Data Science
With meaningful metrics come quality improvement and implementation of effective therapies.

Measurement Science (defined as the design, ascertainment and interpretation of suitable metrics) is at the core of a Learning Healthcare System and a critical component at every stage of the quality improvement and implementation process. Measurement science is used in the context of creating critical-solution enabling tools like metrics, models, and knowledge, in the context of improving healthcare practices and health outcomes. This includes the development of performance metrics, measurement and testing methods, predictive models, knowledge modeling protocols, and  the development of the technical basis for standards, codes, and practices.

Using system-wide data to promote performance measurement, improvement efforts, and electronic tools (i.e., clinical reminders) depends on the uniformity of metrics, the efficiency with which they can be obtained, the accuracy with which they are measured, and the interoperability between systems. Whenever a healthcare decision is made, it must be based on valid and reliable data linked with all relevant information. Without meaningful metrics, quality improvement and implementation of effective therapies cannot be accomplished. 

Implementation Science determines how to integrate effective interventions into diverse practice settings while emphasizing direct engagement with the institutions and communities where health interventions are introduced. Key steps in the cycle of quality improvement and implementation include:

  1.  Identify quality gaps
  2. Assess barriers and facilitators
  3. Design and test implementation strategies
  4. Evaluate outcomes
  5. Disseminate evidence-based interventions

Each step involves an iterative process that dynamically responds to formative evaluation. Cross-cutting principles, such as stakeholder engagement and measurement science are essential components of every step.