Big Data Health Science Scholar Program for Infectious Diseases

摘要 今天，以前收集的临界量的关联医疗保健数据现在可以用于 优化患者的健康结果。存在于这种健康中的信息、洞察力和智慧 使用大数据科学(BDS)可以高效地解锁护理数据。随着人们的年龄和生活 更长时间内，增加的护理需求将是双重的，一是针对那些患有更多合并症的人， 第二，新冠肺炎等新传染病带来的新风险。 新冠肺炎战略规划突出了对高质量科学技术的迫切和重要需求 研究以提高关于疾病传播、监测及其影响的知识 健康结果，并制定生物医学和公共卫生措施以减轻疾病 和死亡。存在着几个海量的、信息丰富的大数据流 医疗保健(例如，电子健康记录[EHR]、移动技术、可穿戴设备、 基因组数据、地理空间数据等)以及在信息和计算方面的进展 技术(例如，机器学习和人工智能)现在提供了一种极好的动手能力 将创新的大数据科学(BDS)研究应用于传染病的培训机会 艾滋病毒/艾滋病和新冠肺炎等疾病。培育一条蒸蒸日上、才华横溢的Next管道 对于新一代科学家来说，及早接触现有学生并提供新的和 创新的培训机会，激发人们对生物医学、社交和行为的兴趣， 和临床科学。因此，我们建议提供为期10周的短期暑期研究 名为《传染病大数据健康科学学者计划》的培训计划 面向物理和/或数量科学的博士前学生(理工系 生物医学工程、综合信息技术、化学/生物化学、 数学、统计学等)来自南卡罗来纳州(SC)和美国(US)。 完成此次培训的博士前学员将通过动手进行体验式学习-- 关于艾滋病毒/艾滋病和新冠肺炎等传染病领域的研究，这两个领域都与 NIAID任务。选定的博士前学生将与以下项目的教师导师配对 一对一指导的杰出参与教职员工队伍。学员将被挑选出来 通过基于他们提出的夏季研究计划和目标的竞争性过程 经验。具体地说，我们计划从物理和定量两个方面招收8名博士前学生 每年在全美范围内(在整个资助期内共有40个科学项目)参与 为期10周的暑期强化训练计划，目标如下： 目标1：为合格博士前打造暑期大数据科学培训管道 通过让学生参加相关课程/培训，以提高他们的能力 BDS在传染病研究中的应用。 目标2：让受训者参与使用艾滋病毒和新冠肺炎数据的动手研究。 目标3：为学员提供丰富的BDS研究和研究指导经验 专业发展至少一年(包括暑期)。拟议中的培训 该计划将在南加州大学大数据健康现有基础设施的支持下实施 中心(BDHSC)。BDHSC是南加州大学卓越倡议之一，促进和支持 南加州大学和整个南加州大学通过能力发展进行的大数据健康科学研究， 学术培训、专业发展、社区参与和方法 进步。BDHSC包含5个内容核心(电子病历、地理空间、基因组、社交媒体和 生物纳米材料)和两个支持中心(商业/创业和技术) 来自南加州大学10所学院/学院的43名教职员工参与。在完成建议的 培训，每位学员应：1)完成12小时的学术培训；2)获得 BDS在NIAID资助的研究数据库上的实际工作经验；以及3)在 至少一份BDS关于艾滋病或新冠肺炎的手稿，与他们的项目部导师一起。培训 该计划将促进研究环境，以鼓励不同的申请者，包括 从代表性不足的群体，到进一步在艾滋病毒领域进行大数据健康科学研究， 新冠肺炎和其他NIAID重点领域。

Abstract Today, a critical mass of previously collected linked health care data is now available for optimizing patient health outcomes. Information, insights, and intelligence existing in such health care data can be unlocked efficiently using Big Data Science (BDS).As people age and live longer, increased demand for care will be two-fold, one for those living with more comorbidities, and second the emergent risks from new infectious diseases like COVID-19.The recent NIAID strategic plan for COVID-19 highlights the urgent and important need for high-quality scientific research to improve knowledge around disease transmission, surveillance, and its impact on health outcomes, and to develop both biomedical and public health measures to mitigate illness and death. The existence of several massive, and information rich big data streams in healthcare (e.g., electronic health records [EHR], mobile technologies, wearable devices, genomic data, geospatial data etc.) and the advances in information and computational technologies (e.g., machine learning and artificial intelligence) now offer an excellent hands-on training opportunity for applying innovative Big Data science (BDS) research to infectious diseases such as HIV/AIDS and COVID-19. To cultivate a thriving and talented pipeline of next generation scientists, it is essential to engage current students early and provide new and innovative training opportunities to generate interest in the biomedical, social, and behavioral, and clinical sciences. Therefore, we propose offering a 10-week Short-Term Summer Research Training Program titled “Big Data Health Science Scholar Program for Infectious Diseases” targeted towards predoctoral students in physical and/or quantitative sciences (departments of biomedical engineering, integrated information technology, chemistry/biochemistry, mathematics, statistics etc.) from across South Carolina (SC) and the United States (US). Predoctoral students completing this training will engage in experiential learning through hands- on research in infectious disease areas like HIV/AIDS, and COVID-19, both relevant to the NIAID mission. Selected predoctoral students will be paired with Program Faculty mentors from a pool of distinguished participating faculty for one-on-one mentoring. Trainees will be chosen through a competitive process based on their proposed research plan and goals for the summer experience. Specifically, we plan to recruit 8 predoctoral students from physical and quantitative sciences across the US per year (a total of 40 over the entire funding period) to participate in the 10-week summer intensive training program with the following objectives: Objective 1: Create a summer big data science training pipeline for qualified predoctoral students by exposing them to relevant courses/training for competency development in the application of BDS to infectious disease research. Objective 2: Engage trainees in hands-on research using HIV and COVID-19 data. Objective 3: Provide trainees with rich research mentoring experience in BDS research and professional development for at least one year (summer included). The proposed training program will be implemented with support of the existing infrastructure of USC's Big Data Health Center (BDHSC). The BDHSC, one of the USC's Excellence initiatives, promotes and supports Big Data health science research at USC and across SC through capacity development, academic training, professional development, community engagement, and methodological advancement. BDHSC contains 5 content cores (EHR, geospatial, genomic, social media, and bio-nanomaterial) and two supporting hubs (business/entrepreneurship and technology) with the involvement of 43 faculty from 10 USC college/schools. Upon the completion of the proposed training, each trainee is expected to: 1) complete 12 hours of academic training; 2) obtain hands-on BDS experience working on NIAID-funded research databases; and 3) develop at least one BDS manuscript on HIV or COVID-19 with their Program Faculty mentor. The training program will foster the research environment to encourage diverse applicants, including those from underrepresented groups, to pursue further Big Data health science research in HIV, COVID-19 and other NIAID focus areas.