Pathologists and clinical laboratory managers could find opportunity to add value as providers learn to use big data to improve patient outcomes and lower costs

Early adopter accountable care organizations (ACOs) are establishing data warehouses. This is a first step in collecting and analyzing healthcare big data. The move toward integrated care makes big data critical to an ACO’s success. Pathologists and clinical laboratory managers will want to follow the healthcare big data trend because laboratory test results will be a major component of that data.

The Goal of Healthcare Big Data

The goal for healthcare big data is twofold: 1) develop the ability to aggregate a vast amount of data from wide-ranging sources, and 2) use that data in real time to improve care and lower costs, a recent story published in Modern Healthcare (MH) reported. New performance-based reimbursement models mean that big data analytics will be essential for ACOs to succeed going forward.

However, only a few of the largest, most sophisticated ACOs have established big data warehouses. “While other industries have been far more successful at harnessing the value from large-scale integration and analysis of big data, healthcare is just getting its feet wet,” wrote Nilay D. Shah, Ph.D. and Jyotishman Pathak, Ph.D. in an article in the Harvard Business Review (HBR). Dr. Shah is an Associate Professor in the Division of Health Care Policy and Research at Mayo Clinic. Dr. Pathak is Director, Clinical Informatics Services, at Mayo and an Associate Professor in Mayo’s Division of Biomedical Statistics and Informatics.

Nilay Shay PhD and Jyotishman Pathak PhD

The current research of Jyotishman Pathak, Ph.D. (on left) focuses on secondary uses of electronic health record data for clinical and health care delivery research, integration of genomic data within electronic health records, and clinical decision support systems for personalized therapeutics. Nilay D. Shah Ph.D.  (on right) has an ongoing research agenda for evaluating alternative models of chronic disease care delivery, medication adherence in chronic disease, policy implications of shared decision making and disparities in care. (Photos and captions copyright Mayo Clinic.)

Dashboards Allow ACOs to Apply Big Data in Real Time

An ACO currently ahead of the curve is Minneapolis-based Medicare Pioneer Allina Health. Allina’s data analysts have developed about 60 dashboards from information from 42 sources, according to a recent MH story. The dashboards allow the system’s providers and administrators to visualize the current status of metrics and track key performance indicators across the entire system. The source information includes clinical data from electronic health records (EHR), as well as information about costs, claims, and patient demographics.

“We’re able to get very specific near real-time information and data on [ACO patients’] health and track our performance on key measures that we could be rewarded for,” stated Ross Gustafson in the MH piece. Gustafson was formerly Vice President of Performance Resources at Allina.

ACOs Still Face Significant Big Data Challenges

ACOs still face many challenges in realizing the potential of big data analytics. For one, the ACO market is still very small, MH reported. That means health IT developers lack incentive to create systems that serve ACOs’ care-coordination needs. For example, an upcoming Healthcare Information and Management Systems Society convention has 81 vendors registered as data analytics system developers. Of those, only five promote ACO capabilities in their event profiles. Lack of standardization and interoperability are also hurdles.

“The vast amount of data generated and collected by a multitude of agents in health care today comes in so many different forms: from insurance claims to physician notes within the medical record, images from patient scans, conversations about health in social media, and information from wearables and other monitoring devices,” wrote Shah and Pathak in HBR.

“The problem is that this data is everywhere, but it’s incredibly fragmented,” echoed Dwayne Spradlin, CEO of the nonprofit Health Data Consortium, in a story published in Forbes.

Existing ACOs are at very different stages of development in their big data capabilities, noted the MH writer. Interfacing the disparate systems can be expensive. “Just the cost of the interfaces is taking up the bulk of the cost of their IT for ACOs,” observed Farzad Mostashari, M.D., former National Coordinator for Health IT at the Department of Health and Human Services. He is co-founder of Aledade, a Bethesda, Md.-based ACO advisory company for primary care physicians.

Development of the Full Potential of Healthcare Big Data Will Require Time and Realistic Expectations

Most ACOs are still a long way from effective use of big data to improve care, MH reported. It will take another five to ten years before big data attains broad market applicability and becomes widely adopted in healthcare, cautioned Robert H. Booz, Vice President of IT research firm, Gartner, Inc. (NYSE:IT).

However, healthcare’s big data future still looks bright, according to Forbes. “We should have realistic expectations,” advised Spradlin in the Forbes story. “There will be big breaches of health data. There will be insights drawn from the data that are wrong, but as we really use and exercise these methods, the system will become evidence-driven and outcomes-driven, and some of the things we want to happen will happen.”

As ACOs and other providers wend their way toward the full potential of big data analytics, well-informed pathologists and clinical laboratory managers will look for value-added ways to interface with clinicians in using the medical laboratory component of big data to improve the ability to maintain health, and to anticipate and treat illnesses.

—Pamela Scherer McLeod

Related Information:

ACOs Make Progress in Using Big Data to Improve Care

How Big Data Will Help Save Healthcare

Why Health Care May Finally Be Ready for Big Data 

What is the Value of Healthcare Dashboards?