A team at Lucile Packard Children’s Hospital at Stanford queried the hospital’s records to help weigh the pros and cons of a risky, but potentially beneficial, treatment that has not yet been evaluated in the medical literature.
Using a data-storage system designed to support clinical research, the team decided the treatment was appropriate, and the patient recovered from her medical crisis and is now doing well.
“This is the future of the electronic medical record and, I hope, the future of a lot of clinical research,” said Scott Sutherland, MD, who is a pediatric nephrologist at Packard Children’s and the senior author of a perspective paper describing the case. The paper was published online Nov. 2 in the New England Journal of Medicine.
“Our story is unique,” said Christopher Longhurst, MD, who is a co-author of the paper and an architect of Packard Children’s electronic medical record system. Few hospitals have research capabilities built into their electronic medical records, he said, and although the concept of using the records to answer clinical questions in real time has been proposed before, the idea has not previously been put into practice.
The advance was possible because, unlike most doctors, the faculty physicians at Packard Children’s can access large sets of de-identified patient data from the hospital’s electronic medical record via a computer tool developed for clinical research.
The patient in this case was a 13-year-old girl admitted to the hospital with severe inflammation of the kidneys and pancreas that had developed as a complication of lupus. Her condition is rare in children, and no clinical trials or other medical literature addressed the best course of care for her unique situation. The medical team, led by rheumatologist Jennifer Frankovich, MD, realized the girl was at risk for blood clots that could cause organ failure or death. However, the anticoagulant drugs that would prevent blood clots would also increase the risk of bleeding from invasive medical procedures, such as the kidney biopsy the girl needed.
Frankovich, who is also an instructor of pediatric rheumatology at the Stanford University School of Medicine, consulted her colleagues about what to do. They said anticoagulation probably wasn’t needed, but had little evidence to back up their advice. That worried Frankovich, who couldn’t shake her anxiety about the patient.
“She was sick, and I felt like in the next three days we could make her a lot sicker or a lot better,” said Frankovich, the first author of the paper.
Faced with such sparse information, she turned to the hospital’s aggregate electronic medical record system. She examined de-identified patient data from the 98 pediatric lupus patients who received care at Packard Children’s between October 2004 and July 2009. Ten patients had developed blood clots. With a quick statistical analysis, Frankovich saw that the risk for blood clots was much higher in lupus patients with kidney and pancreatic inflammation. Extracting this information from paper charts would have taken months; with the electronic tools, Frankovich completed the job in four hours, and gave the patient an anticoagulant drug within 24 hours of her hospital admission.
The analysis is important because it let the team quickly pick up on a pattern that a single physician would never have been able to see otherwise.
Scott Sutherland “Physician recall has the potential to be biased,” said Sutherland, who is also a clinical assistant professor of pediatric nephrology at the School of Medicine. “And with the myriad data currently available within the electronic medical record, sometimes it’s hard to pick out what’s important. This type of chart review is much more accurate and efficient.”
At most hospitals, electronic medical records are still used only like paper charts: as repositories for doctors’ orders and nurses’ notes about the patient’s condition. This case shows that the records can and should become much more powerful, said Longhurst, who is chief medical information officer at Packard Children’s and a clinical assistant professor of pediatrics in systems medicine at Stanford.
“The electronic medical record should not just be a place to document data,” Longhurst said. “We actually should be learning from every patient we’re seeing, creating real-time knowledge bases.”
The ability to learn from electronic records is getting faster, the team said. Thanks to advances in the Packard Children’s electronic medical record and Stanford’s accompanying research tools, the search that took Frankovich four hours when this patient was seen in early 2010 would take about an hour today.
Frankovich added, “I expect in the future that you’ll be able to look at aggregate patient data during rounds, so you can make more-informed patient care decisions right there.”