NPR logo
Big Data Not A Cure-All In Medicine
  • Download
  • <iframe src="https://www.npr.org/player/embed/375201444/375201445" width="100%" height="290" frameborder="0" scrolling="no" title="NPR embedded audio player">
  • Transcript
Big Data Not A Cure-All In Medicine

Health

Big Data Not A Cure-All In Medicine

Big Data Not A Cure-All In Medicine
  • Download
  • <iframe src="https://www.npr.org/player/embed/375201444/375201445" width="100%" height="290" frameborder="0" scrolling="no" title="NPR embedded audio player">
  • Transcript

Big data is a trendy term for the ever-expanding cloud of information that's online and increasingly searchable. Some researchers say it could change the way medical research is done and the way individual doctors make medical decisions. Others say big data raises too many big questions — especially when it comes to medicine.

MELISSA BLOCK, HOST:

The data from those personal health apps and devices will be added to the vast amount of medical information now stored in digital form. For example, electronic medical records of individual treatments and their outcomes. Those are available to professionals and importantly they're searchable. All that information adds up to a great example of big data. It could help practitioners answer important questions about how to treat their patients, but there's also wariness about big data in medical settings. Here's Amy Standen of member station KQED in San Francisco.

AMY STANDEN, BYLINE: In 2011, a young girl from Reno, Nevada, was flown by helicopter to the pediatric intensive care unit at Stanford's Lucile Packard Children's Hospital. Jenny Frankovich was an attending physician there.

JENNY FRANKOVICH: She was gravely ill. Her kidneys were shutting down.

STANDEN: Tests showed the girls had lupus, a disease in which the immune system goes rogue. Frankovich had seen kids like this before. And she recalled that some of them also developed blood clots, which can be deadly. Blood clots can be prevented with an anticoagulant, but that too carries risks.

FRANKOVICH: You could stroke. A patient could bleed into another organ.

STANDEN: Giving the drug was risky. Not giving the drug was also risky. So Frankovich asked the other doctors around the girl's bed, what should we do here? The answer - we don't really know.

FRANKOVICH: There wasn't enough published literature to guide this decision. And really, the best route was to not do anything.

STANDEN: And that's when she had her big idea.

FRANKOVICH: I knew I had the patients' charts, all electronic, in a database that was searchable.

STANDEN: Not long ago, she says, this data would have filled an entire office room with boxes of paper files. Now she could search it with a keystroke.

FRANKOVICH: I brought the data back to that big team of doctors that was around her bed. And I said, hey, this is the number of lupus patients we've had. This is the number that had a clot. What do you think? Universally everybody said, wow, based on those numbers, you know, it seems like we should try to prevent a clot in her.

STANDEN: So they did. It worked.

FRANKOVICH: She didn't develop a clot. And over time, her lupus did get better. And she's, as far as I know, doing well.

STANDEN: This may sound kind of obvious, like something doctors would do all the time. But it's actually really unusual, the only time her hospital had used medical records in a situation like this. And to Atul Butte, who studies medical data at Stanford, this is a big step, an example of a seismic shift he believes is happening right now in medicine.

ATUL BUTTE: The idea here is the scientific method itself is growing obsolete.

STANDEN: This idea draws from an essay published in Wired magazine back in 2008 called "The End Of Theory." And according to the essay, in the future so much information will be available at our fingertips that there will be almost no need for experiments.

BUTTE: Think about it - the scientific method, we learn this in elementary school. You come up with a question, or what we call a hypothesis, and go make the measurements to address and answer that question or hypothesis.

STANDEN: The answers already exist.

BUTTE: We already have the measurements and the data. The struggle is to figure out what do we want to ask of all that data?

STANDEN: To Butte, this cloud of data means that pretty soon we shouldn't need so many controlled trials. The answers are already there in the patient records and other digital health databases. If Butte's right, you might think that what Frankovich did has become standard practice at her hospital. In fact, the opposite happened.

FRANKOVICH: We're actually not doing this anymore.

STANDEN: The system just isn't ready, the hospital decided. What if Frankovich had used the wrong search terms or the engine itself had bugs? What if the records had been mis-transcribed? Even Frankovich agrees that it's just too risky.

FRANKOVICH: I mean, for sure the data is there, right? Now we have to develop the system to use it in a thoughtful, safe way.

STANDEN: Getting that system in place, she and others hope, will lead to better, faster, cheaper medicine. But it's still many years away. For NPR News, I'm Amy Standen.

Copyright © 2015 NPR. All rights reserved. Visit our website terms of use and permissions pages at www.npr.org for further information.

NPR transcripts are created on a rush deadline by Verb8tm, Inc., an NPR contractor, and produced using a proprietary transcription process developed with NPR. This text may not be in its final form and may be updated or revised in the future. Accuracy and availability may vary. The authoritative record of NPR’s programming is the audio record.

Comments

 

Please keep your community civil. All comments must follow the NPR.org Community rules and terms of use, and will be moderated prior to posting. NPR reserves the right to use the comments we receive, in whole or in part, and to use the commenter's name and location, in any medium. See also the Terms of Use, Privacy Policy and Community FAQ.