Healthcare Big Data: Blessing And Curse - InformationWeek

InformationWeek is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them.Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

Healthcare // Analytics
09:06 AM
Paul Cerrato
Paul Cerrato
Connect Directly

Healthcare Big Data: Blessing And Curse

Interpreting government-released healthcare data correctly will pose a massive challenge for analysts, policy makers, and pundits.

"Sliver of Medicare Doctors Get Big Share of Payouts"

"Top Medicare Doctor Paid $21 Million in 2012, Data Show"

Headlines like those, from The New York Times and Bloomberg News, grab the public's attention and generate lots of righteous indignation, but do they represent an accurate analysis of the healthcare data recently provided by the federal government? I doubt it.

In April the Centers for Medicare and Medicaid Services (CMS) released more than 9 million lines of data covering services and procedures done by more than 880,000 healthcare providers. The release of that data started a feeding frenzy among journalists, analysts, and consumer advocates, many of whom were trying to figure out who was exploiting the healthcare system.

The New York Times reported that in 2012, 100 doctors received a total of $610 million in payments, "ranging from a Florida ophthalmologist who was paid $21 million by Medicare to dozens of doctors, eye and cancer specialists chief among them, who received more than $4 million each that year." On the face of it, that seems like an awful lot of money to pay individual physicians in a year.

But those statistics tell only part of the story. They don't take into account the fact that eye doctors and oncologists administer very expensive drugs, or that they pay a significant percentage of their fees to staffers and to maintain an office. And to be fair to the Times, it did explain that the data needs to be examined cautiously: "An individual doctor, for example, may seem to have a high volume of services because that doctor oversees medical residents or physician assistants but bills for those services."

No doubt some providers are cursing CMS for releasing all this claims data because it may put them in a bad light. Nonetheless, the federal agency deserves credit for jumping head first into the big data swimming pool. Among the programs CMS has spearheaded that will transform US healthcare over time is the Hospital Readmission Reduction Program (HRRP), which cut payments to hospitals with excessive 30-day patient readmission rates. That program got providers' attention, forcing them to adopt a variety of creative tactics to reduce their readmits.

[You need the right data before you can reach the right conclusion. Read EHR Reboots: Should You Replace Your System?]

Thanks to a sophisticated predictive modeling system and advances in data storage and processing, the feds have sped up their analysis of readmission data since the program began in 2012 and have reported a rapid decline in the readmission rate in 2012 and 2013.

The predictive modeling system also has helped combat Medicare fraud. Set up in June 2011, the fraud detection system reportedly spotted $115 million in improper payments in one year alone.

Granted, CMS's new programs have many critics. The American Hospital Association, for example, maintains that HRRP "is deeply flawed and must be reformed to adequately account for socioeconomic factors of communities and appropriately exclude readmissions that are not related to the initial admission."

Still, something had to be done about runaway US healthcare costs, and there was no indication that the hospital industry was going to police itself. While the latest CMS programs and the IT tools used to put them in place are far from perfect, the federal government deserves praise for taking on this enormous challenge.

In its ninth year, Interop New York (Sept. 29 to Oct. 3) is the premier event for the Northeast IT market. Strongly represented vertical industries include financial services, government, and education. Join more than 5,000 attendees to learn about IT leadership, cloud, collaboration, infrastructure, mobility, risk management and security, and SDN, as well as explore 125 exhibitors' offerings. Register with Discount Code MPIWK to save $200 off Total Access & Conference Passes.

Paul Cerrato has worked as a healthcare editor and writer for 30 years, including for InformationWeek Healthcare, Contemporary OBGYN, RN magazine and Advancing OBGYN, published by the Yale University School of Medicine. He has been extensively published in business and ... View Full Bio
We welcome your comments on this topic on our social media channels, or [contact us directly] with questions about the site.
Comment  | 
Print  | 
More Insights
Newest First  |  Oldest First  |  Threaded View
User Rank: Ninja
8/28/2014 | 11:46:58 AM
Hitting key goals
Big data is no different from any other disruptive technology in that it has pros and cons as it changes the operating culture. What I find encouraging is that the results highlighted are in line with what CIOs identify as their top three goals. According to a recent IDG SAS survey process optimization, improved customer experience and product/service innovation all rise to the surface. 

Peter Fretty
User Rank: Apprentice
8/13/2014 | 2:25:44 PM
Difficult and contentious, but it needs to happen
It is difficult to reach solid conclusions from the data Paul.  Although rich, the data is a small subset of the big picture, and the meta data released by CMS is so limited that it certainly doesn't help the enthusiastic amateur either.  But, as you say, something has to be done about runaway healthcare costs.  Shining a light, however weakly, onto the economics is one step.  Without tranparency and competition there will be no change.  So a bold move by CMS, but hopefully this is just the start with more datasets and more detailed data to come.
User Rank: Author
8/12/2014 | 12:51:30 PM
Healthcare metrics
Readmission rates would seem to vary greatly by community; that seems a fair point. Different communities have different levels of support at home. One aspect of healthcare data I have found interesting this year is the cost comparisons that have come to light on routine procedures in varying parts of the US.
The Best Way to Get Started with Data Analytics
John Edwards, Technology Journalist & Author,  7/8/2020
10 Cyberattacks on the Rise During the Pandemic
Cynthia Harvey, Freelance Journalist, InformationWeek,  6/24/2020
IT Trade Shows Go Virtual: Your 2020 List of Events
Jessica Davis, Senior Editor, Enterprise Apps,  5/29/2020
White Papers
Register for InformationWeek Newsletters
Current Issue
Key to Cloud Success: The Right Management
This IT Trend highlights some of the steps IT teams can take to keep their cloud environments running in a safe, efficient manner.
Flash Poll