Tag: biomarker

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/

Authors’ Response to “Comment on ‘SMPDL3B as a novel biomarker and therapeutic target in myalgic encephalomyelitis’”

Letter:

We thank Chen and Yan for their thoughtful and positive comments on our recent publication and for their interest in the translational implications of SMPDL3B biology in myalgic encephalomyelitis (ME) [, ]. Their letter provides a welcome opportunity to clarify methodological points related to biomarker validation, in vitro pharmacological assays, and mechanistic interpretation []. We appreciate this constructive dialogue and address each issue below in a collegial and scientifically grounded manner.

Read the rest of this letter HERE>>

Source: Rostami-Afshari B, Elremaly W, Franco A, Moreau A. Authors’ Response to “Comment on ‘SMPDL3B as a novel biomarker and therapeutic target in myalgic encephalomyelitis'”. J Transl Med. 2026 Jan 16;24(1):75. doi: 10.1186/s12967-025-07583-z. PMID: 41546078; PMCID: PMC12809929. https://pmc.ncbi.nlm.nih.gov/articles/PMC12809929/ (Full text)

People with ME/CFS have a consistent faulty cellular structure, new research confirms

Press Release:

A faulty ion channel function is a consistent biological feature of Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS), providing long-awaited validation for hundreds of thousands of Australians living with the debilitating illness.

The new Griffith University research found a crucial cellular structure responsible for calcium transport, the TRPM3 ion channel, was faulty in immune cells from people with ME/CFS.

The paper “Large-scale investigation confirms TRPM3 ion channel dysfunction in ME/CFS” has been published in Frontiers in Medicine.

Director and senior author, Professor Sonya Marshall-Gradisnik from Griffith’s National Center for Neuroimmunology and Emerging Diseases (NCNED), said the TRPM3 played an essential role in calcium transport into cells, regulating responses properly in the body, immune function, and maintaining normal cellular balance.

“When it fails, cells cannot function properly as calcium signaling is essential for healthy immune cell activity,” Professor Marshall-Gradisnik said.

“Our findings provide clear and definitive scientific evidence that TRPM3 ion channels are not working properly in people with ME/CFS.”

Read the rest of this press release HERE>>

Large-scale investigation confirms TRPM3 ion channel dysfunction in Myalgic Encephalomyelitis/Chronic Fatigue Syndrome

Abstract:

Introduction: Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) is a chronic disease hallmarked by multiple systemic symptoms, such as neurocognitive, respiratory, immunological, gastrointestinal, and cardiovascular impairment, which worsen following physical and mental exertion. ME/CFS is characterized by an elusive pathomechanism, profound impact on quality of life, and an absence of diagnostic tests or evidence-based treatments. Transient Receptor Potential Melastatin 3 (TRPM3) ion channel has been suggested as a potential biomarker and target for therapeutics in people with ME/CFS, supported by a series of publications reporting genetic and protein changes. This study aimed to undertake a multi-site, large-scale investigation to determine the consistency of TRPM3 ion channel dysfunction in people with ME/CFS.

Methods: TRPM3 ion channel activity was assessed in two distinct laboratory sites by independent investigators using whole-cell patch-clamp recordings performed in isolated natural killer (NK) cells from 36 ME/CFS participants, characterized according to the Canadian Consensus Criteria, and 42 healthy controls. The Mann–Whitney U test was used to compare endogenous TRPM3-like currents between cohorts. The effect of location was determined using a covariance analysis, while antagonist sensitivity was determined using Fisher’s Exact test.

Results: Electrophysiological experiments revealed a significant reduction in TRPM3 function in NK cells from individuals diagnosed with ME/CFS compared with controls in all parameters analyzed. Importantly, there was no significant effect of the laboratory sites on the results of this investigation, which confirms TRPM3 as a consistent biomarker for ME/CFS.

Conclusion: The current large-sample-size study confirmed previous results regarding TRPM3 ion channel dysfunction in NK cells in ME/CFS, demonstrating involvement of TRPM3 in the pathomechanism of this condition. Therefore, this multiple-site investigation offers strong evidence demonstrating TRPM3 as a potential biomarker for the diagnosis of ME/CFS, given the accumulating evidence.

Source: Sasso Etianne Martini , Er Teagan S. , Eaton-Fitch Natalie , Hool Livia , Muraki Katsuhiko , Marshall-Gradisnik Sonya. Large-scale investigation confirms TRPM3 ion channel dysfunction in Myalgic Encephalomyelitis/Chronic Fatigue Syndrome. Frontiers in Medicine, Volume 12 – 2026. https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2025.1703924 10.3389/fmed.2025.1703924 ISSN=2296-858X https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2025.1703924/full (Full text)

Wheat and chaff in Myalgic Encephalomyelitis/Chronic fatigue syndrome (ME/CFS) in clinics and laboratory

To the Editor,

We read the contribution by Hunter et al., titled “Development and validation of blood-based diagnostic biomarkers for Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) using EpiSwitch® 3-dimensional genomic regulatory immuno-genetic profiling” in this journal, initially impressed for the large collection of data. They actually presented a novel, genome-wide epigenetic profiling approach using EpiSwitch® technology to identify potential diagnostic biomarkers for ME/CFS [1]. The use of 3D chromatin conformation signatures provides a fresh perspective on disease-specific gene regulation, moving beyond conventional transcriptomics and methylation analyses. In general, the diagnostic model demonstrates impressive sensitivity (92%) and specificity (98%) in distinguishing ME/CFS patients from controls, suggesting real clinical potential [1]. Moreover, the application of advanced machine learning techniques adds analytical robustness, while pathway analysis identifies biologically plausible immune-related mechanisms. This integrative approach sets a promising foundation for future biomarker-driven diagnostics and personalized therapy stratification in ME/CFS. Fundamentally, they presented a retrospective case-control analysis aiming to identify diagnostic epigenetic markers for ME/CFS using 3D chromatin conformation profiling (EpiSwitch®). However, while the authors make bold claims regarding diagnostic sensitivity and specificity, the paper suffers from multiple scientific weaknesses and methodological ambiguities that undermine its validity and translational relevance.

First, the article repeatedly asserts that “immune dysregulation” is a hallmark of ME/CFS, citing elevated pro-inflammatory cytokines and natural killer (NK) cell dysfunction. However, whereas the authors cite updated papers with a presumptive relationship with the issue, a critical omission here is the lack of citation of early foundational immunological studies in ME/CFS [2]. Notably absent is the 1994 work by Tirelli et al. in the Scandinavian Journal of Immunology, which documented, for the first time, immunological abnormalities in CFS patients and could serve as an important historical anchor for claims of immune dysregulation [2]. This omission raises concerns about reporting bias and selective citation to frame the narrative around newer, possibly more aligned findings with the current study methodology [2, 3].

Additionally, the paper refers to “ME/CFS inclusion criteria” as requiring severe CFS with patients being “housebound,” but fails to specify which diagnostic criteria were used, whether the Fukuda, Canadian Consensus, International Consensus, or IOM/NAM criteria [1]. This lack of precision is critical, as different case definitions yield different cohorts in terms of clinical features and biological signatures. Using “severe housebound” as a criterion, without reference to a validated clinical definition or stratification tool (e.g., Bell Disability Scale), introduces subjectivity and undermines the reproducibility of patient selection. The term “housebound” is not a recognized diagnostic stratifier and suggests imprecise cohort construction.

Further ambiguity arises when the authors discuss the control group. They state that controls had “none of the four key CFS symptoms present or in the past” and “preferably an existing history of glandular fever or COVID.” The phrase “preferably” is ambiguous and methodologically problematic [1]. Did the control group actually include individuals with prior infectious mononucleosis or COVID-19, and if so, how were these illnesses verified? The phrase “preferably” suggests either inconsistency in selection or retrospective rationalization, both of which compromise the clarity and control of variables in the study. Furthermore, it is scientifically incoherent to describe individuals as controls (i.e., free from ME/CFS) while also including those with a known post-infectious risk profile, potentially biasing the control group with latent post-viral immunogenetic changes [1].

There is further conceptual confusion when the authors state that the ME/CFS network reveals some overlap with pathways involved in multiple sclerosis (MS) and rheumatoid arthritis (RA). While such overlaps are plausible and worth exploring, the authors do not sufficiently explain the biological rationale for this claim or its relevance to ME/CFS pathophysiology [1]. They reference IL-2, IL-10, CD4, and TLR pathways as shared elements, but these are highly pleiotropic and non-specific immunological signals.

The mere presence of these markers in ME/CFS does not imply mechanistic similarity to MS or RA. Without longitudinal or functional studies, this comparison becomes speculative and possibly misleading, especially given the known heterogeneity of ME/CFS and the distinct immunopathology of autoimmune diseases like MS.

Read the rest of this letter HERE.

Source: Tirelli U, Franzini M, Chirumbolo S. Wheat and chaff in Myalgic Encephalomyelitis/Chronic fatigue syndrome (ME/CFS) in clinics and laboratory. J Transl Med. 2026 Jan 5;24(1):20. doi: 10.1186/s12967-025-07397-z. PMID: 41491817. https://link.springer.com/article/10.1186/s12967-025-07397-z (Full text)

Exploring a genetic basis for the metabolic perturbations in ME/CFS using UK Biobank

Highlights:

  • ME/CFS shows distinct genetic influences on metabolic regulation.
  • Lipid and hormone-related pathways emerge as key areas of interest.
  • Many small genetic effects may collectively disrupt metabolic resilience in ME/CFS.

Summary:

Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) is a clinically heterogeneous disease lacking approved therapies. To assess genetic susceptibility towards a specific metabolic phenotype, we performed a genome-wide association study on plasma biomarker levels (mGWAS) in ME/CFS patients (n=875) and healthy controls (HCs) (n=36,033).
We identified 112 significant SNP–biomarker associations in ME/CFS, compared with 4,114 in HCs. Two SNPs specific to ME/CFS, mapping to HSD11B1 and SCGN, were associated to phospholipids in extra-large very low-density lipoproteins (VLDL) and total fatty acids respectively. Genetic effects of VLDL associations were among the least correlated between ME/CFS and HCs. Heterogeneity tests found differential effects for several lipid traits at ADAP1, NR1H3 and CD40, which are involved in immune regulation.
ME/CFS mGWAS summary statistics were decomposed to uncover shared genetic-metabolic patterns, where enrichment analysis highlighted pathways in lipid metabolism, neurotransmitter transport, and inflammation. These findings provide a genetic and molecular rationale for patient heterogeneity and suggest a polygenic predisposition in which many small-effect variants may jointly perturb metabolic mechanisms.
Source: Katherine Huang, Muhammad Muneeb, Natalie Thomas, Elena K. Schneider-Futschik, Paul R. Gooley, David B. Ascher, Christopher W. Armstrong. Exploring a genetic basis for the metabolic perturbations in ME/CFS using UK Biobank. iScience, 2025, 114316 ISSN 2589-0042, https://doi.org/10.1016/j.isci.2025.114316. https://www.sciencedirect.com/science/article/pii/S2589004225025775 (Full text available as PDF file)

The Role of Nuclear and Mitochondrial DNA in Myalgic Encephalomyelitis: Molecular Insights into Susceptibility and Dysfunction

Abstract:

Myalgic Encephalomyelitis (ME), also known as chronic fatigue syndrome (CFS), is a debilitating and heterogeneous disorder marked by persistent fatigue, post-exertional malaise, cognitive impairment, and multisystem dysfunction. Despite its prevalence and impact, the molecular mechanisms underlying ME remain poorly understood.
This review synthesizes current evidence on the role of DNA, both nuclear and mitochondrial, in the susceptibility and pathophysiology of ME. We examined genetic predispositions, including familial clustering and candidate gene associations, and highlighted emerging insights from genome-wide and multi-omics studies.
Mitochondrial DNA variants and oxidative stress-related damage are discussed in relation to impaired bioenergetics and symptom severity. Epigenetic modifications, particularly DNA methylation dynamics and transposable element activation, are explored as mediators of gene–environment interactions and immune dysregulation.
Finally, we explored the translational potential of DNA-based biomarkers and therapeutic targets, emphasizing the need for integrative molecular approaches to advance diagnosis and treatment. Understanding the DNA-associated mechanisms in ME offers a promising path toward precision medicine in post-viral chronic diseases.
Source: Elremaly W, Elbakry M, Vahdani Y, Franco A, Moreau A. The Role of Nuclear and Mitochondrial DNA in Myalgic Encephalomyelitis: Molecular Insights into Susceptibility and Dysfunction. DNA. 2025; 5(4):53. https://doi.org/10.3390/dna5040053 https://www.mdpi.com/2673-8856/5/4/53 (Full text)

Advancing Digital Precision Medicine for Chronic Fatigue Syndrome through Longitudinal Large-Scale Multi-Modal Biological Omics Modeling with Machine Learning and Artificial Intelligence

Abstract:

We studied a generalized question: chronic diseases like ME/CFS and long COVID exhibit high heterogeneity with multifactorial etiology and progression, complicating diagnosis and treatment. To address this, we developed BioMapAI, an explainable Deep Learning framework using the richest longitudinal multi-omics dataset for ME/CFS to date.

This dataset includes gut metagenomics, plasma metabolome, immune profiling, blood labs, and clinical symptoms. By connecting multi-omics to a symptom matrix, BioMapAI identified both disease- and symptom-specific biomarkers, reconstructed symptoms, and achieved state-of-the-art precision in disease classification.

We also created the first connectivity map of these omics in both healthy and disease states and revealed how microbiome-immune-metabolome crosstalk shifted from healthy to ME/CFS.

Source: Xiong R. Advancing Digital Precision Medicine for Chronic Fatigue Syndrome through Longitudinal Large-Scale Multi-Modal Biological Omics Modeling with Machine Learning and Artificial Intelligence. ArXiv [Preprint]. 2025 Jun 18:arXiv:2506.15761v1. PMID: 40980765; PMCID: PMC12447721. https://pmc.ncbi.nlm.nih.gov/articles/PMC12447721/ (Full text available as PDF file)

Metabolic neuroimaging of myalgic encephalomyelitis/chronic fatigue syndrome and Long-COVID

Abstract:

Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) and Long-COVID are complex, disabling conditions that have emerged as significant public health challenges, affecting millions worldwide. Despite their growing prevalence, effective diagnostics and treatments remain limited, largely due to an incomplete understanding of their underlying pathophysiology. Both conditions share hallmark symptoms of chronic fatigue, cognitive dysfunction, and postexertional malaise, but their biological underpinnings remain to be elucidated. Neuroimaging offers a promising, noninvasive window into the brain’s metabolic landscape and has the potential to uncover objective biomarkers for these conditions.

In this mini review, we highlight recent advancements in metabolic neuroimaging, particularly positron emission tomography and magnetic resonance imaging/magnetic resonance spectroscopy, that reveal alterations in glucose and oxygen metabolism, neurotransmitter balance, and oxidative stress. These insights point toward shared disruptions in brain energy metabolism and neuroinflammatory processes, which may underlie the persistent symptoms in both ME/CFS and Long-COVID.

Importantly, while some findings overlap, inconsistencies in metabolite profiles between ME/CFS and Long-COVID underscore the need for further stratification and longitudinal research. Standardizing definitions, such as identifying Long-COVID patients who meet ME/CFS diagnostic criteria, could help improve study comparability.

By summarizing current imaging evidence, this review underscores the potential of neuroimaging to identify imaging biomarkers to advance the clinical diagnosis of Long-COVID and identify therapeutic targets for treatment development. As we continue to face the growing burden of Long-COVID and ME/CFS, metabolic imaging may serve as a powerful tool to bridge gaps in knowledge and accelerate progress toward effective care.

Source: Zhu Y, Quan P, Yamazaki T, Norweg A, Natelson B, Xu X. Metabolic neuroimaging of myalgic encephalomyelitis/chronic fatigue syndrome and Long-COVID. Immunometabolism (Cobham). 2025 Sep 12;7(4):e00068. doi: 10.1097/IN9.0000000000000068. PMID: 40958852; PMCID: PMC12435251. https://pmc.ncbi.nlm.nih.gov/articles/PMC12435251/ (Full text)