Smoking remains the leading cause of preventable mortality and mobility in the world. To assist smoking cessation and promote healthcare for this vulnerable smoking population at low cost and in large scale, a mobile-health solution comprising wearable sensors and mobile phones is more and more widely adopted by researchers. Nonetheless, data especially smoking-related physiological signals collected from such system have not been fully exploited yet. This work has investigated into smokers' profile of electrocardiogram signal measured by a wearable chest patch sensor while they were smoking in real life settings. We implement a time-series clustering technique to model heart rate profile before and during/after smoking events occurred. Statistical analysis on 27 subjects has shown a clear increase of heart rate after smoking, which confirms with findings from other laboratory studies in the literature. And a 15-minute window before and after naturalistic smoking is most suitable to observe such significant changes. Furthermore, using time series distance calculated by dynamic time warping algorithm, we could cluster the heart rate profiles within this period into a few groups, to which we refer as smoking pattern templates. Smoking pattern templates has the potential to be used in automatic detection of smoking events within smoking dishabituation programs and provide new insights into craving, emotion and relapse.
[1]
Mustafa al'Absi,et al.
Opportunities and Challenges in Designing Participant-Centric Smoking Cessation System
,
2017,
2017 IEEE 41st Annual Computer Software and Applications Conference (COMPSAC).
[2]
Elena Smets,et al.
Large-scale wearable data reveal digital phenotypes for daily-life stress detection
,
2018,
npj Digital Medicine.
[3]
Willis J. Tompkins,et al.
A Real-Time QRS Detection Algorithm
,
1985,
IEEE Transactions on Biomedical Engineering.
[4]
B. Lushniak,et al.
The Health consequences of smoking—50 years of progress : a report of the Surgeon General
,
2014
.
[5]
Stan Salvador,et al.
FastDTW: Toward Accurate Dynamic Time Warping in Linear Time and Space
,
2004
.
[6]
Chris Van Hoof,et al.
Ambulatory Smoking Habits Investigation based on Physiology and Context (ASSIST) using wearable sensors and mobile phones: protocol for an observational study
,
2019,
BMJ Open.
[7]
B. Carter,et al.
Meta-analysis of cue-reactivity in addiction research.
,
1999,
Addiction.
[8]
C. Agué,et al.
Cardiovascular variables, skin conductance and time estimation: Changes after the administration of small doses of nicotine
,
1974,
Psychopharmacologia.