TY - JOUR
T1 - mRisk
T2 - Continuous Risk Estimation for Smoking Lapse from Noisy Sensor Data with Incomplete and Positive-Only Labels
AU - Ullah, Md Azim
AU - Chatterjee, Soujanya
AU - Fagundes, Christopher P.
AU - Lam, Cho
AU - Nahum-Shani, Inbal
AU - Rehg, James M.
AU - Wetter, David W.
AU - Kumar, Santosh
N1 - Funding Information:
We thank the anonymous reviewers for significantly improving the organization and presentation of this manuscript. The authors also wish to thank Shahin Samiei, Dr. Timothy Hnat, and Dr. Syed Monowar Hossain from MD2K Center of Excellence at University of Memphis for their contributions to data collection and/or software used for data collection. We sincerely thank the smoking cessation research study coordinators Rebecca Stoffel, Michelle Chen, Kristi Parker, Jeffrey Ramirez, and Andy Leung. This research was supported in part by the National Institutes of Health (NIH) under awards P41EB028242, R01CA224537, R01MD010362, R01CA190329, U01CA229437, and by the National Science Foundation (NSF) under awards ACI-1640813, CNS-1823221, CNS-1705135, and CNS-1822935.
Publisher Copyright:
© 2022 ACM.
PY - 2022/9/7
Y1 - 2022/9/7
N2 - Passive detection of risk factors (that may influence unhealthy or adverse behaviors) via wearable and mobile sensors has created new opportunities to improve the effectiveness of behavioral interventions. A key goal is to find opportune moments for intervention by passively detecting rising risk of an imminent adverse behavior. But, it has been difficult due to substantial noise in the data collected by sensors in the natural environment and a lack of reliable label assignment of low-and high-risk states to the continuous stream of sensor data. In this paper, we propose an event-based encoding of sensor data to reduce the effect of noises and then present an approach to efficiently model the historical influence of recent and past sensor-derived contexts on the likelihood of an adverse behavior. Next, to circumvent the lack of any confirmed negative labels (i.e., time periods with no high-risk moment), and only a few positive labels (i.e., detected adverse behavior), we propose a new loss function. We use 1,012 days of sensor and self-report data collected from 92 participants in a smoking cessation field study to train deep learning models to produce a continuous risk estimate for the likelihood of an impending smoking lapse. The risk dynamics produced by the model show that risk peaks an average of 44 minutes before a lapse. Simulations on field study data show that using our model can create intervention opportunities for 85% of lapses with 5.5 interventions per day.
AB - Passive detection of risk factors (that may influence unhealthy or adverse behaviors) via wearable and mobile sensors has created new opportunities to improve the effectiveness of behavioral interventions. A key goal is to find opportune moments for intervention by passively detecting rising risk of an imminent adverse behavior. But, it has been difficult due to substantial noise in the data collected by sensors in the natural environment and a lack of reliable label assignment of low-and high-risk states to the continuous stream of sensor data. In this paper, we propose an event-based encoding of sensor data to reduce the effect of noises and then present an approach to efficiently model the historical influence of recent and past sensor-derived contexts on the likelihood of an adverse behavior. Next, to circumvent the lack of any confirmed negative labels (i.e., time periods with no high-risk moment), and only a few positive labels (i.e., detected adverse behavior), we propose a new loss function. We use 1,012 days of sensor and self-report data collected from 92 participants in a smoking cessation field study to train deep learning models to produce a continuous risk estimate for the likelihood of an impending smoking lapse. The risk dynamics produced by the model show that risk peaks an average of 44 minutes before a lapse. Simulations on field study data show that using our model can create intervention opportunities for 85% of lapses with 5.5 interventions per day.
KW - Behavioral Intervention
KW - mHealth
KW - Risk prediction
KW - Smoking Cessation
KW - Wearable Sensors
UR - http://www.scopus.com/inward/record.url?scp=85139193357&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85139193357&partnerID=8YFLogxK
U2 - 10.1145/3550308
DO - 10.1145/3550308
M3 - Article
C2 - 36873428
AN - SCOPUS:85139193357
SN - 2474-9567
VL - 6
JO - Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
JF - Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
IS - 3
M1 - 143
ER -