The AI uses algorithms to detect patterns in brain scans that are at times even missed by neurological experts.
As supercomputers take on the mighty challenge of accelerating research in the complexities of life sciences, Artificial Intelligence (AI) is not far behind. Researchers are testing a system based on AI to detect neurological disorders like dementia in just one brain scan.
As researchers begin the trial of the system, currently it takes several scans and tests to diagnose dementia. An earlier diagnosis of the disorder could be life-saving and enhance treatment strategies. The team of researchers from the University of Cambridge are hopeful that the AI system will be tested in a “real-world” clinical setting on about 500 patients, in its first year of trial.
The system uses algorithms to detect patterns in brain scans that are at times even missed by neurological experts. According to a report in BBC, the AI has been able to diagnose dementia in pre-clinical tests and that too years before symptoms develop at a time when there is no sign of damage to the brain.
Professor Kourtzi of Cambridge University, who is part of the study told BBC, "If we intervene early, the treatments can kick in early and slow down the progression of the disease and at the same time avoid more damage. And it's likely that symptoms occur much later in life or may never occur."
As part of the trial, researchers will test whether it works in a clinical setting, alongside conventional ways of diagnosing dementia. The researchers conducting the trial at Addenbrooke's Hospital in the UK will send the reports to participant's doctors for clinical advice.
"These sets of diseases are really devastating for people. So when I am delivering this information 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 lives is a great thing to be able to do," BBC quoted neurologist Dr Tim Rittman, who is leading the study as saying. So far doctors and neurologists have depended upon brain scans and MRIs to identify neurological disorders, however, the new system under development could significantly boost their abilities in identifying the issues and devise an early treatment strategy.
"AI has been shown to improve the diagnostic potential of brain scans compared to a clinical reading of the scans, but there is so much heterogeneity between individuals that it is completely infeasible for a single scan, biomarker or clinical test to be that certain in a single assessment," Professor Clive Ballard, a dementia expert at the University of Exeter told The Guardian.
The clinical trial underway by the Cambridge team is not the first to use the advances of AI, Cambridge-1, one of the world’s fastest AI supercomputers, has also begun operations in the UK as it looks for new medical breakthroughs with its unique ability to process digital biology, genomics, quantum computing and artificial intelligence.
In its first attempt, Cambridge-1 is working with AstraZeneca, GSK, Guy’s and St Thomas’ NHS foundation trust, King’s College London and Oxford Nanopore in developing a deeper understanding of diseases like dementia, look for new drugs, design and run simulations and enhance knowledge around variations in human genomes.