Harvard researchers presented an AI system that generates video radiology reports rated highly by radiologists for patient communication.
Key Details
- 1The ReXplain AI system creates patient-friendly video radiology reports using a large-language model, image segmentation, and conversational avatars.
- 2Tested with five radiologists and 10 CT video reports, the tool received 98-100% positive agreement on understandability and accuracy.
- 3Radiologists strongly agreed that image explanations and normal comparisons improved comprehension.
- 480% were comfortable providing videos to patients, with some hesitance for pre-visit distribution (60%).
- 5Feedback on 3D image rendering was mixed (50%).
- 6Further patient-centered studies are planned.
Why It Matters
Improving patient understanding of radiology results is a key unmet need; AI-generated multimedia reports could bridge the gap between medical reports and patient comprehension, helping radiology demonstrate direct value to patients.
Source
AuntMinnie
Related News
•AuntMinnie
Study: Computer Vision Models Best LLMs in Chest CT Breast Abnormality Detection
Computer vision models (CVMs) surpass large language models (LLMs) in accurately labeling incidental breast abnormalities on chest CT scans.
•Cardiovascular Business
Radiology Maintains Lead in FDA-Cleared AI Algorithms, Cardiology Follows
Radiology remains the top specialty for FDA-cleared AI, with cardiology as a strong second, particularly in cardiovascular imaging.
•AuntMinnie
Deep Learning Models Rival Radiologists for Pancreatic Cancer Detection on CT
Deep-learning models achieved comparable or superior accuracy to experienced radiologists in detecting pancreatic cancer on CT scans, especially for small tumors.