Preparing the Next Generation of Biostatisticians in the Era of Data and Translational Sciences

PROJECT SUMMARY/ABSTRACT In the era of newly emerging computational tools for data science, biostatisticians need to play a fundamental role in health sciences research. There is an urgent need to encourage US Citizens and Permanent Residents to pursue graduate training in biostatistics. The design, conduct, and analysis of clinical trials and observational studies; the setting of regulatory policy; and the conception of laboratory experiments have been shaped by the fundamental contributions of biostatisticians for decades. Advances in genomics, medical imaging technologies, and computational biology; the increasing emphasis on precision and evidence-based medicine; and the widespread adoption of electronic health records; demand the skills of biostatisticians trained to collaborate effectively in a multidisciplinary environment and to develop statistical and machine learning methods to address the challenges presented by this data-rich revolutionary era of health sciences research. The proposed summer program which includes world-renowned clinical scientists and biostatisticians from two local universities, will provide an immense opportunity for student participants to learn basic yet modern statistical methods that are critical to uncovering new insights from such big and complex biomedical data and also illustrate the potential pitfalls of confounding and bias that may arise when analyzing biomedical data. A unique feature of the proposed training program is thus to expose the participants to not only basic statistical methods but also to the topics of computer science and bioinformatics which will be invaluable in creating the multidisciplinary teams required to tackle the complex research questions that often requires multipronged approaches. The proposed six-week training program will be structured around the NIH's Translation Science Spectrum and will introduce participants to opportunities in biostatistics through the lens of the science advanced by the contributions of biostatisticians. Following an initial set of weeks on basic training of biostatistical methods, the program will culminate in a data hack-a-thon style competition in which participants will employ the statistical and scientific knowledge gained during the program to produce the most innovative, statistically-sound, scientifically-relevant and effectively-communicated response to a set of research questions. The proposed research education program will enroll up to 20 such participants from across the nation and, through lectures, field trips, and opportunities to analyze data from real health sciences, inspire them to pursue graduate training. The program will draw upon considerable past collaborations and complementary resources of two local world-renowned universities to provide participants with an unparalleled view of the field, including award-winning instructors, internationally known methodological and clinical researchers, and a local area rich in opportunities to showcase careers in biostatistics. Special efforts will be made to enroll participants from underrepresented groups. Participants will be followed after completion, and the numbers attending graduate school in statistics and pursuing biostatistics careers will be documented.