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
Lucida Medical Raises $11M for AI-Based Prostate MRI Diagnosis Expansion
Lucida Medical, specializing in AI-assisted prostate cancer diagnosis via MRI, raises $11.4M to drive US FDA approval and platform expansion.
•Radiology Business
AI Guidance Cuts Novice Ultrasound Exam Time by 34%
AI guidance significantly reduces exam times and enhances diagnostic quality for novice ultrasound operators performing shoulder exams.
•Radiology Business
NYC Health + Hospitals CEO Considers AI to Replace Radiologists
NYC Health + Hospitals CEO suggests AI could partially replace radiologists, pending regulatory approval.