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
•AuntMinnie
Radiology Receives Declining Share of Industry Research Funding
Radiologists received only 1.1% of industry-funded research payments in 2024, with a continuing downward trend.
•AuntMinnie
GPT-4o AI Matches Radiologists in Follow-Up Imaging Recommendations
GPT-4o matched the performance of experienced radiologists and surpassed residents in recommending follow-up imaging from routine radiology reports.
•Cardiovascular Business
AI Leverages Head CTs for Automated Heart Risk Assessments
AI models can turn routine head CT scans into automated cardiovascular risk assessments, expanding the utility of radiology studies.