BraveCX, an artificial intelligence (AI)-enabled software, reportedly has an area under the curve (AUC) of 98 percent for detecting pneumothorax on chest X-rays.
The Food and Drug Administration (FDA) has granted 510(k) clearance for BraveCX, an emerging triage and notification software for adult chest X-rays, that may facilitate timely diagnosis for urgent cases in an emergency room setting.
BraveCX provides specificity rates ranging between 95 to 97 percent, and areas under the curve (AUC) of 96 percent for pleural effusion and 98 percent for pneumothorax, according to Bering, the developer of BraveCX.
Bering pointed out that findings from a million chest X-rays were utilized to develop the artificial intelligence (AI)-powered software, which was subsequently fine-tuned with over 50,000 labeled chest radiographs from radiologists.
"After over three years of research and collaboration with clinical teams, it's so exciting to see BraveCX emerge as a state-of-the-art tool that has actually 'listened to the end user,’” noted Ignat Drozdov, the CEO and founder of Bering. “FDA clearance means BraveCX prioritizes patient safety (while) still delivering the most advanced risk stratification algorithms where they are needed the most."
Study Assesses Lung CT-Based AI Models for Predicting Interstitial Lung Abnormality
September 6th 2024A machine-learning-based model demonstrated an 87 percent area under the curve and a 90 percent specificity rate for predicting interstitial lung abnormality on CT scans, according to new research.
What a Prospective CT Study Reveals About Adjunctive AI for Triage of Intracranial Hemorrhages
September 4th 2024Adjunctive AI showed no difference in accuracy than unassisted radiologists for intracranial hemorrhage (ICH) detection and had a slightly longer mean report turnaround time for ICH-positive cases, according to newly published prospective research.
FDA Expands Clearance of MRI-Guided AI Platform for Deep Brain Stimulation and Lesioning Techniques
September 3rd 2024Utilizing a new machine learning model, the OptimMRI software may improve radiosurgery applications and lesioning techniques such as MRI-guided focused ultrasound through enhanced targeting of the inferolateral part of the ventral intermediate nucleus (VIM).