Skip to content

Data mining in electronic health records could reveal unexpected patterns

Here's an interesting segment of a Forbes Q&A today with Mike Cummins, CIO of the VHA health-care network, that illustrates how electronic health records (EHRs) might allow hospitals to mine data to improve a variety of treatments:

For example, we can see whether or not a bare metal stint is better in all populations. In general, we're looking at the effectiveness of a stint. It's a high-cost item, and we can see if one brand is doing better than another in a population. We can see whether a hip replacement treatment is doing well and whether the patient is out of the hospital and not having to come back multiple times, or whether they have an infection. We're trying to help our hospitals figure out what is the best and most efficient care at the best cost. That turns out to be the best care for our patients at a reasonable cost.

This is, of course, appears to be an extremely useful development, but I'm more interesting in seeing what unexpected patterns emerge from EHR data mining and how those patterns will inform treatments.

While this may seem like a pretty crude comparison, I'm reminded of a great article that appeared long ago in the New York Times showing how Wal-Mart used data mining to fine-tune its supply chain. By studying their customers' spending habits during hurricane season, for example, they identified a number of unexpected items that spike concurrently with sales of flashlights:

"We didn't know in the past that strawberry Pop-Tarts increase in sales, like seven times their normal sales rate, ahead of a hurricane," Ms. Dillman said in a recent interview. "And the pre-hurricane top-selling item was beer."

Thanks to those insights, trucks filled with toaster pastries and six-packs were soon speeding down Interstate 95 toward Wal-Marts in the path of Frances. Most of the products that were stocked for the storm sold quickly, the company said.

So I am keen to learn about the unexpected patterns EMRs produce - the strawberry Pop-Tarts, if you will, of medicine - and what those patterns can teach hospitals about health care.

Related: Analysis of meaningful use rule calls it a "defining moment", David Blumenthal: "You'll get better care" with electronic health records and Mining electronic medical records for research insights

Popular posts

Category:
Stanford Medicine Unplugged
A medical student’s reading list

Former and current Stanford medical students recommends several nonfiction books — as well as authors —that present science through a humanistic lens.