Functional Connectivity Changes in Resting-State EEG as Potential Biomarker for Amyotrophic Lateral Sclerosis

Abstract

Background: Amyotrophic Lateral Sclerosis (ALS) is heterogeneous and overlaps with frontotemporal dementia. Spectral EEG can predict damage in structural and functional networks in frontotemporal dementia but has never been applied to ALS.

Methods: 18 incident ALS patients with normal cognition and 17 age matched controls underwent 128 channel EEG and neuropsychology assessment. The EEG data was analyzed using FieldTrip software in MATLAB to calculate simple connectivity measures and scalp network measures. sLORETA was used in nodal analysis for source localization and same methods were applied as above to calculate nodal network measures. Graph theory measures were used to assess network integrity.

Results: Cross spectral density in alpha band was higher in patients. In ALS patients, increased degree values of the network nodes was noted in the central and frontal regions in the theta band across seven of the different connectivity maps (p<0.0005). Among patients, clustering coefficient in alpha and gamma bands was increased in all regions of the scalp and connectivity were significantly increased (p=0.02). Nodal network showed increased assortativity in alpha band in the patients group. The Clustering Coefficient in Partial Directed Connectivity (PDC) showed significantly higher values for patients in alpha, beta, gamma, theta and delta frequencies (p=0.05).

Discussion: There is increased connectivity in the fronto-central regions of the scalp and areas corresponding to Salience and Default Mode network in ALS, suggesting a pathologic disruption of neuronal networking in early disease states. Spectral EEG has potential utility as a biomarker in ALS.

Fig 1. Methods Flow Chart.

Flowchart of methods explaining the preprocessing and two stage processing for scalp connectivity and nodal connectivity.

Fig 2. Scalp network connectivity.

Shows difference in clustering coefficients between patients (green) and controls (orange) in different scalp regions. (F = Frontal, C = Central, P = Parietal O = Occipital) (D = Delta, T = Theta, A = Alpha L = Low, H = High).

Fig 3. Nodal connectivity.

Statistically significant differences in nodal connectivity (Directed Transfer Function) between patients and controls in various frequency bands.

Fig 4. Aggregated nodal network connectivity.

Assortativity of Partial Directed Coherence, showing differences between patients (Yellow) and controls (Green) with p = 0.0032 for Alpha range (Delta p = 0.74, theta p = 0.26, beta p = 0.46, gamma p = 0.47).

Fig 5. Non-aggregated nodal network connectivity.

Clustering coefficient of PDC values in nodal analysis for beta band for patients (green) and controls (orange).

Fig 6. The distribution of clustering coefficient of PDC in beta band as a box-plot in patients vs. controls, showing the median and interquartile range.