FAST: A Novel, Executive Function-Based Approach to Cognitive Enhancement

Abstract

The present study introduces a novel cognitive intervention aimed at improving fluid intelligence (Gf), based on a framework we refer to as FAST: Flexible, Adaptive, Synergistic Training. FAST leverages a combination of novel game-based executive function (EF) training-designed specifically to enhance the likelihood of transfer-and transcranial electrical stimulation (tES), with aims to synergistically activate and strengthen mechanisms of cognitive control critical to Gf. To test our intervention, we collected three Gf measures from 113 participants [the advanced short Bochumer Matrizen-Test (BOMAT), Raven's Advanced Progressive Matrices (APM), and matrices similar to Raven's generated by Sandia labs], prior to and following one of three interventions: (1) the FAST + tRNS intervention, a combination of 30 min of daily training with our novel training game, Robot Factory, and 20 min of concurrent transcranial random noise stimulation applied to bilateral dorsolateral prefrontal cortex (DLPFC); (2) an adaptively difficult Active Control intervention comprised of visuospatial tasks that specifically do not target Gf; or (3) a no-contact control condition. Analyses of changes in a Gf factor from pre- to post-test found numerical increases for the FAST + tRNS group compared to the two control conditions, with a 0.3 SD increase relative to Active Control (p = 0.07), and a 0.19 SD increase relative to a No-contact control condition (p = 0.26). This increase was found to be largely driven by significant differences in pre- and post-test Gf as measured on the BOMAT test. Progression through the FAST training game (Robot Factory) was significantly correlated with changes in Gf. This is in contrast with progress in the Active Control condition, as well as with changes in individual EFs during FAST training, which did not significantly correlate with changes in Gf. Taken together, this research represents a useful step forward in providing new insights into, and new methods for studying, the nature of Gf and its malleability. Though our results await replication and extension, they provide preliminary evidence that the crucial characteristic of Gf may, in fact, be the ability to combine EFs rapidly and adaptively according to changing demand, and that Gf may be susceptible to targeted training.

Keywords: FAST; cognitive enhancement; cognitive training; executive function; fluid intelligence; transcranial electrical stimulation (tES).

Figure 1

Robot Factory opening screen image (left), and example task screenshot from the Assembly Line scenario (right). In this task, participants are presented with robot arms one at a time on a moving platform, which rises from a portal at the bottom of the screen. Participants must decide which direction to sort the arm (indicated with the corresponding left or right “Shift” key), based on whether or not it is a match (in color and style) with the arm seen 2-previous. If the participant gives the correct response, the platform moves into the correct sorting tube and an icon appears indicating an increase in points. If the participant gives the incorrect response, the laser in the upper left corner shoots a beam onto the platform, dissolving the arm, and the platform recedes into the tube in the lower portion of the screen.

Figure 2

Example trials from the Adaptive Visual Search task (left), the Silo Detection task (middle) and the Gabor (“Fingerprint") detection task (right).

Figure 3

Mean Gf post-test scores, adjusted for estimated baseline Gf ability, by Condition. ^†p < 0.1.

Figure 4

Standardized accuracy scores on each Gf post-test (BOMAT, Raven’s, Sandia), adjusted for estimated baseline Gf ability, by Condition. *p < 0.05, **p < 0.01, with Bonferroni correction.

Figure 5

Adjusted marginal mean post-test Gf as a function of progress in Robot Factory.

Figure 6

Changes in performance in the first $\frac{1}{3}$ of each participant’s trials in single-EF tasks to their last $\frac{1}{3}$ of trials in single-EF tasks. Measures are plotted so that positive values indicate improvement with training, giving the degree of accuracy improvement in Update trials (left), degree of decrease in average RT switch cost in Switch trials (middle), and degree of reduction in average stop-signal reaction time (SSRT) in Inhibit trials (right). **p < 0.01, ***p < 0.001.