During this workshop, experts in big data, health, and computer science will provide early-, mid-, and late-stage investigators, as well as graduate students, opportunities to:
1. Address knowledge gaps in understanding and utilizing NHLBI health datasets (e.g., BioData Catalyst)
2. Understand the value of collaborations between domain experts and computer scientists, engineers, and statisticians
3. Participate in a needs assessment to ensure diverse participation in HLBS data science
Presenters will:
* Discuss the role of datasets and data scientists using AI systems
* Give an overview of the “Big Data” that have been generated from NHLBI observational cohort studies, registries, and repositories (e.g., BioLINCC, GenTAC), as well as basic science studies at NHLBI
* Demonstrate use of novel data scientific methods and HLBS applications
* Provide guidance on becoming a NHLBI BioData Catalyst user, applying for cloud credits, and getting involved in the BioData Catalyst community
* Explore multiple aspects of machine learning
* Describe synthesis and interpretation of data across scales, including genome-wide searches (GWS)
* Illustrate the promise of NHLBI Data Science, using case studies as examples
* Explain the importance of diversity in STEM
* Explore future needs and directions of data science in heart, lung, blood, and sleep research