Workshop on Data Science, Learning, and Applications to Biomedical and Health Sciences

该提案要求与纽约科学院共同举办数据科学、学习和应用于生物医学和健康科学的研讨会。这次会议将汇集来自计算机科学、卫生和医学研究领域的专家。卫生研究和医疗保健在扩大可用的电子数据方面经历了十年的演变。其中值得注意的领域包括电子健康记录的数字化，制药公司将研发数据聚合到数据库中，联邦政府出于研究目的发布数十年存储的患者数据，以及患者自我跟踪的开始。总而言之，这些前所未有的数据量、种类和速度的增长统称为大数据，提供了一个独特的机会来获得洞察力、获取知识和促进发现，从而改善患者结果、降低成本和加速生物医学进步。然而，有效地处理这些海量信息并使调查人员能够提高其效用将需要多学科的方法。必须在联合研究项目中应用多种能力，以开发相关问题，设计解决这些问题的方法，并开发可传播给整个科学界的工具，以培训未来的研究人员使用大数据。这次研讨会的范围将涉及以下主题：神经科学和癌症，以及使用来自多个来源的数据的心血管疾病。研讨会预计将对大数据和健康领域产生重大影响。研讨会的重点是制定该领域的大数据研究议程，并使从事技术开发、部署和使用的学术界、工业界和政府的科学家、临床医生和研究人员之间能够建立联系和协作。具体地说，研讨会将为这些研究人员提供一个论坛，评估大数据和健康领域的最新研究，并确定相关挑战。讲习班的成果可能包括与会者将确定的新的研究方向，这些方向将通过出版物和讲习班网站向研究界公布。预计成果发布将为卫生研究社区、跨学科合作、教育活动中的大数据提供信息和激励，并刺激其他创新研究方向。如上所述，会议的更广泛影响是促进该领域的进展，并刺激对话、联系和合作，从而在卫生研究中更知情和更有效地产生和使用大数据。

This proposal requests funds to hold the Workshop on Data Science, Learning, and Applications to Biomedical and Health Sciences with the New York Academy of Sciences. The meeting will bring together experts from the areas of computer science, health and medical research. Health research and healthcare have undergone a decade of evolution in the expansion of available electronic data. Notable among these areas are the digitization of electronic health records, the aggregation of research and development data into databases by pharmaceutical companies and the release of decades of stored patient data by the federal government for research purposes and the onset of patient-self tracking. Together, these unprecedented increases in data volume, variety, and velocity, collectively termed 'Big Data', present a unique opportunity to gain insights, derive knowledge and foster discovery that will result in improved patient outcomes, reduced costs and accelerated biomedical advances. However, effectively dealing with this massive information and enabling investigators to enhance its utility will require a multidisciplinary approach. Multiple capabilities must be applied in joint research programs to develop relevant questions, to design approaches to address those questions and to develop tools that can be disseminated to the entire scientific community to train tomorrow's researchers in working with big data. The scope of this workshop will span the following themes: neuroscience and cancer, and cardiovascular disease using data from multiple sources.The workshop is expected to have a significant impact the area of big data and health. The focus of the workshop is develop a big data research agenda for this area and enable connections and collaborations among scientists from academia, industry, and government, clinicians and investigators engaged in technology development, deployment, and use. Specifically, the workshop will provide a forum for these investigators to assess the state-of-the-art research in big data and health and identify related challenges. The workshop results are likely to include new research directions that will be identified by the participants will be publicized to the research community through publications and a workshop website. The results dissemination is expected to inform and motivate the big data in health research community, interdisciplinary collaboration, educational activities, and spur other innovative research directions. As noted above, the broader impacts of the meeting are to facilitate progress in the field and stimulate conversations, connections, and collaborations that will lead toward better informed and effective generation and use of big data in health research.