Dynamic Tracking of State Anxiety via Multi-Modal Data and Machine Learning.

Xiaochen Zhang,Zhi Yang,Jingjing Liu,Yue Ding

doi:10.3389/fpsyt.2022.757961

Xiaochen Zhang, Zhi Yang + Show 2 more

Open Access

https://doi.org/10.3389/fpsyt.2022.757961

Copy DOI

Abstract

Anxiety induction is widely used in the investigations of the mechanism and treatment of state anxiety. State anxiety is accompanied by immediate psychological and physiological responses. However, the existing state anxiety measurement, such as the commonly used state anxiety subscale of the State-Trait Anxiety Inventory, mainly relies on questionnaires with low temporal resolution. This study aims to develop a tracking model of state anxiety with high temporal resolution. To capture the dynamic changes of state anxiety levels, we induced the participants' state anxiety through exposure to aversive pictures or the risk of electric shocks and simultaneously recorded multi-modal data, including dimensional emotion ratings, electrocardiogram, and galvanic skin response. Using the paired self-reported state anxiety levels and multi-modal measures, we trained and validated machine learning models to predict state anxiety based on psychological and physiological features extracted from the multi-modal data. The prediction model achieved a high correlation between the predicted and self-reported state anxiety levels. This quantitative model provides fine-grained and sensitive measures of state anxiety levels for future affective brain-computer interaction and anxiety modulation studies.

Highlights

Anxiety is a mental state of elevated apprehension, arousal, and vigilance usually elicited by the anticipation of threat [1, 2]
We examined whether state anxiety levels can be quantitatively and dynamically evaluated using multi-modal measures
Even for the participants with non-significant changes, the diverse State-Trait Anxiety Inventory (STAI)-S scores throughout the experiment could still be used to explore the relationship between state anxiety level and physiological and psychological features

Summary

Introduction

Anxiety is a mental state of elevated apprehension, arousal, and vigilance usually elicited by the anticipation of threat [1, 2]. Anxiety disorder ranks among the most prevalent mental illnesses overall the world [5]. A better understanding of the neural mechanism and biomarker of anxiety may benefit the large anxious population [6]. One can reproduce concrete transitory anxious states under controlled conditions [9] by using particular situations or stimuli [10–12]. Paradigms, such as exposure to disturbing pictures [13, 14] or anticipatory threats [e.g., electric shock; [15]], and experimental situations of failure [12] have been commonly used to induce anxiety. Regardless of the paradigms, a convenient, timely, and objective marker to indicate state anxiety changes is essential

Objectives

Methods

Results

Conclusion