R in healthcare: ensuring data quality and conducting survival analyses

Location image of event venue


***IMPORTANT NOTE: Flatiron health has a strict building security policy, and you will be required to show your ID card at the door. If your meetup name does not match the first and last name on your ID card, please UPDATE your meetup name to match your ID card OR send an email with your ID name and your meetup account name to [masked] before 5 PM on Wednesday, November 13! If we don't get your official name on the list before Wednesday, you may not be able to enter the building, even if your registration is confirmed. ***

Tonight’s Meetup features a triple-hitter of talks on R in medicine, biostats and health tech. Each speaker will talk for roughly 20 minutes about the topics below, before and after a half hour of socializing and snacks at Flatiron Health. Please RSVP before Wednesday, Nov 13.

Jacqueline Gutman, Data Scientist, Flatiron Health
Jessica Streeter, Data Scientist, Spring Health
Sam Adhikari, Assistant Professor, Biostatistics, NYU School of Medicine

6:00-6:25 pm Introductions and Social Time
6:30-6:35 pm R-Ladies New York Announcements
6:40-7:00 pm Simplified Data Quality Monitoring of Dynamic Longitudinal Data
7:05-7:25 pm Survival analysis for everyone!
7:30-7:50 pm Hierarchical Models for Survival Analysis with Spatial Risk Factors in R
7:55-8:00 pm Community Announcements
8:00-8:30 pm Networking

Talk 1: Simplified Data Quality Monitoring of Dynamic Longitudinal Data
Ensuring the quality of data we deliver to customers or provide as inputs to models is often one of the most under-appreciated and yet time-consuming responsibilities of a modern data scientist. When we have access to dynamic, longitudinal, continuously updating data, that complexity can become an asset. We will demonstrate how to to simplify data quality monitoring of dynamic data with a functional programming approach that enables early and actionable detection of data quality concerns. Using `purrr` as well as `tidyr` and nested tibbles, we will illustrate the five key pillars of enjoyable, user-friendly data quality monitoring with relevant R code: Readability, Reproducibility, Efficiency, Robustness, and Compositionality.

Speaker 1: Jacqueline Gutman is a data scientist on the Quantitative Sciences team at Flatiron Health, supporting cancer research and improving patient care by working with electronic health record data and building accessible data science tools for reproducible research.

Talk 2: Survival analysis for everyone!
When people initially think of survival analysis, they usually think of terminal diseases and mortality. But it had much broader applications in the medical field. I'll be giving a brief overview of survival analysis, it's applications in a behavioral health managed care setting, and some tips on communicating these results to clinical teams.

Speaker 2: Jessica Streeter is a Data Scientist at Spring Health, and a medical sociologist turned data scientist. She has spent her career working in the behavioral health space, including in direct care at an inpatient psychiatrist hospital.

Talk 3: Hierarchical Models for Survival Analysis with Spatial Risk Factors in R
Observations within a community are more likely to be correlated than those from different communities. Hierarchical models with random effects are often built to account for such correlation. In this talk, I will focus on spatial hierarchical models in the context of survival data. I will review survival model with random frailties, to account for clustering within a community, and its extension to account for autocorrelation between frailties of neighboring communities.

Speaker 3: Sam Adhikari an assistant professor of Biostatistics in the Department of Population Health, NYU School of Medicine. Her research interest lies in developing and implementing statistical and machine learning tools to solve problems motivated by real world applications in medicine, global health and education.