Learning Health Systems Overview

Principles

Definition

Learning health systems is a conceptual and operational paradigm that integrates healthcare delivery and research functions into an iterative cycle of data generation, knowledge creation, and evidence application. This approach investigates the processes by which real-world health data is systematically collected, analyzed, and translated into actionable knowledge, characterized by its continuous, data-driven nature and the rapid translation of findings back into clinical practice and policy, with the ultimate significance of optimizing healthcare quality, safety, effectiveness, and equity.

Ontological type

Core Principles

Data Infrastructure

Governance and Ethics

Key developments

Key Figures

Practice-Based Learning Systems era

Howard S. Barrows [1] was active in the practice-based learning systems era, with affiliations at Southern Illinois University School of Medicine [3]. His contribution centers on promoting problem-based learning as a practical framework for integrating clinical education with problem-based pedagogy, a development highlighted in Problem‐based learning in medicine and beyond: A brief overview [6]. Ronald M. Harden [2] was associated with Duke University [4] and the University of Dundee [5] during this era. His key contributions include AMEE Medical Education Guide No. 15: Problem-based learning: a practical guide [7] and AMEE Medical Education Guide No. 7.: Task-based learning: An educational strategy for undergraduat postgraduate and continuing medical education, Part 1 [8], which provided practical frameworks for education across levels and helped standardize practice in this era.

Interprofessional Learning Systems era

Amy C. Edmondson [1], associated with Harvard University [3] in this era, is a foundational figure in interprofessional learning and patient safety culture. Her key contribution is exemplified by the 2003 paper Speaking Up in the Operating Room: How Team Leaders Promote Learning in Interdisciplinary Action Teams [6], which demonstrates how leadership and speaking-up norms facilitate learning in interdisciplinary teams. David C. Leach [2], with ties to Loughborough University [4] and the University of North Carolina at Asheville [5], contributed to General Competencies And Accreditation In Graduate Medical Education [7]. This work [7] helped standardize cross-disciplinary readiness and accreditation, providing a foundational mechanism for learning health systems during the era.

Data-Driven Learning Systems era

Nigam H. Shah [1] is associated with Harvard University [3] and Stanford University [4] during this era of data-driven learning systems. His work, notably the 2018 paper Implementing Machine Learning in Health Care - Addressing Ethical Challenges [7], highlighted ethical governance and fairness considerations essential for embedding real-time analytics into clinical care. Eric S. Holmboe [2] is associated with the University of California, San Francisco [5] and University of Pennsylvania [6] during this era. His papers The role of assessment in competency-based medical education [8] and Coproducing Health Professions Education: A Prerequisite to Coproducing Health Care Services? [9] foreground the centrality of assessment and co-production in education and practice, supporting rapid-cycle learning and equitable implementation.