Hunger and thirst: issues in measurement and prediction of eating and drinking

Abstract

Associations between hunger and eating and between thirst and drinking are generally weak. This stems, in part, from limitations in the measurement of these sensations which generally rely on temporal, motivational, metabolic and/or self-reported descriptive indices. Each is critically reviewed. Also problematic is the fact that the deterministic depletion-repletion concept of ingestive behavior fails to account for influences of a multitude of contravening cognitive, social, sensory and logistical factors. Although hunger and thirst serve some parallel purposes, sharp distinctions are also present with health implications. Of particular note are the observations that thirst ratings are higher and more stable over the day compared to hunger and thirst may be more motivating to drink than hunger is to eat. Coupling these observations with evidence that beverages have limited satiety value, they pose particular challenges and opportunities. Beverages can facilitate the delivery of nutrients to those desiring or requiring them, but also to those where they are not desired or required. The benefits and risks are a function of their use rather than their inherent properties.

Figure 1

Proportion of participants (N=53) self-reporting eating or drinking occurrences each hour of the day. Panel A= percent drinking on weekdays and weekend days; panel B=percent eating on weekdays and weekend days; panel C=percent drinking and eating on weekdays; panel D=percent drinking and eating on weekend days.

Figure 2

Mean energy content of food and volume of beverage consumed during each hour of the day. Panel A= volume (oz) of beverage consumed on weekdays and weekend days; panel B=energy (kcal) consumed on weekdays and weekend days; panel C= volume and energy consumed by drinking and eating on weekdays; panel D= volume and energy consumed by drinking and eating on weekend days.

Figure 3

Mean self-reported ratings of hunger (left panel) and thirst (right panel) over the 4 hour period prior to an eating (left panel) or drinking (right panel) occurrence with no ingestive events occurring during the 4 hour period before or the two hours after the ingestive event (solid bars). Hatched bars represent ratings when excluding only foods, but where some drinking occurred (right panel) or excluding beverages, but some eating occurred (right panel).

Figure 4

Mean and range of daily hunger and thirst ratings (between 09:00 and 21:00 h) for 50 individuals. Each bar represents the highest and lowest daily mean of 7 consecutive days. (reprinted from McKiernan et al., Physiol & Behav 2008;94:700-708).

Figure 5

Mean hunger (rising from the bottom x-axis) and fullness (dropping from the top x-axis) ratings from 34 healthy adults at baseline and weeks six and eight of an intervention involving fruit and vegetable consumption. Ratings were obtained on a 100mm VAS between the hours of 10:00 and 22:00.

Figure 6

Theoretical model of appetitive changes in a preload paradigm.

Figure 7

Least squares regression line fitted to a scatter plot of hunger ratings expressed as percent of scale, from a literature search of studies published between 1995 and 2005.

Figure 8

Least squares regression line fitted to hunger ratings expressed as percent of scale from a literature search of studies published between 1995 and 2005. Data are divided according to selected test conditions.

Figure 9

Least squares regression line fitted to a scatter plot of thirst ratings expressed as percent of scale, from a literature search of studies published between 1995 and 2005.

Figure 10

Slopes of the 5^th and 95^th percentiles of hunger data, plotted as a percent of scale, obtained from a literature search of studies published between 1995 and 2005.