Confirmed date: 03/12 (Tues)
Where: Roam Insight
Speakers: Peter Li, Robyn Ball
Talks:
- Title: Leveraging language data in healthcare (by Robyn Ball)
Description: Many critical questions in healthcare can only be answered by combining structured and unstructured data. Language data is the most rich and high-valued data in healthcare, yet it often is underutilized due to the complexity of developing natural language models that can extract meaningful insights. I will provide a brief overview of using NLP in the healthcare, describe Roam's general framework, and provide datasets and other resources that can be used to jump-start research projects.
Duration: 20min
Bio:
Dr. Robyn Ball is a Clinical Data Scientist at Roam Analytics, where she leverages Roam’s data and machine learning assets to create analyses of patient pathways through disease and treatment progression. Dr. Ball earned her Ph.D. in Statistics from Texas A&M University. She has conducted biomedical research as a NASA fellow and as an intern at UT MD Anderson Cancer Center, developed novel computational methods for genomic data at The Jackson Laboratory in Bar Harbor, Maine, and was most recently a Senior Biostatistician at Stanford University where she collaborated with medical researchers on studies that posed methodological challenges.
- Title: Introduction to the 'cholera' package (by Peter Li)
John Snow's map of the 1854 cholera outbreak in London's Soho is a classic example of data visualization. For Snow, the map helped to support his two then contested, if not controversial claims: that cholera is a waterborne disease and that the water pump on Broad Street was the source of the outbreak.
To evaluate whether the map does or can actually supports such claims, I created the 'cholera' R package (CRAN and GitHub). The package allows you to explore, analyze and test the data embedded in the map. It does so by computing and plotting a pump's neighborhood: the set of locations defined their "proximity" to a pump.
The talk will focus on the tools and techniques used to compute and visualize these "pump neighborhoods" and will include examples (all in R) of everything from orthogonal projection to more specialized topics like Voronoi tessellation ('deldir'), spatial data analysis ('sp'), graph/network analysis ('igraph'), generic functions (e.g., S3 generic functions), and embarrassingly parallel problems ('parallel').
Duration: 60min
AGENDA (preliminary):
5:30pm - 6pm: Help with the setup (install R packages and anything else that is needed for the workshop)
6pm - 6:20pm: Networking
6:20pm - 6:45pm: Talk#1
6:45pm - 7:45pm: Talk#2
7:45pm - 8pm: Networking
(Maybe move the time to an hour later?)