Telling truth from lie in individual subjects with fast event-related fMRI

Abstract

Deception is a clinically important behavior with poorly understood neurobiological correlates. Published functional MRI (fMRI) data on the brain activity during deception indicates that, on a multisubject group level, lie is distinguished from truth by increased prefrontal and parietal activity. These findings are theoretically important; however, their applied value will be determined by the accuracy of the discrimination between single deceptive and truthful responses in individual subjects. This study presents the first quantitative estimate of the accuracy of fMRI in conjunction with a formal forced-choice paradigm in detecting deception in individual subjects. We used a paradigm balancing the salience of the target cues to elicit deceptive and truthful responses and determined the accuracy of this model in the classification of single lie and truth events. The relative salience of the task cues affected the net activation associated with lie in the superior medial and inferolateral prefrontal cortices. Lie was discriminated from truth on a single-event level with an accuracy of 78%, while the predictive ability expressed as the area under the curve (AUC) of the receiver operator characteristic curve (ROC) was 85%. Our findings confirm that fMRI, in conjunction with a carefully controlled query procedure, could be used to detect deception in individual subjects. Salience of the task cues is a potential confounding factor in the fMRI pattern attributed to deception in forced choice deception paradigms.

Figure 1

Group analysis (n = 22) showing significant differences in brain activation between Lie, Truth, and Repeat Distracter conditions. Row 1: Truth > Repeat Distracter; row 2: Lie > Repeat Distracter; row 3: Lie > Truth (blue scale) Truth > Lie (red scale). Images are displayed over a Talairach‐normalized template in radiological convention. Significance thresholds for all contrasts based on spatial extent using a height of z ≥ 2.57 and cluster probability P ≤ 0.05, except Lie > Truth (blue scale) presented at a z ≥ 1.64, uncorrected. See Tables II, III, IV for anatomical localization.

Figure 2

Classification and regression trees (CART) plot, showing the first six nodes (up to three‐way interactions) for the peak and mean MRI signal (max and min). All 19 brain regions were included in the full tree applied to the single trials data.

Figure 3

GKT2 receiver operator characteristic curve (ROC) of the final logistic regression model for the group analysis corresponds to the logistic regression model that includes all terms from the CART model, up to three‐way interactions. The AUC (e.g., the accuracy of prediction) is 0.8467 (chance = 0.5).