Scalable competing risks analysis & Monitoring patient enrollment using Shiny

This is a past event

36 people went

Location image of event venue


Talk 1: A Scalable Regression Estimation Procedure for Competing Risks Data
Speaker: Eric Kawaguchi (Doctoral candidate in biostatistics at UCLA)

Advancements in areas such as medical informatics tools and high-throughput biological experimentation are making large-scale biomedical data routinely accessible to researchers. Competing risks data is typical in biomedical studies where individuals are prone to more than one cause (type of event) which can preclude the others from happening. The Fine-Gray model is a popular approach to model competing risks data and is currently implemented in a number of statistical software packages. Current estimation procedures are not computationally scalable for large-scale data. We develop a novel technique to estimate the parameters of the Fine-Gray model by exploiting the cumulative structure of the risk set for each subject. A two-way linear scan approach allows us to perform parameter estimation in linear (super linear) time, considerably reducing the runtime for optimization. Extensive numerical studies compare the speed and scalability of our implementation to currently available methods for unpenalized and penalized Fine-Gray regression.

Talk 2: Building a Patient Enrollment Monitoring System with the shinydashboard and/or flexdashboard Package
Speaker: Yujie Cui (Data Analyst at Terasaki Research Institute)

Patient enrollment is a critical step of successful randomized controlled trials. We developed a dashboard system using R flexdashboard and/or shinydashboard package to assist with the monitoring of multi-site patient enrollment, visualizations, and comparisons of patient characteristics, and projection of enrollment end date, etc. These dashboards can be interactive, highly customizable, easy to implement and inexpensive to host. These dashboards can also be print-friendly with some components downloadable in formats such as CSV/ pdf. The code structure of these dashboards can be shared among different projects with high reproducibility.

6:30: Socializing
7:00-8:00: Talks
8:00: Socializing

Room 115/116
2001 N. Soto St.
Los Angeles, CA 90032

Invite yourself to our Slack group:
Ask us any questions by email: [masked]
Find our previous talks on GitHub:
Follow us on Twitter: @laeRusers
Check out more events: