Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 13, 2026

Developing Neuroimaging Phenotypes of the Default Mode Network in PTSD: Integrating the Resting State, Working Memory, and Structural Connectivity
10:43

Developing Neuroimaging Phenotypes of the Default Mode Network in PTSD: Integrating the Resting State, Working Memory, and Structural Connectivity

Published on: July 1, 2014

Raman Spectroscopy Combined with Machine Learning Reveals Myalgic Encephalomyelitis-Associated Biomolecular

Maryam Heidarifard1,2,3, Atefeh Moezzi4,5,6,7, Frédérick Dallaire2,8

  • 1Azrieli Research Center, CHU Sainte-Justine, Montreal, QC H3T 1C5, Canada.

International Journal of Molecular Sciences
|June 12, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Irisin Signaling Resistance in Myalgic Encephalomyelitis: A Proposed Mechanistic Framework for Post-Exertional Malaise Involving the TSP-1-HSP90α-αvβ5 Axis.

International journal of molecular sciences·2026
Same author

Single-cell Raman spectroscopy detects pediatric focal cortical dysplasia.

Biophotonics discovery·2026
Same author

Deployment of a real-time prostate cancer confirmation system with Raman spectroscopy: fine-tuning versus test-time adaptation of 1D CNNs.

Biophotonics discovery·2026
Same author

PTPRN2 hypomethylation and PHB2-associated miR-153-3p maturation define dual epigenetic features linked to symptom variability in Myalgic encephalomyelitis.

Journal of translational medicine·2026
Same author

Combining label-free Raman spectroscopy and machine learning to identify early biomarkers of COVID-19 disease severity and mortality.

Journal of biomedical optics·2026
Same author

Biochemical and metabolic tissue discrimination using a dual-modality Raman-fluorescence endonasal spectroscopy probe for pituitary adenoma surgery.

Pituitary·2026

This study introduces a novel screening approach for Myalgic Encephalomyelitis (ME) using Raman spectroscopy and machine learning. It detects specific biomolecular changes in blood plasma, aiding in ME diagnosis and understanding stress-induced alterations.

Area of Science:

  • Biomedical Spectroscopy
  • Machine Learning in Healthcare
  • Biomarker Discovery

Background:

  • Myalgic encephalomyelitis (ME) presents with debilitating fatigue and post-exertional malaise (PEM), but its pathophysiology and diagnostic markers remain elusive.
  • Current diagnostic methods for ME lack speed and validated biomarkers, hindering timely patient management and research.
  • Understanding disease heterogeneity and identifying objective measures are crucial for advancing ME research and clinical care.

Purpose of the Study:

  • To develop a rapid, label-free screening approach for Myalgic Encephalomyelitis (ME) using Raman spectroscopy (RS) and machine learning (ML).
  • To detect distinct biomolecular signatures in blood plasma differentiating ME patients from healthy controls.
  • To investigate biochemical alterations in plasma following a standardized stress test to induce post-exertional malaise (PEM).
Keywords:
biomarkersblood plasmalabel-free Raman spectroscopymachine learning modelingmyalgic encephalomyelitispost-exertional malaise

More Related Videos

Biomarkers in an Animal Model for Revealing Neural, Hematologic, and Behavioral Correlates of PTSD
08:29

Biomarkers in an Animal Model for Revealing Neural, Hematologic, and Behavioral Correlates of PTSD

Published on: October 10, 2012

Related Experiment Videos

Last Updated: Jun 13, 2026

Developing Neuroimaging Phenotypes of the Default Mode Network in PTSD: Integrating the Resting State, Working Memory, and Structural Connectivity
10:43

Developing Neuroimaging Phenotypes of the Default Mode Network in PTSD: Integrating the Resting State, Working Memory, and Structural Connectivity

Published on: July 1, 2014

Biomarkers in an Animal Model for Revealing Neural, Hematologic, and Behavioral Correlates of PTSD
08:29

Biomarkers in an Animal Model for Revealing Neural, Hematologic, and Behavioral Correlates of PTSD

Published on: October 10, 2012

Main Methods:

  • Collected blood plasma from 115 ME patients and 45 controls at rest (T0) and 90 minutes post-stress (T90).
  • Utilized label-free Raman spectroscopy (RS) to analyze plasma samples for biomolecular composition.
  • Developed and validated machine learning (ML) models to differentiate ME patients from controls based on RS data at both time points.

Main Results:

  • Raman spectroscopy identified spectral features indicative of proteins, lipids, and metabolites in plasma.
  • Machine learning models achieved high diagnostic performance: AUC (0.85 at T0, 0.83 at T90), accuracy (79% at T0, 84% at T90), specificity (82% at T0, 90% at T90), and sensitivity (73% at T0, 69% at T90).
  • The RS-ML approach successfully captured biochemical changes associated with standardized physical stress in ME patients.

Conclusions:

  • The combination of Raman spectroscopy and machine learning offers a rapid, cost-effective method for detecting ME-associated biomolecular profiles in plasma.
  • This approach can identify biochemical alterations linked to standardized stress, providing insights into post-exertional malaise (PEM).
  • RS-ML holds potential as a screening tool for ME, facilitating diagnosis and monitoring of disease activity.