STDD: Short-Term Depression Detection with Passive Sensing

Abstract

It has recently been reported that identifying the depression severity of a person requires involvement of mental health professionals who use traditional methods like interviews and self-reports, which results in spending time and money. In this work we made solid contributions on short-term depression detection using every-day mobile devices. To improve the accuracy of depression detection, we extracted five factors influencing depression (symptom clusters) from the DSM-5 (Diagnostic and Statistical Manual of Mental Disorders), namely, physical activity, mood, social activity, sleep, and food intake and extracted features related to each symptom cluster from mobile devices’ sensors. We conducted an experiment, where we recruited 20 participants from four different depression groups based on PHQ-9 (the Patient Health Questionnaire-9, the 9-item depression module from the full PHQ), which are normal, mildly depressed, moderately depressed, and severely depressed and built a machine learning model for automatic classification of depression category in a short period of time. To achieve the aim of short-term depression classification, we developed Short-Term Depression Detector (STDD), a framework that consisted of a smartphone and a wearable device that constantly reported the metrics (sensor data and self-reports) to perform depression group classification. The result of this pilot study revealed high correlations between participants` Ecological Momentary Assessment (EMA) self-reports and passive sensing (sensor data) in physical activity, mood, and sleep levels; STDD demonstrated the feasibility of group classification with an accuracy of 96.00% (standard deviation (SD) = 2.76).

Smart Devices and Wearable Technologies to Detect and Monitor Mental Health Conditions and Stress: A Systematic Review

“…The search term “depression” identified five studies [ 5 , 15 , 21 , 29 , 30 ] which assessed only depression, and one study [ 24 ] which assessed “mental health” broadly. EEG is a non-obtrusive, electrophysiological measure of the spontaneous electrical activity in the brain and is widely used to study antidepressant treatment responses due to its availability and low cost [ 54 ].…”

“…In another study assessing physical activity, Narziev et al (2020) selected five depression symptom factors which were extracted from the DSM-5 questionnaire, with mood, physical activity, sleep, social activity, and food intake (to ascertain appetite information) and monitored to detect depression using the developed “Short-Term Depression Detector” (STDD) framework, which used smart watch (Galaxy S3) sensors and Android smartphone [ 21 ]. Mood was determined by a combination of the above factors using machine learning.…”

“…EDA was considered a useful metric for detecting stress, reported by one author to be the preferred wearable due to simplicity and setup [ 19 ]; however, another author expressed some unreliability in results from EDA measurement through wearable devices due to motion artefact [ 52 ]. Detection of depression using wearable devices is an ongoing challenge, with wearable EEG [ 5 , 15 ] and accelerometers [ 21 , 29 ] currently used for detection, with the prior capable of detecting depression alone, whilst physical activity in a machine learning model can accurately detect depression. Further research into combining an accelerometer and EEG into one wearable device may yield promising results for depression diagnosis, though currently smartphone incorporation is heavily present within the literature for detection using subjective questionnaires and self-reporting [ 57 ].…”

Assessing the Mental Health of Emerging Adults Through a Mental Health App: Protocol for a Prospective Pilot Study

“…Many studies have yet to examine data that support these theoretical advantages. Indeed, holistic and personalized approaches are a recent, emerging topic in the field of psychology; researchers have used machine learning and network analysis techniques for analyzing intensive, self-reported assessment and wearable data, to examine symptom clusters for depression [56]. Furthermore, this approach may help with informing mental health interventions and health care providers' clinical recommendations.…”

Using artificial intelligence and longitudinal location data to differentiate persons who develop posttraumatic stress disorder following childhood trauma

“…At this juncture, one new question deals with the legitimacy of further application and whether or not the recently found significance of passive location data may be utilized within a practical, predictive paradigm for diagnostic benefit. Although it sacrifices interpretability for practicality, machine learning approaches have proven to be frequent and successful tools for benchmarking the predictive efficacy of proposed biomarkers within the mental health research space including those derived from passive sensing data 15 – 17 , 20 – 22 , 26 , 27 , 33 , 55 , 56 .…”