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
•Radiology Business
AI-Powered Tool Streamlines CT Scan Prioritization in Emergency Departments
An AI-based CT queue system significantly reduces wait times for ED patients by prioritizing scans likely to reveal critical findings.
•Radiology Business
AI Workflow Enables General Radiologists to Match Breast Specialists in Screening
AI-powered workflow helps generalist radiologists detect breast cancer at rates comparable to specialists.
•Radiology Business
LLMs Automate Radiology Report Quality Control, Study Finds
LLM-based systems can rapidly automate radiology report quality control, saving significant manual review time.