Category: Methodology

Assessment of symptoms in myalgic encephalomyelitis/chronic fatigue syndrome: a comparative study of existing scales

Abstract:

Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a multifaceted disorder characterized by persistent fatigue, post-exertional malaise (PEM), cognitive dysfunction, sleep disturbance, pain, psychological distress, orthostatic intolerance, and impaired multidimensional health status and functioning. In the absence of reliable biomarkers, standardized symptom assessment is essential for accurate diagnosis and comparability across studies.

This narrative literature review synthesized studies identified through PubMed and Web of Science up to June 2024, covering assessment instruments across major ME/CFS symptom domains. Tools were evaluated for their psychometric validity, clinical applicability, and key limitations.

Overall, existing scales demonstrate acceptable reliability but vary in sensitivity and disease specificity. Harmonized, multidimensional, and digitally or objectively validated measures are needed to improve diagnostic precision, longitudinal monitoring, and clinical translation in ME/CFS.

Source: Lu J, Sun W, Li S, Qu Y, Liu T, Guo S, Feng C, Yang T. Assessment of symptoms in myalgic encephalomyelitis/chronic fatigue syndrome: a comparative study of existing scales. Front Neurol. 2025 Nov 18;16:1618272. doi: 10.3389/fneur.2025.1618272. PMID: 41341517; PMCID: PMC12668935. https://pmc.ncbi.nlm.nih.gov/articles/PMC12668935/ (Full text)

Leveraging Explainable Automated Machine Learning (AutoML) and Metabolomics for Robust Diagnosis and Pathophysiological Insights in Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS)

Abstract:

Background/Objectives: Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) is a debilitating complex disease with an elusive etiology, lacking objective diagnostic biomarkers. This study leverages advanced Automated Machine Learning (AutoML) to analyze plasma metabolomic and lipidomic profiles for the purpose of ME/CFS detection.

Methods: We utilized a publicly available dataset comprising 888 metabolic features from 106 ME/CFS patients and 91 matched controls. Three AutoML frameworks-TPOT, Auto-Sklearn, and H2O AutoML-were benchmarked under identical time constraints. Univariate ROC and PLS-DA analyses with cross-validation, permutation testing, and VIP-based feature selection were applied to standardized, log-transformed omics data to identify significant discriminatory metabolites/lipids and assess their intercorrelations.

Results: TPOT significantly outperformed its counterparts, achieving an area under the curve (AUC) of 92.1%, accuracy of 87.3%, sensitivity of 85.8%, and specificity of 89.0%. The PLS-DA model revealed a moderate but statistically significant discrimination between ME/CFS and controls. Explainable artificial intelligence (XAI) via SHAP analysis of the optimal TPOT model identified key metabolites implicating dysregulated pathways in mitochondrial energy metabolism (succinic acid, pyruvic acid, leucine), chronic inflammation (prostaglandin D2, 11,12-EET), gut-brain axis communication (glycocholic acid), and cell membrane integrity (pc(35:2)a).

Conclusions: Our results demonstrate that TPOT-derived models not only provide a highly accurate and robust diagnostic tool but also yield biologically interpretable insights into the pathophysiology of ME/CFS, highlighting its potential for clinical decision support and elucidating novel therapeutic targets.

Source: Yagin FH, Colak C, Al-Hashem F, Alzakari SA, Alhussan AA, Aghaei M. Leveraging Explainable Automated Machine Learning (AutoML) and Metabolomics for Robust Diagnosis and Pathophysiological Insights in Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS). Diagnostics (Basel). 2025 Oct 30;15(21):2755. doi: 10.3390/diagnostics15212755. PMID: 41226047. https://www.mdpi.com/2075-4418/15/21/2755 (Full text)

Psychometric evaluation of the PROMIS® physical function short form 12a for use by adults with myalgic encephalomyelitis/chronic fatigue syndrome

Abstract:

Background: Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a debilitating, long-term illness that significantly impairs physical functioning. Despite its impact, the use of modern generic instruments to assess physical function in this population remains underexplored. This study aims to assess the psychometric properties of the Patient-Reported Outcome Measurement Information System® (PROMIS) Physical Function Short Form (PF-SF) 12a for use in adults with ME/CFS.

Methods: This study included 334 participants (173 with ME/CFS and 161 healthy controls) who took part in a Cognitive and Exercise sub-study of the Multi-Site Clinical Assessment of ME/CFS study from six clinics across the US. Data was used to examine the ceiling/floor effects, internal consistency reliability, known-groups validity, and convergent validity of the PROMIS PF-SF.

Results: The mean T-score of the PROMIS PF-SF was 40.5 for participants with ME/CFS, about one standard deviation below the national norm (T-score = 50). The PROMIS PF-SF showed no substantial floor/ceiling effects and high internal consistency (standardized Cronbach’s α = 0.88 and ω = 0.92). In addition, this instrument showed good known-groups validity with medium-to-large effect sizes (η2 = 0.08-0.35). A significant, monotonic increase of the physical function score was found across ME/CFS participant groups with low, medium, and high functional impairment as defined by four different measures. Participants with ME/CFS had significantly worse physical function scores than healthy controls (η2 = 0.70). The PROMIS PF-SF also demonstrated good convergent validity with high correlations (magnitude of r = 0.47-0.55) with other relevant measures.

Conclusions: The PROMIS PF-SF 12a demonstrated satisfactory reliability and validity for use in ME/CFS research and clinical practice.

Source: Yang M, Keller S, Rafiee P, Lin JS. Psychometric evaluation of the PROMIS® physical function short form 12a for use by adults with myalgic encephalomyelitis/chronic fatigue syndrome. Health Qual Life Outcomes. 2025 Oct 6;23(1):95. doi: 10.1186/s12955-025-02431-6. PMID: 41053836; PMCID: PMC12502361. https://pmc.ncbi.nlm.nih.gov/articles/PMC12502361/ (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)

AI-driven multi-omics modeling of myalgic encephalomyelitis/chronic fatigue syndrome

Abstract:

Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a chronic illness with a multifactorial etiology and heterogeneous symptomatology, posing major challenges for diagnosis and treatment. Here we present BioMapAI, a supervised deep neural network trained on a 4-year, longitudinal, multi-omics dataset from 249 participants, which integrates gut metagenomics, plasma metabolomics, immune cell profiling, blood laboratory data and detailed clinical symptoms.

By simultaneously modeling these diverse data types to predict clinical severity, BioMapAI identifies disease- and symptom-specific biomarkers and classifies ME/CFS in both held-out and independent external cohorts. Using an explainable AI approach, we construct a unique connectivity map spanning the microbiome, immune system and plasma metabolome in health and ME/CFS adjusted for age, gender and additional clinical factors.

This map uncovers altered associations between microbial metabolism (for example, short-chain fatty acids, branched-chain amino acids, tryptophan, benzoate), plasma lipids and bile acids, and heightened inflammatory responses in mucosal and inflammatory T cell subsets (MAIT, γδT) secreting IFN-γ and GzA.

Overall, BioMapAI provides unprecedented systems-level insights into ME/CFS, refining existing hypotheses and hypothesizing unique mechanisms—specifically, how multi-omics dynamics are associated to the disease’s heterogeneous symptoms.

Source: Xiong, R., Aiken, E., Caldwell, R. et al. AI-driven multi-omics modeling of myalgic encephalomyelitis/chronic fatigue syndrome. Nat Med (2025). https://doi.org/10.1038/s41591-025-03788-3  https://www.nature.com/articles/s41591-025-03788-3

Using the Ratio of Phosphorylated to Non-phosphorylated Forms of Stress Kinase PKR as a Potential Diagnostic Test for ME/CFS

Abstract:

Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a complex illness characterized by a set of mainly neurological symptoms lasting for over 6 months. Currently, there is no definitive laboratory diagnostic test readily accessible to all clinicians and patients, and so clinical diagnosis occurs only after an exhaustive process of exclusion of all other possible causes of the varied symptoms experienced by the patient.

Here we present the development of a method that uses specific antibodies able to identify a changed ratio of phosphorylated and active protein kinase R in the peripheral blood monocyte cells (PBMCs) and neutrophil cells from a small group of ME/CFS sufferers, compared to age and sex-matched controls.

Protein kinase R (PKR) is an RNA-activated immune protein and stress kinase that has been observed to be present in its cleaved, auto-phosphorylated, and active form in past ME/CFS studies. After further validation, the activation status of PKR detected via specific antibodies in an ELISA format has potential for a simple readily accessible diagnostic tool for the early acute stage of ME/CFS illness, or as a long-term measure to evaluate the disease status.

Source: Sweetman E, Tate WP. Using the Ratio of Phosphorylated to Non-phosphorylated Forms of Stress Kinase PKR as a Potential Diagnostic Test for ME/CFS. Methods Mol Biol. 2025;2920:13-28. doi: 10.1007/978-1-0716-4498-0_2. PMID: 40372675. https://link.springer.com/protocol/10.1007/978-1-0716-4498-0_2

Using Single-Cell Raman Microspectroscopy to Profile Human Peripheral Blood Mononuclear Cells

Abstract:

A reliable, validated test would enhance our ability to treat and research chronic conditions. Early and accurate diagnosis would provide an entry point into clinical care, give access to benefits, remove the stigma associated with these conditions, and importantly, provide researchers with a fundamental tool they require to study these heterogeneous disorders.

In this chapter, we describe how Raman microspectroscopy can be utilised to study the biology of peripheral blood mononuclear cells (PBMCs) isolated from human blood samples. Using machine learning approaches, the data generated can be used to attempt to separate different patient and control groups, subgroups within a patient cohort, and identify differences in intracellular metabolites which may provide clues about disease mechanisms.

Source: Gan E, Stoker M, Guo E, Morten KJ, Xu J. Using Single-Cell Raman Microspectroscopy to Profile Human Peripheral Blood Mononuclear Cells. Methods Mol Biol. 2025;2920:29-37. doi: 10.1007/978-1-0716-4498-0_3. PMID: 40372676. https://link.springer.com/protocol/10.1007/978-1-0716-4498-0_3

MicroRNA Profiling of Blood Extracellular Vesicles in ME/CFS

Abstract:

Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a chronic debilitating neuroimmune disease affecting many organs and systems which, in the absence of validated biomarkers, remains diagnosed by clinical criteria. Extracellular vesicles (EV) in blood come from practically all cells in our body and therefore may carry the disease-specific biomarkers needed for the diagnosis of ME.

This chapter presents the methodology used on a single pilot study performed to evaluate this possibility to describe a workflow for EV isolation and the analysis of the miRNAs within, which could serve to interrogate additional cohorts of ME/CFS. Among the diverse nature of EV contents miRNAs may constitute a prominent regulatory layer in the development and progress of complex diseases such as ME/CFS, and therefore their study should be further pursued.

Source:Ljungström M, Nathanson L, Oltra E. MicroRNA Profiling of Blood Extracellular Vesicles in ME/CFS. Methods Mol Biol. 2025;2920:39-55. doi: 10.1007/978-1-0716-4498-0_4. PMID: 40372677. https://link.springer.com/protocol/10.1007/978-1-0716-4498-0_4

Deep Immunophenotyping in ME/CFS Using Spectral Flow Cytometry

Abstract:

Immune dysfunction is reported to play a significant role in the etiology of myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS). To gain an understanding of the underlying immune abnormalities associated with this complex condition, a comprehensive approach for characterizing immune cell subsets and their inferred functional states is essential.

We developed a high-dimensional flow cytometry method that enables detailed immunophenotyping of peripheral blood mononuclear cells (PBMCs) from ME/CFS patients. By simultaneously measuring over 40 markers on individual cells within one sample, this approach provides a comprehensive assessment of immune cell subsets, incorporating effector or functional states, to enable assessment of their potential roles in disease pathogenesis.

Source: Gibson A, Chometon TQ, Damani T, Brooks AES. Deep Immunophenotyping in ME/CFS Using Spectral Flow Cytometry. Methods Mol Biol. 2025;2920:59-82. doi: 10.1007/978-1-0716-4498-0_5. PMID: 40372678. https://link.springer.com/protocol/10.1007/978-1-0716-4498-0_5

Analysis of Transient Receptor Potential Ion Channels in ME/CFS

Abstract:

This chapter provides a comprehensive overview of methodologies currently employed to study ion channels, particularly transient receptor potential melastatin 3 (TRPM3) in the context of myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS). Sample preparation involves the collection of whole blood, separation of peripheral blood mononuclear cells (PBMCs) via density gradient centrifugation, and isolation of natural killer (NK) cells.

Protein expression analysis utilizes flow cytometry, liquid chromatography-mass spectrometry (LC-MS), western blotting, and immunofluorescence techniques. Functional analysis focuses on calcium imaging and electrophysiology techniques to investigate ion channel responses to pharmacological stimuli.

The authors highlight that some experimental protocols included within this chapter require specialized training and equipment. In order to replicate these protocols extended training is advised, specifically when attempting electrophysiology experimentation. The use of advanced techniques for detailed analysis provides insights into ion channel function and potential implications in the pathomechanism of ME/CFS offering avenues for further research and therapeutic exploration.

Source: Eaton-Fitch N, Muraki K, Sasso EM, Magawa C, Marshall-Gradisnik S. Analysis of Transient Receptor Potential Ion Channels in ME/CFS. Methods Mol Biol. 2025;2920:83-99. doi: 10.1007/978-1-0716-4498-0_6. PMID: 40372679. https://link.springer.com/protocol/10.1007/978-1-0716-4498-0_6