Enhancing Diversity through IHSAN (Interdisciplinary Health disparities and data Science trAiNing)

点击翻译按钮获取中文摘要

PROJECT SUMMARY/ABSTRACT To address the gap in expertise in data science in some RCMI U54 Centers, we propose developing a coordinated RCMI Data Science Initiative with two goals: (1) Upskilling RCMI investigators in data science, including tools, methods, and best practices with a focus on reproducible data analysis and effective knowledge mobilization around health disparities and (2) Incentivizing collaborations at the nexus of data science and health disparities between investigators within and outside of the RCMI consortium. Our specific aims are: 1. To enhance the data science capacity of RCMI investigators across the RCMI consortium by collaboratively developing a project-based curriculum and organizing workshops introducing data science fundamentals and tools as well as NIH-funded resources and datasets relevant to minority health disparities. Investigators will learn how to access data from the All of Us research workbench, link it to community-level datasets available on Google’s Cloud Platform, create visualizations, build and evaluate machine learning models, and upload replication files into a repository using R, SQL, and Git. 2. To stimulate data science collaborations across U54 centers as well as between U54 and non-RCMI institutions by organizing Data Science and Health Disparities Demo Days and launching Enrichment awards to support development of collaborative research projects. Our goal is to provide financial support to develop promising research collaborations into proposals for pilot funding. Our long term goal is to leverage existing partnerships with the Atlanta University Center (AUC) Data Science Initiative, the Georgia CTSA, and the National Research Mentoring Network (NRMN) to build a well-coordinated infrastructure to support collaboration between RCMI and non RCMI investigators, and train the next generation of diverse investigators leveraging advances in data science and machine learning to address minority health and health disparities in the 21st century.