GE, Thomson Reuters Collaborate on Clinical Research Analytics

 
 
By Brian T. Horowitz  |  Posted 2011-05-25 Email Print this article Print
 
 
 
 
 
 
 

A joint effort by GE and Thomson Reuters will allow researchers to view both health care claims and clinical data to see how treatments will affect various patient populations.

GE Healthcare and Thomson Reuters have announced an agreement to link claims data on patient outcomes from Reuters' MarketScan Research Databases with electronic health records data from GE to gain insight on how treatment methods affect different patient populations.

The MarketScan Research Databases hold claims and prescription data, while GE's EHR database stores real-world clinical data. Researchers draw on these databases to evaluate the effectiveness of medical treatment. The effort complies with HIPAA regulations, GE reports.

By combining patient data from EHRs with the information in the MarketScan databases, researchers will be able to link claims data on diagnoses such as hypertension with clinical info such as body mass index, symptoms and blood pressure.

Doctors would then have more information to base decisions on treatment options by sifting through both the financial claims data and doctors' records in EHRs.

"We have the evidence-based account of how populations are being managed, how therapies are working, so we don't have sterile clinical trial data taken from a highly structured and managed environment," Peter Bailey, vice president and general manager for GE Healthcare's IT clinical data services, told eWEEK. "We have a very real-world, practical usual-care data set."

While Reuters has the de-identified, or anonymous, claims data, GE will add the clinical data. "The two will link the data for individual scientific efforts they will jointly pursue on behalf of customers," Bailey said.

Although the EHRs and claims data will be stored separately, researchers will still be able to search a population subset in the two databases together, he explained.

GE and Reuters first demonstrated their joint database at the ISPOR (Pharmacoeconomics and Outcomes Research) conference in May 2010. They combined hypertension data from more than 9,000 EHRs with the claims and prescription data in MarketScan for more than 30 million patients.

The news of the joint effort was officially announced during this year's ISPOR conference on May 25 in Baltimore.

These records have grown since that demonstration a year ago, and the two companies have found ways to de-identify the data using algorithms and limiting data fields to protect patient privacy.

"We'll apply the linking algorithms to find the population we're studying-the hypertensives or folks with diabetes, and then we'll have the joint researchers answer the specific questions for clients," Bailey said.

"We can now conduct studies that assess the effectiveness of medical treatments, prescription adherence and disease management initiatives based on both a deep set of clinical data and extensive data on the complete health care experience of a de-identified patient," Bill Marder, senior vice president at Thomson Reuters, said in a statement. "This includes all hospitalizations and ambulatory visits as well as all filled prescriptions, costs and reimbursements."

GE offers Centricity, a leading EHR platform used by hospitals and physician practices.

Real-world clinical data from EHRs may not have been linked with claims data before to examine specific medical cases, Bailey said. Viewing the linked Reuters and GE data will allow physicians to see the financial impact of various treatments.

"In the past we've been able to use claims data independently, and you miss a lot of the clinical background and the context and the outcomes in tracking populations over time," he explained. "Combining those two releases the power of being able to see a picture in terms of the patient populations, where they're getting treated, and what are the outcomes of that treatment."

GE and Reuters have begun working with a pharmaceutical company on studies using the linked data set. Additional projects will follow.

"Once we have a scientist from both teams working collaboratively with the customer side...I think the sophistication of level of questioning they start asking of our researchers is going to grow exponentially," Bailey said.

 

 
 
 
 
 
Brian T. Horowitz is a freelance technology and health writer as well as a copy editor. Brian has worked on the tech beat since 1996 and covered health care IT and rugged mobile computing for eWEEK since 2010. He has contributed to more than 20 publications, including Computer Shopper, Fast Company, FOXNews.com, More, NYSE Magazine, Parents, ScientificAmerican.com, USA Weekend and Womansday.com, as well as other consumer and trade publications. Brian holds a B.A. from Hofstra University in New York.

Follow him on Twitter: @bthorowitz

 
 
 
 
 
 
 

Submit a Comment

Loading Comments...
 
Manage your Newsletters: Login   Register My Newsletters























 
 
 
 
 
 
 
 
 
 
 
Thanks for your registration, follow us on our social networks to keep up-to-date
Rocket Fuel