Tag: fMRI

Use of artificial intelligence and machine learning for the management of fibromyalgia: a scoping review

Abstract:

Background: Fibromyalgia (FM) is a complex and multifactorial syndrome characterized by widespread pain, fatigue, cognitive impairment, and other systemic symptoms. The absence of specific biomarkers and the heterogeneous clinical presentation pose significant diagnostic challenges.

Objective: This scoping review aims to explore the current applications of artificial intelligence (AI) and machine learning (ML) in the diagnosis and clinical management of FM.

Methods: A systematic search was conducted in PubMed, EMBASE, and the Cochrane Library using defined keywords related to FM and AI/ML. Studies were included if they addressed ML applications in FM patients. Following PRISMA-ScR guidelines, 43 studies published between 2011 and 2024 were included and analyzed for ML techniques used, diagnostic targets, data types, and clinical relevance.

Results: As expected, the majority of studies done so far focused on improving diagnostic accuracy through supervised algorithms such as support vector machines, neural networks, and ensemble models, as well as unsupervised clustering and dimensionality reduction techniques. Notable findings include the identification of neurophysiological signatures via fMRI, gene expression patterns, retinal imaging changes, and metabolomic biomarkers that distinguish FM patients from controls. For instance, one study investigating circulating microRNAs used a Random Forest model to identify 11 microRNAs (e.g. hsa-miR-28-5p, hsa-miR-29a-3p, hsa-miR-150-5p) capable of differentiating patients with FM, ME/CFS, and healthy controls, suggesting their potential as biomarkers for more accurate diagnoses. Reported model accuracies ranged from 82% to 100%, although most studies were pilot-based with small and imbalanced samples, limiting generalizability.

Conclusion: AI and ML offer promising tools to overcome longstanding limitations in FM diagnosis and treatment. While current findings demonstrate significant potential, larger, multicenter studies with rigorous validation protocols are essential to finally establish these approaches as clinically reliable solutions.

Source: Clempi Almeida E Silva AL, Reis VHPF, Lamoglia ASA, Souza Desidério C, Freire Oliveira CJ. Use of artificial intelligence and machine learning for the management of fibromyalgia: a scoping review. J Man Manip Ther. 2026 Feb 17:1-17. doi: 10.1080/10669817.2026.2630999. Epub ahead of print. PMID: 41700030. https://pubmed.ncbi.nlm.nih.gov/41700030/

Distinct functional connectivity patterns in myalgic encephalomyelitis and long COVID patients during cognitive fatigue: a 7 Tesla task-fMRI study

Abstract:

Background: Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) and long COVID are chronic debilitating illnesses featuring fatigue, post-exertional malaise (PEM) and neurocognitive deficits. Temporal correlation of neural activity between distinct brain regions, also referred to as functional connectivity (FC), can provide insights into how brain networks coordinate, at rest or during task. Therefore, we explored intrinsic FC correlates of cognitive fatigue in ME/CFS and long COVID patients during two Stroop-colour-word paradigms on 7 Tesla fMRI.

Methods: 450 sagittal volumes were acquired from seventy-eight participants: 32 patients with MECFS (pwME/CFS); 19 long COVID (pwLC) and 27 healthy controls (HC) during performance of baseline or Pre (before/during fatigue build-up) and repeat Post (fatigue set-in) Stroop tasks. Structural and functional data were analysed using the CONN toolbox.

Results: Regions of interest (ROI-to-ROI) analysis revealed significantly increased FC in subcortical regions in HC for Pre vs Post. Relative to HC, pwLC showed significantly reduced FC between nucleus accumbens and vermis 3 (p = 0.02) in Pre and increased FC in the prefrontal cortex and hippocampus (p = 0.02) in Post. pwME/CFS showed a significantly increased FC between the left cuneiform nucleus and right medulla (p = 0.03). Compared to HC, reduced FC was significant in pwLC during Pre, and between medulla and hippocampus (p = 0.04) and between nucleus accumbens and vermis (p = 0.001) during Post. Aberrant FC was significant for pwME/CFS in core networks during Pre. Core network FC to the cerebellum, amygdala, caudate and red nucleus correlated with symptom scores for cognition in both pwME/CFS and pwLC. Hippocampus and cerebellar FC correlated with duration of illness in pwME/CFS.

Conclusions: Our findings of reduced dopaminergic hippocampal-nucleus-accumbens connectivity imply blunted motivation and cognition. Extensive FC differences in subcortical and core networks in patient cohorts were detected relative to an increased FC in HC. High regional communication indicative of greater task engagement by HC was distinctive while FC differences in ME/CFS and long COVID patients indicated reduced and dysregulated regional coordination that may serve as candidate biomarkers of symptomatology in long COVID and ME/CFS.

Source: Inderyas M, Thapaliya K, Marshall-Gradisnik S, Barnden L. Distinct functional connectivity patterns in myalgic encephalomyelitis and long COVID patients during cognitive fatigue: a 7 Tesla task-fMRI study. J Transl Med. 2026 Jan 20. doi: 10.1186/s12967-026-07708-y. Epub ahead of print. PMID: 41559785. https://link.springer.com/article/10.1186/s12967-026-07708-y (Full text)

A Multimodal Magnetic Resonance Imaging Study on Myalgic Encephalomyelitis/Chronic Fatigue Syndrome: Feasibility and Clinical Correlation

Abstract:

Background/Objectives: Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a neurological disorder characterized by post-exertional malaise. Despite its clinical relevance, the disease mechanisms of ME/CFS are not fully understood. The previous studies targeting brain function or metabolites have been inconclusive in understanding ME/CFS complexity. We combined single-voxel magnetic resonance spectroscopy (SV-MRS) and functional magnetic resonance imaging (fMRI). Our objectives were to examine the feasibility of the multimodal MRI protocol, identify possible differences between ME/CFS and healthy controls (HCs), and relate MRI findings with clinical symptoms.

Methods: We enrolled 18 female ME/CFS participants (mean age: 39.7 ± 12.0 years) and five HCs (mean age: 45.6 ± 14.5 years). SV-MRS spectra were acquired from three voxels of interest: the anterior cingulate gyrus (ACC), brainstem (BS), and left dorsolateral prefrontal cortex (L-DLPFC). Whole-brain fMRI used n-back task testing working memory and executive function. The feasibility was assessed as protocol completion rate and time. Group differences in brain metabolites and fMRI activation between ME/CFS and HCs were compared and correlated with behavioral and symptom severity measurements.

Results: The completion rate was 100% regardless of participant group without causing immediate fatigue. ME/CFS appeared to show a higher N-Acetylaspartate in L-DLPFC compared to HCs (OR = 8.49, p = 0.040), correlating with poorer fatigue, pain, and sleep quality scores (p‘s = 0.001-0.015). An increase in brain activation involving the frontal lobe and the brainstem was observed in ME/CFS compared to HCs (Z > 3.4, p‘s < 0.010).

Conclusions: The study demonstrates the feasibility of combining MRS and fMRI to capture neurochemical and neurophysiological features of ME/CFS in female participants. Further research with larger cohorts of more representative sampling and follow-ups is needed to validate these apparent differences between ME/CFS and HCs.

Source: Kaur R, Greeley B, Ciok A, Mehta K, Tsai M, Robertson H, Debelic K, Zhang LX, Nelson T, Boulter T, Siu W, Nacul L, Song X. A Multimodal Magnetic Resonance Imaging Study on Myalgic Encephalomyelitis/Chronic Fatigue Syndrome: Feasibility and Clinical Correlation. Medicina (Kaunas). 2024 Aug 22;60(8):1370. doi: 10.3390/medicina60081370. PMID: 39202651. https://www.mdpi.com/1648-9144/60/8/1370 (Full text)

Absence of BOLD adaptation in chronic fatigue syndrome revealed by task functional MRI

Abstract:

Neurological symptoms are central to Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS), yet its underlying neurophysiological mechanisms remain elusive. We examined a neglected aspect of task-based functional MRI, focusing on how blood oxygenation level-dependent (BOLD) signals alter during cognitive tasks in ME/CFS.

This prospective observational study utilised MRI scans on ME/CFS participants and healthy controls (HCs) with sedentary lifestyles (ACTRN12622001095752). Participants completed two blocks of a Symbol Digit Modalities Test, with 30 trials per block split into two sets. The fMRI signal changes between blocks and sets were compared within and between groups. Thirty-four ME/CFS participants (38 years ± 10; 27 women) and 34 HCs (38 ± 10; 27 women), were evaluated.

In the second task block, ME/CFS participants exhibited increased activation in the right postcentral gyrus, contrasting with decreased activation in multiple regions in HCs. These results were further confirmed by significantly higher bilateral dynamic changes (2nd vs 1st set) in the motor, sensory and cognitive cortex in ME/CFS compared to HCs and significant correlations between those changes in the left primary motor cortex with fatigue severities. BOLD adaptation, potentially improving energy economy, was absent in ME/CFS, which may provide an underlying neurophysiological process in ME/CFS.

Source: Schönberg L, Mohamed AZ, Yu Q, Kwiatek RA, Del Fante P, Calhoun VD, Shan ZY. Absence of BOLD adaptation in chronic fatigue syndrome revealed by task functional MRI. J Cereb Blood Flow Metab. 2024 Aug 7:271678X241270528. doi: 10.1177/0271678X241270528. Epub ahead of print. PMID: 39113421. https://journals.sagepub.com/doi/10.1177/0271678X241270528 (Full text)

Cerebral microstructural alterations in Post-COVID-condition are related to cognitive impairment, olfactory dysfunction and fatigue

Abstract:

After contracting COVID-19, a substantial number of individuals develop a Post-COVID-Condition, marked by neurologic symptoms such as cognitive deficits, olfactory dysfunction, and fatigue. Despite this, biomarkers and pathophysiological understandings of this condition remain limited. Employing magnetic resonance imaging, we conduct a comparative analysis of cerebral microstructure among patients with Post-COVID-Condition, healthy controls, and individuals that contracted COVID-19 without long-term symptoms.

We reveal widespread alterations in cerebral microstructure, attributed to a shift in volume from neuronal compartments to free fluid, associated with the severity of the initial infection. Correlating these alterations with cognition, olfaction, and fatigue unveils distinct affected networks, which are in close anatomical-functional relationship with the respective symptoms.

Source: Hosp JA, Reisert M, Dressing A, Götz V, Kellner E, Mast H, Arndt S, Waller CF, Wagner D, Rieg S, Urbach H, Weiller C, Schröter N, Rau A. Cerebral microstructural alterations in Post-COVID-condition are related to cognitive impairment, olfactory dysfunction and fatigue. Nat Commun. 2024 May 18;15(1):4256. doi: 10.1038/s41467-024-48651-0. PMID: 38762609; PMCID: PMC11102465. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11102465/ (Full text)

A prospective randomized, double-blind placebo-controlled study to evaluate the effectiveness of neuroprotective therapy using functional brain MRI in patients with post-covid chronic fatigue syndrome

Abstract:

Background and purpose: to assess executive network using resting-state fMRI and patterns of brain activation using task fMRI with a cognitive paradigm, against the background of taking the drug in comparison with placebo in patients with post-COVID asthenic syndrome.

Methods: The study employed a prospective, randomized, double-blind, placebo-controlled trial approach to assess the efficacy of utilizing functional MRI of the brain as a neuroprotective therapy for treating patients with chronic fatigue syndrome following COVID-19. The study included 30 patients matched by sex and age with post-COVID asthenic syndrome. All patients were examined with MFI-20, MoCA, FAS-10 scales, MRI using a Siemens MAGNETOM Prisma 3 T scanner before and after a course of therapy with coordination complex with succinate acid anion (CCSA) or placebo (15 patients each) using resting state fMRI and with cognitive paradigm.

Results: The changes obtained as a result of the treatment of post-Covid asthenic syndrome demonstrated clinical superiority in the reduction of asthenic symptoms for the group of patients treated with CCSA (MFI-20 scores: -20·0 points in the CCSA group compared to -12 points in the placebo group, p = 0·043). The data obtained also correlate with the analysis of task fMRI and resting state fMRI may indicate an increase in the functional cognitive status after a course of therapy with CCSA. Clinically, this correlates with a statistically significant improvement in the MoCA score (2 points in the CCSA group compared to 1 point in the placebo group, p < 0·05).

Conclusions: The study demonstrates the potential effectiveness of CCSA therapy in relation to a wide range of symptoms (chronic fatigue syndrome/ asthenic syndrome and cognitive impairment) in patients with post-COVID syndrome. The first time demonstrated the effectiveness of neuroprotective therapy after post-COVID asthenic syndrome with the use of high-tech neuroimaging techniques.

Source: Tanashyan M, Morozova S, Raskurazhev A, Kuznetsova P. A prospective randomized, double-blind placebo-controlled study to evaluate the effectiveness of neuroprotective therapy using functional brain MRI in patients with post-covid chronic fatigue syndrome. Biomed Pharmacother. 2023 Oct 18;168:115723. doi: 10.1016/j.biopha.2023.115723. Epub ahead of print. PMID: 37862966. https://www.sciencedirect.com/science/article/pii/S0753332223015214 (Full study)

Altered brain connectivity in Long Covid during cognitive exertion: a pilot study

Abstract:

Introduction: Debilitating Long-Covid symptoms occur frequently after SARS-COVID-19 infection.

Methods: Functional MRI was acquired in 10 Long Covid (LCov) and 13 healthy controls (HC) with a 7 Tesla scanner during a cognitive (Stroop color-word) task. BOLD time series were computed for 7 salience and 4 default-mode network hubs, 2 hippocampus and 7 brainstem regions (ROIs). Connectivity was characterized by the correlation coefficient between each pair of ROI BOLD time series. We tested for HC versus LCov differences in connectivity between each pair of the 20 regions (ROI-to-ROI) and between each ROI and the rest of the brain (ROI-to-voxel). For LCov, we also performed regressions of ROI-to-ROI connectivity with clinical scores.

Results: Two ROI-to-ROI connectivities differed between HC and LCov. Both involved the brainstem rostral medulla, one connection to the midbrain, another to a DM network hub. Both were stronger in LCov than HC. ROI-to-voxel analysis detected multiple other regions where LCov connectivity differed from HC located in all major lobes. Most, but not all connections, were weaker in LCov than HC. LCov, but not HC connectivity, was correlated with clinical scores for disability and autonomic function and involved brainstem ROI.

Discussion: Multiple connectivity differences and clinical correlations involved brainstem ROIs. Stronger connectivity in LCov between the medulla and midbrain may reflect a compensatory response. This brainstem circuit regulates cortical arousal, autonomic function and the sleep-wake cycle. In contrast, this circuit exhibited weaker connectivity in ME/CFS. LCov connectivity regressions with disability and autonomic scores were consistent with altered brainstem connectivity in LCov.

Source: Barnden L, Thapaliya K, Eaton-Fitch N, Barth M, Marshall-Gradisnik S. Altered brain connectivity in Long Covid during cognitive exertion: a pilot study. Front Neurosci. 2023 Jun 22;17:1182607. doi: 10.3389/fnins.2023.1182607. PMID: 37425014; PMCID: PMC10323677. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10323677/ (Full text)

A Pilot Study of Short-Course Oral Vitamin A and Aerosolised Diffuser Olfactory Training for the Treatment of Smell Loss in Long COVID

Abstract:

Background: Olfactory dysfunction (OD) is a common neurosensory manifestation in long COVID. An effective and safe treatment against COVID-19-related OD is needed.
Methods: This pilot trial recruited long COVID patients with persistent OD. Participants were randomly assigned to receive short-course (14 days) oral vitamin A (VitA; 25,000 IU per day) and aerosolised diffuser olfactory training (OT) thrice daily (combination), OT alone (standard care), or observation (control) for 4 weeks. The primary outcome was differences in olfactory function by butanol threshold tests (BTT) between baseline and end-of-treatment. Secondary outcomes included smell identification tests (SIT), structural MRI brain, and serial seed-based functional connectivity (FC) analyses in the olfactory cortical network by resting-state functional MRI (rs–fMRI).
Results: A total of 24 participants were randomly assigned to receive either combination treatment (n = 10), standard care (n = 9), or control (n = 5). Median OD duration was 157 days (IQR 127–175). Mean baseline BTT score was 2.3 (SD 1.1). At end-of-treatment, mean BTT scores were significantly higher for the combination group than control (p < 0.001, MD = 4.4, 95% CI 1.7 to 7.2) and standard care (p = 0.009) groups. Interval SIT scores increased significantly (p = 0.009) in the combination group. rs–fMRI showed significantly higher FC in the combination group when compared to other groups. At end-of-treatment, positive correlations were found in the increased FC at left inferior frontal gyrus and clinically significant improvements in measured BTT (r = 0.858, p < 0.001) and SIT (r = 0.548, p = 0.042) scores for the combination group.
Conclusions: Short-course oral VitA and aerosolised diffuser OT was effective as a combination treatment for persistent OD in long COVID.
Source: Chung TW-H, Zhang H, Wong FK-C, Sridhar S, Lee TM-C, Leung GK-K, Chan K-H, Lau K-K, Tam AR, Ho DT-Y, et al. A Pilot Study of Short-Course Oral Vitamin A and Aerosolised Diffuser Olfactory Training for the Treatment of Smell Loss in Long COVID. Brain Sciences. 2023; 13(7):1014. https://doi.org/10.3390/brainsci13071014 https://www.mdpi.com/2076-3425/13/7/1014 (Full text)

Investigating the neural substrates of Chronic Fatigue Syndrome/Myalgic Encephalomyelitis (CFS/ME) : a structural and functional MRI study

Abstract:

Chronic Fatigue Syndrome/Myalgic Encephalomyelitis (CFS/ME) is characterised by continuous fatigue and has many diagnostic criteria. Cognitive dysfunction affects 86-94% of adults with CFS/ME.

This thesis used MRI applications to investigate brain structure and function in CFS/ME. This thesis hypothesised to find brain volume differences, functional connectivity differences in brain networks, and functional differences measured by Blood Oxygenation Level Dependant (BOLD) signal activation during working memory task performance.

The working memory paradigm was designed to investigate working memory components, processing and storage separately and combined. The relationship between fatigue and performance was assessed. This thesis’s original contribution provides evidence that the salience network might have altered resting-state functional connectivity in CFS/ME in the absence of morphological differences.

The salience network is involved in detecting and integrating salient sensory information; therefore, disruption in this network might disrupt incoming cognitive stimuli and influence other networks’ connectivity, involved in fatigue and impaired memory.

In the more demanding task, participants with CFS/ME were slower and less accurate but used the same working memory network as healthy controls. No brain volume differences, nor atrophy were found. The differences between these findings compared to previous studies might be due to different study designs, analysis methods, sample sizes with different symptoms, including illness duration, physical inactivity and sleep disturbance.

The salience network alteration could potentially have a significant role in CFS/ME, as we cannot determine cause and effect with current experimental design the association with fatigue and other CFS/ME symptoms remains unclear. Using longitudinal studies that account for neurologically relevant confounders are needed in CFS/ME to further investigate the role of salience network.

Source: Almutairi, Basim S. Investigating the neural substrates of Chronic Fatigue Syndrome/Myalgic Encephalomyelitis (CFS/ME) : a structural and functional MRI study. PhD Thesis, University of Bristol. uk.bl.ethos.866683  https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.866683

Connectivity between Salience and Default Mode Networks and subcortical nodes distinguishes between two classes of ME/CFS

Abstract:

Myalgic Encephalomyelitis or Chronic Fatigue Syndrome (ME/CFS) is a debilitating disease with unknown pathophysiology. Functional MRI (fMRI) studies in ME/CFS have reported disparate connectivities for the brain salience (SA) and default mode (DMN) networks.

In this study, we acquired resting state and task fMRI with an advanced scanner for improved subject numbers: 24 healthy controls (HC) and 42 ME/CFS patients, 18 meeting International Consensus Criteria (ICC) and 24 meeting Fukuda criteria. We evaluated mean FC between SA and DMN network hub, and subcortical regions known to be involved in ME/CFS. We tested the hypothesis that ME/CFS connectivity differed from HC and the ICC and Fukuda classes are distinguished by different connectivities with HC for different pairs of SA, DMN or subcortical hubs.

During resting state fMRI only two connections differed from HC, both for Fukuda ME/CFS and both with an SA hub. During task fMRI 10 ME/CFS connections differed from HC, 5 for ICC and 5 for Fukuda. None were common to both classes. Eight of the 10 different connections involved an SA hub, six of 10 were weaker in ME/CFS, 4 stronger.

SA connections to the hippocampus and brainstem reticular activation system (RAS) differed from and were stronger than HC. The SA mediates the relative activity of the DMN and executive networks and imbalance will have functional consequences. The RAS and hippocampus modulate cortical activation. Different regulatory connections are consistent with the impaired cognitive performance and sleep-wake cycle of ME/CFS. Different neuropathology is involved in ICC and Fukuda classes.

Source: Su J, Thapaliya K, Eaton-Fitch N, Marshall-Gradisnik SM, Barnden LR. Connectivity between Salience and Default Mode Networks and subcortical nodes distinguishes between two classes of ME/CFS. Brain Connect. 2022 Nov 9. doi: 10.1089/brain.2022.0049. Epub ahead of print. PMID: 36352819. https://pubmed.ncbi.nlm.nih.gov/36352819/