Inferential methods for functional data from wearable devices

可穿戴设备功能数据的推理方法

• 批准号: 9924432
• 负责人: IAN WRAY MCKEAGUE
• 金额: $ 29.89万
• 依托单位: COLUMBIA UNIVERSITY HEALTH SCIENCES
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-04-15 至 2024-03-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9924432
• 关键词: Acceleration; Accelerometer; Beds; Bypass; Case Study; Characteristics; Child; Clinical Research; Computer software; Data; Data Analytics; Development; Devices; Dietary Practices; Drug Combinations; Enrollment; Evaluation; Event; Grant; Head Start Program; Health; Health Status; Healthcare; Intervention; Lead; Machine Learning; Measures; Methods; Mitochondria; Modeling; Molecular; Monitor; Motivation; Nature; New York City; Obesity; Occupations; Outcome; Outcome Measure; Patients; Pharmacotherapy; Physical activity; Physiological; Preschool Child; Process; Proxy; Public Health; Recording of previous events; Regimen; Signal Transduction; Specific qualifier value; Statistical Methods; Statistical Models; Stochastic Processes; Survival Analysis; Syndrome; Target Populations; Techniques; Testing; Time; Work; analytical method; base; circadian; data mining; design; experimental study; functional outcomes; indexing; interest; lower income families; novel; patient population; precision medicine; screening; sensor; theories; time use; tool; treatment group; wearable device; wearable sensor technology

Project Summary/Abstract This is a project to develop new statistical methods for comparing groups of subjects in terms of health outcomes that are assessed using data from wearable devices. Inexpensive wearable sensors for health monitoring are now capable of generating massive amounts of data collected longitudinally, up to months at a time. The project will develop inferential methods that can deal with the complexity of such data. A serious challenge is the presence of unmeasured time-dependent confounders (e.g., circadian and dietary patterns), making direct comparisons or borrowing strength across subjects untenable unless the studies are carried out in controlled experimental con- ditions. Generic data mining and machine learning tools have been widely used to provide predictions of health status from such data. However, such tools cannot be used for significance testing of covariate effects, which is necessary for designing precision medicine interventions, for example, without taking the inherent model selection or the presence of the unmeasured confounders into account. To overcome these difficulties, a systematic de- velopment of inferential methods for functional outcome data obtained from wearable devices will be carried out. There are three specific aims: 1) Develop metrics for functional outcome data from wearable devices, 2) Develop nonparametric estimation and testing methods for activity profiles and a screening method for predictors of activity profiles, 3) Implement the methods in an R package and carry out two case studies using accelerometer data. For Aim 1, the approach is to reduce the sensor data to occupation time profiles (e.g., as a function of activity level), and formulate the statistical modeling in terms of these profiles using survival and functional data analytic meth- ods. This will have a number of advantages, the principal one being that time-dependent confounders become less problematic because the effect of differences in temporal alignment across subjects is mitigated. In addition, survival analysis methods can be applied by viewing the occupation time as a time-to-event outcome indexed by activity level. For Aim 2, nonparametric methods will be used to compare and order occupation time distributions between groups of subjects that are specified in terms of baseline covariate levels or treatment groups. Further, a new method of post-selection inference based on marginal screening for function-on-scalar regression will be developed to identify and formally test whether covariates are significantly associated with activity profiles. Aim 3 will develop an R-package implementation, and as a test-bed for the proposed methods they will be applied to two Columbia-based clinical studies: to the study of physical activity in children enrolled in New York City Head Start, and to the study of experimental drugs for the treatment of mitochondrial depletion syndrome.

项目总结/摘要 这是一个开发新的统计方法的项目，用于比较健康结果方面的受试者群体 通过可穿戴设备的数据进行评估。用于健康监测的廉价可穿戴传感器现在 能够产生大量纵向收集的数据，每次长达数月。该项目将 开发出能够处理这些复杂数据的推理方法。一个严峻的挑战是 未测量的时间依赖性混杂因素（例如，昼夜节律和饮食模式），进行直接比较或 除非研究在受控实验条件下进行，否则跨学科借用力量是站不住脚的 ditions。通用数据挖掘和机器学习工具已被广泛用于提供健康预测 这些数据的状态。然而，这些工具不能用于协变量效应的显著性检验， 例如，设计精准医疗干预措施所必需的，而不需要采取固有的模型选择 或未测量混杂因素的存在。为了克服这些困难，一个系统的缺陷， 将对从可穿戴设备获得的功能结果数据的推断方法进行说明。 有三个具体目标：1）开发可穿戴设备功能结果数据的指标，2）开发 活性分布的非参数估计和检验方法以及活性预测因子的筛选方法 3）在R包中实现这些方法，并使用加速度计数据进行两个案例研究。为 目标1，该方法是将传感器数据减少到占用时间分布（例如，作为活动水平的函数）， 并使用生存和功能数据分析方法根据这些特征制定统计模型， 耗氧物质这将有许多优点，主要的一个是时间依赖性混杂因素成为 问题较少，因为减轻了跨对象的时间对准的差异的影响。此外，本发明还提供了一种方法， 生存分析方法可以通过将占用时间视为事件发生时间结果来应用， 活动水平。对于目标2，将使用非参数方法来比较和排序占用时间分布 根据基线协变量水平或治疗组指定的受试者组之间。此外，本发明还 本文提出了一种基于边际筛选的纯量函数回归后选择推理的新方法， 用于识别并正式测试协变量是否与活动特征显著相关。目的 3将开发一个R包实现，并作为所提出的方法的测试平台，它们将被应用于 两项基于哥伦比亚的临床研究：一项是对纽约市儿童身体活动的研究， 开始，并致力于研究治疗线粒体耗竭综合征的实验性药物。