puffMarker: a multi-sensor approach for pinpointing the timing of first lapse in smoking cessation

ABSTRACT

Recent researches have demonstrated the feasibility of detecting smoking from wearable sensors, but their performance on real-life smoking lapse detection is unknown. In this paper, we propose a new model and evaluate its performance on 61 newly abstinent smokers for detecting a first lapse. We use two wearable sensors --- breathing pattern from respiration and arm movements from 6-axis inertial sensors worn on wrists. In 10-fold cross-validation on 40 hours of training data from 6 daily smokers, our model achieves a recall rate of 96.9%, for a false positive rate of 1.1%. When our model is applied to 3 days of post-quit data from 32 lapsers, it correctly pinpoints the timing of first lapse in 28 participants. Only 2 false episodes are detected on 20 abstinent days of these participants. When tested on 84 abstinent days from 28 abstainers, the false episode per day is limited to 1/6.

References

1. Smoking-attributable mortality, years of potential life lost, and productivity losses - United States, 2000--2004. Morbidity and Mortality Weekly Report 57, 45 (2008), 1226--1228.
2. Ali, A., Hossain, S., Hovsepian, K., Rahman, M., Plarre, K., and Kumar, S. mPuff: Automated detection of cigarette smoking puffs from respiration measurements. In Proc. ACM IPSN (2012).
3. Ashton, H., Watson, D., Marsh, R., and Sadler, J. Puffing frequency and nicotine intake in cigarette smokers. The British Medical Journal (1970), 679--681.
4. Brendryen, H., Kraft, P., and Schaalma, H. Looking inside the black box: Using intervention mapping to describe the development of the automated smoking cessation intervention'happy ending'. The Journal of Smoking Cessation 5, 1 (2010), 29--56.
5. Doherty, K., Kinnunen, T., Militello, F., and Garvey, A. Urges to smoke during the first month of abstinence: relationship to relapse and predictors. Psychopharmacology 119, 2 (1995), 171--178.
6. Ertin, E., Stohs, N., Kumar, S., Raij, A., al'Absi, M., and Shah, S. Autosense: Unobtrusively wearable sensor suite for inferring the onset, causality, and consequences of stress in the field. In Proc. of ACM SenSys (2011), 274--287.
7. Hughes, J., and Hatsukami, D. Signs and symptoms of tobacco withdrawal. Archives of General Psychiatry 43, 3 (1986), 289--294.
8. Hymowitz, N., Sexton, M., Ockene, J., and Grandits, G. Baseline factors associated with smoking cessation and relapse. Preventive Medicine 20, 5 (1991), 590--601.
9. Kalman, D. The subjective effects of nicotine: methodological issues, a review of experimental studies, and recommendations for future research. Nicotine & Tobacco Research 4, 1 (2002), 25--70.
10. Killen, J., and Fortmann, S. Craving is associated with smoking relapse: Findings from three prospective studies. Experimental and Clinical Psychopharmacology 5, 2 (1997), 137--142.
11. Lopez-Meyer, P., Tiffany, S., and Sazonov, E. Identification of cigarette smoke inhalations from wearable sensor data using a support vector machine classifier. In Proc. IEEE EMBC (2012).
12. Marian, C., O'Connor, R. J., Djordjevic, M. V., Rees, V. W., Hatsukami, D. K., and Shields, P. G. Reconciling human smoking behavior and machine smoking patterns: implications for understanding smoking behavior and the impact on laboratory studies. Cancer Epidemiology Biomarkers & Prevention 18, 12 (2009), 3305--3320.
13. Matheny, K., and Weatherman, K. Predictors of smoking cessation and maintenance. Journal of Clinical Psychology 54, 2 (1998), 223--235.
14. Mokdad, A., Marks, J., Stroup, D., and Gerberding, J. Actual causes of death in the united states, 2000. The Journal of the Americal Medical Association 291, 10 (2004), 1238--1245.
15. Murphy, J. Technical analysis of the financial markets: A comprehensive guide to trading methods and applications. New York Institute of Finance, 1999.
16. Palmer, J., and Hiiemae, K. Eating and breathing: interactions between respiration and feeding on solid food. Dysphagia 18, 3 (2003), 169--178.
17. Parate, A., Chiu, M.-C., Chadowitz, C., Ganesan, D., and Kalogerakis, E. RisQ: Recognizing smoking gestures with inertial sensors on a wristband. In Proc. ACM MobiSys (2014).
18. Pedley, M. Tilt sensing using a three-axis accelerometer, 2014.
19. Rahman, M., Bari, R., Ali, A., Sharmin, M., Raij, A., Hovsepian, K., and et. al. Are we there yet?: Feasibility of continuous stress assessment via wireless physiological sensors. In Proc. of ACM BCB (2014), 479--488.
20. Scholl, P. M., Kücükyildiz, N., and Laerhoven, K. V. When do you light a fire?: Capturing tobacco use with situated, wearable sensors. In Proc. ACM UbiComp Workshop on Human Factors and Activity Recognition in Healthcare, Wellness, and Assistend Living (2013).
21. Shiffman, S. Reflections on smoking relapse research. Drug and Alcohol Review 25, 1 (2006), 15--20.
22. Shiffman, S., Paty, J., Gnys, M., Kassel, J., and Hickcox, M. First lapses to smoking: Within-subjects analysis of real-time reports. Journal of Consulting and Clinical Psychology 64, 2 (1996), 366--379.
23. Shiffman, S., Scharf, D., Shadel, W., Gwaltney, C., Dang, Q., Paton, S., and Clark, D. Analyzing milestones in smoking cessation: illustration in a nicotine patch trial in adult smokers. Journal of Consulting and Clinical Psychology 74, 2 (2006), 276--285.
24. Shiffman, S., and Waters, A. Negative affect and smoking lapses: A prospective analysis. Journal of Consulting and Clinical Psychology 72, 2 (2004), 192--201.
25. Spohr, S. A., Nandy, R., Gandhiraj, D., Vemulapalli, A., Anne, S., andWalters, S. T. Efficacy of sms text message interventions for smoking cessation: A meta-analysis. Journal of Substance Abuse Treatment (2015).
26. Stitzer, M., and Gross, J. Smoking relapse: the role of pharmacological and behavioral factors. Progress in Clinical and Biological Research 261 (1988), 163--184.
27. Swan, G., Ward, M., and Jack, L. Abstinence effects as predictors of 28-day relapse in smokers. Addictive Behaviors 21, 4 (1996), 481--490.
28. Tang, Q., Vidrine, D. J., Crowder, E., and Intille, S. S. Automated detection of puffing and smoking with wrist accelerometers. In Proc. Pervasive Health) (2014).
29. Wu, P., Hsieh, J., Cheng, J., Cheng, S., and Tseng, S. Human smoking event detection using visual interaction clues. In Proc. IEEE Int'l Conf. Pattern Recognition (2010).

Index Terms

• Human-centered computing

  • Human computer interaction (HCI)