Sense2Stop:Mobile Sensor Data to Knowledge

Sense2Stop Mobile Sensor Data to Knowledge: Preliminary Study of the Effects of Wearable Sensors and Smartphone Apps on Real Time Stress and Smoking in Recently Quit Smokers

University of Memphis, Georgia Institute of Technology, University of Minnesota, Ohio State University, University of Massachusetts, Amherst, University of Michigan, University of California, Los Angeles, University of California, San Diego, University of California, San Francisco, University of Utah

The aim of this research is to build systems that can recognize when people are stressed and then provide them with relaxation prompts in the moment to reduce their likelihood of being stressed, smoking, or overeating in the near future. Using these systems should help smokers be more effective in their attempts to quit by reducing their tendency to lapse when they are stressed or experiencing other negative moods or behaviors.

The purpose of this study is (1) to evaluate the feasibility of a just-in-time intervention to decrease stress in recently quit smokers; and (2) to examine whether a just-in-time adaptive intervention that decreases stress also reduces the near-term odds of a smoking lapse. The primary hypothesis of this study is that the administration of a prompt to perform a relaxation exercise as compared to no prompt will lead to a lower likelihood of being stressed in the subsequent two hours, and that this effect will be stronger when the prompt is administered when the individual is stressed. The secondary hypothesis is that stress episodes will predict the timing of smoking lapses. The third hypothesis is that administration of a prompt to perform a relaxation exercise will reduce the odds of smoking for the next two hours, and that this effect will be stronger when the prompt is administered when the individual is stressed. The fourth (exploratory) hypothesis is that stress will predict the timing of overeating episodes. These data will also be used for developing automated risk prediction of smoking relapse, and for developing decision rules for the timing of Just-In-Time-Adaptive Interventions (JITAIs).

Behavioral Counseling, Cigarette Smoking, Mobile Health, Heart Rate Variability Monitoring, Mindfulness-Based Exercises, Mobile Apps, Physiological Monitoring, Respiratory Pattern Monitoring, Stress-Management Interventions, Sensor-Triggered Stress Intervention, Smartphone Apps, Smoking Cessation, Wearable Sensors, Eating Behavior, Stress-Related Eating

Each time point when participant is available (i.e., not driving, not physically active, a stress classification is possible, hasn't recently received an ecological momentary assessment (EMA) or an intervention prompt) is randomly assigned to intervention prompt or no prompt.

Each minute when participant is available is randomly assigned to either intervention (to practice a stress management exercise) vs. no intervention prompt. When intervention occurs, participant's smartphone vibrates and relaxation app opens, prompting performance of a relaxation exercise.

Study smartphone and software will be used to deliver intervention prompts to use stress management applications on the study smartphone at various times throughout the day, during at least 10 days of study participation. The delivery of prompts will be micro randomized to occur when participants are classified as stressed, and when participants are not classified as stressed. Headspace, a commercial stress management application, will be installed on the study smartphones. Thought Shakeup and Mood Surfing, stress management applications that are not commercially available, also will be installed on the study smartphones. These smartphone applications guide participants through stress management exercises that draw upon techniques from mindfulness, cognitive behavioral therapy, and acceptance and commitment therapy.

2 hour window after each micro-randomized intervention vs. no intervention event during first 10 days after quitting smoking

Inclusion Criteria: Smokes 1+ cigarettes/day for past year Willing to try to quit smoking for at least 48 hours during a 15-day quit trial Will not use non-cigarette tobacco products or nicotine replacement therapy during the study period Not taking or intending to take pharmacological smoking cessation aids (e.g., nicotine replacement, bupropion, venlafaxene) during the study period Exclusion Criteria: Unable to wear study devices due to skin irritation or sizing limitations Planning to move outside of Chicago area during study period Adults unable to provide informed consent Individuals who are not yet adults Pregnant women Prisoners Non-English Speakers

Following completion of this study, a de-identified dataset, (i.e., containing no raw location/GPS information), will be generated and made available to interested researchers upon request. The dataset will be stripped of any information that could be linked back to the original data or to an individual participant. Prospective users of this dataset must sign a confidentiality agreement, requiring that they must get permission from the MD2K Center to share the data with anyone else. All external requests for data will be directed to Dr. Bonnie Spring and routed through the MD2K Center. Prospective investigators will submit a written proposal to the MD2K Executive Committee outlining the question they will investigate, the specific variables that they need to answer that question, their analytic plan for answering that question, and documentation of sufficient Institutional Review Board oversight. Investigators will also need to sign a confidentiality agreement.

Saleheen N, Ali AA, Hossain SM, Sarker H, Chatterjee S, Marlin B, Ertin E, al'Absi M, Kumar S. puffMarker: A Multi-Sensor Approach for Pinpointing the Timing of First Lapse in Smoking Cessation. Proc ACM Int Conf Ubiquitous Comput. 2015 Sep;2015:999-1010.

Kumar S, Abowd GD, Abraham WT, al'Absi M, Beck JG, Chau DH, Condie T, Conroy DE, Ertin E, Estrin D, Ganesan D, Lam C, Marlin B, Marsh CB, Murphy SA, Nahum-Shani I, Patrick K, Rehg JM, Sharmin M, Shetty V, Sim I, Spring B, Srivastava M, Wetter DW. Center of excellence for mobile sensor data-to-knowledge (MD2K). J Am Med Inform Assoc. 2015 Nov;22(6):1137-42. doi: 10.1093/jamia/ocv056. Epub 2015 Jul 3.

Sarker H, Tyburski M, Rahman MM, Hovsepian K, Sharmin M, Epstein DH, Preston KL, Furr-Holden CD, Milam A, Nahum-Shani I, al'Absi M, Kumar S. Finding Significant Stress Episodes in a Discontinuous Time Series of Rapidly Varying Mobile Sensor Data. Proc SIGCHI Conf Hum Factor Comput Syst. 2016 May;2016:4489-4501. doi: 10.1145/2858036.2858218.

Klasnja P, Hekler EB, Shiffman S, Boruvka A, Almirall D, Tewari A, Murphy SA. Microrandomized trials: An experimental design for developing just-in-time adaptive interventions. Health Psychol. 2015 Dec;34S(0):1220-8. doi: 10.1037/hea0000305.

The Mobile Sensor Data-to-Knowledge Center of Excellence is one of 13 national Big Data Centers of Excellence awarded by the National Institutes of Health as part of its Big Data-to-Knowledge initiative.