Food catches the eye but not for everyone: a BMI-contingent attentional bias in rapid detection of nutriments

Abstract

An organism's survival depends crucially on its ability to detect and acquire nutriment. Attention circuits interact with cognitive and motivational systems to facilitate detection of salient sensory events in the environment. Here we show that the human attentional system is tuned to detect food targets among nonfood items. In two visual search experiments participants searched for discrepant food targets embedded in an array of nonfood distracters or vice versa. Detection times were faster when targets were food rather than nonfood items, and the detection advantage for food items showed a significant negative correlation with Body Mass Index (BMI). Also, eye tracking during searching within arrays of visually homogenous food and nonfood targets demonstrated that the BMI-contingent attentional bias was due to rapid capturing of the eyes by food items in individuals with low BMI. However, BMI was not associated with decision times after the discrepant food item was fixated. The results suggest that visual attention is biased towards foods, and that individual differences in energy consumption--as indexed by BMI--are associated with differential attentional effects related to foods. We speculate that such differences may constitute an important risk factor for gaining weight.

Figure 1. Illustration of the stimuli (a: Experiment 1; b: Experiment 2) and an overview of the experimental procedure (c).

In Experiment 1, in target-present trials, the participants searched for appetizing or bland food items embedded in an array of neutral nonfood items (cars) or vice versa; in target-absent trials, all the stimuli belonged to the same category. In Experiment 2, food and nonfood items were matched with respect to shape, colour, and global configuration. Each trial (c) began with a central fixation cross displayed randomly for 800–1200 ms, and was followed by a search array. The array was displayed until the participant responded whether or not it contained a discrepant item, and was followed by a blank screen displayed for 500 ms.

Figure 2. Means and standard errors of the response accuracy (a) and reaction times (b) on target-present trials, as a function of target type in Experiment 1.

The asterisk denotes a significant difference (p<.05).

Figure 3. Linear negative association between food detection bias in manual response latencies and Body Mass Index in Experiment 1 (a) and 2 (b).

The black line shows the least-square regression line.