Oxipit to Preview First Autonomous AI Medical Imaging Application at ECR 2021

The AI medical imaging company will showcase the first autonomous AI diagnostics application for healthy patient report automation. The new product by Oxipit automatically identifies chest X-ray images with no abnormality and produces finalized patient reports without any intervention from the radiologist. The application is pending CE mark certification and will be made available for commercial deployments in the Q3 2021.

“Automation of radiology is no longer a promise – it is finally here. It combines our long-term research with firsthand feedback from medical institutions on how AI diagnostics can benefit daily medical practice. We are excited to be the pioneers in the autonomous AI diagnostics field and strongly believe autonomous products will finally boost AI clinical adoption” – notes CEO of Oxipit Gediminas Peksys.

The new AI application will only produce automated reports for chest X-rays, where it is highly confident that the images feature no abnormalities. This allows the sensitivity metric to be higher than 99%. The application is validated using a 500.000 X-ray dataset from multiple medical institutions where Oxipit AI products are currently deployed. Depending on the type of medical institution, the platform can autonomously report on up to 15% of the daily radiologist’s workflow.

“Initially this would be most helpful for primary care and diagnostics centers, where up to 80% of all chest X-rays feature no abnormalities. Furthermore, a similar autonomy framework can be adapted for large scale screening projects, such as the global tuberculosis effort” – adds Mr Peksys.

The new application builds upon the foundation of Oxipit ChestEye, an earlier Oxipit platform for preliminary chest X-ray reports. Oxipit ChestEye can identify 75 radiological findings – approx. 90% of abnormalities encountered by radiologists on a daily basis.

“Supporting this vast library of radiological findings enables us to rule out any pathologies with high confidence and achieve zero false negative cases across our pilot product deployment sites” – says Mr Peksys.

Leave a Reply

Your email address will not be published. Required fields are marked *