In order to classify the minimal hepatic encephalopathy （MHE） patients from healthy controls, the independent component analysis （ICA） is used to generate the default mode network （DMN） from resting-state functi...In order to classify the minimal hepatic encephalopathy （MHE） patients from healthy controls, the independent component analysis （ICA） is used to generate the default mode network （DMN） from resting-state functional magnetic resonance imaging （fMRI）. Then a Bayesian voxel- wised method, graphical-model-based multivariate analysis （GAMMA）, is used to explore the associations between abnormal functional integration within DMN and clinical variable. Without any prior knowledge, five machine learning methods, namely, support vector machines （SVMs）, classification and regression trees （ CART ）, logistic regression, the Bayesian network, and C4.5, are applied to the classification. The functional integration patterns were alternative within DMN, which have the power to predict MHE with an accuracy of 98%. The GAMMA method generating functional integration patterns within DMN can become a simple, objective, and common imaging biomarker for detecting MIIE and can serve as a supplement to the existing diagnostic methods.展开更多
Hepatic encephalopathy （HE） is a common neuropsychiatric abnormality, which complicates the course of patients with liver disease and results from hepatocellular failure and/or portosystemic shunting. The manifestat...Hepatic encephalopathy （HE） is a common neuropsychiatric abnormality, which complicates the course of patients with liver disease and results from hepatocellular failure and/or portosystemic shunting. The manifestations of HE are widely variable and involve a spectrum from mild subclinical disturbance to deep coma. Research interest has focused on the role of circulating gut-derived toxins, particularly ammonia, the development of brain swelling and changes in cerebral neurotransmitter systems that lead to global CNS depression and disordered function. Until recently the direct investigation of cerebral function has been difficult in man. However, new magnetic resonance imaging （MRI） techniques provide a non-invasive means of assessment of changes in brain volume （coregistered MRI） and impaired brain function （fMRI）, while proton magnetic resonance spectroscopy （^1H MRS） detects changes in brain biochemistry, including direct measurement of cerebral osmolytes, such as myoinositol, glutamate and glutamine which govern processes intrinsic to cellular homeostasis, including the accumulation of intracellular water. The concentrations of these intracellular osmolytes alter with hyperammonaemia. MRS-detected metabolite abnormalities correlate with the severity of neuropsychiatric impairment and since MR spectra return towards normal after treatment, the technique may be of use in objective patient monitoring and in assessing the effectiveness of various treatment regimens.展开更多
基金The National Natural Science Foundation of China(No.8123003481271739+2 种基金81501453)the Special Program of Medical Science of Jiangsu Province(No.BL2013029)the Natural Science Foundation of Jiangsu Province(No.BK20141342)
文摘In order to classify the minimal hepatic encephalopathy （MHE） patients from healthy controls, the independent component analysis （ICA） is used to generate the default mode network （DMN） from resting-state functional magnetic resonance imaging （fMRI）. Then a Bayesian voxel- wised method, graphical-model-based multivariate analysis （GAMMA）, is used to explore the associations between abnormal functional integration within DMN and clinical variable. Without any prior knowledge, five machine learning methods, namely, support vector machines （SVMs）, classification and regression trees （ CART ）, logistic regression, the Bayesian network, and C4.5, are applied to the classification. The functional integration patterns were alternative within DMN, which have the power to predict MHE with an accuracy of 98%. The GAMMA method generating functional integration patterns within DMN can become a simple, objective, and common imaging biomarker for detecting MIIE and can serve as a supplement to the existing diagnostic methods.
基金Supported by grants from BUPA, the Royal College of Physicians of London and Paddington Charitable Trust, St Mary's,London. The European Association for the Study of the Liver, the British Medical Research Council (G9900178)Philips Medical Systems (Cleveland, Ohio, USA) and the United Kingdom Department of Health provided support for some of the studies outlined
文摘Hepatic encephalopathy （HE） is a common neuropsychiatric abnormality, which complicates the course of patients with liver disease and results from hepatocellular failure and/or portosystemic shunting. The manifestations of HE are widely variable and involve a spectrum from mild subclinical disturbance to deep coma. Research interest has focused on the role of circulating gut-derived toxins, particularly ammonia, the development of brain swelling and changes in cerebral neurotransmitter systems that lead to global CNS depression and disordered function. Until recently the direct investigation of cerebral function has been difficult in man. However, new magnetic resonance imaging （MRI） techniques provide a non-invasive means of assessment of changes in brain volume （coregistered MRI） and impaired brain function （fMRI）, while proton magnetic resonance spectroscopy （^1H MRS） detects changes in brain biochemistry, including direct measurement of cerebral osmolytes, such as myoinositol, glutamate and glutamine which govern processes intrinsic to cellular homeostasis, including the accumulation of intracellular water. The concentrations of these intracellular osmolytes alter with hyperammonaemia. MRS-detected metabolite abnormalities correlate with the severity of neuropsychiatric impairment and since MR spectra return towards normal after treatment, the technique may be of use in objective patient monitoring and in assessing the effectiveness of various treatment regimens.
