An integrated system based on physiological signals for the assessment of affective states in patients with anxiety disorders

Anxiety disorders are psychiatric disorders characterized by a constant and abnormal anxiety that interferes with daily-life activities. Their high prevalence in the general population and the severe limitations they cause have drawn attention to the development of new and efficient strategies for their treatment. In this work we describe the INTREPID system which provides an innovative and intelligent solution for the monitoring of patients with anxiety disorders during therapeutic sessions. It recognizes an individual's affective state based on 5 pre-defined classes (relaxed, neutral, startled, apprehensive and very apprehensive), from physiological data collected via non-invasive technologies (blood volume pulse, heart rate, galvanic skin response and respiration). The system is validated using data obtained through an emotion elicitation experiment based on the International Affective Picture System. Four different classification algorithms are implemented (Artificial Neural Networks, Support Vector Machines, Random Forests and a Neuro-Fuzzy System). The overall classification accuracy achieved is 84.3%.