Researchers at the University of Cambridge have developed an AI-based system that can diagnose dementia much faster than current technologies, using a single image.
Researchers at the University of Cambridge have succeeded in developing an artificial intelligence-based system that they believe can diagnose dementia from a single brain scan, potentially years in advance.
Until now, the process of trying to determine whether or not a patient has dementia has been very complicated. It often lasts for weeks, and involves the patient having several cognitive tests as well as several brain imaging scans; All without being able to achieve a decisive result every time.
On the other hand, the system proposed by the Cambridge researchers needs only one image to do what AI does best: identify patterns that are distinct, but are too abstract or complex for humans. This makes it possible to obtain a decisive result faster; Critical data in the management of these diseases.
In fact, many forms of dementia can experience dramatic progression soon after symptoms appear; The earlier it is diagnosed, the more effective the treatment. This system also offers an added value, as it is also able to formulate a diagnosis about the course of the disease.
Artificial intelligence, the expected revolution in diagnostics
Obviously, as always when it comes to health, the results should be taken with caution. Artificial intelligence has revolutionized diagnostics for some time now, but we are not yet ready to fully trust it; At this point, it is essential that the human stay in the loop. And for good reason: even if AI systems are better than us at this game, they are not infallible. They depend entirely on the dataset with which they were trained. So it is It is impossible to have absolute certainty through this method.
But this does not mean that artificial intelligence has no place in this field, far from it. This technology has recently entered the clinical trial stage; In order to judge its effectiveness, approx 500 British patients This device should be tested next year. In particular, this will allow to draw much clearer conclusions from Accuracy level of this technique. If you find it accurate enough, it can be a great diagnostic tool; Enough to find a favorite among specialists in neuropsychiatry and geriatrics for sure. Incidentally, it’s also a new example of AI capabilities applied to health, which could revolutionize our healthcare system much sooner than we think.