Mobile phone sensor-based detection of subjective cannabis intoxication in young adults: A feasibility study in real-world settings.
Mobile phone sensor-based detection of subjective cannabis intoxication in young adults: A feasibility study in real-world settings.
复制标题
DOI：
10.1016/j.drugalcdep.2021.108972
复制
发表时间：
2021-11-01
影响因子：
4.2
通讯作者：
Dey A
中科院分区：
文献类型：
--
作者：
Bae SW;Chung T;Islam R;Suffoletto B;Du J;Jang S;Nishiyama Y;Mulukutla R;Dey A
考虑到与急性大麻中毒有关的精神功能可能受损，我们探讨了基于智能手机的传感器（例如，加速度计）可以检测自然环境中自我报告的急性大麻中毒事件（主观“高”状态）。宾夕法尼亚州匹兹堡的年轻人（18-25岁）每周至少报告两次大麻使用，完成了长达30天的每日数据收集：电话调查（3次/天），大麻使用的自我发起报告（开始/停止时间，主观大麻中毒评级：0-10，10 =非常高），以及连续的电话传感器数据。我们用光梯度增强机（LGBM）测试了多个模型，以区分“未中毒”（评级= 0）与主观大麻“低中毒”（评级=1-3）与“中度中毒”（评级= 4-10）。我们测试了时间特征的重要性（即，一周中的一天，一天中的时间）相对于智能手机传感器数据仅对模型性能起作用，因为时间特征单独可能预测大麻中毒中的“惯例”。年轻人（N = 57; 58%为女性）报告了451例大麻使用事件，平均主观中毒评分= 3.77（SD = 2.64）。LGBM是性能最好的分类器，使用时间特征检测主观“高”的准确率为60%（曲线下面积[AUC] = 0.82）。将智能手机传感器数据与时间特征相结合，提高了模型性能：90%的准确度（AUC = 0.98）。检测主观大麻中毒的重要智能手机功能包括旅行（GPS）和运动（加速度计）。这项概念验证研究表明，使用手机传感器来检测自然环境中的主观大麻中毒是可行的，这可能会引发及时干预。
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. 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. 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). 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.
登录
查看更多内容
吸食大麻对年轻成年男性和女性自评认知的影响。
DOI：
10.1111/ajad.12157
发表时间：
2015-03
期刊：
The American journal on addictions
影响因子：
--
作者：
Conroy DA;Kurth ME;Brower KJ;Strong DR;Stein MD
通讯作者：
Stein MD
DOI：
10.1146/annurev-clinpsy-032816-044949
发表时间：
2017-05-08
影响因子：
18.4
作者：
Mohr DC;Zhang M;Schueller SM
通讯作者：
Schueller SM
影响因子：
4.4
作者：
Phillips, Kristina T.;Phillips, Michael M.;Tormohlen, Kayla N.
通讯作者：
Tormohlen, Kayla N.
影响因子：
5
作者：
Chung, Tammy;Bae, Sang Won;Dey, Anind K.
通讯作者：
Dey, Anind K.
影响因子：
15.2
作者：
Epstein, David H.;Tyburski, Matthew;Preston, Kenzie L.
通讯作者：
Preston, Kenzie L.