Assessment of across-muscle coherence using multi-unit vs. single-unit recordings

Abstract

Coherence between electromyographic (EMG) signals has been used to identify correlated neural inputs to motor units (MUs) innervating different muscles. Simulations using a motor-unit model (Fuglevand et al. 1992) were performed to determine the ability of coherence between two multi-unit EMGs (mEMG) to detect correlated MU activity and the range of correlation strengths in which mEMG coherence can be usefully employed. Coherence between motor-unit and mEMG activities in two muscles was determined as we varied the strength of a 30-Hz periodic common input, the number of correlated MU pairs and variability of MU discharge relative to the common input. Pooled and mEMG coherence amplitudes positively and negatively accelerated, respectively, toward the strongest and most widespread correlating inputs. Furthermore, the relation between pooled and mEMG coherence was also nonlinear and was essentially the same whether correlation strength varied by changing common input strength or its distribution. However, the most important finding is that while the mEMG coherence saturates at the strongest common input strengths, this occurs at common input strengths greater than found in most physiological studies. Thus, we conclude that mEMG coherence would be a useful measure in many experimental conditions and our simulation results suggest further guidelines for using and interpreting coherence between mEMG signals.

Fig. 1

Examples of (a) single MUAP and MUAP trains from two muscles with their respective mEMGs (uncorrelated MUAP’s at a mean discharge rate of 8 Hz). b The timings of individual MUAPs of units that received common input could be reset if they fell within 30 ms following a common input spike, and the previous MUAP occurred more than 20 ms before the common input spike. c If these conditions were met, the MUAP was shifted to align with the common input spike but only if this spike is one of the fraction of spikes chosen for re-alignment. The arrow denotes an adjustment to the timing of one action potential (dashed bar) made based on the criteria shown in (b). Note that jitter is introduced when aligning the target action potential with the common input spike time

Fig. 2

a Average unit-to-unit coherence magnitudes at the common input frequency as a function of common input strength. b and c show average rectified mEMG amplitude and spectral power (computed over all frequencies), respectively, as a function of common input strength and 0.3, 17 and 67.8% correlated MU pairs (dotted, dashed, solid lines, respectively). * and ** indicates p < 0.05 and 0.01, respectively

Fig. 3

Examples of single MU and unrectified mEMG autospectra (top row, left and right panels, respectively), MU and mEMG coherence (middle row) and pooled coherence (bottom row) for common input strengths of 25 and 75% (left and right panels, respectively). Horizontal lines denote 95% confidence limits (limits for pooled coherence are 1.75e × 10⁻⁴). Note the different scales for the y-axes

Fig. 4

mEMG coherence magnitudes at the common input frequency averaged across trials for all distributions of common input and jitter levels at (a) 25 and (b) 75% common input strength. c and d show the same for pooled coherence magnitudes at 25 and 75% common input strengths, respectively. Note the different scale for the y-axis in (c). Lines illustrate trends only and are not best fit lines. e and f show the relation between mEMG and pooled coherence magnitudes at the common input frequency (averaged across trials) as a function of jitter and including all distributions of common input for 25 and 75% common input strength, respectively. Lines indicate the best fit functions for the condition of 0.83 jitter

Fig. 5

Average coherence magnitudes at the common input frequency are shown for a unrectified mEMG, b rectified mEMG and c pooled MU activity. Relations between pooled and d unrectified and e rectified mEMG are also shown. Coherence magnitudes are shown for all common input strengths and for 0.3, 17 and 67.8% correlated MU pairs. Lines indicate best fit functions. Note the different scales for the y-axes

Fig. 6

Percentage of trials with significant 30 Hz coherence for the unrectified and rectified mEMG signals (dashed and dotted lines, respectively) for simulations with 0.3, 17 and 67.8% correlated MU pairs