OpiTrack

Abstract

Opioid use disorder is a medical condition with major social and economic consequences. While ubiquitous physiological sensing technologies have been widely adopted and extensively used to monitor day-to-day activities and deliver targeted interventions to improve human health, the use of these technologies to detect drug use in natural environments has been largely underexplored. The long-term goal of our work is to develop a mobile technology system that can identify high-risk opioid-related events (i.e., development of tolerance in the setting of prescription opioid use, return-to-use events in the setting of opioid use disorder) and deploy just-in-time interventions to mitigate the risk of overdose morbidity and mortality. In the current paper, we take an initial step by asking a crucial question: Can opioid use be detected using physiological signals obtained from a wrist-mounted sensor? Thirty-six individuals who were admitted to the hospital for an acute painful condition and received opioid analgesics as part of their clinical care were enrolled. Subjects wore a noninvasive wrist sensor during this time (1-14 days) that continuously measured physiological signals (heart rate, skin temperature, accelerometry, electrodermal activity, and interbeat interval). We collected a total of 2070 hours (≈ 86 days) of physiological data and observed a total of 339 opioid administrations. Our results are encouraging and show that using a Channel-Temporal Attention TCN (CTA-TCN) model, we can detect an opioid administration in a time-window with an F1-score of 0.80, a specificity of 0.77, sensitivity of 0.80, and an AUC of 0.77. We also predict the exact moment of administration in this time-window with a normalized mean absolute error of 8.6% and R2 coefficient of 0.85.

Users' Acceptability and Perceived Efficacy of mHealth for Opioid Use Disorder: Scoping Review

“…Since that study was published, there have been technological developments in this area to meet the pressing need that arose during the COVID-19 pandemic. Specifically, new wearable sensors have been developed that monitor sweat, heart rate, and temperature and that predict overdose in patients [7][8][9][10][11][12][13]. Several studies have evaluated the application of wearable opioid sensors for detecting overdose by detecting changes in temperature, movement, respiratory rate, heart rate, and electrodermal activity [8,[11][12][13][14][15][16][17].…”

“…Specifically, new wearable sensors have been developed that monitor sweat, heart rate, and temperature and that predict overdose in patients [7][8][9][10][11][12][13]. Several studies have evaluated the application of wearable opioid sensors for detecting overdose by detecting changes in temperature, movement, respiratory rate, heart rate, and electrodermal activity [8,[11][12][13][14][15][16][17]. Most of the studies involved a wrist-worn biosensor, usually the Empatica E4 biosensor and Q sensor, which integrate a machine learning algorithm.…”

“…Most of the studies involved a wrist-worn biosensor, usually the Empatica E4 biosensor and Q sensor, which integrate a machine learning algorithm. A few studies found that wearable technology can detect changes in skin temperature, notably a temperature rise during opioid intake and overdose [8,[12][13][14]16,17]. Carreiro et al [14] found that the mean skin temperature increase after opioid intake was 2.62 °C and that differences in body temperature before and after intake were significant (P<.01).…”

“…Carreiro et al [14] found that the mean skin temperature increase after opioid intake was 2.62 °C and that differences in body temperature before and after intake were significant (P<.01). In addition to temperature changes, several studies found reduced movement or locomotion by evaluating triaxis acceleration data [8,11,13,14,16,17]. Notably, local extremities, such as the fingers, had reduced motion or there was less "fidgeting" after opioid intake.…”

Zoom-Based Mindfulness-Oriented Recovery Enhancement Plus Just-in-Time Mindfulness Practice Triggered by Wearable Sensors for Opioid Craving and Chronic Pain

“…Machine learning, which analyzes patterns in large datasets to build predictive models, may be useful in this pursuit. Prior work has already demonstrated that modeling wearable sensor data with a temporal convolutional neural network can detect opioid use (Gullapalli et al, 2021 ). Hypothetically, a machine learning model can analyze underlying patterns in physiological signals passively recorded during a specific mindfulness session to predict the effectiveness of the session.…”