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
•AuntMinnie
Deep Learning Model Predicts Brain Tumor MRI Enhancement Without Gadolinium
German researchers developed a deep learning approach to predict MRI contrast enhancement in brain tumors without the need for gadolinium-based agents.
•Radiology Business
Study Highlights Limitations of AI in Prostate MRI Screening
New research points to several shortcomings in implementing AI for MRI-based prostate cancer screening.
•AuntMinnie
Multimodal LLMs Achieve High Accuracy Detecting Scoliosis on X-rays
Multimodal LLMs achieved up to 94% accuracy for scoliosis detection on spine x-rays, but struggled with lumbar stenosis on MRI.