Multimodal classification of anxiety based on physiological signals

• Published in: Applied sciences Vol. 13(11); no. 11; pp. 1 - 21
• Main Authors: Vaz, Mariana, Summavielle, Teresa, Sebastião, Raquel, Ribeiro, Rita P.
• Format: Journal Article
• Language: English
• Published: Basel MDPI 23.05.2023; MDPI AG
• Subjects: Accuracy; Algorithms; Analysis; Anxiety; Anxiety disorders; Autonomic nervous system; Biofeedback; Blood pressure; Classification; Computer & video games; Data processing; Datasets; Discriminant analysis; EKG; Electrocardiogram; Electrocardiography; Electromyography; Feature selection; Instrument industry; Machine learning; Medical research; Medicine, Experimental; Mental depression; Mental disorders; Mental health; Multimodal dataset; Nervous system; Physiological aspects; Physiological signals; Physiology; R&D; Research & development; Respiration; Signal processing; Stress; Support vector machines; Virtual reality; Wearable sensors; United States; Portugal; Taiwan
• ISSN: 2076-3417; 2076-3417
• DOI: 10.3390/app13116368

Multiple studies show an association between anxiety disorders and dysregulation in the Autonomic Nervous System (ANS). Thus, understanding how informative the physiological signals are would contribute to effectively detecting anxiety. This study targets the classification of anxiety as an imbalanced binary classification problem using physiological signals collected from a sample of healthy subjects under a neutral condition. For this purpose, the Electrocardiogram (ECG), Electrodermal Activity (EDA), and Electromyogram (EMG) signals from the WESAD publicly available dataset were used. The neutral condition was collected for around 20 min on 15 participants, and anxiety scores were assessed through the shortened 6-item STAI. To achieve the described goal, the subsequent steps were followed: signal pre-processing; feature extraction, analysis, and selection; and classification of anxiety. The findings of this study allowed us to classify anxiety with discriminatory class features based on physiological signals. Moreover, feature selection revealed that ECG features play a relevant role in anxiety classification. Supervised feature selection and data balancing techniques, especially Borderline SMOTE 2, increased the performance of most classifiers. In particular, the combination of feature selection and Borderline SMOTE 2 achieved the best ROC-AUC with the Random Forest classifier.