Radiology Partners leverages large language models (LLMs) to monitor and validate AI tool deployment in clinical radiology workflows.
Key Details
- 1LLMs are used to extract findings from narrative radiology reports for analysis.
- 2Extracted data is compared to outputs from vision AI tools for validation and monitoring.
- 3The data supports pre-deployment and post-deployment assessment of AI tools.
- 4LLMs also help curate data for future AI training and evaluation.
- 5Presented by Dr. Walter Wiggins at the RSNA annual meeting.
Why It Matters
Integrating LLMs to track and assess AI tools enhances the safe and effective adoption of AI in radiology. This approach contributes to better QA, transparency, and iterative improvement in clinical imaging AI deployment.
Source
Radiology Business
Related News
•AuntMinnie
AI Models Reveal Racial Disparities in Breast Cancer Patterns
Machine learning models reveal significant racial disparities and key predictors in breast cancer incidence across diverse groups.
•Radiology Business
UCLA Appoints Inaugural Associate Dean for Health AI Strategy
UCLA has appointed Katherine P. Andriole as its first associate dean for Health AI Strategy and Innovation, with an initial focus on radiology.
•AuntMinnie
AI Algorithm Streamlines and Standardizes Shoulder Ultrasound Acquisition
A multitask AI system demonstrated high accuracy in standardizing and guiding shoulder musculoskeletal ultrasound imaging.