Abstract
Major depressive disorder (MDD) is a common psychiatric disorder and the leading cause of disability worldwide. However, current methods used to diagnose depression mainly rely on clinical interviews and self-reported scales of depressive symptoms, which lack objectivity and efficiency. To address this challenge, we present a machine learning approach to screen for MDD using electrodermal activity (EDA). Participants included 30 patients with MDD and 37 healthy controls. Their EDA was measured during five experimental phases consisted of baseline, mental arithmetic task, recovery from the stress task, relaxation task, and recovery from the relaxation task, which elicited multiple alterations in autonomic activity. Selected EDA features were extracted from each phase, and differential EDA features between two distinct phases were evaluated. By using these features as input data and performing feature selection with SVM-RFE, 74% accuracy, 74% sensitivity, and 71% specificity could be achieved by our decision tree classifier. The most relevant features selected by SVM-RFE included differential EDA features and features from the stress and relaxation tasks. These findings suggest that automatic detection of depression based on EDA features is feasible and that monitoring changes in physiological signal when a subject is experiencing autonomic arousal and recovery may enhance discrimination power.
Highlights
Major depressive disorder (MDD) is one of the most common psychiatric disorders, affecting more than 300 million people worldwide
Through proof-of-principle experiments, that electrodermal activity (EDA) features can be used as a biomarker for MDD
Patients with MDD and healthy control participants were classified with 74% accuracy using a decision tree algorithm
Summary
Major depressive disorder (MDD) is one of the most common psychiatric disorders, affecting more than 300 million people worldwide. The DSM provides clear descriptions of symptoms and MDD diagnostic guidelines, diagnoses are often limited as they rely on patients’ subjective symptom reports, derived from clinical interviews and self-report questionnaires As such, these do not provide an assessment of depression-related physiology or allow for an objective diagnosis[6]. EDA among MDD participants was found to be distinguishable from those with other psychopathologies, such as generalized anxiety disorder (GAD) or panic disorder (PD), as individuals with GAD and PD tended to exhibit autonomic hyper-activation[13,14] These results suggest that autonomic activity, as represented by various physiological signals, serves as a quantitative marker of depression. Ongoing work has focused on further developing data-driven strategies for the diagnosis of psychopathologies due to the recent success of machine learning in various medical and healthcare fields[18]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have