A large radiology practice found a generative AI model beneficial for chest x-ray worklist prioritization and quality assurance.
Key Details
- 1The AI model generated text-based clinical reports for 34,680 chest x-ray studies over two weeks.
- 2An NLP model mapped reports to 155 chest x-ray findings, comparing AI and radiologist results.
- 3Sensitivity and specificity for pneumothorax detection were 62.4% and 99.3%, respectively.
- 4Studies with positive pneumothorax findings were flagged for urgent review; 36 cases with discrepant findings went to secondary review.
- 525% of secondary-reviewed cases revealed missed pneumothorax by radiologists.
- 644% of radiologists rated AI-generated reports as equivalent in quality to their own.
Why It Matters
This demonstrates tangible workflow improvements and diagnostic support from generative AI in radiology, suggesting the potential to reduce radiologist workload and aid in addressing staffing shortages.
Source
AuntMinnie
Related News
•Radiology Business
Meta Funds Ohio State’s Radiology AI Innovation Projects
Meta will fund Ohio State researchers to explore AI-driven advancements in radiology, including chest X-ray reporting and disease prediction.
•AuntMinnie
AI Triage Tool Speeds Up ICH Head CT Turnaround in ED
AI-based triage for intracranial hemorrhage on head CT reduced emergency department report turnaround by 13 minutes.
•AuntMinnie
ChatGPT-5 Performs Poorly at Detecting Distal Radius Fractures on X-rays
ChatGPT-5 missed about half of distal radius fractures on x-rays, showing limited diagnostic capability in a real-world scenario.