[ad_1]
It has been used to detect eye disease, make medical diagnoses, and spot the first signs of esophageal cancer. Now, it has been claimed that artificial intelligence may be able to diagnose dementia from a single brain scan, with researchers starting a trial to test the approach.
The team behind the AI tool hopes it will lead to earlier diagnoses, which could improve patient outcomes, while helping to shed light on their prognosis.
Dr Timothy Rittman, senior clinical research associate and consultant neurologist at the University of Cambridge, who is leading the study, told the BBC that the AI system is a “fantastic development.”
“These diseases are really devastating for people,” he said. “So when I pass this information on to a patient, anything I can do to be more confident about the diagnosis, to give them more information about the likely progression of the disease to help them plan their life is a good thing to be able to do. “
In the first year of the trial, the AI system, which uses algorithms to detect patterns in brain scanners, is expected to be tested in a “real” clinical environment in around 500 patients at Addenbrooke’s Hospital in Cambridge and other memory clinics. Across the country.
“If we intervene early, treatments can start early and slow the progression of the disease and at the same time prevent more damage,” said Professor Zoe Kourtzi, University of Cambridge and a member of the National Center for AI and of data science, Alan. Turing Institute, told the BBC. “And the symptoms are likely to occur much later in life or may never occur.”
Dr Laura Phipps of Alzheimer’s Research UK said Kourtzi was also leading a research project, funded by the charity, which used data from wearable technology to predict conditions like Alzheimer’s disease 15 to 20 years older sooner than was currently possible. Phipps added that applying AI to brain scanners could bring benefits.
“To diagnose dementia today, doctors must rely on the interpretation of brain scans and cognitive tests, often over a period of time,” she said. “Machine learning models such as those developed by Professor Kourtzi could give physicians greater confidence in the interpretation of scans, leading to a more accurate diagnosis for patients.”
Phipps added that it is hoped that such approaches can eventually help detect diseases that cause dementia much earlier.
“It would have a huge impact on people with dementia and their families,” she said.
However, Professor Tara Spiers-Jones, deputy director of the Center for Discovery Brain Sciences at the University of Edinburgh, who was not involved in the study, said the excitement may be premature.
“Finding ways to diagnose dementias very early in the disease process is a very important goal that will help both research and possibly treatment, but it seems to be still at a fairly early stage,” a- she declared.
Professor Clive Ballard, a dementia expert at the University of Exeter, agreed. “AI has been shown to improve the diagnostic potential of brain scans compared to clinical scans reading, but there is so much heterogeneity between individuals that it is totally infeasible that a single scan, biomarker or clinical test is also certain in just one assessment, ”he said.
“This approach is certainly a positive direction of travel that will lead to improvements in diagnosis, but we must be very careful not to create false expectations.”
Source link
