Core B: Biostatistics Core

核心 B：生物统计学核心

• 批准号: 10374816
• 负责人: XIHONG LIN
• 金额: $ 25.91万
• 依托单位: BAYLOR COLLEGE OF MEDICINE
• 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 2023-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10374816
• 关键词: Address; Bioinformatics; Biometry; Biostatistics Core; Cancer Etiology; Case Study; Computer software; Computing Methodologies; Core Facility; Data; Development; Education; Electronic Mail; Ensure; Environment; Equilibrium; Faculty; Genetic; Genetic Markers; Genetic Predisposition to Disease; Genetic study; Genomics; Goals; Image; Individual; Informatics; Infrastructure; Institutes; Internet; Leadership; Malignant neoplasm of lung; Methodology; Methods; Mission; Modeling; Paper; Play; Public Health Schools; Research; Research Methodology; Research Personnel; Resources; Risk Assessment; Risk Factors; Role; Services; Statistical Data Interpretation; Statistical Methods; Students; Technology Transfer; Time; Training; Training and Education; Translating; Universities; Work; X-Ray Computed Tomography; biomedical data science; cancer risk; data integration; design; experience; interest; lung cancer screening; machine learning method; member; novel; programs; risk prediction; risk prediction model; sound; statistical and machine learning; statistical learning; student training; success; symposium

The overarching goal of the Biostatistics and Informatics Core is to provide statistical, informatic and computational support for the Program Project to conduct advanced and large-scale statistical analyses to identify and characterize the accuracy of risk factors in predicting and screening lung cancer. The Core faculty and other researchers engage in mission-related research motivated by questions and methodological challenges that arise from these projects. The members of this Core have extensive expertise and interests that unite their activities among Projects. By forming a Biostatistics and Informatics Core that functions across projects, we anticipate a more robust and profound level of support for Program research than could be achieved if biostatisticians were nested within each project. The Core allows us to pool resources (e.g. expertise in statistical genetics, statistical and machine learning) across projects and also draw on the broader resources available in multiple participating institutes, such as the Department of Biostatistics at Harvard TH Chan School of Public Health and the Department of Biomedical Data Science at Dartmouth University. The members of the Core have extensive experience in the development and application of new statistical and machine learning methods for the study of genetic susceptibility to cancer risk prediction, and risk assessment. They have worked together over years on studies relating to lung cancer development. The Core provides an environment for coordinating and planning of research across the program projects and to develop and apply state-of-the-art statistical and machine learning methods that meet the needs of this Program Project. To support the Program projects, we propose the following aims: (1) To ensure that all Projects are grounded in sound biostatistical and informatic principles and use state-of-the-art methods for design and analysis; (2) To provide expert advice related to design and analysis in statistical genetics, bioinformatics, and machine learning and statistical learning for all Projects; (3) To conduct mission-related statistical methods research by developing novel statistical methods to address the quantitative needs of the Program Project; (4) To disseminate the proposed statistical methodological developments via expository articles, case studies, and web-shared software; (5) To provide education and training for researchers and students by working with the Steering Committee and the Program investigators. The Core members will coordinate their work activities and effectively support the Program Project by having monthly conference calls and regular email exchanges.

生物统计和信息学核心的总体目标是提供统计、信息和 为该计划项目提供计算支持，以进行高级和大规模的统计分析 识别和表征预测和筛查肺癌的危险因素的准确性。核心师资队伍 和其他研究人员在问题和方法论的推动下从事与任务相关的研究 这些项目带来的挑战。该核心成员拥有广泛的专业知识和兴趣 将他们的活动统一到项目中。通过形成一个跨领域发挥作用的生物统计学和信息学核心 项目，我们预计对计划研究的支持将比现有的更加有力和深入。 如果生物统计学家嵌套在每个项目中就可以实现。核心允许我们汇集资源（例如 统计遗传学、统计和机器学习方面的专业知识）跨项目，并利用更广泛的知识 多个参与机构提供的资源，例如哈佛大学生物统计系 达特茅斯大学陈公共卫生学院和生物医学数据科学系。这 核心成员在新统计方法的开发和应用方面拥有丰富的经验 机器学习方法用于研究癌症风险预测和风险评估的遗传易感性。 他们多年来一直合作研究与肺癌发展相关的研究。核心提供了一个 协调和规划整个计划项目的研究以及开发和应用的环境 满足该计划项目需求的最先进的统计和机器学习方法。到 为了支持该计划项目，我们提出以下目标： (1) 确保所有项目都立足于 健全的生物统计学和信息学原理，并使用最先进的方法进行设计和分析； (2) 至 提供与统计遗传学、生物信息学和机器设计和分析相关的专家建议 所有项目的学习和统计学习； (3) 开展与任务相关的统计方法研究 开发新的统计方法来满足该计划项目的定量需求； (4) 至 通过说明性文章、案例研究和传播拟议的统计方法发展 网络共享软件； (5) 与研究人员和学生合作，为研究人员和学生提供教育和培训 指导委员会和计划调查员。核心成员将协调他们的工作活动并 通过每月举行电话会议和定期电子邮件交流来有效支持计划项目。