Related Experiment Video
Updated: May 4, 2026
09:47
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
Published on: December 15, 2023
2.0K
Multiple kernel learning captures a systems-level functional connectivity biomarker signature in amyotrophic lateral
Tomer Fekete1, Neta Zach2, Lilianne R Mujica-Parodi1
1Department of Biomedical Engineering, Stony Brook University, New York, New York, United States of America.
Plos One
|January 7, 2014
Summary
Researchers identified widespread changes in brain network connectivity in amyotrophic lateral sclerosis (ALS) patients using resting-state functional MRI. This systems-level analysis shows potential for developing a non-invasive biomarker for ALS progression and treatment testing.
Area of Science:
- Neuroscience
- Systems Neuroscience
- Biomarker Discovery
Background:
- Amyotrophic lateral sclerosis (ALS) presents significant clinical and prognostic heterogeneity, despite a shared immunohistological profile.
- Pathology in ALS extends beyond motor systems, suggesting a broader system failure.
- Identifying reliable biomarkers is crucial for understanding and treating ALS, but simplistic approaches are insufficient.
Purpose of the Study:
- To explore changes in motor functional connectivity using resting-state functional MRI (fMRI) as a potential systems-level biomarker signature for ALS.
- To investigate the potential of fMRI-derived network alterations for accurate classification of ALS patients across clinical subtypes.
Main Methods:
- Resting-state fMRI data were acquired from 40 ALS patients and 30 healthy controls.
- Intra- and inter-motor functional networks in the 0.03-0.06 Hz frequency band were analyzed.
- Multiple kernel learning was employed for pattern detection and classification of patient groups.
Main Results:
- Accurate classification of ALS patients was achieved using functional connectivity features, requiring an average of 13 regions-of-interest.
- Alterations in motor functional connectivity were widespread, affecting both clinically affected and unaffected brain regions like the cerebellum and basal ganglia.
- Complex network analysis revealed distinct topological differences in ALS, including reduced connectivity with non-motor areas, reduced subcortico-cortical motor connectivity, and increased intra-subcortical motor network connectivity.
Conclusions:
- Systems-level analysis of functional brain networks using resting-state fMRI can non-invasively define a biomarker signature for ALS.
- These findings highlight the systemic nature of ALS and provide a foundation for developing biomarkers to track disease progression.
- This approach holds promise for generating biomarkers to test neuroprotective strategies in preclinical and clinical settings.
