Prediction of Smoking Risk From Repeated Sampling of Environmental Images: Model Validation.
Prediction of Smoking Risk From Repeated Sampling of Environmental Images: Model Validation.
复制标题
DOI：
10.2196/27875
复制
发表时间：
2021-11-01
影响因子：
7.4
通讯作者：
McClernon FJ
中科院分区：
文献类型：
--
作者：
Engelhard MM;D'Arcy J;Oliver JA;Kozink R;McClernon FJ
观察他们习惯吸烟的环境会增加吸烟者在实验室环境中的渴望和吸烟行为。一种深度学习方法可以区分习惯性吸烟和非吸烟环境，这表明有可能通过连续获取吸烟者日常环境的图像来预测与环境相关的吸烟风险。在这项研究中，我们的目标是通过连续获取吸烟者的日常环境图像来预测与环境相关的风险。我们还旨在了解参与者报告的模型性能如何随位置类型而变化。来自北卡罗来纳州达勒姆及周边地区的吸烟者在吸烟后立即或在一天中随机选择的时间完成了为期两周的生态瞬间评估。在每次评估中，参与者都要拍一张他们当前环境的照片，并完成一份关于吸烟、渴望和环境设置的问卷。一个基于卷积神经网络的模型被训练来预测吸烟、渴望、当前环境中是否允许吸烟以及参与者是否在室外，该模型基于参与者的日常环境图像、他们上次吸烟的时间以及日常吸烟习惯的基线数据。预测性能，使用接收器工作特征曲线下的面积（AUC）和平均精度（AP）进行量化，评估样本外预测以及在第1至10天图像上训练的个性化模型。这些模型针对移动设备进行了优化，并作为智能手机应用程序实现。共有48名参与者完成了研究，获得了8008张图像。个性化模型在预测吸烟风险（AUC=0.827； AP=0.882）、渴望（AUC=0.837； AP=0.798）、当前环境是否允许吸烟（AUC=0.932； AP=0.981）和参与者是否在室外（AUC=0.977； AP=0.956）方面非常有效。样本外模型还能有效预测吸烟风险（AUC=0.723， AP=0.785）、当前环境中是否允许吸烟（AUC=0.815， AP=0.937）、参与者是否在室外（AUC=0.949， AP=0.922）；然而，它们不能有效地预测渴望（AUC=0.522； AP=0.427）。在预测除渴望以外的所有结果时，忽略图像特征可使AUC降低0.1以上。对于自我报告的位置类型变量较多的参与者，吸烟预测更为有效（Spearman ρ=0.48； P=.001）。日常环境的图像可以用来有效地预测吸烟风险。模型个性化，通过结合关于日常吸烟习惯的信息和对参与者特定图像的训练来实现，进一步提高了预测性能。环境相关的吸烟风险可以在移动设备上实时评估，并可纳入基于设备的戒烟干预措施。
Viewing their habitual smoking environments increases smokers’ craving and smoking behaviors in laboratory settings. A deep learning approach can differentiate between habitual smoking versus nonsmoking environments, suggesting that it may be possible to predict environment-associated smoking risk from continuously acquired images of smokers’ daily environments. In this study, we aim to predict environment-associated risk from continuously acquired images of smokers’ daily environments. We also aim to understand how model performance varies by location type, as reported by participants. Smokers from Durham, North Carolina and surrounding areas completed ecological momentary assessments both immediately after smoking and at randomly selected times throughout the day for 2 weeks. At each assessment, participants took a picture of their current environment and completed a questionnaire on smoking, craving, and the environmental setting. A convolutional neural network–based model was trained to predict smoking, craving, whether smoking was permitted in the current environment and whether the participant was outside based on images of participants’ daily environments, the time since their last cigarette, and baseline data on daily smoking habits. Prediction performance, quantified using the area under the receiver operating characteristic curve (AUC) and average precision (AP), was assessed for out-of-sample prediction as well as personalized models trained on images from days 1 to 10. The models were optimized for mobile devices and implemented as a smartphone app. A total of 48 participants completed the study, and 8008 images were acquired. The personalized models were highly effective in predicting smoking risk (AUC=0.827; AP=0.882), craving (AUC=0.837; AP=0.798), whether smoking was permitted in the current environment (AUC=0.932; AP=0.981), and whether the participant was outside (AUC=0.977; AP=0.956). The out-of-sample models were also effective in predicting smoking risk (AUC=0.723; AP=0.785), whether smoking was permitted in the current environment (AUC=0.815; AP=0.937), and whether the participant was outside (AUC=0.949; AP=0.922); however, they were not effective in predicting craving (AUC=0.522; AP=0.427). Omitting image features reduced AUC by over 0.1 when predicting all outcomes except craving. Prediction of smoking was more effective for participants whose self-reported location type was more variable (Spearman ρ=0.48; P=.001). Images of daily environments can be used to effectively predict smoking risk. Model personalization, achieved by incorporating information about daily smoking habits and training on participant-specific images, further improves prediction performance. Environment-associated smoking risk can be assessed in real time on a mobile device and can be incorporated into device-based smoking cessation interventions.
登录
查看更多内容
影响因子：
7.6
作者：
McClernon, F. Joseph;Conklin, Cynthia A.;DeVito, Anthony M.
通讯作者：
DeVito, Anthony M.
影响因子：
19.5
作者：
Russakovsky, Olga;Deng, Jia;Fei-Fei, Li
通讯作者：
Fei-Fei, Li
影响因子：
33.9
作者：
Walton, Kimp;Wang, Teresa W.;Babb, Stephen
通讯作者：
Babb, Stephen
影响因子：
15.2
作者：
Engelhard, Matthew M.;Oliver, Jason A.;McClernon, F. Joseph
通讯作者：
McClernon, F. Joseph
影响因子：
11.3
作者：
AhnAllen, Christopher G.;Tidey, Jennifer W.
通讯作者：
Tidey, Jennifer W.