Clinical pain and functional network topology in Parkinson's disease: a resting-state fMRI study

Abstract

Pain is an important non-motor symptom in Parkinson's disease (PD), but its underlying pathophysiological mechanisms are still unclear. Research has shown that functional connectivity during the resting-state may be involved in persistent pain in PD. In the present cross-sectional study, 24 PD patients (both during on and off medication phase) and 27 controls participated. We assessed pain with the colored analogue scale and the McGill pain questionnaire. We examined a possible pathophysiological mechanism with resting-state fMRI using functional network topology, i.e., the architecture of functional connections. We took betweenness centrality (BC) to assess hubness, and global efficiency (GE) to assess integration of the network. We aimed to (1) assess the differences between PD patients and controls with respect to pain and resting-state network topology, and (2) investigate how resting-state network topology (BC and GE) is associated with clinical pain in both PD patients and controls. Results show that PD patients experienced more pain than controls. GE of the whole brain was higher in PD patients (on as well as off medication) compared to healthy controls. GE of the specialized pain network was also higher in PD patients compared to controls, but only when patients were on medication. BC of the pain network was lower in PD patients off medication compared to controls. We found a positive association between pain and GE of the pain network in PD patients off medication. For healthy controls, a negative association was found between pain and GE of the pain network, and also between pain and BC of the pain network. Our results suggest that functional network topology differs between PD patients and healthy controls, and that this topology can be used to investigate the underlying neural mechanisms of pain symptoms in PD.

Keywords: Functional network topology; Pain; Parkinson’s disease; Resting-state fMRI.

Fig. 1

The pain network, based on the positive predictive weights of the NPS (Wager et al. 2013). Areas shown are: 1 = vermis cerebellum; 2 = anterior/mid insula (right); 3 = superior temporal gyrus; 4 = calcarine gyrus; 5 = ventrolateral thalamus (right); 6 = mid insula (left); 7 = hypothalamus; 8 = ventrolateral thalamus (left); 9 = frontal operculum/temporal pole; 10 = dorsal posterior insula/secondary somatosensory area (left); 11 = dorsal posterior insula (right); 12 = somatosensory area (right); 13 = temporoparietal junction; 14 = dorsal anterior cingulate cortex; 15 = supramarginal gyrus; 16 = inferior parietal lobule. BrainNet Viewer version 1.6 was used for visualization (http://www.nitrc.org/projects/bnv/) (Xia et al. 2013)

Fig. 2

Flowchart of inclusion process

Fig. 3

Plots of separate significant effects of the regression analyses. Left panel (blue): a negative linear association of GE of the pain network with NWC-scores for HC. Middle panel (blue): a negative linear association of BC of the pain network with NWC-scores for HC. Right panel (green): A positive linear association of GE of the pain network with NWC-scores for PD OFF. GE global efficiency, NWC number of words chosen, BC betweenness centrality, PD Parkinson’s disease, HC healthy controls, PD OFF PD patients during OFF phase