Resting-state functional connectivity predicts motor cortex stimulation-dependent pain relief in fibromyalgia syndrome patients

Abstract

MRI-based resting-state functional connectivity (rsFC) has been shown to predict response to pharmacological and non-pharmacological treatments for chronic pain, but not yet for motor cortex transcranial magnetic stimulation (M1-rTMS). Twenty-seven fibromyalgia syndrome (FMS) patients participated in this double-blind, crossover, and sham-controlled study. Ten daily treatments of 10 Hz M1-rTMS were given over 2 weeks. Before treatment series, patients underwent resting-state fMRI and clinical pain evaluation. Significant pain reduction occurred following active, but not sham, M1-rTMS. The following rsFC patterns predicted reductions in clinical pain intensity after the active treatment: weaker rsFC of the default-mode network with the middle frontal gyrus (r = 0.76, p < 0.001), the executive control network with the rostro-medial prefrontal cortex (r = 0.80, p < 0.001), the thalamus with the middle frontal gyrus (r = 0.82, p < 0.001), and the pregenual anterior cingulate cortex with the inferior parietal lobule (r = 0.79, p < 0.001); and stronger rsFC of the anterior insula with the angular gyrus (r = - 0.81, p < 0.001). The above regions process the attentional and emotional aspects of pain intensity; serve as components of the resting-state networks; are modulated by rTMS; and are altered in FMS. Therefore, we suggest that in FMS, the weaker pre-existing interplay between pain-related brain regions and networks, the larger the pain relief resulting from M1-rTMS.

Figure 1

Active M1-rTMS is superior to sham in relieving clinical pain. Time × Treatment interaction in MPQ-Sensory was tested using Friedman’s ANOVA with Wilcoxon–Nemenyi–McDonald–Thompson post-hoc tests. All p-values are corrected for 4 preplanned contrasts. BPI Brief Pain Inventory, MPQ McGill Pain Questionnaire, NS not significant, VAS visual analog scale; *p < 0.05; **p < 0.01; ***p < 0.001.

Figure 2

MPQ-VAS reduction following the real, but not sham M1-rTMS, was predicted by stronger resting-state FC of the DMN and ECN with the frontal pole. Coordinates in upper panels are in MNI space. r Pearson’s correlation coefficient; ***p < 0.001.

Figure 3

rsFC of ascending nociceptive and descending pain inhibition brain areas BPI-Severity predict reductions following real, but not sham, M1-rTMS. Coordinates in upper panels are in MNI space. aINS anterior insula r, Pearson’s correlation coefficient, pgACC pregenual anterior cingulate cortex. ***p < 0.001.