Related Experiment Video
Updated: Jun 27, 2026

Development and Implementation of a Multi-Disciplinary Technology Enhanced Care Pathway for Youth and Adults with Concussion
Published on: January 20, 2019
Prompt Architecture as a High-Impact Design Factor in Expert-Rated Clinical Documentation Quality: A Controlled
Idoia Eceizabarrena-Matxinandiarena1,2,3, Emilio Javier Frutos-Reoyo3,4,5, José Ignacio Guerrero-Rojas3,6
1Department of Physical Medicine and Rehabilitation, Hospital Universitario Donostia, 20014 San Sebastian, Spain.
Structured prompting for large language models (LLMs) significantly improved AI-generated clinical documentation quality compared to human authors. Section-based prompting showed the most promise for enhancing AI-assisted healthcare records.
Area of Science:
- Medical Informatics
- Artificial Intelligence in Healthcare
- Clinical Documentation
Background:
- Large language models (LLMs) show potential for clinical documentation support.
- The impact of prompting architecture on LLM documentation quality in complex cases is not well understood.
Purpose of the Study:
- To evaluate three prompting strategies (single prompt, section-based prompt, section-based prompt with writing refinement) for generating inpatient rehabilitation discharge reports using an LLM.
- To compare AI-generated reports with human-authored summaries based on expert physician evaluations.
Main Methods:
- Controlled retrospective methodological study using OpenAI's GPT-5.2.
- Twenty anonymized inpatient rehabilitation cases were processed.
- Outputs were evaluated by two blinded rehabilitation physicians on structure, coherence, completeness, and readability using a structured scale.
Main Results:
- All LLM prompting strategies significantly outperformed human-authored reports in expert-rated quality (p < 0.025).
- Section-based prompting (SBP) showed the highest median performance.
- Prompting strategies explained more variability in quality ratings than case-level factors.
Conclusions:
- Structured, section-based prompting is a practical method for enhancing the perceived quality of AI-assisted clinical documentation.
- Further prospective studies are necessary to assess reliability, safety, and real-world clinical utility.
Related Concept Videos
Methods of Documentation VI: Case Management Model
For example, a patient with a chronic illness...
Methods of Documentation III: PIE
Methods of Documentation II: POMR
Methods of Documentation V: CBE
In CBE, healthcare professionals establish predefined standards of practice that define what constitutes...
Methods of Documentation IV: Focus Charting
It typically involves three columns for recording information:
Guidelines for Nursing Documentation I
Factual:
The following points emphasize the significance of upholding accurate and unbiased documentation in healthcare.
