Four faculty will be part of a virtual 8-week series sponsored by Duke + DataScience (+DS) on data science methods with direct applications for the COVID-19 pandemic.
David Carlson, PhD, will present on “Natural Language Processing and understanding the evolving COVID literature” on July 7th. There has been an explosion of scientific literature on COVID-19 in the past several months with thousands of articles already available. To make sense of this quickly evolving literature, people have turned to data science and natural language processing tools to process the vast literature and find the most relevant articles. Dr. Carlson will go through the basics of natural language processing, introduce the algorithmic foundation of these tools, and discuss how the same toolkit could be applied in diverse scenarios.
The following week, Ricardo Henao, PhD, will address “Molecular methodology connected to COVID data.” Molecular analysis of gene expression, microbiome, and proteomics data attempts to understand biological processes by leveraging high-throughput technologies and data science. This form of analysis is particularly important to study how changes in high-throughput molecular measurements can be linked to health and disease mechanisms that could lead to new diagnostic tools and therapeutics. In the context of COVID-19, we want to understand how the host response quantified via molecular measurements is associated with disease characteristics such as symptoms and severity. The discussion will detail the characteristics of the molecular data generated by some of these technologies and the fundamental processing and statistical analysis tools that can be used to generate knowledge from these complex, high-dimensional data. The use cases will be framed around the COVID-19 molecular analysis work being done at Duke and other institutions.
Ben Goldstein, PhD, will speak on “Using data science to optimize scheduling elective procedures in the time of COVID on August 4th. The COVID-19 pandemic delayed elective surgeries as health care organizations properly focused on the wave of patients. As regions emerge from the crisis, there will be a dramatic surge in demand for elective procedures; a data-driven approach will be needed to prioritize this demand for addressing it quickly and efficiently.
On August 18th, the final seminar will be conducted by Jessilyn Dunn, PhD, on “the opportunity for wearables for early COVID detection.” Data from a wearable devices may reveal Covid-19 symptoms days before the user even notices or feels that that they are sick. If Fitbits, Apple Watches and other wearables can serve as an early-warning system, it could allow communities and workplaces to reopen faster and with more confidence. Wearables might evolve from being tech toys into health essentials.
+DataScience (+DS) is a Duke-wide program, operating in partnership with departments, schools, and institutes to enable faculty, students, and staff to employ data science at a level tailored to their needs, level of expertise, and interests. +DS provides online (digital) and in-person training modules and learning experiences grounded in generalizable data science content, while partnering with individual units or groups to develop additional specialized content. In this way, Duke’s data science activities will be developed collaboratively, synergistically, and strategically.