Leveraging AI-enabled learning health systems to advance value-based health care: A conceptual framework

Area of Science:

• Healthcare Systems Science
• Artificial Intelligence in Medicine
• Organizational Learning

Background:

• Healthcare systems face a significant 17-year gap between evidence discovery and implementation.
• This

Purpose of the Study:

• To propose an AI-enabled Learning Health System (LHS) framework.
• To address the limitations of existing LHS frameworks in institutionalizing learning at speed and scale.

Main Methods:

• Leveraging artificial intelligence (AI) to connect micro-level clinical learning with macro-level organizational decision-making.
• Utilizing organizational learning theory to model AI's role in knowledge capture, conversion, and institutionalization.
• Establishing continuous, bidirectional feedback loops between patient-provider data and system-wide insights.

Main Results:

• The proposed AI-LHS framework integrates speed, scale, and micro↔macro connections.
• AI serves as a foundational learning engine, not merely an adjunct.
• Case examples demonstrate AI's capability in driving real-time operational learning and institutional memory.

Conclusions:

• Organizations must assess readiness and align on value-based goals for AI-LHS implementation.
• Investment in data infrastructure, interoperability, and a learning culture is crucial.
• Adopting a sociotechnical approach with safeguards for equity, privacy, and security accelerates value-based care transformation.