Depressed Patients Identification using Cardiovascular Signals

Mohammad Sami Zitouni and Ahsan Khandoker
Khalifa University


Persistent feeling sadness and worthlessness, loss of interest in outside stimuli, increased fatigue, and suicidal thoughts are characteristics of the mental illness known as Major Depressive disorder (MDD). MDD is associated with the risk of comorbidities, such as cardiovascular disease, as it can be a risk factor for its pathogenesis, where the two conditions are known to have similar causative factors including inflammation and oxidative stress. The clinical diagnosis of MDD is mainly based on self reported experiances and mental status examination through psychiatric interview questionnaires, besides ruling out physical conditions with similar symptoms. Therefore, an automated artificial intelligence based tool can play a crucial role in assisting the diagnosis of MDD, as well as continuous monitoring of mental health and the development of MDD through wearables, to avoid severe cases associated with significant self neglect and risk of harm to self or others. Additionally, it allows early proper intervention. In this study, we present a deep learning based framework for MDD patients identification from cardiovascular signals. In this work, multi-modal cardiovascular signals, including electrocardiogram (ECG) and finger photoplethysmography (PPG), are used. The signals were collected from 40 subjects for 10 minutes, out of whom 22 are diagnosed with MDD, and 20 are healthy. The singles are pre-processed and segmented into 30 seconds segments, allowing the identification in half a minute window, which is proven to be sufficient in this work. Then, time-frequency analysis is performed on the signals for feature extraction and an architecture based on Long Short-Term Memory (LSTM) networks is utilized for the identification of the MDD patients. Preliminary results demonstrated promising performance. This study can be considered an advancement towards the involvement of artificial intelligence tools in the assisted diagnosis and monitoring of mental diseases, and reducing their risk and impact on human daily life.