Related Experiment Video
Updated: May 27, 2026

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
Published on: July 11, 2025
Beyond readability: Advancing patient-centered evaluation of AI-generated clinical reports.
Michela Monaci1, Elena Viviani1, Federico Sottotetti2
1WHYpsy Lab, Department of Brain and Behavioral Sciences, University of Pavia, Pavia, Italy.
Large language models can simplify medical documents, but true patient-centered communication requires more than just readability. Evaluating AI-generated content must include comprehensibility, relevance, and patient empowerment for meaningful engagement in care.
Area of Science:
- Medical Informatics
- Artificial Intelligence in Healthcare
- Patient Communication
Background:
- Large language models (LLMs) show potential for improving clinical documentation and patient access to medical information.
- Recent work has explored LLM-generated patient-centered reports, such as GPT-4 for prostate cancer pathology.
- Readability is a key consideration for AI-generated clinical documents.
Purpose of the Study:
- To argue that readability alone is insufficient for genuinely patient-centered communication.
- To propose broader multidimensional criteria for evaluating AI-generated clinical documents.
- To emphasize the importance of patient and caregiver involvement in AI tool development.
Main Methods:
- Review of recent evidence on various patient-facing medical documents (e.g., after-visit summaries, discharge summaries, open notes).
- Analysis of existing literature on AI in healthcare and patient communication.
- Conceptual framework development for evaluating AI-generated clinical communication.
Main Results:
- Readability is a necessary but not sufficient criterion for patient-centered AI-generated clinical documents.
- Broader evaluation criteria are needed, including comprehensibility, relevance, usability, emotional impact, and empowerment potential.
- Direct patient and caregiver involvement is crucial for designing and evaluating these tools.
Conclusions:
- AI-generated clinical documents must move beyond mere simplification of medical terminology.
- Effective AI tools should support patients in understanding health information and actively participating in their care.
- Multidimensional evaluation and co-design with patients are essential for truly patient-centered AI communication.
Related Concept Videos
Methods of Documentation III: PIE
Introduction to Documentation and Reporting
Nursing documentation records essential information and details regarding a patient's care and treatment in written or electronic form. It is a critical aspect of nursing practice that involves documenting assessments, interventions, outcomes, and other relevant details about a patient's health status.
Documentation maps the patient's health journey by creating a comprehensive and precise...
Patient-centered Care
Data Reporting and Recording
Purpose of Health Records I
Here's a breakdown of how health records serve these purposes:
Guidelines for Writing Outcome
Patient outcomes reflect the patient's response to the goal rather than what the nurse aims to achieve. Terminology should be observable and measurable to avoid the reader's interpretation. The desired outcome should be realistic and achievable in the designated care timeframe. Expected outcomes should align with adjunctive therapies. The outcome should enhance care evaluation by...
