QuBBD: Deep Poisson Methods for Biomedical Time-to-Event and Longitude Data

QuBBD：生物医学事件时间和经度数据的深度泊松方法

• 批准号: 9392642
• 负责人: Lawrence Carin
• 金额: $ 26.22万
• 依托单位: DUKE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-08-01 至 2020-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9392642
• 关键词: Address; Adoption; Advanced Development; Algorithms; Architecture; Big Data; Big Data to Knowledge; Blood Glucose; Blood Pressure; Categories; Characteristics; Clinical; Clinical Data; Clinical Research; Comorbidity; Computer software; Data; Data Sources; Development; Electronic Health Record; Event; Factor Analysis; Formulation; Funding; Gaussian model; Genetic; Gray unit of radiation dose; Hazard Models; Health system; Individual; Learning; Link; Lipids; Machine Learning; Medical Genetics; Medical History; Metabolic; Methodology; Methods; Mission; Modality; Modeling; Noise; Outcome; Performance; Persons; Pharmacology; Principal Investigator; Publications; Recommendation; Research; Research Personnel; Risk; Risk Factors; Risk stratification; Specific qualifier value; Structure; Techniques; Time; Translating; Translations; United States National Institutes of Health; Work; analog; cardiovascular disorder epidemiology; data access; data modeling; database of Genotypes and Phenotypes; genetic information; hazard; insight; learning strategy; novel; patient stratification; practical application; precision medicine; predictive modeling; prognostic; repository; response; semiparametric; temporal measurement; time use; tool; treatment response

The proposed research directly addresses the mission of NIH's BD2K initiative by developing appropriate tools to derive novel insights from available Big Data and by adapting sophisticated machine learning methodology to a framework familiar to biomedical researchers. This new methodology will be one of the first to enable use of machine learning techniques with time-to-event and continuous longitudinal outcome data, and will be the first such extension of the deep Poisson model. In essence, this undertaking builds the missing bridge between the need for advanced prognostic and predictive techniques among biomedical and clinical researchers and the unrealized potential of deep learning methods in the context of biomedical data collected longitudinally. To facilitate smooth adoption in clinical research, the results will be translated into terms familiar to applied practitioners through publications and well-described software packages. The application of the methodology developed will be illustrated using data from the NIH dbGAP repository, thereby further promoting the use of open access data sources.

拟议的研究直接解决了NIH BD2K计划的使命，方法是开发适当的工具，从可用的大数据中获得新的见解，并将复杂的机器学习方法应用于生物医学研究人员熟悉的框架。这种新的方法将是第一个能够使用机器学习技术与事件发生时间和连续纵向结果数据的方法之一，也将是深度泊松模型的第一个扩展。从本质上讲，这项工作在生物医学和临床研究人员对高级预后和预测技术的需求与纵向收集的生物医学数据背景下深度学习方法未实现的潜力之间建立了缺失的桥梁。为了促进临床研究的顺利采用，将通过出版物和描述良好的软件包将结果翻译为应用从业人员熟悉的术语。将使用NIH dbGAP存储库中的数据说明所开发方法的应用，从而进一步促进开放获取数据源的使用。