Stanford and Mayo Clinic Arizona researchers demonstrated that LLMs like GPT-4 can categorize critical findings in radiology reports using few-shot prompting.
Key Details
- 1GPT-4 and Mistral-7B LLMs tested for classifying critical findings in radiology reports from ICU patients.
- 2252 MIMIC-III reports (mixed modalities: 56% CT, ~30% x-ray, 9% MRI) and 180 external chest x-ray reports evaluated.
- 3LLMs categorized findings as true, known/expected, or equivocal critical findings.
- 4GPT-4 achieved 90.1% precision and 86.9% recall for true critical findings in internal test set; 82.6% precision and 98.3% recall in external test set.
- 5Mistral-7B showed lower precision (75.6%) but comparable recall (77.4%-93.1%).
- 6Study highlights few-shot prompting as an efficient strategy; real-world deployment requires further refinement.
Why It Matters
This research suggests that off-the-shelf LLMs could automate detection of urgent findings in radiology workflow with minimal manual annotation, potentially easing communication bottlenecks and improving patient safety. Further development and EHR integration will be needed for clinical implementation.
Source
AuntMinnie
Related News
•HealthExec
Mayo Clinic Sued Over Alleged AI Improprieties and Whistleblower Retaliation
A former Mayo Clinic research director sues the institution, alleging retaliation after raising concerns about improper AI use affecting patient safety and data integrity.
•Radiology Business
Framework Assesses Real-World Financial Impact of Radiology AI Adoption
A new analysis presents a financial calculator for objectively assessing the return on investment (ROI) of implementing radiology AI solutions.
•Radiology Business
AI Technique Unveils Previously Hidden MS Gray Matter Lesions on MRI
Researchers developed an AI-enhanced method to detect previously invisible gray matter lesions in multiple sclerosis using MRI.