Artificial intelligence could help create more specific Alzheimer’s treatment
Medics have devised a new algorithm that can automatically spot different patterns of progression in patients suffering from a range of dementias.
Quicker more specific treatments for Alzheimer’s could be developed using advanced artificial intelligence, according to researchers at University College London (UCL).
Medics have devised a new algorithm that can automatically spot different patterns of progression in patients suffering from a range of dementias, including Alzheimer’s disease.
The algorithm, called Subtype and Stage Inference – or SuStaIn, uses medical images to show doctors what stage the disease has reached and identify whether patients will respond better to certain treatments.
This new algorithm has the unique ability to reveal groups of patients with different variants of disease Professor Daniel Alexander
Researchers said the algorithm was able to identify three separate subtypes of Alzheimer’s disease from MRI scans of people with dementia, and said this “subtyping” would be possible very early in the disease process.
The ability to identify the subtypes early on in the disease process and using non-invasive MRI scanning means there is a better chance of identifying the best treatment for individuals, scientists said.
“One key reason for the failure of drug trials in Alzheimer’s disease is the broad mixture of very different patients they test; a treatment with a strong effect on a particular subgroup of patients may show no overall effect on the full population so fail the drug trial,” said Professor Daniel Alexander at the UCL Centre for Medical Image Computing.
“This new algorithm has the unique ability to reveal groups of patients with different variants of disease.”
Professor Jonathan Schott, from the UCL Institute of Neurology, said understanding how different diseases evolve over time is “critical” for the design of treatments and providing information to patients about their prognosis.
“This is a major challenge for diseases that evolve over years, if not decades, and where there may be substantial differences in the underlying pathology, and pattern and rates of progression between patients,” Professor Scott said.
“This work shows that it is possible to tease out different disease patterns – some hitherto unknown – from single MRI scans taken from patients with a range of different dementias.”
The researchers are now looking for ways to apply the algorithm to other diseases, including chronic obstructive pulmonary disease.
It is believed the algorithm could be used by the NHS within the next few years. The NHS was unable to confirm the report.