Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Machine Learning Classification of Cirrhotic Patients with and without Minimal Hepatic Encephalopathy Based on Regional Homogeneity of Intrinsic Brain Activity.

ABSTRACT: Machine learning-based approaches play an important role in examining functional magnetic resonance imaging (fMRI) data in a multivariate manner and extracting features predictive of group membership. This study was performed to assess the potential for measuring brain intrinsic activity to identify minimal hepatic encephalopathy (MHE) in cirrhotic patients, using the support vector machine (SVM) method. Resting-state fMRI data were acquired in 16 cirrhotic patients with MHE and 19 cirrhotic patients without MHE. The regional homogeneity (ReHo) method was used to investigate the local synchrony of intrinsic brain activity. Psychometric Hepatic Encephalopathy Score (PHES) was used to define MHE condition. SVM-classifier was then applied using leave-one-out cross-validation, to determine the discriminative ReHo-map for MHE. The discrimination map highlights a set of regions, including the prefrontal cortex, anterior cingulate cortex, anterior insular cortex, inferior parietal lobule, precentral and postcentral gyri, superior and medial temporal cortices, and middle and inferior occipital gyri. The optimized discriminative model showed total accuracy of 82.9% and sensitivity of 81.3%. Our results suggested that a combination of the SVM approach and brain intrinsic activity measurement could be helpful for detection of MHE in cirrhotic patients.

SUBMITTER: Chen QF

PROVIDER: S-EPMC4792397 | biostudies-literature | 2016

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Classification of cirrhotic patients with or without minimal hepatic encephalopathy and healthy subjects using resting-state attention-related network analysis.

Project description:BackgroundAttention deficit is an early and key characteristic of minimal hepatic encephalopathy (MHE) and has been used as indicator for MHE detection. The aim of this study is to classify the cirrhotic patients with or without MHE (NMHE) and healthy controls (HC) using the resting-state attention-related brain network analysis.Methods and findingsResting-state fMRI was administrated to 20 MHE patients, 21 NMHE patients, and 17 HCs. Three attention-related networks, including dorsal attention network (DAN), ventral attention network (VAN), and default mode network (DMN), were obtained by independent component analysis. One-way analysis of covariance was performed to determine the regions of interest (ROIs) showing significant functional connectivity (FC) change. With FC strength of ROIs as indicators, Linear Discriminant Analysis (LDA) was conducted to differentiate MHE from HC or NMHE. Across three groups, significant FC differences were found within DAN (left superior/inferior parietal lobule and right inferior parietal lobule), VAN (right superior parietal lobule), and DMN (bilateral posterior cingulate gyrus and precuneus, and left inferior parietal lobule). With FC strength of ROIs from three networks as indicators, LDA yielded 94.6% classification accuracy between MHE and HC (100% sensitivity and 88.2% specificity) and 85.4% classification accuracy between MHE and NMHE (90.0% sensitivity and 81.0% specificity).ConclusionsOur results suggest that the resting-state attention-related brain network analysis can be useful in classification of subjects with MHE, NMHE, and HC and may provide a new insight into MHE detection.

| S-EPMC3960105 | biostudies-literature

Disrupted Brain Intrinsic Networks and Executive Dysfunction in Cirrhotic Patients without Overt Hepatic Encephalopathy.

Project description:ObjectivePatients with cirrhosis often exhibit cognitive deficits, particularly executive dysfunction, which is considered a predictor of overt hepatic encephalopathy (OHE). We examined brain intrinsic networks associated with executive function to investigate the neural basis of this cognitive deficiency in cirrhosis.MethodsResting-state functional MRI data were acquired from 20 cirrhotic patients and 18 healthy controls. Seed-based correlation analysis was used to identify the three well-known networks associated with executive function, including executive control (ECN), default mode (DMN), and salience (SN) networks. Functional connectivity (FC) within each network was compared between groups and correlated with patient executive performance (assessed by the Stroop task).ResultsPatients showed decreased FC between the ECN seed (right dorsolateral prefrontal cortex) and several regions (including right middle/inferior frontal gyrus, left inferior frontal gyrus, bilateral inferior/superior parietal lobules, bilateral middle/inferior temporal gyrus, and right medial frontal gyrus), between the DMN seed [posterior cingulate cortex (PCC)] and several regions (including bilateral medial frontal gyrus, bilateral anterior cingulate cortex, bilateral superior frontal gyrus, bilateral precuneus/PCC, left supramarginal gyrus, and left middle temporal gyrus), and between the SN seed (right anterior insula) and right supramarginal gyrus. FC strength in the ECN and SN was negatively correlated with patient performance during the Stroop task.ConclusionDisrupted functional integration in the core brain cognitive networks, which is reflected by reductions in FC, occurs before OHE bouts and may play an important role in the neural mechanism of executive dysfunction associated with cirrhosis.

| S-EPMC5788959 | biostudies-literature

Psychometric Hepatic Encephalopathy Score for the Diagnosis of Minimal Hepatic Encephalopathy in Thai Cirrhotic Patients.

Project description:The psychometric hepatic encephalopathy score (PHES) is the gold standard for diagnosing minimal hepatic encephalopathy (MHE). Screening for MHE is frequently overlooked in clinical practice due to time constraints. Furthermore, the simplified animal naming test (S-ANT1) is a new simple tool for evaluating MHE in cirrhotic patients. The purpose of this study was to standardize the PHES in a healthy Thai population, assess the prevalence of MHE, and validate the S-ANT1 in detecting MHE in patients with cirrhosis. The study included 194 healthy controls and 203 cirrhotic patients without overt HE. Psychometric tests and the S-ANT1 were administered to all participants. Multiple linear regression was used to analyze factors related to PHES results, and formulas were developed to predict the results for each PHES subtest. In healthy controls, age and education were predictors of all five subtests. The PHES of the control group was -0.26 ± 2.28 points, and the threshold for detecting MHE was set at ≤ -5 points. The cirrhotic group had PHES values of -2.6 ± 3.1 points. Moreover, MHE was found to be present in 26.6% of cirrhotic patients. S-ANT1 had a moderate positive correlation with PHES (r = 0.44, p < 0.001). S-ANT1 < 22 named animals detected MHE with a sensitivity of 71.2%, specificity of 65%, and area under the receiver operating curve of 0.68 (p < 0.001). In conclusion, Thai PHES normative data have been developed to detect MHE in cirrhotic patients who do not have overt HE. The optimal cutoff for detecting MHE in Thai cirrhotic patients was PHES ≤ -5 points and S-ANT1 < 22 named.

| S-EPMC9864758 | biostudies-literature

Predictive models of minimal hepatic encephalopathy for cirrhotic patients based on large-scale brain intrinsic connectivity networks.

Project description: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.

| S-EPMC5599725 | biostudies-literature

Reversibility of minimal hepatic encephalopathy following liver transplantation in Egyptian cirrhotic patients.

Project description:AIM:To evaluate the reversibility of minimal hepatic encephalopathy (MHE) following liver transplantation (LT) in Egyptian cirrhotic patients. METHODS:This prospective study included twenty patients with biopsy-proven liver cirrhosis listed for LT and twenty age- and sex-matched healthy control subjects. All underwent neuro-psychiatric examination, laboratory investigations, radiological studies and psychometric tests including trail making test A (TMT A), TMT B, digit symbol test and serial dotting test. The psychometric hepatic encephalopathy score (PHES) was calculated for patients to diagnose MHE. Psychometric tests were repeated six months following LT in the cirrhotic patient group. RESULTS:Before LT, psychometric tests showed highly significant deficits in cirrhotic patients in comparison to controls (P < 0.001). There was a statistically significant improvement in test values in the patient group after LT; however, their values were still significantly worse than those of the controls (P < 0.001). The PHES detected MHE in 16 patients (80%) before LT with a median value of -7 ± 3.5. The median PHES value was significantly improved following LT, reaching -4.5 ± 5 (P < 0.001), and the number of patients with MHE decreased to 11 (55%). The pre-transplant model for end-stage liver disease (MELD) score ? 15 was significantly related to the presence of post-transplant MHE (P = 0.005). More patients in whom reversal of MHE was observed had a pre-transplant MELD score < 15. CONCLUSION:Reversal of MHE in cirrhotic patients could be achieved by LT, especially in those with a MELD score < 15.

| S-EPMC5084057 | biostudies-literature

Altered modular organization of functional connectivity networks in cirrhotic patients without overt hepatic encephalopathy.

Project description:Minimal hepatic encephalopathy (MHE) is associated with changes in functional connectivity. To investigate the patterns of modular changes of the functional connectivity in the progression of MHE, resting-state functional magnetic resonance imaging was acquired in 24 MHE patients, 31 cirrhotic patients without minimal hepatic encephalopathy (non-HE), and 38 healthy controls. Newman's metric, the modularity Q value, was maximized and compared in three groups. Topological roles with the progression of MHE were illustrated by intra- and intermodular connectivity changes. Results showed that the Q value of MHE patients was significantly lower than that of controls (P < 0.01) rather than that of non-HE patients (P > 0.05), which was correlated with neuropsychological test scores rather than the ammonia level and Child-Pugh score. Less intrasubcortical connections and more isolated subcortical modules were found with the progression of MHE. The non-HE patients had the same numbers of connect nodes as controls and had more hubs compared with MHE patients and healthy controls. Our findings supported that both intra- and intermodular connectivity, especially those related to subcortical regions, were continuously impaired in cirrhotic patients. The adjustments of hubs and connector nodes in non-HE patients could be a compensation for the decreased modularity in their functional connectivity networks.

| S-EPMC4066720 | biostudies-literature

Minimal Hepatic Encephalopathy Affects Daily Life of Cirrhotic Patients: A Viewpoint on Clinical Consequences and Therapeutic Opportunities.

Project description:Minimal hepatic encephalopathy (MHE) is a frequent complication of hepatic encephalopathy (HE) and can affect up to 80% of patients with liver cirrhosis. It is characterized by the lack of obvious clinical signs and the presence of alterations detectable using psychometric or electrophysiological testing focused on attention, working memory, psychomotor speed and visuospatial ability. Ideally, each patient should be tested for this condition because, despite the absence of symptoms, it has severe repercussions on daily life activities. It may be responsible for an inability to drive, sleep disturbances, risk of falls and inability to work. Some studies have highlighted its prognostically unfavorable role on mortality and risk of "overt" HE (OHE). Finally, MHE severely affects the lives of patients and caregivers, altering their quality of life and their socioeconomic status. Several treatments have been proposed for MHE treatment, including non-absorbable disaccharides, poorly absorbable antibiotics, such as rifaximin, probiotics and branched-chain amino acids, with promising results. For this reason, early diagnosis and intervention with appropriate measures is essential, with the aim of improving both performance on psychometric tests, as well as clinical aspects related to this condition.

| S-EPMC9736966 | biostudies-literature

Multi-omic analysis unveils biological pathways in peripheral immune system associated to minimal hepatic encephalopathy appearance in cirrhotic patients.

Project description:Patients with liver cirrhosis may develop minimal hepatic encephalopathy (MHE) which affects their quality of life and life span. It has been proposed that a shift in peripheral inflammation triggers the appearance of MHE. However, the mechanisms involved in this immune system shift remain unknown. In this work we studied the broad molecular changes involved in the induction of MHE with the goal of identifying (1) altered genes and pathways in peripheral blood cells associated to the appearance of MHE, (2) serum metabolites and cytokines with modified levels in MHE patients and (3) MHE-regulated immune response processes related to changes in specific serum molecules. We adopted a multi-omic approach to profile the transcriptome, metabolome and a panel of cytokines of blood samples taken from cirrhotic patients with or without MHE. Transcriptomic analysis supports the hypothesis of alternations in the Th1/Th2 and Th17 lymphocytes cell populations as major drivers of MHE. Cluster analysis of serum molecules resulted in six groups of chemically similar compounds, suggesting that functional modules operate during the induction of MHE. Finally, the multi-omic integrative analysis suggested a relationship between cytokines CCL20, CX3CL1, CXCL13, IL-15, IL-22 and IL-6 with alteration in chemotaxis, as well as a link between long-chain unsaturated phospholipids and the increased fatty acid transport and prostaglandin production. We found altered immune pathways that may collectively contribute to the mild cognitive impairment phenotype in MHE. Our approach is able to combine extracellular and intracellular information, opening new insights to the understanding of the disease.

| S-EPMC7820002 | biostudies-literature

Multi-omic analysis unveils biological pathways in peripheral immune system associated to minimal hepatic encephalopathy appearance in cirrhotic patients

2021-01-27 | GSE149741 | GEO

Usefulness of the Stroop Test in Diagnosing Minimal Hepatic Encephalopathy and Predicting Overt Hepatic Encephalopathy.

Project description:Minimal hepatic encephalopathy (MHE) adversely affects the clinical outcomes of patients with liver cirrhosis. This prospective study aimed to evaluate the utility of the Stroop test in the diagnosis of MHE and prediction of overt hepatic encephalopathy (OHE) in Japanese patients with cirrhosis. We enrolled 152 patients who underwent the Stroop test between November 2018 and February 2020. MHE was diagnosed using a combination of neuropsychological tests as the gold standard. The enrolled patients were followed up prospectively until the occurrence of OHE or August 2020. The optimal cutoff value of the Stroop test measurements was determined by receiver operating characteristic (ROC) curve analysis, and its predictive ability was assessed using the area under the ROC curve (AUC). Among the 139 eligible patients, 50 (36%) were diagnosed with MHE. The OffTime+OnTime cutoff value of 218.3 seconds had the best discriminative ability for MHE diagnosis, with an AUC of 0.77, a sensitivity of 74%, and a specificity of 75%. During a median follow-up of 10.8 months, 6 (4%) patients developed OHE. The OffTime+OnTime cutoff value of 305.6 seconds had the highest predictive ability for OHE, with an AUC of 0.79, a sensitivity of 67%, and a specificity of 92%. This value predicted OHE occurrence independent of liver functional reserve and prior OHE (hazard ratio, 19.8; P = 0.003). These two cutoff values remained statistically significant even when patients with prior OHE were excluded from the analysis. Conclusion: The Stroop test was useful for diagnosing patients with MHE and predicting OHE in Japanese patients with cirrhosis.

| S-EPMC8435282 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data