Providers Use Big Data Instead Of Costly Trials
By Katie Wike, contributing writer
Mining existing data might be a cost-effective alternative to time consuming and expensive clinical trials.
Clinical trials can take years to complete and come with a high price tag, but what if all the information needed to zero in on rare conditions was in patient records already?
That’s the theory Jennifer Frankovich, a rheumatologist at Lucile Packard Children's Hospital in California, tested when she came across a case with no similar past scientific studies. According to the New York Times, Frankovich was presented with the case of a 13-year-old girl who showed symptoms suggestive of kidney failure and was quickly diagnosed with lupus.
The particular combination of symptoms seemed familiar to Frankovich, though, and she decided to do more research. Since there were no published studies on cases like this, she searched the hospital database and came up with what she had been looking for – cases where patients with the same symptoms had developed life-threatening blood clots.
“I did some very simple statistics and brought the data to everybody that I had met with that morning,” she says. “It was very clear, based on the database, that she could be at an increased risk for a clot.”
Based on this information, the patient was given drugs and did not develop a clot. It’s not certain if she would have developed one, but as the Times explains, A large, costly and time-consuming clinical trial with proper controls might someday prove Frankovich’s hypothesis correct. But large, costly and time-consuming clinical trials are rarely carried out for uncommon complications of this sort.”
“In the absence of such focused research, doctors and scientists are increasingly dipping into enormous troves of data that already exist – namely the aggregated medical records of thousands or even millions of patients to uncover patterns that might help steer care.”
According to iHealth Beat, data mining can prove vital in situations like this where previous study has been limited. There are concerns, however, that privacy may be at risk. While patients might allow their data to be used in the direct care of a patient, if their records were used for research each patient would need to sign a consent form. Another point is that the research could be incomplete since health records would only show those who sought care and not healthy individuals.
Frankovich recalled to the Times something another colleague had told her, “She told me, ‘Research this decade benefits the next decade,’ ” Frankovich says. “That was how it was. But I feel like it doesn’t have to be that way anymore.”