I feel BEDDA – A Vocal Biomarker for Subclinical Depression
Worldwide millions of people are suffering from depression. This trend is fueled by the ongoing COVID-19 pandemic. Due to the pandemic long-term negative effects on mental health including depression are expected. Given this high prevalence and steady influx of new cases, focusing on treating depression alone is not enough. Therefore, aims to improve the effectiveness and availability of treatment by using digital interventions (e.g., apps) need to be underpinned by efforts to improve prevention.
One main challenge of improving prevention is reaching vulnerable individuals. A promising approach to reaching vulnerable individuals is to determine when they are in times of need. To identify these times of need, measurements are indispensable. Different digital measurements – so called digital bio markers – have been investigated in related work. These markers have been used to diagnose a mental health problem or adjust treatment to the specific needs and symptoms of individuals. However, existing markers lack real-world practicality and have not yet been investigated thoroughly. Therefore, the aim of the project BEDDA (Breathing Exercise for the Detection of Symptoms of Depression and Anxiety) is to develop markers from data captured in real-world settings using the breathing exercise Breeze.
To capture real-time breathing data and voice data for the development of the markers, the slow-paced breathing exercises app Breeze (https://www.c4dhi.org/projects/breeze/) – also developed at our center – will be used. Slow paced breathing exercises such as Breeze have been shown to be effective in reducing symptoms of depression and anxiety. Breeze is not presented as a stand-alone tool but is incorporated in an intervention using the MobileCoach (https://www.mobile-coach.eu/) platform.
Breeze and a chatbot developed using the Mobile Coach platform will be used to gather data on breathing patterns and deliver supportive interventions. BEDDA tells the story of two people (the user and the chatbot) that go on a journey to find a treasure buried by the uncle of the chatbot. Along the way they receive advice (i.e., intervention components) that may help them to reduce symptoms of depression such as sadness, loss of interest or pleasure, and loss of energy. The breathing sounds and voice commands recorded in Breeze from individuals interacting with the app will be used to investigate and measure underlying changes of depression. The aim of using these recordings is to develop markers that can ultimately be used to tailor the breathing exercise to the participant. With this tailoring we aim to contribute to improving the prevention of depression.
Teepe, G., Da Fonseca, A., Kleim, B., Jacobson, N.C., Salamanca-Sanabria, A., Tudor Car, L., Fleisch, E., Kowatsch, T., Just-in-time Adaptive Mechanisms of Popular Mobile Applications for Individuals with Depression: Systematic Review, Journal of Medical Internet Research Preprints, 06/04/2021:29412, preprints.jmir.org/preprint/29412. [PDF]
Shih, C. H., Tomita, N., Lukic, Y. X., Reguera, Á. H., Fleisch, E., & Kowatsch, T. (2019) Breeze: Smartphone-based Acoustic Real-time Detection of Breathing Phases for a Gamified Biofeedback Breathing Training. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT), 3(4), 1-30. 10.1145/3369835
Shih, I., Nißen, M.K., Büchter, D., Durrer, D., l’Allemand, D., Fleisch, E., Kowatsch, T. (2018) Smartphone-based Biofeedback Breathing Training for Stress Management, Poster presented at the Applied Maschine Learning Days, EPFL, Lausanne, Switzerland. (PDF)
Shih, I., Kowatsch, T., Tinschert, P., Barata, F., Nißen, M.K., Towards The Design of a Smartphone-Based Biofeedback Breathing Training: Identifying Diaphragmatic Breathing Patterns from a Smartphone’s Microphone, Proc. of the 10th Mediterranean Conference on Information Systems (MCIS), Paphos, Cyprus. (PDF)
Nahum-Shani I, Hekler EB, Spruijt-Metz D. (2015) Building health behavior models to guide the development of just-in-time adaptive interventions: A pragmatic framework. Health Psychol.
Nahum-Shani I, Smith SN, Spring BJ, Collins LM, Witkiewitz K, Tewari A, et al. (2018) Just-in-Time Adaptive Interventions (JITAIs) in Mobile Health: Key Components and Design Principles for Ongoing Health Behavior Support. Ann Behav Med.
Cornet VP, Holden RJ. (2018) Systematic review of smartphone-based passive sensing for health and wellbeing. J Biomed Inform.
Low DM, Bentley KH, Ghosh SS. (2020) Automated assessment of psychiatric disorders using speech: A systematic review. Laryngoscope Investigative Otolaryngology. 2020
VIDEO OF BREEZE – Version 4: Revision of the graphics and airflow detection, November 2020