Transforming Analytical Learning in the Era of Big Data

大数据时代的分析学习变革

• 批准号: 9888408
• 负责人: Jian Kang
• 金额: $ 25.1万
• 依托单位: UNIVERSITY OF MICHIGAN AT ANN ARBOR
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-03-15 至 2022-02-28
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9888408
• 关键词: Admission activity; Adverse drug effect; Advocate; Alzheimer' s Disease; Area; Arts; Award; Basic Science; Big Data; Big Data to Knowledge; Bioinformatics; Biological Markers; Biological Sciences; Biology; Biometry; Cardiovascular Diseases; Cardiovascular system; Case Study; Clinical; Clinical Sciences; Code; Collaborations; Collection; Computing Methodologies; Data; Data Science; Data Scientist; Data Set; Development; Diabetes Mellitus; Disease; Educational process of instructing; Educational workshop; Electronic Health Record; Engineering; Epidemiology; Epigenetic Process; Evaluation; Exposure to; Faculty; Female; Foundations; Funding; Funding Mechanisms; Generations; Genetic; Genomics; Goals; Grant; Health; Health Sciences; Human; Image; Influentials; Information Sciences; Injury; International; Kidney Diseases; Learning; Literature; Macular degeneration; Malignant Neoplasms; Medical; Medical Imaging; Medical Records; Medicine; Mentors; Methodology; Methods; Michigan; Minority Groups; Natural Language Processing; Neurosciences; Obesity; Oral; Participant; Prevention; Privatization; Problem Sets; Public Health Informatics; Public Health Schools; Research; Research Personnel; Research Project Grants; Resources; STEM program; Schools; Science; Science, Technology, Engineering and Mathematics; Scientist; Social Behavior; Social Sciences; Statistical Methods; Statistical Models; Structure; Student recruitment; Students; Talents; Techniques; Traction; Training; Underrepresented Minority; United States National Institutes of Health; Universities; Woman; Work; base; big-data science; burden of illness; cluster computing; college; computer science; data integration; data management; data mining; data visualization; design; experience; graduate school preparation; graduate student; heterogenous data; high dimensionality; instructor; interest; lectures; medical schools; member; metabolomics; nervous system disorder; network models; next generation; novel therapeutics; open source; personalized medicine; population health; posters; precision medicine; programs; recruit; signal processing; skills; statistical and machine learning; statistics; student training; success; summer institute; summer program; summer research; symposium; tool; undergraduate student; underrepresented minority student; wiki

PROJECT SUMMARY In this dawning era of `Big Data' it is vital to recruit and train the next generation of biomedical data scientists in `Big Data'. The collection of `Big Data' in the biomedical sciences is growing rapidly and has the potential to solve many of today's pressing medical needs including personalized medicine, eradication of disease, and curing cancer. Realizing the benefits of Big Data will require a new generation of leaders in (bio)statistical and computational methods who will be able to develop the approaches and tools necessary to unlock the information contained in large heterogeneous datasets. There is a great need for scientists trained in this specialized, highly heterogeneous, and interdisciplinary new field of health big data. Thus, the recruitment of talented undergraduates in science, technology, engineering and mathematics (STEM) programs is vital to our ability to tap into the potential that `Big Data' offers and the challenges that it presents. The University of Michigan Undergraduate Summer Institute: Transforming Analytical Learning in the Era of Big Data will primarily draw from the expertise and experience of faculty from three different departments within three different schools at the University of Michigan: Biostatistics in the School of Public Health, Computer Science in the School of Engineering, Statistics in the College of Literature, Sciences and the Arts. The faculty instructors and mentors have backgrounds in Statistics, Computer Science, Information Science, Medicine, Population Health, Social and Biological Sciences. They have active research programs in a broad spectrum of methodological areas including statistical modeling, data mining, natural language processing, statistical and machine learning, large-scale optimization, matrix computation, medical computing, health informatics, high- dimensional statistics, distributed computing, missing data, causal inference, data management and integration, signal processing and medical imaging. The diseases and conditions they study include obesity, diabetes, cardiovascular disease, cancer, neurological disease, kidney disease, injury, macular degeneration and Alzheimer's disease. The areas of biology include neuroscience, genetics, genomics, metabolomics, epigenetics and socio-behavioral science. Undergraduate trainees selected will have strong quantitative skills and a background in STEM. The summer institute will consist of a combination of coursework, to raise the skills and interests of the participants to a sufficient level to consider pursuing graduate studies in `Big Data' science, along with an in depth mentoring component that will allow the participants to research a specific topic/project utilizing `Big Data'. We have witnessed tremendous enthusiasm and success with the current summer program on Big Data led by this team with 164 students trained in the last 4 years (2015-2018) including 90 female students and 30 students from underrepresented minority groups. Fourteen of these participants from the last three years are currently graduate students in Michigan Biostatistics. The ongoing program has gained traction in the national landscape of summer research programs with 20% rate of admission and 80% rate of acceptance among those who are offered this opportunity. The program has consistently received very strong evaluation and our past alumni have become brand ambassadors and advocates for our program. We plan to build on the success and legacy of this program in the next three year funding cycle of this grant (2019-2021). The overarching goal of our summer institute in big data is to recruit and train the next generation of big data scientists using a non-traditional, action-based learning paradigm. This six week long summer institute will recruit a group of approximately 45 undergraduates nationally and internationally, with 20 domestic students supported by the requested SIBS funding mechanism and others supported by supplementary institutional and foundation support. We propose to expose the trainees to diverse techniques, skills and problems in the field of health Big Data. They will be taught and mentored by a team of interdisciplinary faculty, reflecting the shared intellectual landscape needed for Big Data research. They will engage in mentored research projects in three primary areas of health big data: Electronic Health Records/Medical Claims, Genomics and Imaging. Some of the projects will be defined in the area of cardiovascular precision medicine, defined by a team of highly quantitative researchers engaged in cardiovascular research that uses big data. At the conclusion of the program there will be a concluding capstone symposium showcasing the research of the students via poster and oral presentation. There will be lectures by U-M researchers, outside guests and a professional development workshop to prepare the students for graduate school. We propose an inter-SIBS collaboration with Dordt College summer program trainees who will attend this concluding symposium. The resources developed for the summer institute, including lectures, assignments, projects, template codes and datasets will be freely available through a wiki page so that this format can be replicated anywhere in the world. This democratic dissemination plan will lead to access of teaching and training material for undergraduate students in this new field across the world. We will offer multiple professional development opportunities and resources for graduate school preparation to our trainees so that they can reflect and plan beyond their senior year. All of our proposed activities are reflected through our three specific aims: Teaching, Mentoring and Dissemination.

项目总结 在这个大数据的曙光时代，招募和培训下一代生物医学数据科学家在 ‘大数据’。生物医学科学中的大数据收集正在迅速增长，并有可能解决 当今许多紧迫的医疗需求，包括个性化药物、根除疾病和治愈 癌症。实现大数据的好处将需要新一代(生物)统计和 谁将能够开发解锁信息所需的方法和工具的计算方法 包含在大型异类数据集中。非常需要在这方面受过专门训练的科学家。 异构性、跨学科的健康大数据新领域。因此，人才的招聘 科学、技术、工程和数学(STEM)课程的本科生对我们的能力至关重要 挖掘‘大数据’提供的潜力和它带来的挑战。 密歇根大学本科生暑期学院：转变分析学习的时代 大数据将主要借鉴来自以下三个不同部门的教师的专业知识和经验 密歇根大学三个不同的学院：公共卫生学院的生物统计学，计算机 工程学院理科，文学、科学和艺术学院统计学。教职员工 教师和导师具有统计学、计算机科学、信息科学、医学、 人口健康、社会科学和生物科学。他们在广泛的范围内有积极的研究计划 方法论领域包括统计建模、数据挖掘、自然语言处理、统计和 机器学习、大规模优化、矩阵计算、医疗计算、健康信息学、高科技 维度统计、分布式计算、缺失数据、因果推理、数据管理和集成、 信号处理和医学成像。他们研究的疾病和状况包括肥胖、糖尿病、 心血管疾病、癌症、神经疾病、肾脏疾病、损伤、黄斑变性和 阿尔茨海默氏症。生物学领域包括神经科学、遗传学、基因组学、代谢组学、表观遗传学。 和社会行为科学。被选中的本科生将具有很强的量化技能和 STEM背景。暑期研习班将由课程作业组成，以提高技能和 学员的兴趣达到足以考虑攻读“大数据”科学研究生课程的程度， 具有深入的指导组件，允许参与者利用 ‘大数据’。我们见证了当前Big上的暑期节目的巨大热情和成功 数据由该团队领导，在过去4年(2015-2018)培训了164名学生，其中包括90名女学生 以及30名来自少数族裔群体的学生。这些参与者中有14人来自过去三年 几年来都是密歇根生物统计学专业的研究生。正在进行的计划在 20%录取率和80%录取率的暑期研究项目国家景观 在那些被提供这个机会的人中。该计划一直受到非常强烈的评价 我们过去的校友已经成为我们项目的品牌大使和倡导者。我们计划在 在这笔赠款的下一个三年资金周期(2019-2021年)中，这一方案的成功和遗产。 我们大数据暑期学院的总体目标是招聘和培训下一代大数据 数据科学家使用非传统的、基于行动的学习范式。这个长达六周的夏天 学院将在国内外招收约45名本科生，其中20名来自国内 由申请的SIBS资助机制支持的学生和由补充资金支持的其他学生 制度支撑和基础支撑。我们建议让受训人员接触到不同的技术、技能和 健康大数据领域的问题。他们将由一个跨学科的教职员工团队授课和指导， 反映了大数据研究所需的共享知识格局。他们将从事有指导的研究 健康大数据的三个主要领域的项目：电子健康记录/医疗索赔、基因组学和 成像。其中一些项目将在心血管精确医学领域定义，该领域由一个 一组高度量化的研究人员从事使用大数据的心血管研究。在结束时 在项目的最后，将有一个顶峰研讨会，展示学生的研究通过 海报和口头演示。届时将有密歇根大学研究人员、外部嘉宾和一位专业人士的演讲 开发工作坊，为学生进入研究生院做准备。我们建议在SIBS之间进行协作 将参加本次总结研讨会的多德学院暑期项目实习生。资源 为暑期学院开发的课程，包括讲座、作业、项目、模板代码和数据集 可以通过维基页面免费获得，这样这种格式就可以复制到世界任何地方。这 民主传播计划将导致本科生获得教学和培训材料 在世界各地的这一新领域。我们将提供多元化的职业发展机会和资源。 为我们的实习生提供研究生院准备，以便他们能够反思和规划他们大四之后的计划。所有的 我们提议的活动通过我们的三个具体目标反映出来：教学、指导和传播。