Tag: machine learning

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/

Metabolomics-Based Machine Learning Diagnostics of Post-Acute Sequelae of SARS-CoV-2 Infection

Abstract:

Background: COVID-19 has taken millions of lives and continues to affect people worldwide. Post-Acute Sequelae of SARS-CoV-2 Infection (also known as Post-Acute Sequelae of COVID-19 (PASC) or more commonly, Long COVID) occurs in the aftermath of COVID-19 and is poorly understood despite its widespread effects.

Methods: We created a machine-learning model that distinguishes PASC from PASC-similar diseases. The model was trained to recognize PASC-dysregulated metabolites (p ≤ 0.05) using molecular descriptors.

Results: Our multi-layer perceptron model accurately recognizes PASC-dysregulated metabolites in the independent testing set, with an AUC-ROC of 0.8991, and differentiates PASC from myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS), Lyme disease, postural orthostatic tachycardia syndrome (POTS), and irritable bowel syndrome (IBS). However, it was unable to differentiate fibromyalgia (FM) from PASC.

Conclusions: By creating and testing models pairwise on each of these diseases, we elucidated the unique strength of the similarity between FM and PASC relative to other PASC-similar diseases. Our approach is unique to PASC diagnosis, and our use of molecular descriptors enables our model to work with any metabolite where molecular descriptors can be identified, as these descriptors can be generated and compared for any metabolite. Our study presents a novel approach to PASC diagnosis that partially circumvents the lengthy process of exclusion, potentially facilitating faster interventions and improved patient outcomes.

Source: Cai E, Kouznetsova VL, Tsigelny IF. Metabolomics-Based Machine Learning Diagnostics of Post-Acute Sequelae of SARS-CoV-2 Infection. Metabolites. 2025 Dec 17;15(12):801. doi: 10.3390/metabo15120801. PMID: 41441042; PMCID: PMC12734907. https://pmc.ncbi.nlm.nih.gov/articles/PMC12734907/ (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)

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)

Circulating cell-free RNA signatures for the characterization and diagnosis of myalgic encephalomyelitis/chronic fatigue syndrome

Abstract:

People living with myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) experience heterogeneous and debilitating symptoms that lack sufficient biological explanation, compounded by the absence of accurate, noninvasive diagnostic tools. To address these challenges, we explored circulating cell-free RNA (cfRNA) as a blood-borne bioanalyte to monitor ME/CFS. cfRNA is released into the bloodstream during cellular turnover and reflects dynamic changes in gene expression, cellular signaling, and tissue-specific processes.

We profiled cfRNA in plasma by RNA sequencing for 93 ME/CFS cases and 75 healthy sedentary controls, then applied machine learning to develop diagnostic models and advance our understanding of ME/CFS pathobiology. A generalized linear model with least absolute shrinkage selector operator regression trained on condition-specific signatures achieved a test-set AUC of 0.81 and an accuracy of 77%.

Immune cfRNA deconvolution revealed differences in platelet-derived cfRNA between cases and controls, as well as elevated levels of plasmacytoid dendritic, monocyte, and T cell-derived cfRNA in ME/CFS. Biological network analysis further implicated immune dysfunction in ME/CFS, with signatures of cytokine signaling and T cell exhaustion. These findings demonstrate the utility of RNA liquid biopsy as a minimally invasive tool for unraveling the complex biology behind chronic illnesses.

Source: Gardella AE, Eweis-LaBolle D, Loy CJ, Belcher ED, Lenz JS, Franconi CJ, Scofield SY, Grimson A, Hanson MR, De Vlaminck I. Circulating cell-free RNA signatures for the characterization and diagnosis of myalgic encephalomyelitis/chronic fatigue syndrome. Proc Natl Acad Sci U S A. 2025 Aug 19;122(33):e2507345122. doi: 10.1073/pnas.2507345122. Epub 2025 Aug 11. PMID: 40789036. https://pubmed.ncbi.nlm.nih.gov/40789036/

The Implications and Predictability of Sleep Reversal for People with Myalgic Encephalomyelitis/Chronic Fatigue Syndrome: A Machine Learning Approach

Abstract:

Background/objectives: Impaired sleep is one of the core symptoms of myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS), yet the mechanisms and impact of sleep-related issues are poorly understood. Sleep dysfunctions for patients with ME/CFS include frequent napping, difficulties falling asleep, waking up early, and sleep reversal patterns (e.g., sleeping throughout the day and staying awake throughout the night). The current study focuses on sleep reversal for patients with ME/CFS.

Methods: We explored the symptoms and functional impairment of those with and without sleep reversal by analyzing the responses of a large international sample (N = 2313) using the DePaul Symptom Questionnaire (DSQ) and Medical Outcomes Study 36-item Short-Form Health Survey (SF-36).

Results: We found that those in our Sleep Reversal group (N = 327) compared to those without sleep reversal (N = 1986) reported higher symptom burden for 53 out of 54 DSQ symptoms and greater impairments for all six SF-36 subscales. The most accurate predictors of sleep reversal included age (p < 0.05), body mass index (p < 0.05), eleven DSQ symptoms (p < 0.01), and two SF-36 subscales (p < 0.01).

Conclusions: These features provide clues regarding some of the possible pathophysiological underpinnings of sleep reversal among those with ME/CFS.

Source: Dietrich MP, Pravin R, Furst J, Jason LA. The Implications and Predictability of Sleep Reversal for People with Myalgic Encephalomyelitis/Chronic Fatigue Syndrome: A Machine Learning Approach. Healthcare (Basel). 2025 May 26;13(11):1255. doi: 10.3390/healthcare13111255. PMID: 40508869. https://www.mdpi.com/2227-9032/13/11/1255 (Full text)

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

Distinct pro-inflammatory/pro-angiogenetic signatures distinguish children with Long COVID from controls

Abstract:

Background: Recent proteomic studies have documented that Long COVID in adults is characterized by a pro-inflammatory signature with thromboinflammation. However, if similar events happen also in children with Long COVID has never been investigated.

Methods: We performed an extensive protein analysis of blood plasma from pediatric patients younger than 19 years of age Long COVID and a control group of children with acute COVID-19, MIS-C, and healthy controls resulted similar for sex distribution and age. Children were classified as Long COVID if symptoms persisted for at least 8 weeks since the initial infection, negatively impacted daily life and could not be explained otherwise.

Results: 112 children were included in the study, including 34 children fulfilling clinical criteria of Long COVID, 32 acute SARS-CoV-2 infection, 27 MIS-C and 19 healthy controls. Compared with controls, pediatric Long COVID was characterized by higher expression of the proinflammatory and pro-angiogenetic set of chemokines CXCL11, CXCL1, CXCL5, CXCL6, CXCL8, TNFSF11, OSM, STAMBP1a. A Machine Learning model based on proteomic profile was able to identify LC with an accuracy of 0.93, specificity of 0.86 and sensitivity of 0.97.

Conclusions: Pediatric Long COVID patients have a well distinct blood protein signature marked by increased ongoing general and endothelial inflammation, similarly as happens in adults.

Impact:

  • Pediatric Long COVID has a distinct blood protein signature marked by increased ongoing general and endothelial inflammation.
  • This is the first study studying and documenting proinflammatory profile in blood samples of children with long COVID.
  • Long COVID was characterized by higher expression of the proinflammatory and pro-angiogenetic set of chemokines CXCL11, CXCL1, CXCL5, CXCL6, CXCL8, TNFSF11, OSM, STAMBP1a.
  • A proteomic profile was able to identify Long COVID with an accuracy of 0.93, specificity of 0.86 and sensitivity of 0.97.
  • These findings may inform development of future diagnostic tests.

Source: Buonsenso, D., Cotugno, N., Amodio, D. et al. Distinct pro-inflammatory/pro-angiogenetic signatures distinguish children with Long COVID from controls. Pediatr Res (2025). https://doi.org/10.1038/s41390-025-03837-0  https://www.nature.com/articles/s41390-025-03837-0

Machine learning and multi-omics in precision medicine for ME/CFS

Abstract:

Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) is a complex and multifaceted disorder that defies simplistic characterisation. Traditional approaches to diagnosing and treating ME/CFS have often fallen short due to the condition’s heterogeneity and the lack of validated biomarkers. The growing field of precision medicine offers a promising approach which focuses on the genetic and molecular underpinnings of individual patients.

In this review, we explore how machine learning and multi-omics (genomics, transcriptomics, proteomics, and metabolomics) can transform precision medicine in ME/CFS research and healthcare. We provide an overview on machine learning concepts for analysing large-scale biological data, highlight key advancements in multi-omics biomarker discovery, data quality and integration strategies, while reflecting on ME/CFS case study examples. We also highlight several priorities, including the critical need for applying robust computational tools and collaborative data-sharing initiatives in the endeavour to unravel the biological intricacies of ME/CFS.

Source: Huang K, Lidbury BA, Thomas N, Gooley PR, Armstrong CW. Machine learning and multi-omics in precision medicine for ME/CFS. J Transl Med. 2025 Jan 14;23(1):68. doi: 10.1186/s12967-024-05915-z. PMID: 39810236. Huang K, Lidbury BA, Thomas N, Gooley PR, Armstrong CW. Machine learning and multi-omics in precision medicine for ME/CFS. J Transl Med. 2025 Jan 14;23(1):68. doi: 10.1186/s12967-024-05915-z. PMID: 39810236. https://translational-medicine.biomedcentral.com/articles/10.1186/s12967-024-05915-z (Full text)

Discriminating Myalgic Encephalomyelitis/Chronic Fatigue Syndrome and comorbid conditions using metabolomics in UK Biobank

Abstract:

Background: Diagnosing complex illnesses like Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) is complicated due to the diverse symptomology and presence of comorbid conditions. ME/CFS patients often present with multiple health issues, therefore, incorporating comorbidities into research can provide a more accurate understanding of the condition’s symptomatology and severity, to better reflect real-life patient experiences.

Methods: We performed association studies and machine learning on 1194 ME/CFS individuals with blood plasma nuclear magnetic resonance (NMR) metabolomics profiles, and seven exclusive comorbid cohorts: hypertension (n = 13,559), depression (n = 2522), asthma (n = 6406), irritable bowel syndrome (n = 859), hay fever (n = 3025), hypothyroidism (n = 1226), migraine (n = 1551) and a non-diseased control group (n = 53,009).

Results: We present a lipoprotein perspective on ME/CFS pathophysiology, highlighting gender-specific differences and identifying overlapping associations with comorbid conditions, specifically surface lipids, and ketone bodies from 168 significant individual biomarker associations. Additionally, we searched for, trained, and optimised a machine learning algorithm, resulting in a predictive model using 19 baseline characteristics and nine NMR biomarkers which could identify ME/CFS with an AUC of 0.83 and recall of 0.70. A multi-variable score was subsequently derived from the same 28 features, which exhibited ~2.5 times greater association than the top individual biomarker.

Conclusions: This study provides an end-to-end analytical workflow that explores the potential clinical utility that association scores may have for ME/CFS and other difficult to diagnose conditions.

Source: Huang K, G C de Sá A, Thomas N, Phair RD, Gooley PR, Ascher DB, Armstrong CW. Discriminating Myalgic Encephalomyelitis/Chronic Fatigue Syndrome and comorbid conditions using metabolomics in UK Biobank. Commun Med (Lond). 2024 Nov 26;4(1):248. doi: 10.1038/s43856-024-00669-7. PMID: 39592839; PMCID: PMC11599898.  https://pmc.ncbi.nlm.nih.gov/articles/PMC11599898/ (Full text)