How a Learning Health System Fueled COVID-19 Clinical Guidelines

Healthcare stakeholders leveraged a learning health system model of clinical decision support to develop and implement agile COVID-19 clinical guidelines, according to a Health Affairs blog post.

A learning health system is a closed loop clinical decision support model that combines current evidence, clinical experience, and data analytics to accelerate the creation of clinical guidelines, according to blog authors Blackford Middleton, Matthew Burton, Christopher J. Tignanelli, John D. Halamka, Sandy Schneider, Michael Barr, and Pawan Goyalwrote.

While stakeholders have discussed the health IT concept for years, the infrastructure to support a learning health system is relatively new, the group noted. COVID-19 presented a unique opportunity to test the concept of a learning health system.

The C19 Healthcare Consortium, led by Mayo and MITRE, convened a workgroup to develop a clinical guideline for COVID-19 severity classification. Members of the workgroup came from a variety of healthcare organizations, including the American College of Emergency Physicians (ACEP) and the COVID-19 Healthcare Coalition. 

While it usually takes years for healthcare stakeholders to implement clinical guidelines, the learning health system model allowed the group to put out COVID-19 severity classification guidelines within weeks.

“A guideline approved by top emergency physicians meant that each facility treating COVID-19 patients didn’t have to start from scratch learning how to triage for this emerging infection through empirical observation; instead, the data and knowledge from tens of thousands of COVID-19 cases was brought to bear in a guideline that clinicians could trust,” the authors wrote.

The work group leveraged agile knowledge engineering to assemble the guidelines, which “weaves emerging evidence and data with clinical knowledge to form faithful, computable expressions of best-practice recommendations.”

Since the start of the pandemic brought few studies related to COVID-19 to reference, the stakeholders reviewed Italian and other European outbreak data and resulting studies on how clinicians quantified COVID-19 severity to create an initial framework for the learning health system.

From this framework, the work group drafted digital representations of clinical guidance. As more evidence emerged and real-world patient data poured in, the guideline and its digital representation sharpened.

“Tasks such as clinical concept identification, value set specification, test case creation, and key inference and decision logic were defined in parallel with the narrative—rather than the traditional sequential approach,” the authors noted. “Once assembled, a national group of ACEP clinical experts reviewed and approved these best practices.”

Health IT vendors then put the recommendations into a digital format by engineering interoperable computable practice guidelines (CPGs) for clinician workflow integration.

“The resulting care guidance dashboard shows recommended treatment pathways based on 120 data points for an individual patient’s demographics, risk factors, and test results,” the authors wrote.

Unlike a static PDF flowchart guideline that may possibly be revisited years after publishing, the workgroup updated the COVID-19 severity tool four times in its first nine months.

The computable guidelines are continuously updated based on data collected from patients who were treated using the recommendations.

“These interoperable, computable guidelines represent a new wave of team-based, technology-enabled clinical guideline development,” the authors explained. “Historically, software engineering proceeded lockstep through a series of activities: requirements assessment, workflow assessment, design, quality assurance, user-testing, and so forth. This approach reflected “waterfall” software development, in which one phase must be completed before the next begins.”

“Today, that method has been replaced by Agile: With cloud software and application delivery through websites and app stores, most smartphone, tablet, laptop, and desktop computer users are accustomed to installing light, continual updates to the many apps they use—monthly, or even weekly,” they continued.

The authors emphasized that clinical guideline developers should leverage agile knowledge engineering to stay on the cutting edge of medicine as data uncovers new understandings of a disease.

“The COVID-19 guidelines prove that it is possible to create point-of-care decision support based on the latest clinical best-practice guidance in an agile fashion, which initiates a true learning feedback loop,” the authors concluded.