Healthcare Analytics, Population Health Management, Healthcare Big Data

Tools & Strategies News

Bridging the Gap Between Big Data Science, Health IT Usability

How can the healthcare system overcome the persistent divide between the science of big data analytics and real-world health IT usability?

By Jennifer Bresnick

- The health IT landscape often seems starkly divided between two opposing camps: those who design elegant algorithms and regimented workflows in the idealized sterility of the R&D department, and those whose frenzied, frustrating daily experience in the hospital, office, or clinic have taught them that there is no such thing as an out-of-the-box solution to any of their big data needs.

This gulf between theoretical data science and the harsh realities of clinical practice are at the root of the healthcare system’s ongoing health IT usability problems, which have only compounded in recent years as new regulatory programs and the demands of value-based care ramp up providers’ critical need for actionable insights and intuitive documentation tools at the point of care.

As pay-for-performance reimbursement structures pressure providers to engage in shrewder decision-making about the costs and necessities of common procedures, healthcare organizations have started to scoop up big data analytics tools that promise meaningful clinical decision support (CDS), predictive analytics, and population health management capabilities.

But many of these tools have quickly fallen short of those promises, argues a team of data scientists and researchers from MIT, leaving providers feeling more than a little cheated by the health IT revolution. 

In order to truly extract value from healthcare analytics, the industry must use emerging strategies, including research incentives and better education, to overcome the chasm between theory and practice.

READ MORE: IBM Watson Health, FDA Partner for EHR, IoT Blockchain Project

“Medicine has clumsily entered its digital age via the back door,” the team says in an article published last month in the Journal of Medical Internet Research. “There is a persistent gap between the clinicians required to understand the clinical relevance of the data and the data scientists who are critical to extracting useable information from the increasing amount of health care data that are being generated.”

“Practitioners continue to make determinations in a technically unsupported and unmonitored manner due to a lack of high-quality evidence or tools to support most day-to-day decisions, and as a result the rate of diagnostic errors by individual practitioners is unacceptably high.”

Since the beginning of the EHR Incentive Programs, federal rule makers have made it a top priority to reduce those variations in care by implementing a layer of data-driven technologies to help discover, address, and eliminate quality and performance issues. 

Opinions vary as to whether or not electronic health records and digital documentation requirements have helped or hindered this goal, but there is little question that a secondary layer of complementary technologies, such as CDS systems, integrated risk scoring tools, and patient management systems are often required to supplement the basic capabilities of the EHR.

Increasingly, these systems are driven by machine learning algorithms that use previous data inputs and past results to refine future recommendations, allowing clinicians to leverage mistakes and successes to improve the accuracy and delivery of patient care.

These strategies have started to find favor with designers and clinicians exploring complex and multi-faceted use cases in patient care, including chronic disease management, imaging analytics, hospital readmissions, and sepsis.  But many providers are either hesitant to accept yet another step in their convoluted workflows, or do not believe that the investment required in such cutting-edge tools will produce a sufficient return.

Creating and implementing machine learning tools that bring value to clinicians and patients without overwhelming the workflow will require industry-wide collaboration, a broader understanding of how to apply data science to clinical practice, and enhanced opportunities to build knowledge and engage in research about the role and adoption of big data analytics, the researchers assert.

Continuing to increase cooperation between data scientists, health IT developers, and end-users will be vital for harnessing the potential of machine learning, the article says, citing the positive example of the Icahn Institute for Genomics and Multiscale Biology at Mount Sinai Health System in New York.

Staffing the precision medicine center with researchers, scientists, and clinicians from a variety of backgrounds allows the Institute to use each individual’s unique perspectives on the role and application of big data to clinical care as a way to achieve a unified goal.

“By linking this talent with disease centers within Mount Sinai, and using the tools of machine learning and predictive modeling (elements of big data), scientists have already published on inflammatory models in common-variant Alzheimer disease and are taking a closer look at one of the most complex and biodiverse cell populations in the human body, the gut microbiome, which may be responsible for far more of the body’s homeostasis than previously realized,” the researchers said.

“Bridging the divide may be facilitated by instilling researchers with a greater appreciation of the benefits offered through collaboration with colleagues of complementary disciplines.”

Bringing this strategy to scale across the entire care continuum will require the healthcare system to retool its educational system to promote the value and utility of big data analytics – a process that is also already underway in many organizations.

Training medical students to understand the underlying principles of data science and machine learning to equip new physicians with the strategies required to engage in population health management and preventive care has recently become a top priority for groups such as the American Medical Association.

Yet qualified instructors in health informatics, statistics, and machine learning are hard to find, the MIT team points out, due to the newness of the field.  Training a new generation of educators who can blend clinical experience with a big data background will require a concerted, long-term effort.

“If we accept that over the next half century there will likely be an increasing need for hybrid skills of this nature, then there is a strong case for inclusion of data science in the core curriculum in medical school and during residency training,” says the article.

“Perhaps most important, creating a medical culture that is aware of and respectful of the importance and potential power of data for supporting and improving both practice and research may be the most important and ultimately effective element. It is desirable that each participant in the clinical process realizes and understands their role in the overall system of providing reliable and robust data that they and others will subsequently use in improving care.”

The last piece of the puzzle is aligning financial and career incentives for adopting a big data outlook.  Academic publications may encourage collaborative research by seeking out joint submissions from clinicians and data scientists, the team suggests, which may make it easier for hybrid researchers to remain competitive in their chosen fields.

Opening up new opportunities for grant funding would likewise enhance the research landscape, encouraging clinicians and data scientists to collaborate and enhance the industry’s underlying knowledge of how to combine the two disciplines effectively.

Implementing these recommendations will push the healthcare industry along the path of discovery while helping data scientists and clinicians better understand each other’s’ needs, viewpoints, and capabilities.

“Better use of clinical data has the potential to address a number of important, problematic, and unresolved issues in the health care system,” the paper concludes.

“Clinicians should not feel like interchangeable cogs entering reams of data blindly into a vast black hole of no return; data scientists should not be discovering new knowledge and developing predictive algorithms isolated from the domain experts. Rather, all should see themselves as diversely necessary components of a truly functional clinical data system that works toward providing excellent care to individuals and populations while working to improve all facets of that care.”

The Difference Between Big Data and Smart Data in Healthcare

Reducing Medical Errors with Improved Communication, EHR Use

Health IT usability and big data analytics

Continue to site...