Evaluation of the Performance of an Artificial Intelligence (AI) Algorithm in Detecting Thoracic Pathologies on Chest Radiographs

Published in

Diagnostics

June 2024

Authors

Hubert Bettinger, Gregory Lenczner,Jean Guigui,Luc Rotenberg,Elie Zerbib,Alexandre Attia 3ORCID,Julien Vidal,dPauline Beaumel

Objective

Methods

Results

Conclusion

Our Rayvolve® AI Suite

fda

trauma

fda

83%

Turnaround Time reduction

67%

False Negatives reduction

99.7%

Negative predictive value

chest

36%

Reading Time reduction

11%

Sensitivity improvement

97.9%

Negative predictive value

measures

1.4°

Average MAE for Angles

1.3mm

Average MAE for Lengths

coming soon

bone age

COMING SOON

Based on Greulich & Pyle reference methodology

Statistical comparison with chronological age

Latest evidence

Optimize Your Workflow and Improve Quality of Care with AZmed

Discover the power of our AI Suite today!

Book a Demo

Evaluation of the Performance of an Artificial Intelligence (AI) Algorithm in Detecting Thoracic Pathologies on Chest Radiographs

Our Rayvolve® AI Suite

Latest evidence

External validation of a commercially available deep learning algorithm for fracture detection in children

Evaluation of the Performance of an Artificial Intelligence (AI) Algorithm in Detecting Thoracic Pathologies on Chest Radiographs

Comparison of diagnostic performance of a deep learning algorithm, emergency physicians, junior radiologists and senior radiologists in the detection of appendicular fractures in children

How Can a Deep Learning Algorithm Improve Fracture Detection on X-rays in the Emergency Room?

Assessing the Potential of a Deep Learning Tool to Improve Fracture Detection by Radiologists and Emergency Physicians on Extremity Radiographs

Optimize Your Workflow and Improve Quality of Care with AZmed