Penn Medicine’s team that includes chief medical information officer and vice president of Penn Medicine C. William Hanson and chief data scientist at Penn Medicine Mike Draugelis, is using the power of big data to find new ways how to improve healthcare and hopefully save patient’s lives. Hanson and Draugelis, according to IT World, are both working closely with faculty in the Institute for Biomedical Informatics to manage, integrate, and analyze petabytes of data. By using big data insights, the team is building and testing prototypes with patients and “feeding the results back into algorithms so that the computer can learn from its mistakes.” So far the use of big data has helped the Penn team to predict 24 hours in advance which patients are developing life-threatening infections such as sepsis.

“We're still on the rising part of the curve of what we're going to learn from big data,” said Steven Steinhubl, director of digital medicine at the Scripps Translational Science Institute. “It's rapidly growing, but it will accelerate even more as large medical centers like UPenn take advantage of the data they're already collecting and add genomics on top of that,” he added.

Draugelis explained for IT World that Penn’ team is using all the algorithms to guide the doctors and nurses to follow particular treating ways, and in the meantime find new ways of treatment each time the algorithms are updated, which usually happens every six months. “We're working in two week sprints, where the clinicians adjust their pathways, and we adjust the algorithms to their needs.” he said.

The team is currently working hard on acute conditions and finding new ways to better predict which patients have congestive heart failure. “We're creating machine learning predictive models based on thousands of variables. We look at them in real time, but we train them up over millions of patient records,” Draugelis said. While Dean Sittig, a professor at the University of Texas Health School of Biomedical Informatics said that “as a rule of thumb, if the computer is right more than half the time – especially with something serious like sepsis – clinicians will pay attention to it. But if it's only right 10 percent of the time, it starts to be a bother.”

With the help of EGRs systems, which are now present in most hospitals, and the drop of genomic sequencing costs,  correlating genotypic and phenotypic variants is now getting way easier, but there are still some challenges The Penn Medicine team is facing, such as the lack of interoperability among EHRs and a more structured data.

Regardless, Steinhubl is still positive about the new approach using big data. “Eventually, it's going to completely change medicine and the way we treat common chronic conditions,” he said for IT World.

(Picture source: connexica.com)