Modeling Precision Feedback Knowledge for Healthcare Professional Learning and Quality Improvement

Area of Science:

• Health Informatics
• Medical Education
• Learning Health Systems

Background:

• Healthcare providers require continuous learning due to rapidly expanding biomedical knowledge.
• Electronic Health Record (EHR) data is increasingly used for clinical performance measurement, necessitating improved learning support.
• Existing support systems often lack personalization, failing to optimize learning based on individual provider needs.

Purpose of the Study:

• To develop a Precision Feedback Knowledge Base (PFKB) as an open resource.
• To support the creation of precision feedback systems for healthcare providers.
• To provide infrastructure for learning health systems by modeling feedback personalization.

Main Methods:

• Designed and developed the PFKB, incorporating knowledge models for feedback personalization.
• Included key components such as quality measures, feedback message templates, causal pathway models, signal detectors, and prioritization algorithms.
• Established the PFKB as an open resource for broader implementation.

Main Results:

• The PFKB was successfully developed, containing structured knowledge for personalized feedback.
• The knowledge base integrates various components essential for effective precision feedback systems.
• The PFKB is currently implemented in a national quality improvement consortium for anesthesia care.

Conclusions:

• The PFKB offers a foundational resource for enhancing provider learning through personalized feedback.
• Precision feedback, supported by the PFKB, has the potential to improve learning health systems.
• The implemented system aims to optimize provider feedback emails, promoting continuous professional development.