Spinal cord stimulation alleviates motor deficits in a primate model of Parkinson disease

Abstract

Although deep brain electrical stimulation can alleviate the motor symptoms of Parkinson disease (PD), just a small fraction of patients with PD can take advantage of this procedure due to its invasive nature. A significantly less invasive method--epidural spinal cord stimulation (SCS)--has been suggested as an alternative approach for symptomatic treatment of PD. However, the mechanisms underlying motor improvements through SCS are unknown. Here, we show that SCS reproducibly alleviates motor deficits in a primate model of PD. Simultaneous neuronal recordings from multiple structures of the cortico-basal ganglia-thalamic loop in parkinsonian monkeys revealed abnormal highly synchronized neuronal activity within each of these structures and excessive functional coupling among them. SCS disrupted this pathological circuit behavior in a manner that mimics the effects caused by pharmacological dopamine replacement therapy or deep brain stimulation. These results suggest that SCS should be considered as an additional treatment option for patients with PD.

Fig. 1. Spinal cord stimulation alleviates motor symptoms in parkinsonian primates

(A) Average effect on general motility in response to SCS. Each color line represents one recorded animal over all trials. (B-D), Average recovery of locomotion: bout distance, bout frequency and duration, respectively (colors represent the four different subjects and asterisks denote significant group differences). (E), Reduction in bradykinesia reflected by the preferential recovery of faster movement components in locomotion. (F), Average improvements in PD-score in all testing sessions divided by symptom category (mean and SEM shown). (G), Example of functional motor improvement from a state of severe Parkinsonism enabling an animal to retrieve food rewards using skilled reaching and grasping movements.

Fig. 2. Spinal cord stimulation alters neuronal activity patterns in basal ganglia circuits

(A), Example of parallel changes in LFP power in multiple structures of the cortico-basal ganglia-thalamic loop. For each brain structure, the panel at the right depicts pooled LFP spectrograms. Note the immediate reduction of low-frequency oscillations (beta band) in response to SCS (red bar, stimulation frequency: 4 Hz; color codes denote dB above pink noise background for LFPs). (B), Average LFP spectra for all recording sessions normalized to pink noise showing a significant SCS-induced reduction in LFP beta-power in all structures except GPe. (C), Changes in normalized firing rates of individual neurons were diverse but, on average, they decreased in response to SCS in GPi and VL.

Fig. 3

Spinal cord stimulation alters the firing rate and rhythmicity of neuronal units in basal ganglia circuits. (A), Standardized neuronal firing rate response to different SCS frequencies in multiple structures of the basal ganglia circuits (neurons rank ordered according to responses). (B), The fraction of inhibitory responses increased with higher SCS frequencies. (C), Autocorrelograms of two single units in MI exemplifying beta-range rhythmic firing pattern in a parkinsonian animal (SCS OFF). (D), Autocorrelograms of the same two units showing that the rhythmic spiking is effectively interrupted by SCS. (E), The respective power spectra OFF/ON (black/red) for the units shown in C-D. Note the peak (arrow) in the beta-range during the OFF period, which disappears during the ON period. (F), Changes in power of rhythmic beta-firing plotted for all 183 units that presented significant beta oscillations either in the OFF or ON period. Colored circles represent the units with significant suppression in beta power during the ON period. Black line denotes equal power in ON and OFF conditions, thus units located to the right of the line display beta suppression.

Fig. 4. Spinal cord stimulation and L-DOPA treatment suppresses multi-structure LFP coherence

(A), Example of LFP coherence spectra from one of the hemilesioned animals (black trace) showing coherent oscillations restricted to the beta-band in the parkinsonian condition (arrows) that are suppressed by SCS (red trace; bold line and shaded area denote median and interquartile range, stimulation artefacts around 20 and 40Hz have been removed). (B), Connectivity diagram representing the pooled LFP coherence in the 8-15Hz range in relation to the 30-40Hz band between all pairs of electrodes in the different structures (values represent averages from all five recordings in the two hemi-lesioned animals; all changes in beta-to-gamma coherence for SCS ON/OFF are significant p<0.05, Wilcoxon rank sum test). Note that the excessive beta-band coherence, represented by the warm colors in the parkinsonian state, is effectively reduced by SCS in the same way as for L-DOPA treatment.