SmartChest is an AI software that analyzes frontal chest X-rays to detect suspected pleural effusion and pneumothorax. It helps radiologists by prioritizing cases with critical findings in their worklists, improving workflow efficiency. The software passively notifies the radiologist without replacing clinical decision-making.
SmartChest is a radiological computer assisted triage and notification software that analyzes frontal chest X-ray images of transitional adolescents and adults for suspected pleural effusion and/or pneumothorax. It provides case-level output for worklist prioritization but does not send proactive alerts or provide standalone diagnostic decisions.
SmartChest uses AI-based image analysis algorithms applied to frontal chest X-rays (PA/AP) to identify suspected pleural effusion and pneumothorax. It integrates with PACS or other DICOM storage platforms to passively notify radiologists for case prioritization by generating a DICOM secondary capture series with analysis results.
SmartChest was validated on two independent datasets of 300 chest X-rays each from US sites, with ground-truth provided by experienced radiologists. Performance metrics for pneumothorax were ROC AUC 0.989, sensitivity 92.7%, specificity 97.3%. For pleural effusion, ROC AUC was 0.975, sensitivity 93.3%, specificity 90.0%. The software meets safety and effectiveness standards and is substantially equivalent to the predicate device.
No predicate devices specified
Submission
8/10/2023
FDA Approval
5/10/2024
Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.