Introducing the healthvis R package – one line D3 graphics with R

April 2, 2013
By

(This article was first published on Simply Statistics » R, and kindly contributed to R-bloggers)

We have been a little slow on the posting for the last couple of months here at Simply Stats. That’s bad news for the blog, but good news for our research programs!

Today I’m announcing the new healthvis R package that is being developed by my student Prasad Patil (who needs a website like yesterday), Hector Corrada Bravo, and myself*. The basic idea is that I have loved D3 interactive graphics for a while. But they are hard to create from scratch, since they require knowledge of both Javascript and the D3 library.

Even with those skills, it can take a while to develop a new graphic. On the other hand, I know a lot about R and am often analyzing biomedical data where interactive graphics could be hugely useful. There are a couple of really useful tools for creating interactive graphics in R, most notably Shiny, which is awesome. But these tools still require a bit of development to get right and are designed for “stand alone” tools.

So we created an R package that builds specific graphs that come up commonly in the analysis of health data like survival curves, heatmaps, and icon arrays. For example, here is how you make an interactive survival plot comparing treated to untreated individuals with healthvis:


# Load libraries

library(healthvis)
library(survival)

# Run a cox proportional hazards regression

cobj <- coxph(Surv(time, status)~trt+age+celltype+prior, data=veteran)

# Plot using healthvis - one line!

survivalVis(cobj, data=veteran, plot.title="Veteran Survival Data", group="trt", group.names=c("Treatment", "No Treatment"), line.col=c("#E495A5","#39BEB1"))

The “survivalVis” command above  produces an interactive graphic like this. Here it is embedded (you may have to scroll to see the dropdowns on the right - we are working on resizing)

The advantage of this approach is that you can make common graphics interactive without a lot of development time. Here are some other unique features:

We have started a blog over at healthvis.org where we will be talking about the tricks we learn while developing D3 graphics, updates to the healthvis package, and generally talking about visualization for new technologies like those developed by the CCNE and individualized health. If you are interested in getting involved as a developer, user or tester, drop us a line and let us know. In the meantime, happy visualizing!

* This project is supported by the JHU CCNE (U54CA151838) and the Johns Hopkins inHealth initiative.

To leave a comment for the author, please follow the link and comment on his blog: Simply Statistics » R.

R-bloggers.com offers daily e-mail updates about R news and tutorials on topics such as: visualization (ggplot2, Boxplots, maps, animation), programming (RStudio, Sweave, LaTeX, SQL, Eclipse, git, hadoop, Web Scraping) statistics (regression, PCA, time series, trading) and more...



If you got this far, why not subscribe for updates from the site? Choose your flavor: e-mail, twitter, RSS, or facebook...

Comments are closed.