EHR database drastically enhances medical research: Game-Breaker for Medical Informatics
August 29, 2012, 8:00 PM
By Brie Zeltner, The Plain Dealer
CLEVELAND, Ohio — Large databases of electronic medical records hold great promise for medical research. In theory they can provide doctors access to huge amounts of anonymous patient data, allowing large-scale population studies without the cost and hassle of patient recruitment, review boards and staff training.
Now, a team of data experts at MetroHealth Medical Center and the Cleveland Clinic Innovations spinoff company Explorys has shown just how powerful such medical records can be: In three months, they’ve replicated a major medical study that took a Norwegian team 14 years to research and report. And they’ve done it at a fraction of the cost, with a sample about 40 times as large.
The local effort, led by MetroHealth Chief Medical Informatics Officer Dr. David Kaelber, was possible because of Explorys’ database of 14 million electronic medical records gathered from 12 major health systems.
Explorys began collecting the records, which were in many different formats, onto a single platform in 2009. The goal was to standardize the records in a safe and privacy-protected manner so that the health systems involved could use it for patient care and research, said Dr. Anil Jain, senior VP and chief medical information officer at Explorys.
Kaelber knew that if Explorys could pull it off, the magnitude of data it provided access to would be invaluable to medical research. In his words, a “game-changer.”
But Kaelber found that as he talked to people outside his highly data-educated bubble about the vast potential of a “platform” like Explorys for research, most didn’t understand. He needed to prove its power, speed and cost-effectiveness.
Most of all though, he needed to prove that it worked — that he could get exactly the same results as traditional research studies that required more time and resources.
Enter the Norwegian study. In 1994, a group of researchers started registering 26,714 people in the northern region’s largest city, Tromso. It was part of a much longer study on the population’s heart disease risk. They recorded height, weight and other measures of obesity, then followed participants for 13 years, recording any blood clots they had.
Their conclusion: the combination of obesity and a tall stature significantly increases risk of blood clots, especially in men.
Kaelber was on a plane when he read the study’s result, which was published online in the journal Arteriosclerosis, Thrombosis, and Vascular Biology in April, 2011. When he disembarked, he called Explorys.
“This is the study we have to do,” Kaelber told Jain and two of his colleagues at the company. It was just the type of concrete example they needed to make their case.
The sample: 959,030 patients with medical records in the Explorys platform. The method: using software to search for blood clots in the health and claims records contained in the database, and then looking for patterns in those patients’ height and weight. The result: Exactly the same as the Tromso study.
“And actually the statistical significance of our study was much, much higher because our sample size was 40 times greater,” Kaelber said. Kaelber and his team published their results online in July in the Journal of the American Medical Informatics Association.
It took Kaelber and the Explorys team about three months to gather and analyze the data. They donated their time, but Kaelber estimates the study would have cost about $25,000.
A traditional longitudinal study the size of the one in Norway costs millions of dollars. Patient recruitment takes time, and staff has to be trained to interview patients and collect and enter data.
The main advantage of using Explorys and other large electronic medical record databases for research is that doctors and nurses have already done all of the time-consuming and costly data entry as part of the patients’ routine healthcare visits.
“It’s not necessarily a shortcut, it’s just that we’ve done a lot of the legwork upfront in the Explorys system,” Jain said.
There is no charge for member health systems to do research using the Explorys system, unless they want help in analyzing or interpreting the data. The company makes money in other areas, such as analyzing data for the hospitals and using data to help them identify ways to improve efficiency and deliver better patient care.
“There is tremendous potential to make discoveries, to improve medical outcomes,” said Sharona Hoffman, professor of law and bioethics at Case Western Reserve University School of Law. “This allows researchers to really access millions of records very quickly, to see patients who receive care in real clinical settings with diverse demographics and diverse geographical settings.”
The other main research advantage to the Explorys platform is that because all of the patient data in its system has been “de-identified” (it contains none of the privacy information that is protected by the Health Insurance Portability and Accountability Act, or HIPAA) researchers do not have to go through the time-consuming human subjects approval process with their institutions.
“That right there is a jaw-dropper for a lot of people doing research,” Kaelber said. “There aren’t the same level of privacy concerns.”
Privacy concerns in the electronic medical records world are real, though, Jain said. Explorys hired experts at “reidentifying” data and asked them to see if they could break down the company’s privacy protections, much the way a bank would hire a hacker to test its security measures. The Explorys platform kept the data private, he said.
Hoffman warns that experts were able to re-identify data at a rate of about 0.25 percent in some studies. That’s not a big risk, but when you have 314 million records, that’s still a good number of people, she said.
The Explorys platform isn’t the perfect tool for all types of clinical research, of course. Kaelber compared it to a fancy new power drill. If you’ve been using a hand drill for while, your new tool is going to be revolutionary.
If you’re doing some plumbing, however, you’re not going to need that drill, no matter how cool and powerful it is. It can’t do everything.
“You have to be aware of the limitations of electronic health records and this mode of analysis,” Hoffman said. “Since you don’t have live patients in front of you to examine, you’re completely dependent on the record, and if it’s incomplete or flawed, you’re stuck with it and you better realize it so that your analysis isn’t skewed.”
What researchers can do with the Explorys database is pretty impressive, though. For example, a MetroHealth colleague had a hunch that there may be a higher incidence of gout among Down Syndrome patients, and mentioned it to Kaelber. Normally, that kind of study would be extremely difficult to do because both health problems are relatively rare.
Kaelber was able to log into the database at home and find a three to five-fold increased risk using the Explorys platform. Their results should be published within a year.
Another study in the works will demonstrate the power of the Explorys system in detecting rare but potentially dangerous side effects in new drugs on the market.
“The Explorys platform has 14 million patients today, so even something that happens 1 in a million times is going to happen 14 times in that database,” Kaelber said.
He hopes to be able to use the Explorys platform to compare the side effects of different drugs in patients, and to see if there’s any way of predicting which patients will have certain reactions.
“Those are the things that in my mind are taking this tool to the next level. We don’t want to repeat other people’s work, we want to do original work.”