GE Healthcare and media conglomerate Thomson Reuters have entered into a partnership to mine each company's massive storehouses of healthcare data on behalf of organizations interested in research across large patient populations.
The unnamed partnership is intended to support comparative effectiveness research, which is the study of how effective certain treatments are for specified medical conditions. The 2009 American Recovery and Reinvestment Act allocated $1.1 billion for comparative effectiveness research, also known as outcomes research.
The companies will market the analytics service to pharmaceutical and medical device manufacturers, as well as to government agencies interested in population-based research, according to Peter Bailey, GE Healthcare's VP and general manager for clinical data services. Bailey said the partnership this month landed its first customer, a pharmaceutical company he would not specify. "We do have several more [customers] in the pipeline," he said.
Data will come from two sources: GE's Medical Quality Improvement Consortium, a database of de-identified ambulatory electronic medical records on more than 20 million patients from 22,000 providers; and the Thomson Reuters MarketScan research databases, a compendium of information on more than 130 million people culled from Medicare, Medicaid, and commercial health insurance claims. GE and Thomson Reuters will cross-reference the massive databases based on specific variables to match clinical and administrative records without identifying patients.
If researchers have claims showing a group of patients with hypertension, for example, the clinical database can add details such as blood pressure and body mass index to help in the development of medical evidence that can lead to better care in the future. "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 healthcare experience of a de-identified patient," Thomson Reuters senior VP Bill Marder said in a press release.
"We’ve tackled what was once considered an insurmountable barrier to outcomes-based research," added Brandon Savage, M.D., chief medical officer for GE Healthcare's IT division. "We're extremely enthusiastic about the opportunities this discovery creates for the field and the improvements it may someday bring to patient care, across the world."
The companies said they publicly demonstrated how coupling de-identified clinical and administrative data can help in comparative effectiveness research at the 2010 International Society for Pharmacoeconomics and Outcomes Research meeting. The announcement of the partnership coincided with the last day of the 2011 ISPOR conference.
Bailey told InformationWeek that the two companies have cross-linked their databases so there is "an almost certain match between the two," even though the records contain no patient identifiers.
GE and Thomson Reuters are taking steps to assuage fears that data could be re-identified. "We don't handle any PHI," Bailey said, using the acronym for protected health information, the kind of personally identifiable records that Health Insurance Portability and Accountability Act restricts disclosure of. He also said that both companies have obtained independent verification that their privacy practices meet HIPAA standards.
The Healthcare IT Leadership Forum is a day-long venue where senior IT leaders in healthcare come together to discuss how they're using technology to improve clinical care. It happens in New York City on July 12. Find out more.