Request a Quote

Health care has a data disparity problem

December 20, 2018

View from a computer screen in a hospital setting

If you’ve been reading this blog, you know that we’re inspired by the promise of big data to improve human health. Big data and analytics promise to uncover hidden patterns that can improve population health and precision medicine. At the same time, nobody understands data’s challenges better than we do.

One such challenge is detailed in this new STAT piece on the difficulty of extracting insights from the health records of American patients since there are so many disparate products holding that data. Says the article:

In the U.S., patient data are stored across more than 700 electronic medical records systems. About 92 percent of hospitals use one of the top five or six EMR providers; but just 60 percent of health care providers’ offices can say the same.

“Most of medicine happens at the primary care interface. And if that part of medicine is cut off from the advances that we’re seeing in machine learning, then we’re missing an incredible opportunity,” Dr. Mark Michalski, the executive director of the Massachusetts General Hospital and Brigham and Women’s Hospital’s Center for Clinical Data Science, told STAT.

Countries like Canada and England, which are closer to EMR standardization in primary care, have better opportunities for extracting insights, the article says. And EMR interoperability through a universal data standard has not yet arrived.

Data acquisitive and EMR agnostic

Although analytics aren’t iSpecimen’s primary business, we’re doing our part to help. Every biofluid, tissue or cell sample on the iSpecimen Marketplace is annotated with de-identified medical data that our suppliers share (with the absolute exception of patient identity information).

Learn More About the iSpecimen Marketplace

We use technology to extract and manage compliant, de-identified patient and specimen data directly from suppliers’ medical records and laboratory information systems. Using that data, we automatically annotate every specimen with information such as:

  • Patient age, gender, ethnicity, race, and geography.
  • Medical conditions covering a wide variety of diagnoses from oncology and cardiology to autoimmune and infectious diseases, as well as healthy normal.
  • Medications and outcomes.
  • Medical procedures.

Every specimen also contains latent information about disease processes, potential biomarkers and genes.

As medicine and technology advance, we won’t stand in the way. Rather, we’ll be part of the solution. We’ll do our best to responsibly share data and overcome data-sharing obstacles. Medical progress and human health depend on it.

Learn about the iSpecimen Marketplace where you can browse millions of richly annotated, de-identified human tissue and biofluid biospecimens, in addition to hematopoietic and immune cell products. You can join for free and creating a login is easy. Request a quote or custom collection today.

Request a Quote