Emory University demonstrated that LLM-based tools can enhance patient comprehension of radiology reports.
Key Details
- 1Emory University's radiology department piloted a web app using OpenAI's GPT-5 to summarize radiology reports for patients.
- 2The system produced LLM-generated report summaries, clickable terms with educational content, and AI-created explanatory videos.
- 3In a study of 100 patients, 48% rated AI report summaries as the most helpful feature.
- 4Patient comprehension scores increased from a median 4/5 before the intervention to 5/5 after using the AI-generated tools.
- 5Summaries required clinician review and editing, averaging 24.75 words removed and 0.13 words added per summary.
- 6Patients voiced reservations about using unedited AI summaries, stressing the need for professional oversight.
Why It Matters
This study demonstrates the potential of AI-driven tools to make complex radiology results more accessible and understandable for patients, but highlights the necessity for clinical oversight to maintain accuracy and patient trust. It supports the case for integrating LLMs into radiological workflows to improve communication, with considerations for scalability and regulation.
Source
Radiology Business
Related News
•AuntMinnie
Radiologists Struggle to Spot AI-Generated Radiology Images
Radiologists correctly identify AI-generated images 75% of the time, with CT and MRI images being particularly challenging to spot.
•AuntMinnie
Radiology Leads FDA AI Device Approvals Over Three Decades
Radiology accounts for 76% of all FDA-cleared AI/ML-enabled medical devices as of the end of 2025.
•Radiology Business
Automation Bias: How AI Can Compromise Radiologist Accuracy
AI decision support can induce automation bias, leading radiologists to accept incorrect interpretations and potentially reduce their diagnostic accuracy.