Abstract
We aimed to find the most representative connectivity patterns for minimal hepatic encephalopathy (MHE) using large-scale intrinsic connectivity networks (ICNs) and machine learning methods. Resting-state fMRI was administered to 33 cirrhotic patients with MHE and 43 cirrhotic patients without MHE (NMHE). The connectivity maps of 20 ICNs for each participant were obtained by dual regression. A Bayesian machine learning technique, called Graphical Model-based Multivariate Analysis, was applied to determine ICN regions that characterized group differences. The most representative ICNs were evaluated by the performance of three machine learning methods (support vector machines (SVMs), multilayer perceptrons (MLP), and C4.5). The clinical significance of these potential biomarkers was further tested. The temporal lobe network (TLN), and subcortical network (SCN), and sensorimotor network (SMN) were selected as representative ICNs. The distinct functional integration patterns of the representative ICNs were significantly correlated with behavior criteria and Child-Pugh scores. Our findings suggest the representative ICNs based on GAMMA can distinguish MHE from NMHE and provide supplementary information to current MHE diagnostic criteria.
Highlights
33–50% of patients with liver cirrhosis without clinical symptoms of encephalopathy have minimal hepatic encephalopathy (MHE)[1]
We found that the diagnostic models based on the three intrinsic connectivity networks (ICNs), temporal lobe network (TLN), subcortical network (SCN), and sensorimotor network (SMN), were accurate in distinguishing MHE patients from NMHE patients with high sensitivity and specificity
The graphical model-based multivariate analysis (GAMMA)-based biomarkers selected by machine learning methods demonstrated that patients with MHE tended to have disconnections within these three ICNs, and distinct functional integration patterns were significantly associated with behavior criteria and Child-Pugh scores
Summary
33–50% of patients with liver cirrhosis without clinical symptoms of encephalopathy have minimal hepatic encephalopathy (MHE)[1]. Previous studies have indicated that the benefits of MRI/fMRI-based diagnostic models are twofold[24,25,26] These methods could provide objective and accurate neuroimaging markers for subsequent investigation. The principal limitation of this work was that all features were preselected out of CV based on statistical analysis between groups Both of the previously discussed studies considered limited ICNs in the model generation, whereas the investigation of large-scale ICNs is more beneficial for understudying the neuropathological mechanism of MHE22. There exists a vast body of literature regarding quantification of voxel-wise intrinsic connectivity levels of certain ICNs for MHE20–23, 27, 28 Most of these studies were based on general linear models (GLMs), a widely used method that models interactions by computing a t statistic between groups[29]. GAMMA has been employed in many neuroscience related applications, such as brain volume morphometry of sickle cell disease[33] and fMRI data of Alzheimer’s Disease[34]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
