A Preliminary Study on the Biased Attention and Interpretation in the Recognition of Face-Body Compound of the Individuals with Social Anxiety

Toward Robust Anxiety Biomarkers: A Machine Learning Approach in a Large-Scale Sample

BACKGROUND

The field of psychiatry has long sought biomarkers that can objectively diagnose patients, predict treatment response, or identify individuals at risk of illness onset. However, reliable psychiatric biomarkers have yet to emerge. The recent application of machine learning techniques to develop neuroimaging-based biomarkers has yielded promising preliminary results. However, much of the work in this domain has not met best practice standards from the field of machine learning. This is especially true for studies of anxiety, creating uncertainty about the potential for anxiety biomarker development.

METHODS

We applied machine learning tools to predict trait anxiety from neuroimaging measurements in humans. Using publicly available data from the Brain Genomics Superstruct Project, we compared a suite of neuroimaging-based machine learning models predicting anxiety within a discovery sample (n = 531, 307 women) via k-fold cross-validation, and we tested the final model (a stacked model incorporating region-to-region functional connectivity, amygdala seed-to-voxel connectivity, and volumetric and cortical thickness data) in a held-out, unseen test sample (n = 348, 209 women).

RESULTS

Though the best model was able to predict anxiety within the discovery sample (cross-validated R2 of .06, permutation test p < .001), the generalization test within the holdout sample failed (R2 of -.04, permutation test p > .05).

CONCLUSIONS

In this study, we did not find evidence of a generalizable anxiety biomarker. However, we encourage other researchers to investigate this topic, utilizing large samples and proper methodology, to clarify the potential of neuroimaging-based anxiety biomarkers.

A systematic review of visual avoidance of faces in socially anxious individuals: Influence of severity, type of social situation, and development

Although visual avoidance of faces is a hallmark feature of social anxiety disorder (SAD) on clinical and theoretical grounds, empirical support is equivocal. This review aims to clarify under which conditions socially anxious individuals display visual avoidance of faces. Through a systematic search in Web of Science and PubMed up to March 2019 we identified 61 publications that met the inclusion criteria. We discuss the influence of three factors on the extent to which socially anxious individuals avoid looking at faces: (a) severity of social anxiety symptoms (diagnosed SAD versus High Social Anxiety levels in community samples [HSA] or related characteristics [Shyness, Fear of Negative Evaluation]), (b) three types of social situation (computer facial-viewing tasks, speaking tasks, social interactions), and (c) development (age-group). Adults with SAD exhibit visual avoidance across all three types of social situations, whereas adults with HSA exhibit visual avoidance in speaking and interaction tasks but not in facial-viewing tasks. The relatively few studies with children and adolescents suggest that visual avoidance emerges during adolescence. The findings are discussed in the context of cognitive-behavioral and skills-deficit models. Suggestions for future research include the need for developmental studies and more fine-grained analyses of specific areas of the face.

Facial expressions and eye tracking in individuals with social anxiety disorder: a systematic review

Social anxiety disorder (SAD) is characterized by the fear of being judged negatively in social situations. Eye-tracking techniques have been prominent among the methods used in recent decades to investigate emotional processing in SAD. This study offers a systematic review of studies on eye-tracking patterns in individuals with SAD and controls in facial emotion recognition tasks. Thirteen articles were selected from the consulted databases. It was observed that the subjects with SAD exhibited hypervigilance-avoidance in response to emotions, primarily in the case of negative expressions. There was avoidance of conspicuous areas of the face, particularly the eyes, during observations of negative expressions. However, this hypervigilance did not occur if the stimulus was presented in virtual reality. An important limitation of these studies is that they use only static expressions, which can reduce the ecological validity of the results.

A Systematic Review of Experimental Paradigms for Exploring Biased Interpretation of Ambiguous Information with Emotional and Neutral Associations

Interpretation biases have been extensively explored in a range of populations, including patients with anxiety and depressive disorders where they have been argued to influence the onset and maintenance of such conditions. Other populations in which interpretation biases have been explored include patients with chronic pain, anorexia nervosa, and alcohol dependency among others, although this literature is more limited. In this research, stimuli with threatening/emotional and neutral meanings are presented, with participant responses indicative of ambiguity resolution. A large number of paradigms have been designed and implemented in the exploration of interpretation biases, some varying in minor features only. This article provides a review of experimental paradigms available for exploring interpretation biases, with the aim to stimulate and inform the design of future research exploring cognitive biases across a range of populations. A systematic search of the experimental literature was conducted in Medline, PsychINFO, Web of Science, CINAHL, and Cochrane Library databases. Search terms were information, stimuli, and ambiguous intersected with the terms interpretation and bias*. Forty-five paradigms were found, categorized into those using ambiguous words, ambiguous images, and ambiguous scenarios. The key features, strengths and limitations of the paradigms identified are discussed.

Can We Distinguish Emotions from Faces? Investigation of Implicit and Explicit Processes of Peak Facial Expressions

Most previous studies on facial expression recognition have focused on the moderate emotions; to date, few studies have been conducted to investigate the explicit and implicit processes of peak emotions. In the current study, we used transiently peak intense expression images of athletes at the winning or losing point in competition as materials, and investigated the diagnosability of peak facial expressions at both implicit and explicit levels. In Experiment 1, participants were instructed to evaluate isolated faces, isolated bodies, and the face-body compounds, and eye-tracking movement was recorded. The results revealed that the isolated body and face-body congruent images were better recognized than isolated face and face-body incongruent images, indicating that the emotional information conveyed by facial cues was ambiguous, and the body cues influenced facial emotion recognition. Furthermore, eye movement records showed that the participants displayed distinct gaze patterns for the congruent and incongruent compounds. In Experiment 2A, the subliminal affective priming task was used, with faces as primes and bodies as targets, to investigate the unconscious emotion perception of peak facial expressions. The results showed that winning face prime facilitated reaction to winning body target, whereas losing face prime inhibited reaction to winning body target, suggesting that peak facial expressions could be perceived at the implicit level. In general, the results indicate that peak facial expressions cannot be consciously recognized but can be perceived at the unconscious level. In Experiment 2B, revised subliminal affective priming task and a strict awareness test were used to examine the validity of unconscious perception of peak facial expressions found in Experiment 2A. Results of Experiment 2B showed that reaction time to both winning body targets and losing body targets was influenced by the invisibly peak facial expression primes, which indicated the unconscious perception of peak facial expressions.