摘要
机器人与机器学习的新闻编辑每日新闻-机器学习的新研究是一篇报道的主题。根据NewsRx记者在弗吉尼亚州夏洛茨维尔的新闻报道，研究表明，“利用免费的智能手机应用程序可以帮助扩大循证戒烟干预的可用性和使用。然而，还需要进行更多的研究，调查这些应用程序中的不同功能如何影响其有效性。”新闻记者从弗吉尼亚大学医学院获得了这项研究的引用，“我们使用从一个公开的戒烟应用程序的实验中收集的观察数据，开发了有监督的机器学习(SML)算法，旨在区分有助于成功戒烟的应用程序功能。然后我们评估了应用程序功能使用模式在多大程度上解释了其他已知戒烟预测因素无法解释的戒烟差异（例如，烟草使用行为。数据来自一项实验(ClinicalTrials.gov NCT04623736)，该实验测试了在国家癌症研究所的quitSTART应用程序中实施生态瞬时评估的影响。参与者(N=133)的应用程序活动，包括他们在应用程序中采取的每一个行动及其相应的时间戳，在实验开始时测量人口统计学和基线烟草使用特征。采用Logistic回归SML模型从28个变量中估计参与者戒烟的概率，这些变量反映参与者使用不同的APP特征、指定的实验条件、不同的实验条件和不同的APP特征。D电话类型（iPhone[苹果公司]或Android D[谷歌]）。SML模型首先在训练集（n=100）中拟合，然后在预留测试集（n=33）中评估其准确性。在测试集中，似然比测试（n=30）评估R是否将个人的SML预测戒烟概率添加到包括人口统计学和烟草使用（例如，SML模型的敏感性(0.67)和特异度(0.67)在搁置检验中表明,个体使用不同APP特征的模式预测戒烟具有合理的准确性。似然比检验表明,包括SML模型预测概率在内的Logistic回归分析表明,SML模型预测的概率与SML模型预测的概率之间存在显著差异。在统计学上等同于只包括人口统计学和烟草使用变量的模型（P=.16）。通过SML利用用户数据可以帮助确定吸烟消费应用程序最有用的特征。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news reporting from Charlottesville, Virgini a, by NewsRx journalists, research stated, “Leveraging free smartphone apps can help expand the availability and use of evidence-based smoking cessation interve ntions. However, there is a need for additional research investigating how the u se of different features within such apps impacts their effectiveness.” The news correspondents obtained a quote from the research from the University o f Virginia School of Medicine, “We used observational data collected from an exp eriment of a publicly available smoking cessation app to develop supervised mach ine learning (SML) algorithms intended to distinguish the app features that prom ote successful smoking cessation. We then assessed the extent to which patterns of app feature use accounted for variance in cessation that could not be explain ed by other known predictors of cessation (eg, tobacco use behaviors). Data came from an experiment (ClinicalTrials.gov NCT04623736) testing the impacts of ince ntivizing ecological momentary assessments within the National Cancer Institute’ s quitSTART app. Participants’ (N=133) app activity, including every action they took within the app and its corresponding time stamp, was recorded. Demographic and baseline tobacco use characteristics were measured at the start of the expe riment, and short-term smoking cessation (7-day point prevalence abstinence) was measured at 4 weeks after baseline. Logistic regression SML modeling was used t o estimate participants’ probability of cessation from 28 variables reflecting p articipants’ use of different app features, assigned experimental conditions, an d phone type (iPhone [Apple Inc] or Androi d [Google]). The SML model was first fit i n a training set (n=100) and then its accuracy was assessed in a held-aside test set (n=33). Within the test set, a likelihood ratio test (n=30) assessed whethe r adding individuals’ SMLpredicted probabilities of cessation to a logistic reg ression model that included demographic and tobacco use (eg, polyuse) variables explained additional variance in 4-week cessation. The SML model’s sensitivity ( 0.67) and specificity (0.67) in the held-aside test set indicated that individua ls’ patterns of using different app features predicted cessation with reasonable accuracy. The likelihood ratio test showed that the logistic regression, which included the SML model-predicted probabilities, was statistically equivalent to the model that only included the demographic and tobacco use variables (P=.16). Harnessing user data through SML could help determine the features of smoking ce ssation apps that are most useful.”
NETL
NSTL