Magazine
Intelligence Unit Special Reports Special Events Subscribe Sponsored Departments Follow Us

Twitter Facebook LinkedIn RSS

A Data Gold Mine

Gienna Shaw, for HealthLeaders Magazine, June 9, 2010
Are you a health leader?
Qualify for a free subscription to HealthLeaders magazine.

Tech-savvy hospitals are using EMR data to conduct clinical research, improve quality, and inform business decisions.

Clinical studies can take years to conduct. Just one example: A study of the widely used antibiotic gatifloxacin showed it could cause dangerous fluctuations in blood sugar levels among diabetic patients. After further research showed that all patients were at risk for the dangerous side effect, the drug was pulled from the market.

At Montefiore Medical Center in Bronx, NY, an analyst was curious whether a new clinical research tool the system had developed could duplicate the results of the gatifloxacin studies. The analyst isolated a cohort of the four-hospital system's patients who had been on the antibiotic and compared them to a group that was on a different antibiotic. Sure enough, the query showed that the patients on gatifloxacin were six times more likely to have high or low blood sugar than those who were not.

But the analyst didn't have to study the drug for months or years, go in front of a committee of physicians and data experts for research review, nor wait for the results to be published in a peer-reviewed journal. The analyst performed the query on his lunch break using a software program called Clinical Looking Glass that taps into more than a decade's worth of electronic medical record data.

The program interprets de-indentified data for entire patient populations and can be used to gauge the effectiveness of patient safety measures, identify and track public health threats, and provide data for professional articles and published studies. CLG has been used to measure the impact of Medicare regulations on rehabilitation patients, quantify the reduction in radiation exposure for emergency department patients, and track the care and progress of diabetes patients over time.

It also helped the system react quickly to a surprise FDA hospitalwide study during the heparin scare to check if patients using the blood-thinning drug had a longer hospitalization or died. Montefiore analysts quickly tracked all the patients who were given the drug from December 2007 through January 2008 and compared length of stay and mortality against those who were given the drug during the same period 12 months earlier, before the quality concerns were raised. The query found no increase in either measure—and no cause for alarm for Montefiore patients.

"The goal of these analytics is to gather information and conduct studies that lead to better clinical decision-making," says Eran Bellin, MD, vice president for clinical IT research and development at Montefiore, who was instrumental in designing CLG. "The queries have provided the quantitative evidence for dozens of peer-review journal articles, presentations at professional meetings, institutionwide patient quality improvement initiatives and programs that benefit entire populations."

"We believe it offers a glimpse into how healthcare informatics is shaping the future of medicine," says Montefiore's president and CEO Steven Safyer, MD.

An explosion of data
As the government pushes for widespread adoption of EMRs, the use of secondary data for clinical and business purposes is expected to increase dramatically. And that will have a big impact on the healthcare economy, says Dan Garrett, a partner at PricewaterhouseCoopers in New York City and a leader in its health information technology practice.

"When we start to combine clinical, financial, and administrative data in unique and valuable ways, there really isn't a limit as to how much that will grow," he says.

The most impact comes from combining clinical, financial, and administrative data, such as treatments, results, GPO contract information, ICD9 and ICD10 codes, how much time clinicians spend treating patients, patient accounting records, and the costs of medical devices, to name just a few. When organizations harvest, digest, and absorb such data over time, the result is a comprehensive look at what works and what doesn't, Garrett says.

Comments are moderated. Please be patient.