Bravis ziekenhuis Bergen op Zoom & Roosendaal is currently testing Aidoc’s AI algorithms that flag and prioritize abnormalities in CT scans including intracranial hemorrhage, cervical spine fractures and pulmonary embolism. The company’s solutions reduce turnaround time and increase quality and efficiency by flagging acute anomalies in real time. Radiologists benefit from state-of-the art deep learning technology that is “Always-on”, running behind the scenes and freeing them to focus on the diagnosis itself. Doctor Elmer Naaktgeboren is a radiologist at Bravis hospital and the initiator of this project. “I came across Aidoc at a conference two years ago and I immediately found it to be a great addition to our workflow. As human beings, we are sometimes less sharp due to fatigue or stress but a computer is consistent whether it is three o’clock in the morning or two o’clock in the afternoon.”
Artificial Intelligence often seems like “science fiction” and is perceived as something that will only be available in a “futuristic world”. “The beauty of this solution is that it is very practical and can be used immediately. We are taking great steps in the field of innovation and it helps us to gain experience and confidence in artificial intelligence. This trust is essential if we want to further leverage artificial intelligence moving forward: we must learn to trust the machines.” Dr. Naaktgeboren notes that he can envision a distant future where smart computers “take over the world”. “Perhaps a lot is technically possible, but ethically we have to make wise choices. The software that we are now going to test helps doctors to detect the smallest abnormalities but the diagnosis and next steps are still determined by the doctors themselves. ” Elmer does not see this changing in the near future. “I expect that a large number of less critical actions will no longer be taken by humans, for these actions AI may take over. Compared to a machine, doctors have a consultative ability that makes it possible for them to analyze cases that deviate from the norm and provide conclusions based on their prior knowledge and experience”.
An important precondition in the use of this technology is data privacy. Aidoc’s algorithms are regulatorily cleared and ready for use at a high level of performance – there is no need for further training on live data. In addition, all analyzed data is HIPAA and GDPR compliant with de-identification methodology so that no PHI ever leaves your premises.
Bravis is a medium-sized general hospital in the Netherlands and one of the first hospitals in the Netherlands to work with Aidoc. For more information, please visit https://www.bravisziekenhuis.nl/.