Prediction of alcohol intake patterns with olfactory and gustatory brain connectivity networks

Abstract

Craving in alcohol drinkers is often triggered by chemosensory cues, such as taste and smell, which are linked to brain network connectivity. This study aimed to investigate whether these brain connectivity patterns could predict alcohol intake in young adults. Resting-state fMRI data were obtained from the Human Connectome Project (HCP) Young Adult cohort, comprising 1003 participants. Functional connectomes generated from 100 independent components were analyzed, identifying significant connections correlated with taste and odor scores after applying a false discovery rate (FDR) correction using the Benjamini-Hochberg (BH) method. These significant connections were then utilized as predictors in general linear models for various alcohol intake metrics. The models were validated in an independent sample to assess their accuracy. The training sample (n = 702) and the validation sample (n = 117) showed no significant demographic differences. Out of 742 possible connections, 41 related to odor and 25 related to taste passed the significance threshold (P < 0.05) after FDR-BH correction. Notable predictors included visual-visual connectivity (node32-node13: β = 0.028, P = 0.02) for wine consumption and connectivity between the ventral attention network (VAN) and the frontal parietal/caudate nucleus (FP/CN) (node27-node9: β = -0.31, P = 0.04) for total alcohol intake in the past-week and maximum number of drinks per day in the past-year. The predictive models demonstrated strong accuracy, with root mean square error (RMSE) values of 5.15 for odor-related models and 5.14 for taste-related models. The F1 scores were 0.74 for the odor model and 0.71 for the taste model, indicating reliable performance. These findings suggest that specific patterns of brain connectivity associated with taste and olfactory perception may serve as predictors of alcohol consumption behaviors in young adults. Our study highlight the need for longitudinal research to evaluate the potential of taste- and smell-related brain connectivity patterns for early screening and targeted interventions, as well as their role in personalized treatment strategies for individuals at risk of AUD.

Fig. 1. Analytical pipeline to validate brain networks for olfaction and gustation in predicting alcohol consumption.

The analytic pipeline was developed to delineate brain networks associated with olfaction and gustation on a global scale and to confirm the predictive validity of these networks concerning alcohol consumption measures. Here, ICA stands for independent component analysis, FDR BH refers to false discovery rate correction using the Bonferroni-Holm method, GLM denotes the general linear model, FTND is the Fagerström Test for Nicotine Dependence, and BMI represents body mass index.

Fig. 2. Correlation matrices of olfactory and gustatory networks reveal distinct connectivity patterns across brain regions.

The correlation matrices of the computed networks for olfaction (A) and taste (B) within the training sample (primary dataset) are presented. Here, SMN stands for somatomotor network; DAN/VAN for dorsal attention network/ventral attention network; Vis for visual network; CN for control network; and DMN for default mode network. The color bar indicates the correlation coefficient, and the IC numbers are denoted on the x- and y-axes.

Fig. 3. Associations between brain connectivity in olfaction and gustation networks and alcohol consumption metrics.

A general linear model (GLM) was used to analyze the associations between brain connectivity variables and responses to a 7-day retrospective questionnaire for each alcohol consumption metric within the training sample. These trained GLMs were then applied to the validation sample to determine the relationship between each alcohol metric and the identified brain connections within the olfaction and gustation networks. All connections within these networks, as well as significant correlations with the alcohol consumption metrics mentioned in the manuscript, are illustrated in figures (A, B) for odor and (C, D) for taste. In the figures, an upward arrow with a plus sign indicates a positive association, while a downward arrow with a plus sign indicates a negative association between brain connections and alcohol intake metrics. Here, SMN stands for somatomotor network; DAN/VAN for dorsal attention network/ventral attention network; Vis for visual network; CN for control network; FP for frontoparietal network; DMN for default mode network; and TP for temporoparietal network.

Fig. 4. Associations between alcohol intake and brain connections.

A Scatter plot showing the relationship between Total Wine Intake and Olfactory Network/Visual-Visual connection. A significant positive correlation is observed (R² = 0.15, P < 0.001), indicating a strong association between wine intake and this specific brain connection. B Scatter plot showing the relationship between Total Alcohol Intake and Gustatory Network/VA-FP/CN connection. The data shows a positive correlation (R² = 0.05, P < 0.001), suggesting a significant positive association between overall alcohol intake and this brain connection. C Scatter plot illustrating the relationship between Total Beer/Wine/Cooler Intake and Gustatory Network/DA-Visual connection. A moderate positive correlation is observed (R² = 0.30, P < 0.001), indicating a positive association between beer/wine/cooler intake and this brain connection. In all panels, the red line represents the best-fit regression line, and the shaded area around the line represents the 95% confidence interval. The actual values of the brain connections are plotted against the predicted values based on the alcohol intake measures.