JMIR Publications

ABSTRACT

Background:

Administrative workload in general practice limits time for direct patient care. Artificial intelligence (AI)-assisted documentation has been proposed as a way to reduce documentation burden, but evidence from routine primary care settings remains limited.

Objective:

To evaluate general practitioners’ acceptance of AI-assisted documentation and its association with documentation time and clinical note quality in routine Danish general practice.

Methods:

We conducted a quantitative pre-post study in Danish general practice. Twenty general practitioners documented 12 consecutive consultations before and after implementation of an AI-assisted documentation system. Documentation quality, structure, clinical clarity, and documentation time were self-assessed using standardized audit forms. All notes were additionally evaluated by two independent blinded physicians. Technology acceptance and usability were assessed using the Technology Acceptance Model (TAM) and the System Usability Scale (SUS).

Results:

Self-assessed documentation structure and clinical clarity improved after implementation, while documentation time category decreased. GP-level paired analyses showed moderate improvements in structure and clarity and a reduction in documentation time. Blinded external assessment demonstrated comparable improvements in quality, structure, and clinical clarity. The association between documentation time and perceived quality was negligible. TAM and SUS indicated high clinician acceptance.

Conclusions:

AI-assisted documentation was associated with reduced documentation time and maintained or modestly improved clinical note quality in routine general practice, with high clinician acceptance. These findings support the feasibility of AI-assisted documentation in primary care.