Longitudinal changes in adolescent risk-taking: a comprehensive study of neural responses to rewards, pubertal development, and risk-taking behavior

Abstract

Prior studies have highlighted adolescence as a period of increased risk-taking, which is postulated to result from an overactive reward system in the brain. Longitudinal studies are pivotal for testing these brain-behavior relations because individual slopes are more sensitive for detecting change. The aim of the current study was twofold: (1) to test patterns of age-related change (i.e., linear, quadratic, and cubic) in activity in the nucleus accumbens, a key reward region in the brain, in relation to change in puberty (self-report and testosterone levels), laboratory risk-taking and self-reported risk-taking tendency; and (2) to test whether individual differences in pubertal development and risk-taking behavior were contributors to longitudinal change in nucleus accumbens activity. We included 299 human participants at the first time point and 254 participants at the second time point, ranging between ages 8-27 years, time points were separated by a 2 year interval. Neural responses to rewards, pubertal development (self-report and testosterone levels), laboratory risk-taking (balloon analog risk task; BART), and self-reported risk-taking tendency (Behavior Inhibition System/Behavior Activation System questionnaire) were collected at both time points. The longitudinal analyses confirmed the quadratic age pattern for nucleus accumbens activity to rewards (peaking in adolescence), and the same quadratic pattern was found for laboratory risk-taking (BART). Nucleus accumbens activity change was further related to change in testosterone and self-reported reward-sensitivity (BAS Drive). Thus, this longitudinal analysis provides new insight in risk-taking and reward sensitivity in adolescence: (1) confirming an adolescent peak in nucleus accumbens activity, and (2) underlining a critical role for pubertal hormones and individual differences in risk-taking tendency.

Keywords: adolescence; puberty; reward processing; risk-taking.

Figure 1.

Example of a trial. On trial onset, participants were presented with a screen for 4000 ms indicating how many coins could be won or lost. During this time, participants chose to play heads or tails by pressing the corresponding button. After a 1000 ms delay, trial outcome was presented for 1500 ms. Participants won when the computer randomly selected the same side of the coin as chosen by the participant (Braams et al., 2013).

Figure 2.

Win > lose when playing for self for T1 and T2 and the anatomical region of the nucleus accumbens used for analyses. All activation is familywise error corrected at voxel level. A threshold of 10 voxels was used as a cutoff for display purposes only. All slices MNI Y = 12.

Figure 3.

Correlation matrix of all variables on time points 1 and 2.

Figure 4.

A, Longitudinal graphic representation of age at both time points and contrast values for win > lose for the left nucleus accumbens on both time points. Individual subjects are represented by individual lines. Subjects measured only once are represented by points. Right nucleus accumbens, not represented in a figure, shows similar effects. B, Predicted values for contrast values for win > lose for the left nucleus accumbens based on the optimal fitting model. Right nucleus accumbens, not represented in a figure, shows similar effects. Dotted lines represent 95% confidence interval.

Figure 5.

A, Longitudinal graphic representation of age at both time points and PDS scores on both time points. Individual subjects are represented by individual lines Subjects measured only once are represented by points. B, Predicted values for PDS scores based on the optimal fitting model. Dotted lines represent 95% confidence interval.

Figure 6.

A, Longitudinal graphic representation of age at both time points and testosterone values on both time points. Individual subjects are represented by individual lines. Subjects measured only once are represented by points. B, Predicted values for testosterone values based on the optimal fitting model. Dotted lines represent 95% confidence interval.

Figure 7.

A, Longitudinal graphic representation of age at both time points and total number of explosions in the BART on both time points. Individual subjects are represented by individual lines. Subjects measured only once are represented by points. B, Predicted values for total numbers of explosions in the BART based on the optimal fitting model. Dotted lines represent 95% confidence interval.