Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data
Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data
复制标题
DOI：
10.1038/s41746-020-0234-6
复制
发表时间：
2020-03-04
影响因子：
15.2
通讯作者：
Preston, Kenzie L.
中科院分区：
文献类型：
--
作者：
Epstein, David H.;Tyburski, Matthew;Preston, Kenzie L.
即时适应性干预（JITAIs），通常是智能手机应用程序，学会在用户需要时提供治疗内容。挑战在于在算法选择的时刻“推送”内容，而不需要用户费力地输入。我们训练了一个随机森林算法来预测未来90分钟的海洛因渴望，可卡因渴望或压力（通过智能手机应用程序报告3次/天），使用来自189名接受阿片类药物使用障碍治疗的门诊患者的16周现场数据。我们只使用了一种被动收集的连续输入形式（以及个人层面的人口统计数据）：一个由GPS评估的过去5小时运动中的环境暴露指标。我们的模型达到了极好的整体准确度——在16周的裁剪结束时，准确率高达0.93——但这主要是由于对缺席的正确预测。对于存在感的预测，“可信度”（阳性预测值，PPV）通常在16周结束时达到0.70的峰值。预测目标越少，PPV越低。我们的发现补充了其他研究人员的发现，他们使用机器学习和更广泛的“数字表型”输入来预测或检测心理和行为事件。当目标事件相对微妙时，如压力或药物渴望，准确的检测或预测可能需要用户努力输入，而不仅仅是被动监测。我们讨论了难以达到甚至评估准确性的方法，并警告说，高整体准确性（包括高特异性）可以掩盖低PPV所显示的大量假警报。
Just-in-time adaptive interventions (JITAIs), typically smartphone apps, learn to deliver therapeutic content when users need it. The challenge is to "push" content at algorithmically chosen moments without making users trigger it with effortful input. We trained a randomForest algorithm to predict heroin craving, cocaine craving, or stress (reported via smartphone app 3x/day) 90 min into the future, using 16 weeks of field data from 189 outpatients being treated for opioid-use disorder. We used only one form of continuous input (along with person-level demographic data), collected passively: an indicator of environmental exposures along the past 5 h of movement, as assessed by GPS. Our models achieved excellent overall accuracy-as high as 0.93 by the end of 16 weeks of tailoring-but this was driven mostly by correct predictions of absence. For predictions of presence, "believability" (positive predictive value, PPV) usually peaked in the high 0.70s toward the end of the 16 weeks. When the prediction target was more rare, PPV was lower. Our findings complement those of other investigators who use machine learning with more broadly based "digital phenotyping" inputs to predict or detect mental and behavioral events. When target events are comparatively subtle, like stress or drug craving, accurate detection or prediction probably needs effortful input from users, not passive monitoring alone. We discuss ways in which accuracy is difficult to achieve or even assess, and warn that high overall accuracy (including high specificity) can mask the abundance of false alarms that low PPV reveals.