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
Real-World Study: Radiology AI Best in Emergency and Inpatient Settings
A commercial AI tool for intracranial aneurysm detection outperformed in inpatient and emergency settings but yielded limited benefits for outpatients in a major health system study.
•Radiology Business
New Rubric Enhances Safety of AI-Generated Radiology Summaries
Researchers developed a five-factor rubric to assess the safety and quality of AI-generated, patient-friendly radiology report summaries.
•Radiology Business
Healthcare Leader Warns AI Will Dominate Diagnostic Radiology
A leading oncologist urges future radiologists to specialize in interventional procedures due to AI advances in image interpretation.