监督机器学习从生态瞬间评估和传感器数据预测吸烟失误:适应性干预 Just-in-time开发的含义
Olga Perski1,2,3, Dimitra Kale3, Corinna Leppin3
1Faculty of Social Sciences, Tampere University, Finland.
PLOS digital health
|August 23, 2024
概括
机器学习模型使用生态瞬间评估和可穿戴数据预测吸烟失效. 个性化模型显示出正确适应性干预 (JITAI) 的前景,以防止复发.
科学领域:
- 数字健康数字健康
- 机器学习在行为科学中的应用
- 戒烟干预措施 戒烟干预措施
背景情况:
- 吸烟失误往往在完全复发之前,需要及时干预.
- 准时适应性干预 (JITAI) 提供了一种有前途的方法,可以主动地针对漏洞.
- 开发有效的JITAI需要了解失效触发因素,并预测失效发生率.
研究的目的:
- 训练和测试监督机器学习算法,用于预测吸烟失误.
- 用生态瞬间评估 (EMA) 和可穿戴传感器数据评估算法的可行性和性能.
- 确定最优的算法,以告知决策点和定制变量的一个失误预防JITAI.
主要方法:
- 试图戒烟的成年吸烟者每小时完成一次EMA,评估10天内的渴望,情绪,背景和失禁发生率.
- 参与者戴着Fitbit Charge 4来收集有关步骤和心率的被动数据.
- 训练和测试了带有和没有传感器数据的组级,个人级和混合机器学习算法.
主要成果:
- 集团级算法实现了高预测性能 (AUC高达0.952与传感器数据),但显示了可变的个人性能.
- 个人级别和混合算法,虽然可以为更少的参与者构建,但表现出更好的性能,特别是传感器数据 (中位数AUC高达0.983).
- 传感器数据集成显著提高了算法的预测准确性,特别是在个人级别模型中.
结论:
- 机器学习算法,特别是在结合可穿戴传感器数据时,可以有效地预测吸烟失误.
- 个性化和混合算法显示了个性化JITAI的潜力,尽管对一些用户而言存在可行性限制.
- 需要进一步开发以平衡JITAI的算法性能,可行性和实施标准.
更多相关视频
10:37Automated Measurement of Pulmonary Emphysema and Small Airway Remodeling in Cigarette Smoke-exposed Mice
Published on: January 16, 2015
13.2K
11:21Methodology for Establishing a Community-Wide Life Laboratory for Capturing Unobtrusive and Continuous Remote Activity and Health Data
Published on: July 27, 2018
8.2K
相关概念视频
Statistical Methods for Analyzing Epidemiological Data
336
Epidemiological data primarily involves information on specific populations' occurrence, distribution, and determinants of health and diseases. This data is crucial for understanding disease patterns and impacts, aiding public health decision-making and disease prevention strategies. The analysis of epidemiological data employs various statistical methods to interpret health-related data effectively. Here are some commonly used methods:
336
Observational Studies
8.4K
Observational studies are a type of analytical study where researchers observe events without any interventions. In other words, the researcher does not influence the response variable or the experiment's outcome.
There are three types of observational studies – Prospective, retrospective, and cross-sectional.
Prospective Study
Prospective studies, also known as longitudinal or cohort studies, are carried out by collecting future data from groups sharing similar characteristics. One...
There are three types of observational studies – Prospective, retrospective, and cross-sectional.
Prospective Study
Prospective studies, also known as longitudinal or cohort studies, are carried out by collecting future data from groups sharing similar characteristics. One...
8.4K
