Tag: fMRI

Machine Learning Detects Pattern of Differences in Functional Magnetic Resonance Imaging (fMRI) Data between Chronic Fatigue Syndrome (CFS) and Gulf War Illness (GWI)

Abstract:

Background: Gulf War Illness (GWI) and Chronic Fatigue Syndrome (CFS) are two debilitating disorders that share similar symptoms of chronic pain, fatigue, and exertional exhaustion after exercise. Many physicians continue to believe that both are psychosomatic disorders and to date no underlying etiology has been discovered. As such, uncovering objective biomarkers is important to lend credibility to criteria for diagnosis and to help differentiate the two disorders.

Methods: We assessed cognitive differences in 80 subjects with GWI and 38 with CFS by comparing corresponding fMRI scans during 2-back working memory tasks before and after exercise to model brain activation during normal activity and after exertional exhaustion, respectively. Voxels were grouped by the count of total activity into the Automated Anatomical Labeling (AAL) atlas and used in an “ensemble” series of machine learning algorithms to assess if a multi-regional pattern of differences in the fMRI scans could be detected.

Results: A K-Nearest Neighbor (70%/81%), Linear Support Vector Machine (SVM) (70%/77%), Decision Tree (82%/82%), Random Forest (77%/78%), AdaBoost (69%/81%), Naïve Bayes (74%/78%), Quadratic Discriminant Analysis (QDA) (73%/75%), Logistic Regression model (82%/82%), and Neural Net (76%/77%) were able to differentiate CFS from GWI before and after exercise with an average of 75% accuracy in predictions across all models before exercise and 79% after exercise. An iterative feature selection and removal process based on Recursive Feature Elimination (RFE) and Random Forest importance selected 30 regions before exercise and 33 regions after exercise that differentiated CFS from GWI across all models, and produced the ultimate best accuracies of 82% before exercise and 82% after exercise by Logistic Regression or Decision Tree by a single model, and 100% before and after exercise when selected by any six or more models. Differential activation on both days included the right anterior insula, left putamen, and bilateral orbital frontal, ventrolateral prefrontal cortex, superior, inferior, and precuneus (medial) parietal, and lateral temporal regions. Day 2 had the cerebellum, left supplementary motor area and bilateral pre- and post-central gyri. Changes between days included the right Rolandic operculum switching to the left on Day 2, and the bilateral midcingulum switching to the left anterior cingulum.

Conclusion: We concluded that CFS and GWI are significantly differentiable using a pattern of fMRI activity based on an ensemble machine learning model.

Source: Provenzano D, Washington SD, Rao YJ, Loew M, Baraniuk J. Machine Learning Detects Pattern of Differences in Functional Magnetic Resonance Imaging (fMRI) Data between Chronic Fatigue Syndrome (CFS) and Gulf War Illness (GWI). Brain Sci. 2020;10(7):E456. Published 2020 Jul 17. doi:10.3390/brainsci10070456 https://www.mdpi.com/2076-3425/10/7/456 (Full text)

A Machine Learning Approach to the Differentiation of Functional Magnetic Resonance Imaging Data of Chronic Fatigue Syndrome (CFS) From a Sedentary Control

Abstract:

Chronic Fatigue Syndrome (CFS) is a debilitating condition estimated to impact at least 1 million individuals in the United States, however there persists controversy about its existence. Machine learning algorithms have become a powerful methodology for evaluating multi-regional areas of fMRI activation that can classify disease phenotype from sedentary control. Uncovering objective biomarkers such as an fMRI pattern is important for lending credibility to diagnosis of CFS.

fMRI scans were evaluated for 69 patients (38 CFS and 31 Control) taken before (Day 1) and after (Day 2) a submaximal exercise test while undergoing the n-back memory paradigm. A predictive model was created by grouping fMRI voxels into the Automated Anatomical Labeling (AAL) atlas, splitting the data into a training and testing dataset, and feeding these inputs into a logistic regression to evaluate differences between CFS and control. Model results were cross-validated 10 times to ensure accuracy. Model results were able to differentiate CFS from sedentary controls at a 80% accuracy on Day 1 and 76% accuracy on Day 2 (Table 3).

Recursive features selection identified 29 ROI’s that significantly distinguished CFS from control on Day 1 and 28 ROI’s on Day 2 with 10 regions of overlap shared with Day 1 (Figure 3). These 10 shared regions included the putamen, inferior frontal gyrus, orbital (F3O), supramarginal gyrus (SMG), temporal pole; superior temporal gyrus (T1P) and caudate ROIs. This study was able to uncover a pattern of activated neurological regions that differentiated CFS from Control.

This pattern provides a first step toward developing fMRI as a diagnostic biomarker and suggests this methodology could be emulated for other disorders. We concluded that a logistic regression model performed on fMRI data significantly differentiated CFS from Control.

Source: Provenzano D, Washington SD, Baraniuk JN. A Machine Learning Approach to the Differentiation of Functional Magnetic Resonance Imaging Data of Chronic Fatigue Syndrome (CFS) From a Sedentary Control. Front Comput Neurosci. 2020 Jan 29;14:2. doi: 10.3389/fncom.2020.00002. eCollection 2020. https://www.ncbi.nlm.nih.gov/pubmed/32063839

Brain function characteristics of chronic fatigue syndrome: A task fMRI study

Abstract:

The mechanism underlying neurological dysfunction in chronic fatigue syndrome/myalgic encephalomyelitis (CFS/ME) is yet to be established. This study investigated the temporal complexity of blood oxygenation level dependent (BOLD) changes in response to the Stroop task in CFS patients. 43 CFS patients (47.4 ± 11.8 yrs) and 26 normal controls (NCs, 43.4 ± 13.9 yrs) were included in this study. Their mental component summary (MCS) and physical component summary (PCS) from the 36-item Short Form Health Survey (SF-36) questionnaire were recorded. Their Stroop colour-word task performance was measured by accuracy and response time (RT). The BOLD changes associated with the Stroop task were evaluated using a 2-level general linear model approach. The temporal complexity of the BOLD responses, a measure of information capacity and thus adaptability to a challenging environment, in each activated region was measured by sample entropy (SampEn).

The CFS patients showed significantly longer RTs than the NCs (P < 0.05) but no significant difference in accuracy. One sample t-tests for the two groups (Family wise error adjusted PFWE < 0.05) showed more BOLD activation regions in the CFS, although a two sample group comparison did not show significant difference. BOLD SampEns in ten regions were significantly lower (FDR-q < 0.05) in CFS patients. BOLD SampEns in 15 regions were significantly associated with PCS (FDR-q < 0.05) and in 9 regions were associated with MCS (FDR-q < 0.05) across all subjects. SampEn of the BOLD signal in the medioventral occipital cortex could explain 40% and 31% of the variance in the SF-36 PCS and MCS scores, and those in the precentral gyrus could explain an additional 16% and 7% across all subjects.

This is the first study to investigate BOLD signal SampEn in response to tasks in CFS. The results suggest the brain responds differently to a cognitive challenge in patients with CFS, with recruitment of wider regions to compensate for lower information capacity.

Source: Shan ZY, Finegan K, Bhuta S, Ireland T, Staines DR, Marshall-Gradisnik SM, Barnden LR. Brain function characteristics of chronic fatigue syndrome: A task fMRI study. Neuroimage Clin. 2018 Apr 25;19:279-286. doi: 10.1016/j.nicl.2018.04.025. eCollection 2018. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6051500/ (Full study)

Low putamen activity associated with poor reward sensitivity in childhood chronic fatigue syndrome

Abstract:

Motivational signals influence a wide variety of cognitive processes and components of behavioral performance. Cognitive dysfunction in patients with childhood chronic fatigue syndrome (CCFS) may be closely associated with a low motivation to learn induced by impaired neural reward processing. However, the extent to which reward processing is impaired in CCFS patients is unclear.

The aim of the present functional magnetic resonance imaging (fMRI) study was to determine whether brain activity in regions related to reward sensitivity is impaired in CCFS patients. fMRI data were collected from 13 CCFS patients (mean age, 13.6 ± 1.0 years) and 13 healthy children and adolescents (HCA) (mean age, 13.7 ± 1.3 years) performing a monetary reward task. Neural activity in high- and low-monetary-reward conditions was compared between CCFS and HCA groups. Severity of fatigue and the reward obtained from learning in daily life were evaluated by questionnaires.

Activity of the putamen was lower in the CCFS group than in the HCA group in the low-reward condition, but not in the high-reward condition. Activity of the putamen in the low-reward condition in CCFS patients was negatively and positively correlated with severity of fatigue and the reward from learning in daily life, respectively.

We previously revealed that motivation to learn was correlated with striatal activity, particularly the neural activity in the putamen. This suggests that in CCFS patients low putamen activity, associated with altered dopaminergic function, decreases reward sensitivity and lowers motivation to learn.

 

Source: Mizuno K, Kawatani J, Tajima K, Sasaki AT, Yoneda T, Komi M, Hirai T, Tomoda A, Joudoi T, Watanabe Y. Low putamen activity associated with poor reward sensitivity in childhood chronic fatigue syndrome. Neuroimage Clin. 2016 Sep 26;12:600-606. eCollection 2016. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5043413/ (Full article)

 

Static and dynamic functional connectivity in patients with chronic fatigue syndrome: use of arterial spin labelling fMRI

Abstract:

Studies using arterial spin labelling (ASL) have shown that individuals with chronic fatigue syndrome (CFS) have decreased regional cerebral blood flow, which may be associated with changes in functional neural networks.

Indeed, recent studies indicate disruptions in functional connectivity (FC) at rest in chronically fatigued patients including perturbations in static FC (sFC), that is average FC at rest between several brain regions subserving neurocognitive, motor and affect-related networks.

Whereas sFC often provides information of functional network reorganization in chronic illnesses, investigations of temporal changes in functional connectivity between multiple brain areas may shed light on the dynamic characteristics of brain network activation associated with such maladies.

We used ASL fMRI in 19 patients with CFS and 15 healthy controls (HC) to examine both static and dynamic changes in FC among several a priori selected brain regions during a fatiguing cognitive task. HC showed greater increases than CFS in static FC (sFC) between insula and temporo-occipital structures and between precuneus and thalamus/striatum.

Furthermore, inferior frontal gyrus connectivity to cerebellum, occipital and temporal structures declined in HC but increased in CFS. Patients also showed lower dynamic FC (dFC) between hippocampus and right superior parietal lobule. Both sFC and dFC correlated with task-related fatigue increases.

These data provide the first evidence that perturbations in static and dynamic FC may underlie chronically fatigued patients’ report of task-induced fatigue. Further research will determine whether such changes in sFC and dFC are also characteristic for other fatigued individuals, including patients with chronic pain, cancer and multiple sclerosis.

© 2016 Scandinavian Society of Clinical Physiology and Nuclear Medicine. Published by John Wiley & Sons Ltd.

 

Source: Boissoneault J, Letzen J, Lai S, Robinson ME, Staud R. Static and dynamic functional connectivity in patients with chronic fatigue syndrome: use of arterial spin labelling fMRI. Clin Physiol Funct Imaging. 2016 Sep 28. doi: 10.1111/cpf.12393. [Epub ahead of print] https://www.ncbi.nlm.nih.gov/pubmed/27678090

 

 

Emotional conflict processing in adolescent chronic fatigue syndrome: A pilot study using functional magnetic resonance imaging

Abstract:

INTRODUCTION: Studies of neurocognition suggest that abnormalities in cognitive control contribute to the pathophysiology of chronic fatigue syndrome (CFS) in adolescents, yet these abnormalities remain poorly understood at the neurobiological level. Reports indicate that adolescents with CFS are significantly impaired in conflict processing, a primary element of cognitive control.

METHOD: In this study, we examine whether emotional conflict processing is altered on behavioral and neural levels in adolescents with CFS and a healthy comparison group. Fifteen adolescent patients with CFS and 24 healthy adolescent participants underwent functional magnetic resonance imaging (fMRI) while performing an emotional conflict task that involved categorizing facial affect while ignoring overlaid affect labeled words.

RESULTS: Adolescent CFS patients were less able to engage the left amygdala and left midposterior insula (mpINS) in response to conflict than the healthy comparison group. An association between accuracy interference and conflict-related reactivity in the amygdala was observed in CFS patients. A relationship between response time interference and conflict-related reactivity in the mpINS was also reported. Neural responses in the amygdala and mpINS were specific to fatigue severity.

CONCLUSIONS: These data demonstrate that adolescent CFS patients displayed deficits in emotional conflict processing. Our results suggest abnormalities in affective and cognitive functioning of the salience network, which might underlie the pathophysiology of adolescent CFS.

 

Source: Wortinger LA, Endestad T, Melinder AM, Øie MG, Sulheim D, Fagermoen E, Wyller VB. Emotional conflict processing in adolescent chronic fatigue syndrome: A pilot study using functional magnetic resonance imaging. J Clin Exp Neuropsychol. 2016 Sep 20:1-14. [Epub ahead of print] https://www.ncbi.nlm.nih.gov/pubmed/27647312

 

Abnormal resting state functional connectivity in patients with chronic fatigue syndrome: an arterial spin-labeling fMRI study

Abstract:

BACKGROUND: Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a debilitating disorder characterized by severe fatigue and neurocognitive dysfunction. Recent work from our laboratory and others utilizing arterial spin labeling functional magnetic resonance imaging (ASL) indicated that ME/CFS patients have lower resting state regional cerebral blood flow (rCBF) in several brain areas associated with memory, cognitive, affective, and motor function. This hypoperfusion may underlie ME/CFS pathogenesis and may result in alterations of functional relationships between brain regions. The current report used ASL to compare functional connectivity of regions implicated in ME/CFS between patients and healthy controls (HC).

METHODS: Participants were 17 ME/CFS patients (Mage=48.88years, SD=12) fulfilling the 1994 CDC criteria and 17 age/sex matched HC (Mage=49.82years, SD=11.32). All participants underwent T1-weighted structural MRI as well as a 6-min pseudo-continuous arterial spin labeling (pCASL) sequence, which quantifies CBF by magnetically labeling blood as it enters the brain. Imaging data were preprocessed using SPM 12 and ASL tbx, and seed-to-voxel functional connectivity analysis was conducted using the CONN toolbox. All effects noted below are significant at p<0.05 with cluster-wise FDR correction for multiple comparisons.

RESULTS: ME/CFS patients demonstrated greater functional connectivity relative to HC in bilateral superior frontal gyrus, ACC, precuneus, and right angular gyrus to regions including precuneus, right postcentral gyrus, supplementary motor area, posterior cingulate gyrus, and thalamus. In contrast, HC patients had greater functional connectivity than ME/CFS in ACC, left parahippocampal gyrus, and bilateral pallidum to regions including right insula, right precentral gyrus, and hippocampus. Connectivity of the left parahippocampal gyrus correlated strongly with overall clinical fatigue of ME/CFS patients.

CONCLUSION: This is the first ASL based connectivity analysis of patients with ME/CFS. Our results demonstrate altered functional connectivity of several regions associated with cognitive, affective, memory, and higher cognitive function in ME/CFS patients. Connectivity to memory related brain areas (parahippocampal gyrus) was correlated with clinical fatigue ratings, providing supporting evidence that brain network abnormalities may contribute to ME/CFS pathogenesis.

Copyright © 2015 Elsevier Inc. All rights reserved.

 

Source: Boissoneault J, Letzen J, Lai S, O’Shea A, Craggs J, Robinson ME, Staud R. Abnormal resting state functional connectivity in patients with chronic fatigue syndrome: an arterial spin-labeling fMRI study. Magn Reson Imaging. 2016 May;34(4):603-8. doi: 10.1016/j.mri.2015.12.008. Epub 2015 Dec 18. https://www.ncbi.nlm.nih.gov/pubmed/26708036

 

Abnormal Resting-State Functional Connectivity in Patients with Chronic Fatigue Syndrome: Results of Seed and Data-Driven Analyses

Abstract:

Although altered resting-state functional connectivity (FC) is a characteristic of many chronic pain conditions, it has not yet been evaluated in patients with chronic fatigue. Our objective was to investigate the association between fatigue and altered resting-state FC in myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS).

Thirty-six female subjects, 19 ME/CFS and 17 healthy controls, completed a fatigue inventory before undergoing functional magnetic resonance imaging. Two methods, (1) data driven and (2) model based, were used to estimate and compare the intraregional FC between both groups during the resting state (RS).

The first approach using independent component analysis was applied to investigate five RS networks: the default mode network, salience network (SN), left frontoparietal networks (LFPN) and right frontoparietal networks, and the sensory motor network (SMN).

The second approach used a priori selected seed regions demonstrating abnormal regional cerebral blood flow (rCBF) in ME/CFS patients at rest. In ME/CFS patients, Method-1 identified decreased intrinsic connectivity among regions within the LFPN. Furthermore, the FC of the left anterior midcingulate with the SMN and the connectivity of the left posterior cingulate cortex with the SN were significantly decreased.

For Method-2, five distinct clusters within the right parahippocampus and occipital lobes, demonstrating significant rCBF reductions in ME/CFS patients, were used as seeds. The parahippocampal seed and three occipital lobe seeds showed altered FC with other brain regions. The degree of abnormal connectivity correlated with the level of self-reported fatigue.

Our results confirm altered RS FC in patients with ME/CFS, which was significantly correlated with the severity of their chronic fatigue.

 

Source: Gay CW, Robinson ME, Lai S, O’Shea A, Craggs JG, Price DD, Staud R. Abnormal Resting-State Functional Connectivity in Patients with Chronic Fatigue Syndrome: Results of Seed and Data-Driven Analyses. Brain Connect. 2016 Feb;6(1):48-56. doi: 10.1089/brain.2015.0366. Epub 2015 Nov 10. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4744887/ (Full article)

 

Caught in the thickness of brain fog: exploring the cognitive symptoms of Chronic Fatigue Syndrome

Abstract:

Chronic Fatigue Syndrome (CFS) is defined as greater than 6 months of persistent fatigue that is experienced physically and cognitively. The cognitive symptoms are generally thought to be a mild cognitive impairment, but individuals with CFS subjectively describe them as “brain fog.” The impairment is not fully understood and often is described as slow thinking, difficulty focusing, confusion, lack of concentration, forgetfulness, or a haziness in thought processes.

Causes of “brain fog” and mild cognitive impairment have been investigated. Possible physiological correlates may be due to the effects of chronic orthostatic intolerance (OI) in the form of the Postural Tachycardia Syndrome (POTS) and decreases in cerebral blood flow (CBF). In addition, fMRI studies suggest that individuals with CFS may require increased cortical and subcortical brain activation to complete difficult mental tasks.

Furthermore, neurocognitive testing in CFS has demonstrated deficits in speed and efficiency of information processing, attention, concentration, and working memory. The cognitive impairments are then perceived as an exaggerated mental fatigue. As a whole, this is experienced by those with CFS as “brain fog” and may be viewed as the interaction of physiological, cognitive, and perceptual factors.

Thus, the cognitive symptoms of CFS may be due to altered CBF activation and regulation that are exacerbated by a stressor, such as orthostasis or a difficult mental task, resulting in the decreased ability to readily process information, which is then perceived as fatiguing and experienced as “brain fog.” Future research looks to further explore these interactions, how they produce cognitive impairments, and explain the perception of “brain fog” from a mechanistic standpoint.

 

Source: Ocon AJ. Caught in the thickness of brain fog: exploring the cognitive symptoms of Chronic Fatigue Syndrome. Front Physiol. 2013 Apr 5;4:63. doi: 10.3389/fphys.2013.00063. ECollection 2013. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3617392/ (Full article)

 

Probing the working memory system in chronic fatigue syndrome: a functional magnetic resonance imaging study using the n-back task

Abstract:

OBJECTIVE: Up to 90% of patients with chronic fatigue syndrome (CFS) report substantial cognitive difficulties. However, objective evidence supporting these claims is inconsistent. The present functional magnetic resonance imaging study examined the neural correlates of working memory in patients with CFS compared with controls.

METHODS: Seventeen patients with CFS and 12 healthy control subjects were scanned while performing a parametric version of the n-back task (0-, 1-, 2-, and 3-back).

RESULTS: Both groups performed comparably well and activated the verbal working memory network during all task levels. However, during the 1-back condition, patients with CFS showed greater activation than control subjects in medial prefrontal regions, including the anterior cingulate gyrus. Conversely, on the more challenging conditions, patients with CFS demonstrated reduced activation in dorsolateral prefrontal and parietal cortices. Furthermore, on the 2- and 3-back conditions, patients but not control subjects significantly activated a large cluster in the right inferior/medial temporal cortex. Trend analyses of task load demonstrated statistically significant differences in brain activation between the two groups as the demands of the task increased.

CONCLUSIONS: These results suggest that patients with CFS show both quantitative and qualitative differences in activation of the working memory network compared with healthy control subjects. It remains to be determined whether these findings stay stable after successful treatment.

 

Source: Caseras X, Mataix-Cols D, Giampietro V, Rimes KA, Brammer M, Zelaya F, Chalder T, Godfrey EL. Probing the working memory system in chronic fatigue syndrome: a functional magnetic resonance imaging study using the n-back task. Psychosom Med. 2006 Nov-Dec;68(6):947-55. Epub 2006 Nov 1. https://www.ncbi.nlm.nih.gov/pubmed/17079703