Technology has greatly contributed to and enhanced medicine. Now, it is known that the treatment of aneurysms can be revolutionized by software powered by Artificial Intelligence (AI).
An aneurysm is, simply put, a weak or thin spot in the wall of a vessel in the brain that fills with blood. If it bursts, it could be fatal.
In turn, a stent is a tube, used to divert blood flow, avoiding additional pressure that could cause the rupture of the aneurysm.
Second Katerina Spranger, founder of Oxford Heartbeat, currently, “there is a lot of guesswork” in stent placement: they are placed from a catheter in the groin and an x-ray is used to introduce them into the body. During the process, complications may arise.
If the device is, for example, undersized, it can become detached from the blood vessels and begin to travel through the body’s circulatory system, which is a huge complication. Or, if it’s too big, it could almost burst the vase.
Following these problems comes PreSize, signed by Oxford Heartbeat: a program that provides an exact image of the patient’s brain, as well as “digital twins” that behave like a real stent to predict what will happen “if we place a certain device in a given location.”
In fact, a study published in the BMJ Journal of Neurointerventional Surgery concluded that the system was more accurate in predicting where a stent would “land” in the brain.
This program, powered by AIcan be used in the operating room, allowing different stents to be tested to see which works best.
The researchers who created PreSize found that they were more accurate at placing a stent graft than experienced surgeons. This is important, as “a fraction of a millimeter can make or unmake a surgery.”
So far, PreSize has been used in operations on 375 patients in seven hospitals in England and Scotland, as well as in Germany, Finland and Ukraine.
The National Institute for Health and Care Research (NIHR) recognizes that there is “enormous potential for AI technologies to speed diagnosis and treatment, and improve outcomes for patients.”
The NIHR is funding a number of AI projects, including this one, alongside the NHS AI Lab, to gather the evidence needed to bring this technology to more patients in the future, across the NHS.
The researchers found that human clinicians had an average accuracy rate of 81%, while PreSize achieved 95%.
AI has the potential to revolutionize healthcare, but before we adopt it we need to rigorously test new systems.
Medical device software companies like ours must be held accountable to address any distrust about AI.
Spranger explained, assuring that more research will be carried out in order to make the technology unequivocally safe.
