Insurer Uses Personal Data To Predict Who Will Get Sick : Shots - Health News A Philadelphia health insurance company analyzes its clients' health data and other factors to find the frailest and assign them health coaches. That may improve health, but is it a breach of privacy?

Insurer Uses Personal Data To Predict Who Will Get Sick

  • Download
  • <iframe src="" width="100%" height="290" frameborder="0" scrolling="no" title="NPR embedded audio player">
  • Transcript


And now health and your data for this week's All Tech Considered.


SIEGEL: Information about you and your health is tracked with more efficiency than ever. Doctors and insurers hope that that will help improve treatment and lower costs. WHYY's Todd Bookman has the story of one Philadelphia insurer and how it's using all the information it gathers about people.

TODD BOOKMAN, BYLINE: The first thing out of John Iovine’s mouth was an apology.

JOHN IOVINE: You've got to forgive me if I don't remember too much. I had a stroke.

BOOKMAN: Signs of that stroke are everywhere. His bed is in the dining room. There's a shower installed in the pantry. John's thin, in blue pajama pants, sitting in a blue wheelchair. But the memory issues - I think he's overstating them. He still remembers laying eyes on something special back in 1952.

J. IOVINE: We went to Harding, and that's the school right up here. And I seen this girl in this long, red sweater and her red hair, and I said, that's the girl for me (laughter).

BOOKMAN: Carol Iovine, redhead and wife, is on a plastic-covered couch right next to John. His stroke, she says, came in the middle of a really bad run.

CAROL IOVINE: He had pneumonia, jaundice, sepsis, clot in the right lung and all the above between 10-16 '13 to January 3 of '14.

BOOKMAN: John spent 79 days in the hospital.

J. IOVINE: Oh man, it was hell.

BOOKMAN: After a few months in a rehab facility, he was finally sent back home. And this moment in a patient's recovery when they seemingly have to sink or swim on their own, this is the moment that everyone in the health system is paying a lot of attention to right now.

SOMESH NIGAM: We are trying to identify which patients are likely to be hospitalized in the next three months.

BOOKMAN: This is Somesh Nigam, chief informatics officer for Independence Blue Cross. He says the company wants to find customers most at risk like John Iovine, the ones sick or frail enough to be right on the edge of hospitalization. And they're doing it by crunching all the data at their disposal - billing claims, lab readings, medications, height, weight, family history plus neighborhood information like poverty rates.

NIGAM: The health care data that we provided to build these algorithms is equivalent to, I think, five Wikipedias.

BOOKMAN: They take that five Wikipedias' worth of data, run the algorithm, and out pops a score - high scores for people most at risk; low numbers, the opposite. Independence then notifies the primary care physicians and hospitals that treat the high scores. Plus, Nigam says, it assigns them what they call a health coach whose job is simply to see what these people need.

NIGAM: This coordinated effort then works for the patient to try to get them the right level of education, physician appointments, medication issues, perhaps transportation to go to a doctor, even home care.

BOOKMAN: Big picture - the money spent on a health coach is nothing compared to the cost of a hospital admission. Nigam says they've identified 18,000 people for extra attention, and he says they've already seen a 40 percent reduction in expected hospital admission rates in patients with congestive heart failure. Glenn Cohen is a professor at Harvard Law School and says a number of big health systems are experimenting with algorithms.

GLENN COHEN: They've got their pulse on the future. We have huge amounts of data to inform clinical practice.

BOOKMAN: But he cautions that this collision of health care and big data brings up a number of concerns, like whose information is it and who gets to see it?

COHEN: And so there has to be a certain amount of discussion with patients. At the very least, I think it's incumbent upon a system to allow patients to know that their data is being used in a different way.

BOOKMAN: Cohen says the field is too new for there to be accepted standards yet for how this data should be handled. For its part, Independence Blue Cross says it follows federal anonymity guidelines. But it doesn't ask people to opt in. It just does it, says Somesh Nigam.

NIGAM: The data is only used to improve or coordinate care, right? And that's something that you would agree is our role.

BOOKMAN: Coordinated care has made all the difference for John Iovine. He hasn't been hospitalized in the year since Independence Blue Cross assigned him a health coach. For NPR News, I'm Todd Bookman in Philadelphia.

SIEGEL: That story came thanks to our reporting partnership with WHYY and Kaiser Health News.

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

NPR transcripts are created on a rush deadline by an NPR contractor. 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.