Wearable sensor-based detection of stress and craving in patients during treatment for substance use disorder: A mixed methods pilot study.

AIMS: To determine the accuracy of a wearable sensor to detect and differentiate episodes of self-reported craving and stress in individuals with substance use disorders, and to assess acceptability, barriers, and facilitators to sensor-based monitoring in this population. METHODS: This was an observational mixed methods pilot study. Adults enrolled in an outpatient treatment program for a substance use disorder wore a non-invasive wrist-mounted sensor for four days and self-reported episodes of stress and craving. Continuous physiologic data (accelerometry, skin conductance, skin temperature, and heart rate) were extracted from the sensors and analyzed via various machine learning algorithms. Semi-structured interviews were conducted upon study completion, and thematic analysis was conducted on qualitative data from semi-structured interviews. RESULTS: Thirty individuals completed the protocol, and 43 % (N = 13) were female. A total of 41 craving and 104 stress events were analyzed. The differentiation accuracies of the top performing models were as follows: stress vs. non-stress states 74.5 % (AUC 0.82), craving vs. no-craving 75.7 % (AUC 0.82), and craving vs. stress 76.8 % (AUC 0.8). Overall participant perception was positive, and acceptability was high. Emergent themes from the exit interviews included a perception of connectedness and increased mindfulness related to wearing the sensor, both of which were reported as helpful to recovery. Barriers to engagement included interference with other daily wear items, and perceived stigma. CONCLUSIONS: Wearable sensors can be used to objectively differentiate episodes of craving and stress, and individuals in recovery from substance use disorder are accepting of continuous monitoring with these devices.

Point process time-frequency analysis of dynamic respiratory patterns during meditation practice.

Respiratory sinus arrhythmia (RSA) is largely mediated by the autonomic nervous system through its modulating influence on the heart beats. We propose a robust algorithm for quantifying instantaneous RSA as applied to heart beat intervals and respiratory recordings under dynamic breathing patterns. The blood volume pressure-derived heart beat series (pulse intervals, PIs) are modeled as an inverse Gaussian point process, with the instantaneous mean PI modeled as a bivariate regression incorporating both past PIs and respiration values observed at the beats. A point process maximum likelihood algorithm is used to estimate the model parameters, and instantaneous RSA is estimated via a frequency domain transfer function evaluated at instantaneous respiratory frequency where high coherence between respiration and PIs is observed. The model is statistically validated using Kolmogorov-Smirnov goodness-of-fit analysis, as well as independence tests. The algorithm is applied to subjects engaged in meditative practice, with distinctive dynamics in the respiration patterns elicited as a result. The presented analysis confirms the ability of the algorithm to track important changes in cardiorespiratory interactions elicited during meditation, otherwise not evidenced in control resting states, reporting statistically significant increase in RSA gain as measured by our paradigm.