“Big Data” is a major buzzword these days.
The topic has been making waves in other industries for some time, but many of its applications in healthcare are still in their early stages. The use of big data shows exciting promise for improving health outcomes and controlling costs, as evidenced by some interesting use cases, but the practice seems to be defined somewhat differently by each expert we ask.
In this article, we’ll explain exactly what big data in medicine is and how (and by whom) it’s currently being used to improve patient care today.
Here’s what we’ll cover:
What is big data in healthcare?
Big data in healthcare refers to the vast quantities of data—created by the mass adoption of the Internet and digitization of all sorts of information, including health records—too large or complex for traditional technology to make sense of.
The problem has traditionally been figuring out how to collect all that data and quickly analyze it to produce actionable insights. But with emerging big data technologies, healthcare organizations are able to consolidate and analyze these digital treasure troves in order to discover trends, better treat patients, and make more accurate predictions.
I wanted to understand what big data will mean for healthcare, so I turned to big data analytics and healthcare informatics expert Dr. Russell Richmond to discuss what the future holds.
Dr. Richmond is a leading healthcare technology authority whose experience includes building large data analytics companies, advising health system executives as a consultant, and serving on the boards of big data organizations.
The biggest big data benefit: more precise treatments
According to Dr. Richmond, one of the most exciting implications for big data in healthcare is that providers will be able to deliver much more precise and personalized care.
With a more complete, detailed picture of patients and populations, they’ll be able to determine how a particular patient will respond to a specific treatment, or even identify at-risk patients before a health issue arises.
Big data is already being used in healthcare—here’s how
Understanding the big picture of big data in medicine is important, but so is recognizing the real-world applications of data analytics as they’re being used today.
To that end, here are a few notable examples of big data analytics being deployed in the healthcare community right now.
More accurate diagnoses
Right now, data analytics tools exist that provide better clinical support, at-risk patient population management, and cost of care measurement. Many of these systems have established expansive databases—some with billions of data points—that they can then apply sorting and filtering algorithms to in order to rapidly analyze all that information.
One amazing thing that allows users to do is pinpoint how variations among patients and treatments influence health outcomes. Based on these insights, providers can determine more precise treatment plans for individual patients or patient populations.
For example, according to Dr. Richmond, in a world with big data, “general asthma” may no longer be a sufficient diagnosis. Big data’s granularity could allow us to detect and diagnose multiple variants of asthma, with different treatment pathways for each. Data mining could point physicians to the precise treatment plan called for by each patient’s unique case.
Genomics, as Dr. Richmond pointed out in our discussion, is the next frontier of medicine.
The cost of genome sequencing is falling; you can sequence your complete genome for a couple of thousand dollars these days, down from around $100 million a decade ago. As a result, the volume of genomics data is growing rapidly—and so is our ability to take advantage of that data.
Using genomic data is one way we’re already able to more accurately predict how illnesses like cancer will progress.
For example, Emory University and the Aflac Cancer Center partnered with a genomic data analytics organization called NextBio to study data related to medulloblastoma, the most common malignant brain tumor among children.
Medulloblastoma currently has a uniform treatment approach: radiation therapy. Emory and Aflac are using NextBio to look at clinical and genomic data to discover biomarkers that can help predict the metastases of cancer in young patients. Providers, in turn, will use this information to pinpoint targeted therapy approaches based on the biomarkers of their individual patients.
Population health management
While big data’s main goal for medicine is to improve patient outcomes, another major benefit to data analytics is cost savings.
Some systems are able to collect information from revenue cycle software and billing systems to aggregate cost-related data and identify areas for reduction.
For example, the state of Rhode Island has partnered with InterSystems to use its HealthShare Active Analytics tool to collect and analyze patient data on a statewide level. The state’s Quality Institute then found that about 10% of major lab tests performed in over 25% of the state’s population were medically unnecessary—a discovery that has since helped Rhode Island reign in spending as well as improve quality of care.
Big data for the small practice
So, this is all well and good for major health organizations that can afford big data analytics tools today, but what does this mean for the independent practice?
Dr. Richmond summarizes the challenge: “We’re spending an awful lot of time putting information in [to digital systems like EHRs], but we haven’t yet harnessed the insight that comes from using that information once it’s in.”
Some strides are being made, though. In a recent survey we conducted of medical providers on the impact of the HITECH Act, interoperability was a very common theme. Patient too are eager to see the benefits of more widely shared health data.
Legislators have been talking about empowering medical providers to become more connected for a long time, but only recently has interoperability truly become imperative for Medicare reimbursement qualification. MACRA is now incentivizing interoperability and requiring the use of EHRs that support interoperable functionality.
Outside of federal regulations, investors also see big data as a huge moneymaker—and more investment will lead to more solutions.
In a few years, Dr. Richmond expects big data and the personalized medicine it facilitates to help eliminate “one-size-fits-all” approaches to treatment. And importantly, he says, this ability to better manage care should result in lowered health costs as well.