High-quality data enables medical research

While our focus on the pandemic has now faded, our health data quality issues remain. We’re swimming in health data – by some estimates, a third of all data generated globally is related to health and healthcare, and that amount is growing by more than 30% every year.

With all this data, why can’t we answer our most pressing health questions? Which of the top five diabetes medications (if any) will work best for me? Will back surgery be more effective than physiotherapy for my spine? What are the chances that I will need chemotherapy in addition to radiation therapy to make my tumor go away?

EHRs have become ubiquitous

Electronic health records (EHRs) have become ubiquitous in the United States, thanks in large part to a multibillion-dollar federal initiative that made interoperable EHRs a national goal. The HITECH Act of 2009 provided incentives for healthcare providers who computerized and penalties for those who did not. In addition to the improved patient care this would enable, the millions of digitized health records would create opportunities to transform medical research.

“Before EHRs, clinical research was all paper-based,” says Dale Sanders, chief strategy officer at Intelligent Medical Objects (IMO), a health data enablement company that provides clinical terminology and tools to improve quality of medical data. “You were transferring that paper data into spreadsheets and doing your own data analysis in a very small local environment. It didn’t give a broader view of a patient’s life, and it certainly didn’t allow for a broader analysis of the population.

Theoretically, EHRs should make it possible to aggregate, analyze and search information gathered from millions of patients to uncover patterns that are not obvious on a smaller scale, as well as methodically track the health status of a single patient over time. Imagine being able to quickly compare and analyze the cases of a few thousand people with a particular rare disease or follow the users of a certain drug over a period of time to observe long-term side effects that weren’t not evident in the tests.

Of course, it’s not that easy. “There’s a lot of raw data (in EHRs) and it’s very, very dirty,” says John Lee, MD, an emergency physician and clinical informatics specialist who has served as chief medical information officer for several health systems. “Some of them aren’t accurate, and what’s accurate isn’t presented in a usable and scalable way. There is a tantalizing opportunity at hand if we could get out of our own way.

Sanders agrees. “Covid has made us all realize that the data we collect with EHRs is not very good for clinical research, or for responding to pandemics and public health challenges. It’s time to change the way we use them.

Download the report.

This content was produced by Insights, the custom content arm of MIT Technology Review. It was not authored by the editorial staff of MIT Technology Review.