Valere Lemon, MBA, MHIA, RN, CPHQ

Resilience in healthcare means that organizations are continually ready to navigate disruptions of any size without sacrificing quality of care or patient and staff safety. Health systems maintain resilience by embedding the principles of high reliability into their culture, workflows, and processes. These high-reliability organizations (HROs) don’t approach reliability as a short-term project or checklist; rather, they embed the principles into every interaction and action beginning with senior leadership. As a result of a practice, not project, approach to reliability, HROs “rarely fail even though they encounter numerous unexpected events,” as authors Karl Weick and Kathleen Sutcliffe explain in their book series, “Managing the Unexpected.”

Healthcare organizations have worked hard to improve patient safety over the past several decades, however harm is still occurring at an unacceptable rate. Though the healthcare industry has made efforts (largely regulatory) to reduce patient harm, these measures are often not integrated with health system quality improvement efforts and may not result in fewer adverse events. This is largely because they fail to integrate regulatory data with improvement initiatives and, thus, to turn patient harm information into actionable insight.

Fully integrated clinical, cost, and operational data coupled with predictive analytics and machine learning are crucial to patient safety improvement. Tools that leverage this methodology will identify risk and suggest interventions across the continuum of care.

Health systems can leverage the predictive potential of machine learning to improve outcomes, lower costs, and save lives. Machine learning, however, doesn’t inherently produce insights that are actionable in the clinical setting, and frontline clinicians need information that’s accessible and meaningful at the point of care. Thoughtfully designed visualizations of machine learning insights are a powerful way to give clinical users the information they need, when and how they need it, to support informed decision making.

A design framework for machine learning visualizations addresses three key questions about who will use the decision-support insights and how:

1. People: who are the targeted users?
2. Context: in what context or environment do they work?
3. Activities: what activities do they perform?