ChestLink AI Will See You Now: First Autonomous AI Medical Imaging Application Granted Regulatory Approval in Europe

By , in news startups on . Tagged width: , , ,

Leading AI medical imaging application developer Oxipit was granted CE Class IIb certification for ChestLink autonomous AI imaging suite.

ChestLink AI application will produce final reports for healthy patients without any involvement from a human radiologist. It is the first regulatory approved AI medical imaging application to perform diagnostics autonomously. 

*- On-demand Oxipit could send preliminary reports, heatmaps, priority labels or pathology labels to improve the radiologist’s experience.

ChestLink ushers in the era of AI autonomy in healthcare – something we have been promised by medical futurists and technology experts.

It presents the first case where a medical diagnostic evaluation will be carried out solely by an artificial intelligence application.

ChestLink showcases the future of healthcare diagnostics, where AI operates as an integral part of the clinical workflow.

says CEO of Oxipit Gediminas Peksys.

ChestLink works with chest X-ray studies. The AI application will produce final reports for chest X-rays where the application is highly confident that the image features no abnormalities, removing them from a human radiologist workflow. The automation of healthy patient reports is especially relevant for primary care centres, where up to 80% of all chest X-ray images may feature no pathologies. 

Despite the patient being healthy, the radiologist still has to review these X-ray studies and produce final study reports.

Considering the global shortage of radiologists, ChestLink can automate a significant portion of daily imaging workflow, allowing medical specialists to devote more time to cases with pathologies.

says Gediminas Peksys.

To provide a patient with a clean bill of health, ChestLink has to check for common pathologies, as well as subtle secondary findings, including pulmonary nodules, which are a potential indication of lung cancer. In case it cannot rule out all findings with absolute certainty, the X-ray study will be left to report to the human radiologist.

The CE mark certification for ChestLink indicates that the product complies with relevant EU legislation for medical products, making the product available for deployment in clinical practice. Prior to being greenlit for clinical deployments, ChestLink underwent extensive validation studies at pilot medical institutions in the US, Germany, the Netherlands, Finland, Spain and Lithuania. In a supervised setting, ChestLink performance was validated with more than 500.000 chest X-ray studies. 

The CE mark paves the way for clinical ChestLink deployments in 32 European countries. Fully autonomous ChestLink operations in a clinical setting are expected to begin in early 2023.

Contrary to a common belief, autonomy in medical imaging will not come with a bang. It will be a step-by-step process, gradually covering an ever-increasing scope of modalities and patient conditions.

We are starting with a solution reporting on average only 30% of cases, to make sure only extremely confident studies are picked.

However, even in the current scope of automation, autonomous AI solutions bring tangible cost savings and productivity gains.

adds Gediminas Peksys.

ChestLink is the third medical imaging application developed by Oxipit. The five-year-old AI imaging startup offers ChestEye CAD application for preliminary chest X-ray reports and ChestEye Quality for real-time diagnostic quality assurance.

Much of the debate in AI medical imaging focused on whether AI can outperform or even replace a human medical specialist. This question is wrong in itself. Firstly, AI in medical imaging is not driven by technological determinism.

At Oxipit we focus on clinical value-centred AI services – be it work scope reduction via automation or real-time diagnostic quality.

The future of health diagnostics is not about determining the winner – it’s about combining the best of AI and human capabilities to improve patient outcomes.

adds Gediminas Peksys.
Oxipit team
Oxipit team