Adolescent female rats recovered from the activity-based anorexia display blunted hedonic responding

Abstract

Objective: As patients with anorexia nervosa tend to "like" palatable tastants less than controls, we set out to model this preclinically by using the taste reactivity test (TRT) to assess hedonic state in rats following weight restoration from a bout of activity-based anorexia (ABA).

Method: Female rats (n = 31) were surgically implanted with an intraoral catheter, which allowed experimenters to assess baseline TRT to six tastants. Following baseline TRT, animals were either exposed to the activity-based anorexia condition (ABA; 1.5HR chow/ad lib wheel until 25% weight loss), kept sedentary (SED; ad lib chow/locked wheel), given access to running wheels with ad lib chow access (RW; ad lib chow/wheel), or were body weight matched to the ABA group (BWM; restricted chow/locked wheel). Following 25% weight loss, wheels were locked and food returned to ABA rats. Paired RW groups had their wheels locked and paired BWM rats were given ad lib access to food. Animals were given 10 days to recover prior to a second TRT. Videos were analyzed for liking (tongue protrusions) and disliking (gape) behaviors.

Results: The ABA group displayed a significant within-subject reduction in cumulative lick responses to water and 1 M sucrose. Additionally, we found the SED and ABA group displayed a significant within-subject reduction in cumulative lick responses to .1 M sucrose. Positive hedonic responses did not decline in either the BWM or the RW groups.

Discussion: The data show a novel phenomenon that a history of ABA results in an anhedonia phenotype that mirrors aspects of AN.

Significance statement: Patients recovered from anorexia nervosa report anhedonia, or the lack of pleasure in consuming palatable foods. Unfortunately, the biological mechanism underpinning anhedonia in anorexia nervosa is not well understood. The current study assessed hedonic state in adolescent female rats prior to and 10 days recovered following the activity-based anorexia paradigm. Age-matched, running wheel-matched and body weight-matched control groups were also tested at the same time points.

Keywords: animal models; anorexia nervosa; eating disorders; hedonics; machine learning.

FIGURE 1

Adolescent female rats were offered time‐limited feeding (1.5 HR/day) with ad lib access to a running wheel produces behaviors that mirror symptoms of anorexia nervosa. (a) Experimental design of novel taste reactivity test + activity‐based anorexia paradigm. (b) 24‐hour food intake measurements throughout the duration of the study. ABA animals have significantly lower food intake compared with the SED or RW group while the animals are actively on the paradigm. (c) Daily body weight measurements in sedentary controls (SED), running wheel controls (RW) and activity‐based anorexia (ABA) throughout the duration of the experiment. ABA animals lost a significant amount of body weight compared with SED and RW groups during the ABA paradigm. (d) Cumulative 24‐hour wheel revolutions in the ABA and RW group over the duration of the study. Wheel running was significantly increased in the ABA animals during time‐limited feeding + ad lib wheel. Data are presented ± SEM, *p < .05 post hoc (Tukey) ABA versus SED or RW; #p < .05 post hoc (Tukey) ABA versus SED. ABA, activity‐based anorexia; RW, wheel habituation; S, surgery; TR, taste reactivity

FIGURE 2

Taste reactivity data. (a) Representative images of frame‐by‐frame orofacial “liking” (top) and “disliking” (bottom) responses. (b) When comparing cumulative lick responses to water via paired t‐test for each group (b1‐4), we found only the ABA group showed a significant reduction in responding (b4). This was not observed in the SED (b1), RW (b2), or BWM (b3) groups. When comparing the percent change in lick behavior from group baseline (b5), we found no significant differences between the groups when analyzed by one‐way ANOVA. (c) When comparing cumulative lick responses to .01 M sucrose via paired t‐test (c1‐4), we found none of the groups demonstrated a significant change. When comparing the percent change in lick behavior from group baseline (c5) we found no significant differences between the groups when analyzed by one‐way ANOVA. (d) Paired t‐test results comparing pre and post cumulative lick responses to .1 M sucrose show the SED (d1) and ABA (d4) groups show a significant reduction in responding. This within‐subject difference was not observed in the RW (d2) or the BWM (d3) groups. When comparing the percent change in lick behavior from group baseline (d5) we found no significant differences between the groups when analyzed by one‐way ANOVA. (e) Paired t‐test results comparing pre and post cumulative lick responses to 1.0 M sucrose show the ABA (e4) animals are the only group with a significant reduction. This within‐subject reduction in lick responding was not observed in the SED (e1), RW (e2), or BWM (e3) groups. When comparing the percent change in lick behavior from group baseline (e5), we found a significant post hoc difference such that the ABA group showed a larger negative change in responding compared with the SED group. (f) Paired t‐test comparing cumulative gape behavior to .0003 M quinine at the pre and post timepoint in all four groups. There were no within‐subject differences in the SED (f1), RW (f2), BWM (f3), or ABA (f4) groups. When comparing the percent change in lick behavior from group baseline (f5) we found no significant differences between the groups when analyzed by one‐way ANOVA. (g) Paired t‐test comparing cumulative gape behavior to .003 M quinine at the pre and post timepoints in all four groups. We found a significant within‐subject reduction in gape behavior in the RW group (g2), but not in the SED (g1), BWM (g3), or ABA (g4) groups. When comparing the percent change in lick behavior from group baseline (g5), we found no significant differences between the groups when analyzed by one‐way ANOVA. (h) Regression analysis comparing DEG finalized labels versus labels provided by two raters that scored videos using a more conventional method. We found regression with an r‐squared value of .9038 for rater 1 (h1) and .9080 for rater 2 (h2). Data is presented as individual animals or mean ± SEM. *p < .05 paired t‐test or one‐way ANOVA post hoc Tukey comparison

FIGURE 3

Machine learning model performance identifying orofacial responding. In total, 360 videos labeled for orofacial behaviors were randomly divided into training and validating dataset. (Left) Accuracy and F1 score on validating dataset after 19 epochs (cycles) of training identifying background, lick, paw lick, gape, paw flail and wet dog shake. (Right) Table showing exact values of accuracy and F1 graphed in the left panel