Transcranial random noise stimulation mitigates increased difficulty in an arithmetic learning task

Abstract

Proficiency in arithmetic learning can be achieved by using a multitude of strategies, the most salient of which are procedural learning (applying a certain set of computations) and rote learning (direct retrieval from long-term memory). Here we investigated the effect of transcranial random noise stimulation (tRNS), a non-invasive brain stimulation method previously shown to enhance cognitive training, on both types of learning in a 5-day sham-controlled training study, under two conditions of task difficulty, defined in terms of item repetition. On the basis of previous research implicating the prefrontal and posterior parietal cortex in early and late stages of arithmetic learning, respectively, sham-controlled tRNS was applied to bilateral prefrontal cortex for the first 3 days and to the posterior parietal cortex for the last 2 days of a 5-day training phase. The training involved learning to solve arithmetic problems by applying a calculation algorithm; both trained and untrained problems were used in a brief testing phase at the end of the training phase. Task difficulty was manipulated between subjects by using either a large ("easy" condition) or a small ("difficult" condition) number of repetition of problems during training. Measures of attention and working memory were acquired before and after the training phase. As compared to sham, participants in the tRNS condition displayed faster reaction times and increased learning rate during the training phase; as well as faster reaction times for both trained and untrained (new) problems, which indicated a transfer effect after the end of training. All stimulation effects reached significance only in the "difficult" condition when number of repetition was lower. There were no transfer effects of tRNS on attention or working memory. The results support the view that tRNS can produce specific facilitative effects on numerical cognition--specifically, on arithmetic learning. They also highlight the importance of task difficulty in the neuromodulation of learning, which in the current study due to the manipulation of item repetition might have being mediated by the memory system.

Keywords: Cognitive training; Mental arithmetic; Posterior parietal cortex; Prefrontal cortex; Task difficulty; Transcranial random noise stimulation.

Fig. 1

Structure of a trial for each type of problem (left panel: Drill; right panel: Calculation).

Fig. 2

RTs on Calculation trials, as a function of Difficulty and Stimulation Group. Data is collapsed across all five training sessions. Error bars represent 95% confidence intervals. * p<.05, ** p<.01.

Fig. 3

Calculation RT distributions for the (a) easy and (b) difficult conditions as a function of Stimulation Group. Data points represent the mean proportion of responses across participants, within 500 ms-wide bins. (c) The ex-Gaussian parameters – µ (mu), σ (sigma) and τ (tau) – that describe these distributions as a function of Difficulty and Stimulation Group. Error bars represent 95% confidence intervals. * p<.05, ** p<.01.

Fig. 4

(a) RTs and (b) accuracy on Calculation problems in the testing phase, as a function of (a) Difficulty and Stimulation Group or (b) Difficulty, Stimulation Group and Problem Novelty. Error bars represent 95% confidence intervals. * p<.05.