Penn Medicine's analytics efforts are highlighting how big data can save lives, according to an article at Health Data Management.
For instance, clinical studies have shown that every hour a patient goes undiagnosed increases the mortality rate by more than 7 percent. Penn uses an algorithm to detect when a patient is slipping into severe sepsis by analyzing six vital sign measurements and lab values. It credits its early warning system with a 4 percent reduction in sepsis mortality rates.
Another algorithm helps detect 20 percent more patients who are trending toward cardiac failure, and has identified patients that are five times more likely to be readmitted after heart failure.
It uses a trove of data with Penn Signals, an open source platform that provides the tools for building predictive applications. At its base is a clinical data warehouse that holds records on 3 million patients going back 10 years. It's focused on building predictive models based on that historical data and then positioning those models to use real-time data, according to Corey Chivers, a data scientist at Penn Medicine who is one of the leads on the project.
The organization now finds the volume, velocity and variety of data increasing exponentially.
"We're planning to utilize new data streams--from wearable devices, telemetry devices and ICU monitors--and as we move toward that machine-generated data that's coming in at much higher rate, we have to focus on scalability," Chivers said.
To that end, Penn Medicine plans to deploy a 100-terabyte data stack through a partnership with Intel. It also plans to make its predictive models available outside the organization.
Michael Draugelis, chief data scientist for Penn Medicine, previously said that discovering the "pain points" in clinical care is just the beginning:
"Any time you produce these new pieces of information that never existed before, you need to do a redesign of your [care] pathway, and that is where the hard work is," Draugelis told Healthcare Informatics.
To learn more:
- read the article