Healthcare // Analytics
News
6/30/2014
09:00 AM
Connect Directly
RSS
E-Mail
50%
50%

Big Data Helps Insurer Pinpoint At-Risk Patients

Aetna and GNS Healthcare use analytics to predict patients at risk for metabolic syndrome.

Healthcare Dives Into Big Data
Healthcare Dives Into Big Data
(Click image for larger view and slideshow.)

Analyzing big data can predict patients' future risk of metabolic syndrome and allow individuals and clinicians to work together on preventative steps that save lives and money.

While organizations have used a lot of big data projects to discern trends, a study conducted by Aetna and GNS Healthcare analyzed data from almost 37,000 members of an Aetna employer customer who opted in for screening of metabolic syndrome -- which can lead to chronic heart disease, stroke, and diabetes. GNS analyzed information such as medical claims records, demographics, pharmacy claims, lab tests, and biometric screening results from a two-year period.

"Over the past few years, Aetna has had a number of customers -- mostly larger and middle-market employer groups -- that have been screening members for metabolic syndrome," said Adam Scott, managing director of Aetna Innovation Labs, in an interview. "We had a thesis we could marry that information to other information we had at Aetna and come up with personalized [therapies]."

The partners used two analytical models on this data: One used a claims-based approach to predict the probability of each of five metabolic syndrome factors occurring for each individual, while the other -- based on both claims and biometric data -- reviewed whether each member would worsen, improve, or remain the same for each of five metabolic syndrome factors.

[Want to know more about how big data can keep people healthier? See Analytics Help Patients Follow Doctors' Orders.]

GNS used its proprietary blend of artificial intelligence, analytics, and machine learning to transform these "mashups of big data" into useful, actionable information for individuals, GNS CEO Colin Hill told InformationWeek.  

"You need really large populations to make large models like this to get down to individual levels," he said.

In both cases, models precisely predicted future risk of metabolic syndrome on a population and individual level. If an individual had two of the five risk factors, researchers could accurately predict which third factor was most likely to develop next without intervention.

(Source: Pixabay)
(Source: Pixabay)

Researchers reviewed the most effective interventions for each risk. Visiting a primary care physician lowers the one-year probability of having metabolic syndrome in approximately 90% of individuals, the companies said. Improving waist circumference and blood glucose dramatically lessened patients' risk and medical costs, the report found.

Because Aetna's system already is set up to typically pay claims within 48 hours, its culture, infrastructure, and technology support the use of big data for almost real-time information on metabolic syndrome, said Scott. As a result, Aetna and GNS can determine a patient's condition today and a year from now, and identify the most appropriate interventions to improve that individual's health outlook, he said.

Members opted in, often because their employers offered an incentive, said Scott. (These awards can include lower insurance rates or out-of-pocket expenses, according to industry executives.)

"If we can use information that we have on hand to understand more about disease and risk and provide that information to both our membership and those providers that care for those members, we can drive toward better value, delivered toward better outcomes," Scott added.

Aetna is considering other ways in which it can use this big data approach to common syndromes or illnesses, he said. Likewise, GNS expects other organizations within the healthcare spectrum to expand their use of big data, artificial intelligence, machine learning, and other tools to gain insights from vast databases for accurate individual diagnoses and treatments, said Hill.

"The focus and the investment on data analytics, machine learning, new approaches on population management, and next-generation care management is increasing. The slope is pretty steep," he noted. "There's a lot of pressure on the healthcare system to become more efficient and to leverage assets and to become smarter. Data is a clear asset. It's not about building more hospitals, adding more docs, more surgeries. It's about how can we use data to be smarter about how we use those interventions."

Most IT teams have their conventional databases covered in terms of security and business continuity. But as we enter the era of big data, Hadoop, and NoSQL, protection schemes need to evolve. In fact, big data could drive the next big security strategy shift. Get the 6 Tools To Protect Big Data report today (registration required).

Alison Diana has written about technology and business for more than 20 years. She was editor, contributors, at Internet Evolution; editor-in-chief of 21st Century IT; and managing editor, sections, at CRN. She has also written for eWeek, Baseline Magazine, Redmond Channel ... View Full Bio

Comment  | 
Print  | 
More Insights
Comments
Newest First  |  Oldest First  |  Threaded View
pcharles09
50%
50%
pcharles09,
User Rank: Moderator
7/22/2014 | 9:08:41 AM
Re: Hmmm...
@Alison,

They might still consider you heathly. In the best case scenario, you break even. It'll be like an equation: if Gym - all the bad stuff = 0
Alison_Diana
50%
50%
Alison_Diana,
User Rank: Author
7/2/2014 | 4:00:01 PM
Benefits Outweigh Worries
In this particular case -- with Aetna and GNS -- I have no qualms about how the data was used because patients opted in and clearly understood who was using their data and what it was being used for. When an organization uses individuals' information in such a transparent way, clearly telling patients what they are doing with the data, and patients directly benefit then I don't find there to be any privacy issues. Rather, data is being used to help individuals' health. Sure, it saves money -- but it really means people could well be on the path to better quality, longer lives, and that's a benefit you can't beat!
Alison_Diana
50%
50%
Alison_Diana,
User Rank: Author
7/2/2014 | 3:42:34 PM
Re: Hmmm...
You raise a good point. Under Obamacare, insurers can no longer deny coverage or drop someone due to a pre-existing condition -- but that doesn't mean your rates won't be higher if you have a condition than if you don't. It's not only insurers and other payers (such as government or employers -- although it's illegal to not hire someone because of their health, unless it's part of the job -- such as the job requires you to lift 50 pounds). Marketers and pharmaceutical companies want this data to advertise to us and also to help in their drug-development plans. 

I worry about the point at which this all intersects: What happens if our supermarket loyalty cards, our debit/ credit cards, our personal health information, and data from all these health apps and wearables comes together? What happens when a payer sees that, although you go to the gym four days a week, you also buy a carton of Camel unfiltered and buy two cases of beer, 1 bottle of vodka, and fast food dinners every other night?
AnfH156
50%
50%
AnfH156,
User Rank: Apprentice
7/2/2014 | 12:14:26 PM
Risk Vs. Reward
I think you are correct, I agree with you completely. This can be very scary and beneficial at the same time. With anything, we must evaluate the risk and reward of the technology we trust to ensure the cost and effectiveness of our healthcare. Being we cannot control how Insurance companies and healthcare institutions use or interpret the information, we can only hope they do not abuse it. But companies like Due North Analytics are the wave of the furture when it comes to tracking and analyzing medical data for the healthcare industry. 
pcharles09
50%
50%
pcharles09,
User Rank: Moderator
6/30/2014 | 6:16:54 PM
Hmmm...
That seems good & scary all at the same time. I feel like having this information is good for the healthcare professionals. But the HMOs & insurance companies may use this to start dropping patients ahead of time. I don't know if it's a sure thing but someone once told me that the objective of big data in insurance is to figure out who NOT to cover, not the other way around.
Big Love for Big Data? The Remedy for Healthcare Quality Improvements
Big Love for Big Data? The Remedy for Healthcare Quality Improvements
Healthcare data is nothing new, but yet, why do healthcare improvements from quantifiable data seem almost rare today? Healthcare administrators have a wealth of data accessible to them but aren't sure how much of that data is usable or even correct.
Register for InformationWeek Newsletters
White Papers
Current Issue
InformationWeek Must Reads Oct. 21, 2014
InformationWeek's new Must Reads is a compendium of our best recent coverage of digital strategy. Learn why you should learn to embrace DevOps, how to avoid roadblocks for digital projects, what the five steps to API management are, and more.
Video
Slideshows
Twitter Feed
InformationWeek Radio
Archived InformationWeek Radio
A roundup of the top stories and trends on InformationWeek.com
Sponsored Live Streaming Video
Everything You've Been Told About Mobility Is Wrong
Attend this video symposium with Sean Wisdom, Global Director of Mobility Solutions, and learn about how you can harness powerful new products to mobilize your business potential.