脉动成分已在之前的研究中进行了注释。该算法获得了96.56%，92.39%和94.04%的准确度检测测试集上的每一个脉动分量，显示出显着的改进，比现有的方法。连续ICP监测对于指导创伤性脑损伤等神经系统疾病的治疗至关重要。ICP形态分析的自动化方法朝着以最少的监督来增强患者护理迈出了一步。与以前的方法相比，我们的框架提供了几个优点。它以无监督的方式学习对每个患者的ICP进行建模的参数，从而进行准确的形态分析。基于贝叶斯模型的框架提供了不确定性估计，并揭示了关于国际比较方案动态的有趣事实。该框架可以很容易地应用于取代现有的形态分析方法，并支持ICP脉冲形态特征的应用，以帮助监测与急性脑损伤患者护理相关的病理生理变化。
We present a framework for analyzing the intracranial pressure (ICP) morphology. Analyzing ICP signals is challenging due to the non-linear and non-Gaussian characteristics of the signal dynamics, inevitable corruption with noise and artifacts, and variations in the ICP pulse morphology among individuals with different neurological conditions. Existing frameworks make unrealistic assumptions regarding ICP dynamics and are not tuned for individual patients. We propose a dynamic Bayesian network (DBN) for automated detection of three major ICP pulsatile components. The proposed model captures the non-linear and non-Gaussian dynamics of the ICP morphology and further adapts to a patient as the individual’s ICP measurements are received. To make the approach more robust, we leverage evidence reversal and present an inference algorithm to obtain the posterior distribution over the locations of pulsatile components. We evaluate our approach on a dataset with over 700 hours of recordings from 66 neurological patients, where the pulsatile components have been annotated in prior studies. The algorithm obtains an accuracy of 96.56%, 92.39%, and 94.04% for detecting each pulsatile component on the test set, showing significant improvements over existing approaches. Continuous ICP monitoring is essential in guiding the treatment of neurological conditions such as traumatic brain injuries. An automated approach for ICP morphology analysis takes a step toward enhancing patient care with minimal supervision. Compared to previous methods, our framework offers several advantages. It learns the parameters that model each patient’s ICP in an unsupervised manner, resulting in an accurate morphology analysis. The Bayesian model-based framework provides uncertainty estimates and reveals interesting facts about ICP dynamics. The framework can be readily applied to replace existing morphological analysis methods and support the application of ICP pulse morphological features to aid the monitoring of pathophysiological changes of relevance to the care of patients with acute brain injuries.
登录
查看更多内容
DOI：
10.1109/tbme.2008.2008636
发表时间：
2009-03
期刊：
IEEE transactions on bio-medical engineering
影响因子：
--
作者：
Hu X;Xu P;Scalzo F;Vespa P;Bergsneider M
通讯作者：
Bergsneider M
影响因子：
4.6
作者：
Hornero, R;Aboy, M;Goldstein, B
通讯作者：
Goldstein, B
影响因子：
3.5
作者：
Asgari, Shadnaz;Bergsneider, Marvin;Hamilton, Robert;Vespa, Paul;Hu, Xiao
通讯作者：
Hu, Xiao
影响因子：
3.2
作者：
Asgari S;Vespa P;Bergsneider M;Hu X
通讯作者：
Hu X
影响因子：
4.6
作者：
Calisto, Andrea;Galeano, Massimiliano;Azzerboni, Bruno
通讯作者：
Azzerboni, Bruno