Leveraging Mobile Phone Sensors, Machine Learning, and Explainable Artificial Intelligence to Predict Imminent Same-Day Binge-drinking Events to Support Just-in-time Adaptive Interventions: Algorithm Development and Validation Study.
Leveraging Mobile Phone Sensors, Machine Learning, and Explainable Artificial Intelligence to Predict Imminent Same-Day Binge-drinking Events to Support Just-in-time Adaptive Interventions: Algorithm Development and Validation Study.
复制标题
DOI：
10.2196/39862
复制
发表时间：
2023-05-04
影响因子：
2.2
通讯作者：
Dey, Anind K.
中科院分区：
文献类型：
--
作者：
Bae, Sang Won;Suffoletto, Brian;Zhang, Tongze;Chung, Tammy;Ozolcer, Melik;Islam, Mohammad Rahul;Dey, Anind K.
关键词：
数字即时适应性干预措施可减少年轻人的酗酒事件（酗酒事件定义为：女性每次饮酒≥4杯，男性每次饮酒≥5杯），但在时间和内容方面需要优化。在酗酒事件发生前的数小时提供即时支持信息可能会提高干预效果。
我们旨在确定开发一种机器学习模型的可行性，该模型利用智能手机传感器数据准确预测未来，即酗酒事件发生前1至6小时的当日酗酒事件，并确定与周末和工作日酗酒事件相关的最具信息量的手机传感器特征，以确定解释预测模型性能的关键特征。
我们从75名有危险饮酒行为的年轻人（年龄21至25岁；平均22.4岁，标准差1.9岁）那里收集了手机传感器数据，这些人报告了他们14周内的饮酒行为。本次二次分析的参与者参加了一项临床试验。我们开发了机器学习模型，测试不同算法（例如，极端梯度提升[XGBoost]和决策树），利用智能手机传感器数据（例如，加速度计和全球定位系统）预测当日酗酒事件（与低风险饮酒事件和不饮酒时段相对）。我们测试了从饮酒开始的各种“预测距离”时间窗口（更近的：1小时；更远的：6小时）。我们还测试了各种分析时间窗口（即要分析的数据量），范围是从饮酒开始前1至12小时，因为这决定了为计算模型需要在手机上存储的数据量。可解释人工智能被用于探索对酗酒事件预测有贡献的最具信息量的手机传感器特征之间的相互作用。
XGBoost模型在预测即将发生的当日酗酒事件方面表现最佳，周末准确率为95%，工作日准确率为94.3%（F1分数分别为0.95和0.94）。在预测当日酗酒事件之前，这个XGBoost模型在周末和工作日分别需要距离饮酒开始3小时和6小时预测距离的12小时和9小时的手机传感器数据。对酗酒事件预测最具信息量的手机传感器特征是时间（例如，一天中的时间）和全球定位系统衍生的特征，如回转半径（一种出行指标）。关键特征（例如，一天中的时间和全球定位系统衍生的特征）之间的相互作用有助于当日酗酒事件的预测。
我们证明了智能手机传感器数据和机器学习用于准确预测年轻人即将发生的（当日）酗酒事件的可行性和潜在用途。该预测模型提供了“机会窗口”，并且通过采用可解释人工智能，我们确定了在酗酒事件发生前触发即时适应性干预的“关键促成特征”，这有可能降低年轻人发生酗酒事件的可能性。
ClinicalTrials.gov NCT02918565；https://clinicaltrials.gov/ct2/show/NCT02918565
Digital just-in-time adaptive interventions can reduce binge-drinking events (BDEs; consuming ≥4 drinks for women and ≥5 drinks for men per occasion) in young adults but need to be optimized for timing and content. Delivering just-in-time support messages in the hours prior to BDEs could improve intervention impact. We aimed to determine the feasibility of developing a machine learning (ML) model to accurately predict future, that is, same-day BDEs 1 to 6 hours prior BDEs, using smartphone sensor data and to identify the most informative phone sensor features associated with BDEs on weekends and weekdays to determine the key features that explain prediction model performance. We collected phone sensor data from 75 young adults (aged 21 to 25 years; mean 22.4, SD 1.9 years) with risky drinking behavior who reported their drinking behavior over 14 weeks. The participants in this secondary analysis were enrolled in a clinical trial. We developed ML models testing different algorithms (eg, extreme gradient boosting [XGBoost] and decision tree) to predict same-day BDEs (vs low-risk drinking events and non-drinking periods) using smartphone sensor data (eg, accelerometer and GPS). We tested various “prediction distance” time windows (more proximal: 1 hour; distant: 6 hours) from drinking onset. We also tested various analysis time windows (ie, the amount of data to be analyzed), ranging from 1 to 12 hours prior to drinking onset, because this determines the amount of data that needs to be stored on the phone to compute the model. Explainable artificial intelligence was used to explore interactions among the most informative phone sensor features contributing to the prediction of BDEs. The XGBoost model performed the best in predicting imminent same-day BDEs, with 95% accuracy on weekends and 94.3% accuracy on weekdays (F1-score=0.95 and 0.94, respectively). This XGBoost model needed 12 and 9 hours of phone sensor data at 3- and 6-hour prediction distance from the onset of drinking on weekends and weekdays, respectively, prior to predicting same-day BDEs. The most informative phone sensor features for BDE prediction were time (eg, time of day) and GPS-derived features, such as the radius of gyration (an indicator of travel). Interactions among key features (eg, time of day and GPS-derived features) contributed to the prediction of same-day BDEs. We demonstrated the feasibility and potential use of smartphone sensor data and ML for accurately predicting imminent (same-day) BDEs in young adults. The prediction model provides “windows of opportunity,” and with the adoption of explainable artificial intelligence, we identified “key contributing features” to trigger just-in-time adaptive intervention prior to the onset of BDEs, which has the potential to reduce the likelihood of BDEs in young adults. ClinicalTrials.gov NCT02918565; https://clinicaltrials.gov/ct2/show/NCT02918565
登录
查看更多内容
影响因子：
2
作者：
Coughlin LN;Nahum-Shani I;Bonar EE;Philyaw-Kotov ML;Rabbi M;Klasnja P;Walton MA
通讯作者：
Walton MA
DOI：
10.15288/jsas.2002.s14.118
发表时间：
2002-03-01
期刊：
JOURNAL OF STUDIES ON ALCOHOL
影响因子：
--
作者：
Abbey, A
通讯作者：
Abbey, A
影响因子：
3.9
作者：
Chih, Ming-Yuan;Patton, Timothy;Gustafson, David H.
通讯作者：
Gustafson, David H.
DOI：
10.1093/abm/kax029
发表时间：
2018-05-18
期刊：
Annals of behavioral medicine : a publication of the Society of Behavioral Medicine
影响因子：
--
作者：
Garnett CV;Crane D;Brown J;Kaner EFS;Beyer FR;Muirhead CR;Hickman M;Beard E;Redmore J;de Vocht F;Michie S
通讯作者：
Michie S
DOI：
10.1093/jamia/ocy160
发表时间：
2019-03-01
影响因子：
6.4
作者：
Gonul, Suat;Namli, Tuncay;Cosar, Ahmet
通讯作者：
Cosar, Ahmet