Blubber cortisol: a potential tool for assessing stress response in free-ranging dolphins without effects due to sampling

Abstract

When paired with dart biopsying, quantifying cortisol in blubber tissue may provide an index of relative stress levels (i.e., activation of the hypothalamus-pituitary-adrenal axis) in free-ranging cetacean populations while minimizing the effects of the act of sampling. To validate this approach, cortisol was extracted from blubber samples collected from beach-stranded and bycaught short-beaked common dolphins using a modified blubber steroid isolation technique and measured via commercially available enzyme immunoassays. The measurements exhibited appropriate quality characteristics when analyzed via a bootstraped stepwise parallelism analysis (observed/expected = 1.03, 95%CI: 99.6 - 1.08) and showed no evidence of matrix interference with increasing sample size across typical biopsy tissue masses (75-150 mg; r(2) = 0.012, p = 0.78, slope = 0.022 ng(cortisol deviation)/ul(tissue extract added)). The relationships between blubber cortisol and eight potential cofactors namely, 1) fatality type (e.g., stranded or bycaught), 2) specimen condition (state of decomposition), 3) total body length, 4) sex, 5) sexual maturity state, 6) pregnancy status, 7) lactation state, and 8) adrenal mass, were assessed using a Bayesian generalized linear model averaging technique. Fatality type was the only factor correlated with blubber cortisol, and the magnitude of the effect size was substantial: beach-stranded individuals had on average 6.1-fold higher cortisol levels than those of bycaught individuals. Because of the difference in conditions surrounding these two fatality types, we interpret this relationship as evidence that blubber cortisol is indicative of stress response. We found no evidence of seasonal variation or a relationship between cortisol and the remaining cofactors.

Fig 1. Results from linearity assessment of cortisol enzyme immunoassay (EIA) with blubber tissue extracts.

Serial dilutions of extracts (open circles) show parallelism with the standards of the cortisol EIA (dark squares) (observed/expected = 1.01, 95%CI: 99.3–1.06); an indication that the assay is measuring the same antigens in the blubber as in the standards and therefore suitable for use with the short-beaked common dolphin blubber tissue extracts. Four individuals were represented in the pooled blubber extracts; 1 male and 3 female.

Fig 2. Results from matrix interference assessment.

A standard solution (final concentration 240pg/ml) was spiked with either phosphate-buffered saline or a set of serial dilutions of a pooled sample (“uL of sample added”) composed of blubber cortisol extracts from four individuals to make a final equivalent volume of 240ul. The concentration of cortisol contributed from the pooled sample (neat = ± 398.5pg/ml) was subtracted from each sample-spiked measurement so its contribution would be factored out of the assessment. Little to no evidence of matrix interference was observed (r² = 0.012, p = 0.78).

Fig 3. Blubber cortisol concentrations for bycaught (n = 40) and beach stranded (n = 23) D. delphis.

Horizontal box lines represent the lower quartile, median, and upper quartile values. Whiskers lines indicate range of concentrations. Points of inflection represent upper and lower bounds to the 95% confidence interval. Stranded individuals (24.3 ng/g) had on average 6.1 times more blubber cortisol than bycaught animals (3.99 ng/g).

Fig 4. Results of a seasonal analysis of blubber cortisol levels in stranded D. delphis.

The open circles represent cortisol concentrations for each individual. The observed three-month-running averages were calculated for each month (see text) and represented by the solid line. The dotted lines represent the 95% confidence envelope for the total seasonal randomness, i.e., the cortisol measurements were randomized relative to sampling date in 10,000 permuted datasets from which three-month-running averages were calculated. All observed three-month-running average values (represented by the solid line) are contained within the 95% confidence interval of the randomized null distributions indicating there was no evidence of seasonal fluctuations in blubber cortisol value.