PosterPDF Available

Smartphone-based Biofeedback Breathing Training for Stress Management

Authors:
Chen-Hsuan Iris Shih at ETH Zurich
Chen-Hsuan Iris Shih
Marcia Nißen at ETH Zurich
Marcia Nißen
Dirk Büchter at Ostschweizer Kinderspital (KISPI)
Dirk Büchter
D. Durrer-Schutz at Independent Researcher
D. Durrer-Schutz
  • Independent Researcher
Show all 7 authorsHide
Download file PDF
Read file
Download citation

Abstract

Biofeedback-based Breathing Trainings (BBTs) shows significant effect on health (WAN10, DIL16). State-of-the-art BBTs require dedicated (high cost) hardware and health professionals which represent a significant barrier to their widespread adoption. While It has been shown that a smartphone microphone has the ability to record audio signals from exhalation in a quality of professional respiratory devices (LAR12), the ultimate goal of this project is to answer the research question: To which degree of accuracy can a mobile application detect respiratory acoustic patterns in quasi-real-time with a smartphone’s microphone, thus capable of triggering adequate biofeedback?
Content uploaded by Chen-Hsuan Iris Shih
Author content
All content in this area was uploaded by Chen-Hsuan Iris Shih on Dec 14, 2017
Content may be subject to copyright.
www.c4dhi.org
Iris Shih 1, Marcia Nißen1, Dirk Büchter 2, Dominique Durrer 3, Dagmar l’Allemand2,
Elgar Fleisch 1,4 & Tobias Kowatsch4
1 ETH Zurich, 2 Children’s Hospital of Eastern Switzerland St.Gallen, 3 Eurobesitas, Vevey & 4 University of St.Gallen
Smartphone-based Biofeedback Breathing
Training for Stress Management
1. Problem
Biofeedback-based Breathing Trainings (BBTs) shows
significant effect on health (WAN10, DIL16).
State-of-the-art BBTs require dedicated (high cost)
hardware and health professionals which represent a
significant barrier for their widespread adoption.
It has been shown that a smartphone microphone has the
ability to record audio signals from exhalation in a quality
of professional respiratory devices (LAR12).
2. Research Question
To which degree of accuracy can a mobile application
detect respiratory acoustic patterns in quasi real-time
with a smartphone’s microphone, thus capable of
triggering adequate biofeedback?
4. Method: Design & Learning
§A smartphone’s acoustic sensor can obtain useful
breathing signals which can be classified as
inhale/exhale and chest/abdominal breathing.
§Evidence-based biofeedback can be generated
based on the classification results.
§A positive effect of Smartphone-based Biofeedback
can be observed through a designed intervention.
References
Dillon,A. et al. (2016)Smartphone Applications Utilizing Biofeedback Can Aid StressReduction, Frontiers in Psychology 7:832
Larson et al. (2012)SpiroSmart:using amicrophone to measure lung function on amobile phone.In Proceedings of the 2012 ACM Conference on
Ubiquitous Computing (UbiComp'12) . ACM,New York, NY, USA, 280-289.
Kowatsch, Nißen,Shih et al. (2017)Text-based Healthcare Chatbots Supporting Patient and Health Professional Teams:Preliminary Results of a
Randomized Controlled Trial on Childhood Obesity,Persuasive Embodied Agents for Behavior Change (PEACH2017)Workshop, co-located with the
17th IVA 2017,Stockholm, Sweden.
Kowatsch, Volland, Shih et al. (2017)Design and Evaluation of aMobile Chat App for the Open Source Behavioral Health Intervention Platform
MobileCoach, In:Maedche A., vom Brocke J., Hevner A. (eds)Designing the Digital Transformation.DESRIST 2017.Lecture Notes in Computer
Science, vol 10243.Springer:Berlin;Germany, 485-489.
Shih, I., Kowatsch, T., Tinschert, P., Barata, F., Nißen, M.K., (2016)Towards The Design of aSmartphone-Based Biofeedback Breathing Training:
Identifying Diaphragmatic Breathing Patterns from aSmartphone’s Microphone,Proc.of the 10th Mediterranean Conference on Information
Systems (MCIS), Paphos,Cyprus.
Wang, S. et al. (2010). Effect of slow abdominal breathing combined with biofeedback on blood pressure and heart rate variability in prehypertension.
The Journal of Alternative and ComplementaryMedicine, 16(10):1039-45.
EPFL Lausanne | January 29 | 2018Applied Machine Learning Days
FundingPartner
Justificatory knowledge from physics and physiology
(diaphragmatic breathing) is applied as respiration is the
only autonomic function you have direct control over.
3. Research Framework
Chest
Breath
Abdominal
Breath
Biofeedback
Inhale Exhale
a. Data Collection: Feasibility Study + Lab Study (47 subjects)
b. Data Annotation: Human Perception + Respiratory Belt
c. Learning Algorithms: (0. Signal pre-processing)
à1. Feature Extraction: Energy / Spectrogram / MFCC
à2. Classification: RF / HMM / ANN / RNN
à3. Evaluation: Leave-One-Out / Confusion Matrix
d. Game-based Biofeedback Design: Game + Visual + Audio
Built-in
Microphone
Daily messages from a digital coach
Data Labeling Signal windowing
Feature Extraction
Acoustic Breathing Signals
Prediction Prediction & Raw Data
Machine Learning
Algorithm
Rule-based Coaching Syst em
Sensing
Support
http://p3.snf.ch/Project-159289
5. Expected Results
http://www.inpursuito fyoga.com/blog /20
15/3/11/chest-breath-vs-belly-breath
SBBT
ResearchGate has not been able to resolve any citations for this publication.
Text-based Healthcare Chatbots Supporting Patient and Health Professional Teams: Preliminary Results of a Randomized Controlled Trial on Childhood Obesity
Conference Paper
Full-text available
  • Aug 2017
Health professionals have limited resources and are not able to personally monitor and support patients in their everyday life. Against this background and due to the increasing number of self-service channels and digital health interventions, we investigate how text-based healthcare chatbots (THCB) can be designed to effectively support patients and health professionals in therapeutic settings beyond on-site consultations. We present an open source THCB system and how the THCP was designed for a childhood obesity intervention. Preliminary results with 15 patients indicate promising results with respect to intervention adherence (ca. 13.000 conversational turns over the course of 4 months or ca. 8 per day and patient), scalability of the THCB approach (ca. 99.5% of all conversational turns were THCB-driven) and over-average scores on perceived enjoyment and attachment bond between patient and THCB. Future work is discussed.
View
Towards The Design of a Smartphone-Based Biofeedback Breathing Training: Identifying Diaphragmatic Breathing Patterns from a Smartphone’s Microphone
Conference Paper
Full-text available
  • Sep 2016
Asthma, diabetes, hypertension, or major depression are non-communicable diseases (NCDs) and impose a major burden on global health. Stress is linked to both the causes and consequences of NCDs and it has been shown that biofeedback-based breathing trainings (BBTs) are effective in coping with stress. Here, diaphragmatic breathing, i.e. deep abdominal breathing, belongs to the most distinguished breathing techniques. However, high costs and low scalability of state-of-the-art BBTs that require expensive medical hardware and health professionals, represent a significant barrier for their widespread adoption. Health information technology has the potential to address this important practical problem. Particularly, it has been shown that a smartphone microphone has the ability to record audio signals from exhalation in a quality that can be compared to professional respiratory devices. As this finding is highly relevant for low-cost and scalable smartphone-based BBTs (SBBT) and – to the best of our knowledge-because it has not been investigated so far, we aim to design and evaluate the efficacy of such a SBBT. As a very first step, we apply design-science research and investigate in this research-in-progress the relationship of diaphragmatic breathing and its acoustic components by just using a smartphone's microphone. For that purpose, we review related work and develop our hypotheses based on justificatory knowledge from physiology, physics and acoustics. We finally describe a laboratory study that is used to test our hypotheses. We conclude with a brief outlook on future work.
View
Smartphone Applications Utilizing Biofeedback Can Aid Stress Reduction
Article
Full-text available
  • Jun 2016
Introduction: Stress is one of the leading global causes of disease and premature mortality. Despite this, interventions aimed at reducing stress have low adherence rates. The proliferation of mobile phone devices along with gaming-style applications allows for a unique opportunity to broaden the reach and appeal of stress-reduction interventions in modern society. We assessed the effectiveness of two smartphone applications games combined with biofeedback in reducing stress. Methods: We compared a control game to gaming-style smartphone applications combined with a skin conductance biofeedback device (the Pip). Fifty participants aged between 18 and 35 completed the Trier Social Stress Test. They were then randomly assigned to the intervention (biofeedback game) or control group (a non-biofeedback game) for thirty minutes. Perceived stress, heart rate and mood were measured before and after participants had played the games. Results: A mixed factorial ANOVA showed a significant interaction between time and game type in predicting perceived stress [F(1,48) = 14.19, p < 0.001]. Participants in the biofeedback intervention had significantly reduced stress compared to the control group. There was also a significant interaction between time and game in predicting heart rate [F(1,48) = 6.41, p < 0.05]. Participants in the biofeedback intervention showed significant reductions in heart rate compared to the control group. Discussion: This illustrates the potential for gaming-style smartphone applications combined with biofeedback as stress reduction interventions.
View
Effect of Slow Abdominal Breathing Combined with Biofeedback on Blood Pressure and Heart Rate Variability in Prehypertension
Article
  • Oct 2010
  • J ALTERN COMPLEM MED
Prehypertension is a new category designated by the Seventh Report of the Joint National Committee on Prevention, Detection, Evaluation, and Treatment of High Blood Pressure (JNC7) in 2003. Managing prehypertension with nonpharmacological intervention is possibly beneficial to the prevention of hypertension. In this study, we observed the effect of slow abdominal breathing combined with electromyographic (EMG) biofeedback training on blood pressure (BP) in prehypertensives and assessed the changes of heart rate variability (HRV) in order to find an optional intervention to prevent hypertension and acquire some experimental data to clarify the underlying neural mechanism. Twenty-two (22) postmenopausal women with prehypertension were randomly assigned to either the experiment group or the control group. The experiment group performed 10 sessions of slow abdominal breathing (six cycles/min) combined with frontal electromyographic (EMG) biofeedback training and daily home practice, while the control group only performed slow abdominal breathing and daily home practice. BP and HRV (including R-R interval and standard deviation of the normal-normal intervals [SDNN]) were measured. Participants with prehypertension could lower their systolic blood pressure (SBP) 8.4 mm Hg (p < 0.001) and diastolic blood pressure (DBP) 3.9 mm Hg (p < 0.05) using slow abdominal breathing combined with EMG biofeedback. The slow abdominal breathing also significantly decreased the SBP 4.3 mm Hg (p < 0.05), while it had no effect on the DBP (p > 0.05). Repeated-measures analyses showed that the biofeedback group + abdominal respiratory group (AB+BF) training was more effective in lowering the BP than the slow breathing (p < 0.05). Compared with the control group, the R-R interval increased significantly during the training in the AB+BF group (p < 0.05). The SDNN increased remarkably in both groups during the training (p < 0.05). Slow abdominal breathing combined with EMG biofeedback is an effective intervention to manage prehypertension. The possible mechanism is that slow abdominal breathing combined with EMG biofeedback could reduce sympathetic activity and meanwhile could enhance vagal activity.
View
SpiroSmart: using a microphone to measure lung function on a mobile phone
  • Jan 2012
  • 280-289
  • Larson
Larson et al. (2012) SpiroSmart: using a microphone to measure lung function on a mobile phone. In Proceedings of the 2012 ACM Conference on Ubiquitous Computing (UbiComp '12). ACM, New York, NY, USA, 280-289.
Design and Evaluation of a Mobile Chat App for the Open Source Behavioral Health Intervention Platform MobileCoach
  • Jan 2017
  • Lect Notes Comput Sci
  • 485-489
  • Kowatsch
  • Volland
  • Shih
Kowatsch, Volland, Shih et al. (2017) Design and Evaluation of a Mobile Chat App for the Open Source Behavioral Health Intervention Platform MobileCoach, In: Maedche A., vom Brocke J., Hevner A. (eds) Designing the Digital Transformation. DESRIST 2017. Lecture Notes in Computer Science, vol 10243. Springer: Berlin; Germany, 485-489.