Mobile phone sensor-based detection of subjective cannabis intoxication in young adults: A feasibility study in real-world settings.

Abstract

BACKGROUND\nGiven 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 high state) in the natural environment.\n\n\nMETHODS\nYoung 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\u2009=\u2009very high), and continuous phone sensor data. We tested multiple models with Light Gradient Boosting Machine (LGBM) in distinguishing not intoxicated (rating\u2009=\u20090) vs subjective cannabis low-intoxication (rating\u2009=\u20091-3) vs moderate-intensive intoxication (rating\u2009=\u20094-10). 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 routines in cannabis intoxication.\n\n\nRESULTS\nYoung adults (N\u2009=\u200957; 58 % female) reported 451 cannabis use episodes, mean subjective intoxication rating\u2009=\u20093.77 (SD\u2009=\u20092.64). LGBM, the best performing classifier, had 60 % accuracy using time features to detect subjective high (Area Under the Curve [AUC]\u2009=\u20090.82). Combining smartphone sensor data with time features improved model performance: 90 % accuracy (AUC\u2009=\u20090.98). Important smartphone features to detect subjective cannabis intoxication included travel (GPS) and movement (accelerometer).\n\n\nCONCLUSIONS\nThis 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.