ShareThis Page

Molecular differences in cancers found in UPMC's 'big data' results

| Saturday, June 15, 2013, 12:01 a.m.

Less than a year into a $100 million project to compile all of UPMC's electronic data into one system, health system researchers have produced their first “big data” results.

They discovered that there are molecular differences between the breast cancers that affect pre- and post-menopausal women. That might appear underwhelming, but the finding provides a glimpse of what UPMC hopes to achieve with the project: using large amounts of data to formulate medical treatments specific to an individual and his or her unique conditions.

“Rather than a blanket approach” to treating diseases, “you can be much more tailored to what is the best treatment for this set of circumstances,” said Lisa Khorey, vice president of enterprise systems and data management at UPMC.

Along the way, experts say, efforts by UPMC and others to analyze huge sets of data may lead to better health outcomes for patients and reduced spending on health care.

“We're getting fed up with all the errors we're making” in health care, said Dr. Atul Butte, a medical professor at Stanford University and expert in the growing use of big data in health care.

Errors are costly, to patients' pocketbooks and to their health, Butte said.

An estimated $300 billion a year in health care spending could be saved with big data analysis leading to better treatments, according to a 2011 analysis from McKinsey & Co., an accounting and consulting firm.

By better analyzing the huge amounts of data being collected every day in hospitals, research labs and doctors' offices, the hope is to better understand some basic questions, Butte said. Why do some people respond better to treatments than others? Is a more expensive treatment truly more effective than a less expensive one? How can we reduce waste and duplicative procedures?

“Your average reader, when they go to make a decision about where they go to invest their money, it's amazing the amount of data they have to make sure they don't lose their money,” Atul said. “Why don't we have something like that in health care? This is the first step in helping us get there.”

Khorey said UPMC's $100 million data center in Oakland is still being established. There is additional hardware to install, more data from around UPMC's sprawling health care empire to compile and more users to set up on the system.

But there was enough medical and genetic data on 140 breast cancer patients to do an initial study to show that the system, in a very basic way, works.

“What has been really important to us is to show some value early,” Khorey said.

More research is needed to understand the differences in breast cancer detected in the study. But having the ability to ask the question, “Is there a difference?” and getting the answer quickly hints at the power of big data analysis, said Adrian Lee, director of the Women's Cancer Research Center at the University of Pittsburgh's Cancer Institute.

“The integration of data, which is the goal of the enterprise data warehouse, allows us to ask questions that we just simply couldn't ask before,” Lee said.

Khorey said UPMC's data center works with petabytes of data, and the amount is constantly growing as the electronic medical record becomes ubiquitous. A petabyte is equal to 1 million gigabytes.

“Clearly, we're capturing more and more data elements in health care,” Butte said.

Alex Nixon is a staff writer for Trib Total Media. He can be reached at 412-320-7928 or

TribLIVE commenting policy

You are solely responsible for your comments and by using you agree to our Terms of Service.

We moderate comments. Our goal is to provide substantive commentary for a general readership. By screening submissions, we provide a space where readers can share intelligent and informed commentary that enhances the quality of our news and information.

While most comments will be posted if they are on-topic and not abusive, moderating decisions are subjective. We will make them as carefully and consistently as we can. Because of the volume of reader comments, we cannot review individual moderation decisions with readers.

We value thoughtful comments representing a range of views that make their point quickly and politely. We make an effort to protect discussions from repeated comments either by the same reader or different readers

We follow the same standards for taste as the daily newspaper. A few things we won't tolerate: personal attacks, obscenity, vulgarity, profanity (including expletives and letters followed by dashes), commercial promotion, impersonations, incoherence, proselytizing and SHOUTING. Don't include URLs to Web sites.

We do not edit comments. They are either approved or deleted. We reserve the right to edit a comment that is quoted or excerpted in an article. In this case, we may fix spelling and punctuation.

We welcome strong opinions and criticism of our work, but we don't want comments to become bogged down with discussions of our policies and we will moderate accordingly.

We appreciate it when readers and people quoted in articles or blog posts point out errors of fact or emphasis and will investigate all assertions. But these suggestions should be sent via e-mail. To avoid distracting other readers, we won't publish comments that suggest a correction. Instead, corrections will be made in a blog post or in an article.