A Framework for Integrating Multiple Data Sources for Modeling and Forecasting of Infectious Diseases

描述（申请人提供）：我是一名训练有素的计算生物学家和统计学家，目前在哈佛医学院波士顿儿童医院博士后。我的主要职业目标是成为一家大型研究机构的独立研究员。我计划继续我目前在全球健康和传染病方面的研究。具体来说，我的目标是继续发展数学和计算方法建模，以了解疾病传播，预测未来的动态和评估公共政策决策的干预措施。作为一名博士后研究员，我有机会处理来自多个来源的数据。虽然这些数据流中有几个可以被标记为“大数据”，但我通常是在处理、过滤和汇总成每日或每周的分辨率后才使用这些数据。虽然我已经掌握了对这些已经处理过的数据进行建模的必要技能，但在三个重要领域，我需要额外的培训、指导和经验：(1)先进的计算技能，特别是在使用高性能计算和信息学工具方面；(2)数据采集和处理所需的计算机器学习和数据挖掘技术；(3)涉及大数据的研究统计设计所需的生物统计方法。这三个培训和指导目标将使我能够发展成为生物医学研究大数据科学独立研究者所需的技能。波士顿儿童学校和哈佛医学院在转化生物医学研究方面处于领先地位，因此它们是实现本提案中培训和研究目标的理想环境。近期中国出现H7N9禽流感等传染病，叙利亚再次出现脊髓灰质炎等疾病，凸显了加强传染病预防和控制免疫和应急反应规划的重要性。研究人员开发了计算和数学模型来捕捉传染病动态的决定因素，并确定支持这些动态预测的因素，提供疾病风险估计，并评估各种干预方案。虽然这些研究对了解传染病的传播和控制非常有用，但大多数研究都是针对特定疾病的，并且仅使用传统疾病监测系统的数据。相比之下，在过去十年中，有大量基于互联网的数据已被广泛评估和验证，用于公共卫生监测，但很少与其他数据源结合使用，用于建模预测疾病传播。利用这些新颖的基于事件的数字数据源，结合来自传统疾病监测系统的气候和病例数据，我们将建立一个急需的框架，将这些不同的数据源整合起来，用于建模，以估计疾病风险和预测传染病的时间动态。我们的方针将通过三个目标来实现。第一个目标是开发用于获取、处理和过滤建模数据的自动化过程（目标1）。一旦我们收集了这些数据，我们将开发时间模型，以动态评估各种数据变量与传染病发病率之间的关系（目标2）。最后，我们将评估在目标2下开发的建模方法在预测传染病的时间趋势方面的效用（目标3）。通过数据采集、彻底处理、统计和流行病学建模，并在具有生物医学信息学、计算机科学和统计学专业知识的顾问的指导下，我们计划实现一种综合方法，将多个数据流整合起来进行建模，以预测传染病。

DESCRIPTION (provided by applicant): I am trained as a computational biologist and statistician, and I am currently a postdoctoral fellow at Boston Children's Hospital, Harvard Medical School. My main career goal is to become an independent researcher at a major research institution. I plan to continue my current research pursuits in global health and infectious diseases. Specifically, I aim to continue developing mathematical and computational approaches for modeling to understand disease transmission, forecasting future dynamics and evaluating interventions for public policy decisions. As a postdoctoral research fellow, I have had the wonderful opportunity of working with data from multiple sources. Although several of these data streams could be labeled as "Big Data", I typically work with the data after it is already processed, filtered and aggregated to a daily or weekly resolution. While I have developed the necessary skills for modeling these already processed data, there are three important areas where I require additional training, mentoring, and experience: (1) advanced computational skills especially in the use of high performance computing and informatics tools, (2) techniques in computational machine learning and data mining necessary for data acquisition and processing, and (3) biostatistical methodology needed for the statistical design of studies involving big data. These three training and mentoring aims would enable me to develop the skills necessary to become an independent investigator in Big Data Science for biomedical research. Boston Children's School and Harvard Medical School are leading institutions in translational biomedical research, thereby making them the ideal environment to pursue the training and research aims in this proposal. The recent emergence of infectious diseases such as the avian influenza H7N9 in China, and re-emergence of diseases such as polio in Syria underscores the importance of strengthening immunization and emergency response programs for the prevention and control of infectious diseases. Researchers have developed computational and mathematical models to capture determinants of infectious disease dynamics and identify factors that support prediction of these dynamics, provide estimates of disease risk, and evaluate various intervention scenarios. While these studies have been extremely useful for the understanding of infectious disease transmission and control, most have been disease specific and solely used data from traditional disease surveillance systems. In contrast, there is a huge amount of internet-based data that have been extensively assessed and validated for public health surveillance in the last decade, but it has been scarcely used in conjunction with other data sources for modeling to predict disease spread. Using these novel digital event-based data sources in combination with climate and case data from traditional disease surveillance systems, we will establish a much needed framework for integrating these disparate data sources for modeling to estimate disease risk and forecasting temporal dynamics of infectious diseases. Our approach will be achieved through three aims. The first objective is to develop an automated process for acquiring, processing and filtering data for modeling (Aim 1). Once we gather this data, we will develop temporal models for the dynamical assessment of the relationship between the various data variables and infectious disease incidence (Aim 2). Finally, we will assess the utility of the modeling approaches developed under Aim 2 for forecasting temporal trends of infectious diseases (Aim 3). Through data acquisition, thorough processing, statistical and epidemiological modeling, and guided by advisers with expertise in biomedical informatics, computer science and statistics, we plan to achieve a comprehensive approach to integrating multiple data streams for modeling to forecast infectious diseases.