Causal evidence supporting functional dissociation of verbal and spatial working memory in the human dorsolateral prefrontal cortex

Abstract

The human dorsolateral prefrontal cortex (dlPFC) is crucial for monitoring and manipulating information in working memory, but whether such contributions are domain-specific remains unsettled. Neuroimaging studies have shown bilateral dlPFC activity associated with working memory independent of the stimulus domain, but the causality of this relationship cannot be inferred. Repetitive transcranial magnetic stimulation (rTMS) has the potential to test whether the left and right dlPFC contribute equally to verbal and spatial domains; however, this is the first study to investigate the interaction of task domain and hemisphere using offline rTMS to temporarily modulate dlPFC activity. In separate sessions, 20 healthy right-handed adults received 1 Hz rTMS to the left dlPFC and right dlPFC, plus the vertex as a control site. The working memory performance was assessed pre-rTMS and post-rTMS using both verbal-'letter' and spatial-'location' versions of the 3-back task. The response times were faster post-rTMS, independent of the task domain or stimulation condition, indicating the influence of practice or other nonspecific effects. For accuracy, rTMS of the right dlPFC, but not the left dlPFC or vertex, led to a transient dissociation, reducing spatial, but increasing verbal accuracy. A post-hoc correlation analysis found no relationship between these changes, indicating that the substrates underlying the verbal and spatial domains are functionally independent. Collapsing across time, there was a trend towards a double dissociation, suggesting a potential laterality in the functional organisation of verbal and spatial working memory. At a minimum, these findings provide human evidence for domain-specific contributions of the dlPFC to working memory and reinforce the potential of rTMS to ameliorate cognition.

Keywords: dorsolateral prefrontal cortex; functional neuroanatomy; functional specialisation; repetitive transcranial magnetic stimulation; working memory.

Figure 1. Schematic of 3-back Tasks and Experimental Protocol

A. Verbal and spatial versions of the 3-back task were administered as participant as sat in front of a computer screen with a response box in their right hand. The verbal stimuli consisted of single letters (‘A-J’) that were presented in the center of the screen. Letters were randomly presented in either upper- or lowercase, and participants had to treat both cases as matching stimuli. In the spatial version, participants had to remember the visuotopic position of a dot that appeared in one of ten locations. B. For each trial, the participant had to remember the previous three stimuli, determine whether the next stimulus (n) matched the oldest member of the set (n – 3), respond “yes” or “no” by pressing one of two buttons, and then shift the set forward by one for the next trial. C. Each participant completed three experimental sessions in which a different site was targeted for repetitive transcranial magnetic stimulation (rTMS). All sessions followed the same format: (1) working memory abilities were assessed at baseline with alternating blocks of the verbal and spatial 3-back tasks; (2) the target site was determined based on scalp landmarks; (3) the resting motor threshold (RMT) was assessed; (4) a 1Hz train of rTMS was applied to the target site for 20 minutes at 100% of the RMT; (4) immediately after rTMS ended, working memory abilities were reassessed with alternating blocks of the verbal and spatial 3-back tasks. Task order was consistent throughout each session, but counterbalanced between sessions. Individual sessions were separated by at least 48 hours.

Figure 2. Direct Impact of rTMS on 3-back Accuracy

The mean accuracy (percent correct) for both tasks (verbal, spatial) and all three rTMS conditions (left dlPFC, right dlPFC, vertex) for Experiment 1. Error bars represent standard error. *p < 0.05. Right panel. An MRI was obtained in a twelve participants with vitamin D capsules in place over the stimulation sites.

Figure 3. Interaction Between rTMS Condition and Task Domain for 3-back Accuracy

Net change in accuracy (% correct) calculated by subtracting baseline from post-rTMS scores for Experiment 1. Error bars represent standard error of the mean. **p < 0.01, ^†p < 0.1.

Figure 4. Nonspecific Impact of rTMS on 3-back Task Response Time

Response times (ms) averaged across tasks and rTMS conditions for Experiment 1. Error bars represent standard error of the mean. *p < 0.05.