Journal of the American College of Radiology

The model identified vertebral compression fracture accurately with a sensitivity 89.3% (95% CI: 85.7%-92.7%) and specificity of 89.2% (95% CI: 85.4%-92.3%).

Its automated use could help identify patients who have undiagnosed osteoporosis and who may benefit from taking disease-modifying medications.

Radiology

Annalise Enterprise CXR demonstrates the ability to identify 63.2% of unremarkable CXR cases with high precision, unlocking the potential to automate reporting for 23.5% of the total CXR case load.

Cureus

A single case study highlighting the potential benefits of adopting decision-support AI solutions in radiology, flagging a pneumothorax on CXR with the potential to avoid additional CT examinations.

Presentation at ECR 2024

Reducing CXR to follow-up CT for suspected lung cancer cases by 10 days (22 to 10.3 days) with high rates of sensitivity and specificity in a real life prospective clinical environment.

Presentation at RSNA 2023

Reasonable efficiency gains in teleradiology reporting time were observed through the deployment of a comprehensive AI algorithm as standard practice.

Poster at RSNA 2023

The two AI algorithms demonstrated high diagnostic accuracy in a real-world dataset.

Presentation at RSNA 2023

Investigating a use-case to enhance patient osteoporosis risk characterisation using AI on CXR to improve patient care and management through the detection of unreported findings suggestive of osteoporosis.

Poster at RSNA 2023

NLP and comprehensive AI discrepancy analysis can be a valuable approach to quality assessment and control.