Artificial Intelligence to Improve Patient Understanding of Radiology Reports.

Area of Science:

• Medical Imaging
• Health Informatics
• Natural Language Processing

Background:

• Diagnostic imaging reports are written for medical professionals, using technical jargon.
• The 21st Century Cures Act grants patients direct access to these reports.
• Current report formats exceed average patient comprehension levels, hindering understanding of medical conditions.

Purpose of the Study:

• To explore the potential of artificial intelligence (AI) to simplify diagnostic imaging reports for patient understanding.
• To address the gap in patient-focused AI solutions for radiology reports.
• To investigate the application of natural language processing (NLP) and large language models (LLMs) for improving patient comprehension of imaging findings.

Main Methods:

• Review of existing literature on AI applications in radiology.
• Analysis of the potential of NLP and LLMs for simplifying complex medical text.
• Consideration of workflow implications for proposed AI-driven solutions.

Main Results:

• AI, particularly LLMs, offers a potential solution for simplifying imaging reports without major workflow disruption.
• Existing AI applications in radiology have largely overlooked patient-focused simplification.
• LLMs present a novel approach to enhance patient understanding of diagnostic imaging results.

Conclusions:

• Simplifying imaging reports using AI can improve patient comprehension and potentially lead to better health outcomes.
• LLM-driven simplification requires further research before clinical implementation.
• Patient-centered AI solutions are crucial for improving healthcare accessibility and patient engagement.