Learning invariant representation from high- dimensional data for quantitative stroke reha

从高维数据中学习不变表示以进行定量中风康复

• 批准号: 9916457
• 负责人: Carlos Fernandez-Granda
• 金额: $ 30万
• 依托单位: NEW YORK UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-07-16 至 2022-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9916457
• 关键词: Address; Biomedical Research; Calibration; Caring; Classification; Data; Data Set; Diagnostic; Dose; Due Process; Electronics; Genetic; Genomics; Image; Impairment; Instruction; Learning; Measurement; Medical; Methodology; Modeling; Motion; Motor; Movement; Noise; Patients; Performance; Procedures; Public Health; Recovery; Rehabilitation therapy; Research; Research Personnel; Stroke; Techniques; Training; Work; base; clinical practice; disability; handheld mobile device; improved; innovation; interest; machine learning algorithm; multidimensional data; network models; novel; patient variability; sensor; sensor technology; stroke outcome; stroke patient; stroke rehabilitation

Advances in wearable electronics, personal mobile devices, and sensor technology are opening the door to many promising applications in medical care and biomedical research. However, the resulting datasets are often challenging to process due to variability caused by extraneous effects unrelated to the tasks of interest, such as changes in environmental conditions, heteroscedasticity in measurement noise, or patient idiosyncrasies. These effects produce systematic differences between the data used to train machine- learning algorithms and the data on which they are applied in practice, impairing real-world performance. The proposed research will address the fundamental problem of factoring out extraneous effects associated with known nuisance variables. We will develop a novel methodology for extracting features that ar.e invariant to nuisance variables-and hence also to the associated extraneous effects-but that are still useful for classification or regression. The methodology is based on nonparametric deep-network models that perform automatic normalization of the data, and further enforce invariance via adversarial learning. We will apply the approach to an important problem in stroke rehabilitation, the quantitated dosing of motor training. Using a dataset of sensor-based motion data, we will train the model to identify and count functional movements in stroke patients performing rehabilitation activities. We expect to show that our approach can surmount patient variability to enable rigorous movement classification and quantitation. The proposed work is significant, because it will empower investigators to undertake the dosing trials critically needed in stroke rehabilitation. The proposed work is innovative, because it departs from traditional data preprocessing techniques by combining advanced data normalization and model calibration procedures. Our work is likely to have a positive impact on stroke rehabilitation by facilitating the research required to change clinical practice and improve stroke outcomes. Our quantitative approach is broadly generalizable to applications hindered by nuisance variables, such as medical diagnostics and genomics.

可穿戴电子设备，个人移动设备和传感器技术的进步正在为 许多有希望的医疗和生物医学研究应用。但是，结果数据集是 由于与与任务无关的无关效应引起的可变性，通常具有挑战性的过程 兴趣，例如环境条件的变化，测量噪声中的异质性或患者 特质。这些效果会在用于训练机器的数据之间产生系统的差异 - 学习算法及其在实践中应用的数据，从而损害了现实世界的性能。 拟议的研究将解决解决无关效应的基本问题 与已知的滋扰变量有关。我们将开发一种新的方法来提取特征 Ar.e对滋扰变量不变，因此也与相关的无关效应，但仍在 可用于分类或回归。该方法基于非参数深网模型 该数据对数据进行自动归一化，并通过对抗性学习进一步执行不变性。 我们将把方法应用于中风康复中的重要问题，电机定量剂量 训练。使用基于传感器的运动数据数据集，我们将训练该模型以识别和计数 进行康复活动的中风患者的功能运动。我们希望证明我们的 方法可以克服患者的变异性，以实现严格的运动分类和定量。这 拟议的工作很重要，因为它将授权调查人员进行严格的剂量试验 中风康复需要。拟议的工作具有创新性，因为它偏离了传统数据 通过结合高级数据归一化和模型校准程序，预处理技术。 我们的工作可能通过促进所需的研究对中风康复产生积极影响 改变临床实践并改善中风结果。我们的定量方法是可以广泛推广的 受滋扰变量（例如医学诊断和基因组学）阻碍的应用。