Predicting Electronic Health Record Usability: Scoping Review of Adoption Models, Metrics, and Future Directions

Area of Science:

• Health Informatics
• Human-Computer Interaction
• Software Engineering

Background:

• Electronic health records (EHRs) are crucial for healthcare data sharing and patient safety.
• Despite vendor adherence to usability standards, persistent EHR usability issues hinder efficiency and increase error risks.
• Existing research often focuses on EHR adoption rather than predicting usability.

Purpose of the Study:

• To synthesize research on EHR adoption and usability, focusing on theoretical models, measurement, factors, and analytic methods.
• To identify research gaps and opportunities for integrating predictive analytics and artificial intelligence (AI) to enhance EHR usability.
• To extend prior reviews by focusing on the prediction of EHR usability.

Main Methods:

• Scoping review following Joanna Briggs Institute and PRISMA-ScR guidelines.
• Systematic search of MEDLINE, Web of Science, IEEE Xplore, and Scopus (2009-2025).
• Inclusion of empirical research using predictive methods for EHR usability; thematic synthesis of data.

Main Results:

• 47 studies met inclusion criteria, with most examining EHR adoption using frameworks like the Technology Acceptance Model.
• Commonly identified usability factors include perceived usefulness, ease of use, effort expectancy, and facilitating conditions.
• Regression-based methods and structural equation modeling were prevalent; no studies applied predictive modeling or AI for EHR usability.

Conclusions:

• Predictive modeling for EHR usability remains significantly underdeveloped.
• Dominant EHR frameworks prioritize adoption over operational usability, using biased, cross-sectional measures.
• There is a substantial opportunity to integrate predictive analytics, AI, and longitudinal measures for dynamic EHR usability models.