Sang Won Bae1, Tammy Chung2, Rahul Islam1, Brian Suffoletto3, Jiameng Du4, Serim Jang4, Yuuki Nishiyama5, Raghu Mulukutla4, Anind Dey6. 1. School of Systems and Enterprises, Stevens Institute of Technology, USA. 2. Institute for Health, Healthcare Policy and Aging Research, Rutgers University, USA. Electronic address: tammy.chung@rutgers.edu. 3. Department of Emergency Medicine, Stanford University, USA. 4. Computer Science Department, Carnegie Mellon University, USA. 5. Institute of Industrial Science, University of Tokyo, Japan. 6. Information School, University of Washington, Seattle, USA.
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 "high" 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 "not intoxicated" (rating = 0) vs subjective cannabis "low-intoxication" (rating = 1-3) vs "moderate-intensive intoxication" (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 "routines" 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 "high" (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.
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 "high" 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 "not intoxicated" (rating = 0) vs subjective cannabis "low-intoxication" (rating = 1-3) vs "moderate-intensive intoxication" (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 "routines" 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 "high" (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.
Authors: David H Epstein; Matthew Tyburski; William J Kowalczyk; Albert J Burgess-Hull; Karran A Phillips; Brenda L Curtis; Kenzie L Preston Journal: NPJ Digit Med Date: 2020-03-04