Using machine learning for real-time BAC estimation from a new-generation transdermal biosensor in the laboratory.
Using machine learning for real-time BAC estimation from a new-generation transdermal biosensor in the laboratory.
复制标题
DOI：
10.1016/j.drugalcdep.2020.108205
复制
发表时间：
2020-11-01
影响因子：
4.2
通讯作者：
Bosch N
中科院分区：
文献类型：
--
作者：
Fairbairn CE;Kang D;Bosch N
经皮生物传感器为酒精消费的评估提供了一种非侵入性，低成本的技术，在成瘾科学中具有广泛的潜在应用。老一代的透皮设备具有庞大的设计和稀疏的采样间隔，限制了透皮技术的潜在应用。最近，新一代的透皮设备已经上市，具有智能手机连接，紧凑的设计和快速采样。在这里，我们提出了初步的实验室研究，检查新一代透皮传感器原型的有效性。参与者是年轻的饮酒者，在实验室中饮酒（目标BAC= 0.08%）或不饮酒。参与者佩戴透皮传感器，同时提供重复的呼吸测醉器（BrAC）读数。我们评估了BrAC（在特定时间点测量的BrAC）和eBrAC（仅基于前一时间间隔内收集的经皮读数估计的BrAC）之间的关联。Extra-Trees机器学习算法，将经皮时间序列特征作为预测因子，用于创建eBrAC。新一代原型传感器的故障率很高（16%-34%）。在具有可用的新一代传感器数据的参与者中，模型表现出将饮酒与非饮酒事件分开的强大能力，以及区分醉酒参与者中BrAC水平的显著（中等）能力。基于老一代与新一代设备数据的模型，eBrAC和BrAC之间的差异高出60%。模型比较表明，时间序列分析和机器学习都对最终模型的准确性做出了重大贡献。结果提供了有利的初步证据，从新一代传感器的实时BAC估计的准确性。未来的研究将需要可变的酒精剂量和现实环境，以进一步验证这些设备。
Transdermal biosensors offer a noninvasive, low-cost technology for the assessment of alcohol consumption with broad potential applications in addiction science. Older-generation transdermal devices feature bulky designs and sparse sampling intervals, limiting potential applications for transdermal technology. Recently a new-generation of transdermal device has become available, featuring smartphone connectivity, compact designs, and rapid sampling. Here we present initial laboratory research examining the validity of a new-generation transdermal sensor prototype. Participants were young drinkers administered alcohol (target BAC=.08%) or no-alcohol in the laboratory. Participants wore transdermal sensors while providing repeated breathalyzer (BrAC) readings. We assessed the association between BrAC (measured BrAC for a specific time point) and eBrAC (BrAC estimated based only on transdermal readings collected in the immediately preceding time interval). Extra-Trees machine learning algorithms, incorporating transdermal time series features as predictors, were used to create eBrAC. Failure rates for the new-generation prototype sensor were high (16%−34%). Among participants with useable new-generation sensor data, models demonstrated strong capabilities for separating drinking from non-drinking episodes, and significant (moderate) ability to differentiate BrAC levels within intoxicated participants. Differences between eBrAC and BrAC were 60% higher for models based on data from old-generation vs new-generation devices. Model comparisons indicated that both time series analysis and machine learning contributed significantly to final model accuracy. Results provide favorable preliminary evidence for the accuracy of real-time BAC estimates from a new-generation sensor. Future research featuring variable alcohol doses and real-world contexts will be required to further validate these devices.
登录
查看更多内容
影响因子：
3.2
作者：
Luczak, Susan E.;Rosen, I. Gary
通讯作者：
Rosen, I. Gary
影响因子：
2.3
作者：
Dougherty, Donald M.;Charles, Nora E.;Hill-Kapturczak, Nathalie
通讯作者：
Hill-Kapturczak, Nathalie
DOI：
10.1097/00000374-199909000-00004
发表时间：
1999-09-01
影响因子：
3.2
作者：
Bendtsen, P;Hultberg, J;Jones, AW
通讯作者：
Jones, AW
影响因子：
6
作者：
Christ, Maximilian;Braun, Nils;Kempa-Liehr, Andreas W.
通讯作者：
Kempa-Liehr, Andreas W.
DOI：
10.1111/j.1530-0277.1997.tb04451.x
发表时间：
1997-10-01
影响因子：
3.2
作者：
Davidson, D;Camara, P;Swift, R
通讯作者：
Swift, R