Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 32 min ago
Peer-reviewedCC BY 4.0PLOS One

Graph theory-based machine learning for automated fibromyalgia diagnosis using fMRI during an emotional task

  • Leila Solouki1
  • Soodeh Shahsavari2
  • Hamid Sharini3
  • Amir Hossein Hashemian4
  • Volker Johann Schmid5
  • Samira Jafari6
  • Saleh Rouhi7
  • Behzad Mahaki
7 affiliations
  1. 1Student Research Committee, Kermanshah University of Medical Sciences, Kermanshah, Iran
  2. 2Health Data Science Research Center, Health Research Institute, Kermanshah University of Medical Sciences, Kermanshah, Iran
  3. 3Department of Biostatistics, School of Health, Kermanshah University of Medical Sciences, Kermanshah, Iran
  4. 4Department of Biomedical Engineering, Faculty of Medicine, Kermanshah University of Medical Sciences, Kermanshah, Iran
  5. 5Bioimaging Group, Department of Statistics, Ludwig Maximimilians, Munich, Germany
  6. 6Modeling in Health Research Center, Institute for Futures Studies in Health, Kerman University of Medical Sciences, Kerman, Iran
  7. 7Department of Medical Physics, Faculty of Medicine, Kermanshah University of Medical Sciences, Kermanshah, Iran
Open at sourcePDFDOICite

Abstract

Background: Fibromyalgia (FM) is a multifaceted chronic pain disorder presenting with pain throughout the musculoskeletal system, alongside chronic fatigue,sleep disturbances, and cognitive impairments. Current diagnostic criteria primarily rely on symptom questionnaires, with no specific laboratory markers or definitive tests, making diagnosis subjective and often delayed. Moreover, the overlap with other central pain syndromes further complicates accurate diagnosis. Neuroimaging studies, particularly functional magnetic resonance imaging (fMRI), have shown promise in elucidating brain abnormalities underlying FM. However, translating these findings into reliable diagnostic tools remains challenging, especially given small sample sizes. Therefore, this study aims to enhance the diagnostic accuracy of FM based on fMRI data by developing an intelligent model. This model employs machine learning algorithms designed to perform effectively with limited dataset sizes and incorporates features extracted through graph theory methods. We analyzed fMRI data from 32 FM patients and 30 healthy controls. Graph theory metrics were extracted from 13 regions of the emotion regulation network. A genetic algorithm was employed to select the most effective features, which were then used to train multiple machine learning classifiers—including Support Vector Machine (SVM) with polynomial and Radial Basis Function (RBF) kernels, Random Forest, Gradient Boosting Machine, Adaptive Boosting, and SVM with Mixture Kernels—within a cross-validation framework to ensure robustness. Result: The genetic algorithm selected 84 features as inputs for machine learning algorithms. The polynomial SVM achieved the highest overall accuracy, whereas the SVM with mixture kernels demonstrated superior sensitivity and AUC. Sensitivity and AUC were prioritized as the main criteria for model selection due to their clinical relevance in reducing false negatives. Conclusion: The study identified the SVM with Mixture Kernels as the most effective model for distinguishing FM patients from healthy controls. This approach demonstrates promising potential for enhancing diagnostic accuracy and supporting psychological and psychiatric interventions.

Related

  1. Machine learning classification of fibromyalgia from blood transcriptomes: confounder benchmarking and implications for endometriosis-associated pain
    S. Ouni, F. Ouni, A. Chebbi
    bioRxivPreprintCC BYFull textBioinformatics & computational biologybioRxiv
  2. An automated ranking platform for machine learning regression models for meat spoilage prediction using multi-spectral imaging and metabolic profiling
    Lucia Estelles-Lopez, Athina Ropodi, Dimitris Pavlidis +6
    Food Research InternationalPeer-reviewedLicence not stated86 citedGeneral biologyStatisticsHAL
  3. Serum proteins predict incident inflammatory bowel disease 14 years before diagnosis: a machine-learning and Cox modelling in the UK Biobank
    T. E. Niebuhr, J. Fieggen, B. M. Segal +3
    medRxivPreprintAll rights reservedFull textGenetics & genomicsmedRxiv
  4. Early vs late fusion of qMIDS with machine learning based classifiers for oral cancer diagnosis from gene expression data
    Ferid Ben Ali, Iosif Mporas, Vaishnavi Balaji +4
    PLOS Computational BiologyPeer-reviewedCC BY 4.0Full textMolecular biology & gene regulationGenetics & genomicsPLOSPMC
  5. Emotional Modulation of Face Working Memory Precision in Specific Learning Disorders: Valence Flattening and Mnemonic Distortions
    M. Makhsous, M. Honar, S. Akbari +1
    bioRxivPreprintAll rights reservedFull textNeurosciencebioRxiv

Cite

BibTeXRIS
BibTeX
@article{solouki2026graph,
  title = {{Graph theory-based machine learning for automated fibromyalgia diagnosis using fMRI during an emotional task}},
  author = {Leila Solouki and Soodeh Shahsavari and Hamid Sharini and Amir Hossein Hashemian and Volker Johann Schmid and Samira Jafari and Saleh Rouhi and Behzad Mahaki},
  journal = {PLOS One},
  year = {2026},
  month = oct,
  doi = {10.1371/journal.pone.0357964},
  url = {https://doi.org/10.1371/journal.pone.0357964},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Graph theory-based machine learning for automated fibromyalgia diagnosis using fMRI during an emotional task
AU  - Leila Solouki
AU  - Soodeh Shahsavari
AU  - Hamid Sharini
AU  - Amir Hossein Hashemian
AU  - Volker Johann Schmid
AU  - Samira Jafari
AU  - Saleh Rouhi
AU  - Behzad Mahaki
PY  - 2026
DA  - 2026/10/01
JO  - PLOS One
DO  - 10.1371/journal.pone.0357964
UR  - https://doi.org/10.1371/journal.pone.0357964
AB  - Background: Fibromyalgia (FM) is a multifaceted chronic pain disorder presenting with pain throughout the musculoskeletal system, alongside chronic fatigue,sleep disturbances, and cognitive impairments. Current diagnostic criteria primarily rely on symptom questionnaires, with no specific laboratory markers or definitive tests, making diagnosis subjective and often delayed. Moreover, the overlap with other central pain syndromes further complicates accurate diagnosis. Neuroimaging studies, particularly functional magnetic resonance imaging (fMRI), have shown promise in elucidating brain abnormalities underlying FM. However, translating these findings into reliable diagnostic tools remains challenging, especially given small sample sizes. Therefore, this study aims to enhance the diagnostic accuracy of FM based on fMRI data by developing an intelligent model. This model employs machine learning algorithms designed to perform effectively with limited dataset sizes and incorporates features extracted through graph theory methods. We analyzed fMRI data from 32 FM patients and 30 healthy controls. Graph theory metrics were extracted from 13 regions of the emotion regulation network. A genetic algorithm was employed to select the most effective features, which were then used to train multiple machine learning classifiers—including Support Vector Machine (SVM) with polynomial and Radial Basis Function (RBF) kernels, Random Forest, Gradient Boosting Machine, Adaptive Boosting, and SVM with Mixture Kernels—within a cross-validation framework to ensure robustness. Result: The genetic algorithm selected 84 features as inputs for machine learning algorithms. The polynomial SVM achieved the highest overall accuracy, whereas the SVM with mixture kernels demonstrated superior sensitivity and AUC. Sensitivity and AUC were prioritized as the main criteria for model selection due to their clinical relevance in reducing false negatives. Conclusion: The study identified the SVM with Mixture Kernels as the most effective model for distinguishing FM patients from healthy controls. This approach demonstrates promising potential for enhancing diagnostic accuracy and supporting psychological and psychiatric interventions.
SN  - 1932-6203
ER  -