Zhang Gaoyan, Li Yuexuan, Zhang Xiaodong, Huang Lixiang, Cheng Yue, Shen Wen
College of Intelligence and Computing, Tianjin Key Lab of Cognitive Computing and Application, Tianjin University, Tianjin, China.
Department of Radiology, Tianjin First Central Hospital, Tianjin, China.
Front Neurosci. 2021 Jan 11;14:627062. doi: 10.3389/fnins.2020.627062. eCollection 2020.
Hepatic encephalopathy (HE) is a neurocognitive dysfunction based on metabolic disorders caused by severe liver disease, which has a high one-year mortality. Mild hepatic encephalopathy (MHE) has a high risk of converting to overt HE, and thus the accurate identification of MHE from cirrhosis with no HE (noHE) is of great significance in reducing mortality. Previously, most studies focused on studying abnormality in the static brain networks of MHE to find biomarkers. In this study, we aimed to use multi-layer modular algorithm to study abnormality in dynamic graph properties of brain network in MHE patients and construct a machine learning model to identify individual MHE from noHE. Here, a time length of 500-second resting-state functional MRI data were collected from 41 healthy subjects, 32 noHE patients and 30 MHE patients. Multi-layer modular algorithm was performed on dynamic brain functional connectivity graph. The connection-stability score was used to characterize the loyalty in each brain network module. Nodal flexibility, cohesion and disjointness were calculated to describe how the node changes the network affiliation across time. Results show that significant differences between MHE and noHE were found merely in nodal disjointness in higher cognitive network modules (ventral attention, fronto-parietal, default mode networks) and these abnormalities were associated with the decline in patients' attention and visual memory function evaluated by Digit Symbol Test. Finally, feature extraction from node disjointness with the support vector machine classifier showed an accuracy of 88.71% in discrimination of MHE from noHE, which was verified by different window sizes, modular partition parameters and machine learning parameters. All these results show that abnormal nodal disjointness in higher cognitive networks during brain network evolution can be seemed as a biomarker for identification of MHE, which help us understand the disease mechanism of MHE at a fine scale.
肝性脑病（HE）是一种由严重肝病引起的基于代谢紊乱的神经认知功能障碍，其一年死亡率很高。轻度肝性脑病（MHE）转化为显性HE的风险很高，因此从无HE（noHE）的肝硬化患者中准确识别MHE对于降低死亡率具有重要意义。此前，大多数研究集中在研究MHE静态脑网络的异常以寻找生物标志物。在本研究中，我们旨在使用多层模块化算法研究MHE患者脑网络动态图属性的异常，并构建一个机器学习模型以从noHE中识别个体MHE。在此，我们收集了41名健康受试者、32名noHE患者和30名MHE患者的时长为500秒的静息态功能磁共振成像数据。对动态脑功能连接图执行多层模块化算法。连接稳定性评分用于表征每个脑网络模块中的忠诚度。计算节点灵活性、凝聚性和不相交性以描述节点如何随时间改变网络归属。结果表明，仅在较高认知网络模块（腹侧注意、额顶叶、默认模式网络）的节点不相交性方面发现MHE与noHE之间存在显著差异，并且这些异常与通过数字符号测试评估的患者注意力和视觉记忆功能下降相关。最后，使用支持向量机分类器从节点不相交性进行特征提取，在区分MHE与noHE方面的准确率为88.71%，这在不同窗口大小、模块化划分参数和机器学习参数下得到了验证。所有这些结果表明，脑网络演化过程中较高认知网络中异常的节点不相交性可被视为识别MHE的生物标志物，这有助于我们在精细尺度上理解MHE的疾病机制。
