@article{ref1,
title="Mobile phone sensor-based detection of subjective cannabis intoxication in young adults: a feasibility study in real-world settings",
journal="Drug and alcohol dependence",
year="2021",
author="Bae, Sang Won and Chung, Tammy and Islam, Rahul and Suffoletto, Brian and Du, Jiameng and Jang, Serim and Nishiyama, Yuuki and Mulukutla, Raghu and Dey, Anind",
volume="228",
number="",
pages="108972-108972",
abstract="Background Given possible impairment in psychomotor functioning related to acute cannabis intoxication, we explored whether smartphone-based sensors (e.g., accelerometer) can detect self-reported episodes of acute cannabis intoxication (subjective &quot;high&quot; state) in the natural environment.  Methods Young adults (ages 18-25) in Pittsburgh, PA, who reported cannabis use at least twice per week, completed up to 30 days of daily data collection: phone surveys (3 times/day), self-initiated reports of cannabis use (start/stop time, subjective cannabis intoxication rating: 0-10, 10 = very high), and continuous phone sensor data. We tested multiple models with Light Gradient Boosting Machine (LGBM) in distinguishing &quot;not intoxicated&quot; (rating = 0) vs subjective cannabis &quot;low-intoxication&quot; (rating = 1-3) vs &quot;moderate-intensive intoxication&quot; (rating = 4-10). We tested the importance of time features (i.e., day of the week, time of day) relative to smartphone sensor data only on model performance, since time features alone might predict &quot;routines&quot; in cannabis intoxication.  Results Young adults (N = 57; 58 % female) reported 451 cannabis use episodes, mean subjective intoxication rating = 3.77 (SD = 2.64). LGBM, the best performing classifier, had 60 % accuracy using time features to detect subjective &quot;high&quot; (Area Under the Curve [AUC] = 0.82). Combining smartphone sensor data with time features improved model performance: 90 % accuracy (AUC = 0.98). Important smartphone features to detect subjective cannabis intoxication included travel (GPS) and movement (accelerometer).  Conclusions This proof-of-concept study indicates the feasibility of using phone sensors to detect subjective cannabis intoxication in the natural environment, with potential implications for triggering just-in-time interventions.  Keywords: Cannabis impaired driving <p /> <p>Language: en</p>",
language="en",
issn="0376-8716",
doi="10.1016/j.drugalcdep.2021.108972",
url="http://dx.doi.org/10.1016/j.drugalcdep.2021.108972"
}