Skip to Main Content

We have a new app!

Take the Access library with you wherever you go—easy access to books, videos, images, podcasts, personalized features, and more.

Download the Access App here: iOS and Android. Learn more here!

“In order to succeed, you have to look at everything from your own unique perspective. When you think, you have to think in your own creative way— not accepting everything that's already out there… . ”

-Jacob Barnett, 2012


  • Discuss the science of sight and its application to healthcare analytics.

  • Describe various methods of effective healthcare data visualization.

  • Discuss the introduction of infographics and Big Data technologies to healthcare.

  • Identify appropriate data sources for population management.

  • Discuss the various educational opportunities available to clinical informaticists to successfully deploy healthcare analytic solutions.


Healthcare analytics serves the clinical, quality, operational, and research needs of our organizations. The field of healthcare analytics is advancing exponentially due to new and emerging technologies; these exponential advances make it difficult for the clinical informaticist to stay current. This chapter surveys healthcare analytics, covering the following topics: data visualization, predictive analytics, and Big Data. The deepest dive is on the visualization of healthcare data, the importance of which cannot be overstated. We can build the best predictive algorithms, make important data discoveries, and build the most efficient decision-support systems—but if we do not visualize the data in a manner in which the viewer can immediately understand it, then we have failed.


Healthcare analytics can best be described as an evolutionary process. As technology evolves, so too must the clinical informaticist's role and skill set evolve. This also holds true for healthcare organizations. In most cases, this process is organic, but due to necessity, this process has been expedited in many healthcare organizations (Boicey, 2014). As shown in Figure 16.1, there are four stages to this evolution. To better help understand the stages, go through them by looking at the workflow of a department we are all familiar with: Quality.


Healthcare analytics evolution (Boicey, 2014).

The first stage is the use of spreadsheets to collect and analyze quality data. At this stage, quality data is accumulated in spreadsheets via manual abstraction of quality data from such sources as paper documentation, electronic health records (EHRs), and other healthcare systems. The folks in Quality spend 25 or so days on data collection and analysis and have little time to produce data visualizations in the form of reports that are then emailed, posted in SharePoint, or distributed at departmental meetings. After analysis of the quality data is complete, 30 days have passed, leaving very little time for quality improvement projects as the cycle now repeats itself.

In stage 2, we introduce a data visualization application to the spreadsheet. This one addition to the technology stack reaps many benefits. First, by using a data visualization application to build quality dashboards, we now have a means for members of the healthcare ...

Pop-up div Successfully Displayed

This div only appears when the trigger link is hovered over. Otherwise it is hidden from view.