Risk-averse personalities have a systemically potentiated neuroendocrine stress axis: A multilevel experiment in Parus major

Abstract

Hormonal pleiotropy-the simultaneous influence of a single hormone on multiple traits-has been hypothesized as an important mechanism underlying personality, and circulating glucocorticoids are central to this idea. A major gap in our understanding is the neural basis for this link. Here we examine the stability and structure of behavioral, endocrine and neuroendocrine traits in a population of songbirds (Parus major). Upon identifying stable and covarying behavioral and endocrine traits, we test the hypothesis that risk-averse personalities exhibit a neuroendocrine stress axis that is systemically potentiated-characterized by stronger glucocorticoid reactivity and weaker negative feedback. We show high among-individual variation and covariation (i.e. personality) in risk-taking behaviors and demonstrate that four aspects of glucocorticoid physiology (baseline, stress response, negative feedback strength and adrenal sensitivity) are also repeatable and covary. Further, we establish that high expression of mineralocorticoid and low expression of glucocorticoid receptor in the brain are linked with systemically elevated plasma glucocorticoid levels and more risk-averse personalities. Our findings support the hypothesis that steroid hormones can exert pleiotropic effects that organize behavioral phenotypes and provide novel evidence that neuroendocrine factors robustly explain a large fraction of endocrine and personality variation.

Keywords: ACTH; Behavioral syndromes; Corticosterone; Dexamethasone; Glucocorticoid receptor; HPA axis; Mineralocorticoid receptor; Negative feedback; Personality; Stress.

Fig. 1

Experimental timeline. Birds were tested on a risk-taking assay on three occasions (RTA_1–3) with 6-day intervals. Following a 9-day recovery period, they were sampled using a four component HPA assessment (A–D), once in August (HPA₁) and again in November (HPA₂) with a 52 day interval separating these two assessments. Following a 14-day recovery period, brains and trunk blood were harvested.

Fig. 2

Relationships among traits depicted in a path model. For each level of organization (neuroendocrine: MR and GR expression; endocrine: HPA₁ components; behavior: Initial and Startle Latencies), traits were reduced to the first principal component (PC1). For traits measured repeatedly per bird, agreement repeatabilities (R; subject as random factor) are indicated inside circular arrows. Estimates of covariance between traits within each category are indicated with bi-directional black arrows at the among- (Cov-A) and the within-individual levels (Cov-W). The phenotypic correlations (Pearson's r) for MR and GR across the two nuclei are indicated with bi-directional grey arrows. The path model yields beta coefficients (β) describing the direction and magnitude of effect of independent variables (GR, MR, HPA) on dependent variables (HPA, risk-taking). Error estimates for dependent variables in the path model are indicated in grey ellipses. The model indicates that higher MR expression in the hippocampus and hypothalamus and lower GR expression in these two brain areas predicts a more potentiated HPA axis (higher CORT) and more risk-averse personalities (higher latencies). Inset: the reduced model has two dropped paths. * denotes statistical significance (p < 0.05) for repeatability (R), covariance (Cov) and correlation (r) estimates.

Fig. 3

Graphical representations of the among-individual correlations for the three behavioral traits (a,b) and four HPA components (c,d). All values are log₁₀-transformed and plotted as standardized (z) scores and best fit lines are linear regressions. Plots show the correlation between the average (per bird) values of the three behavioral trails (a,b) and two HPA assessments (c,d). A statistically significant positive correlation in (a) is graphical evidence of among-individual correlation (i.e. syndrome) between Initial Latency and Startle Latency (i.e. consistently neophilic birds are also consistently more risk-taking). The other trait pairs (b–d) were not statistically significant but positive trends here suggest the possibility of among-individual correlations.