 |
By Allen Cone, UPI
Machine learning may someday allow physicians to prescribe the best treatment for dementia, according to a study.
Researchers devised and applied a new algorithm that can spot different patterns of progression in patients with a range of dementias in MRI scans, including Alzheimer's disease. The findings were published this month in the journal Nature Communications.
"This new algorithm has the unique ability to reveal groups of patients with different variants of disease," Dr. Daniel Alexander, a professor in the University College London Center for Medical Image computing, said in a press release. "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.
The algorithm is called Subtype and Stage Inference, or SuStaIn.
SuStaIn data came from scans of 313 participants at 13 medical centers in Britain, Canada, Italy, The Netherlands, Sweden and Portugal.
The process identified three separate subtypes of Alzheimer's disease, matching those observed in post-mortems of brain tissue and several different subtypes of frontotemporal dementia.
With SuStaIn, doctors can see how the disease is progressing, examine specific locations of protein buildup within the brain and determine parts that are degenerating.
This method can be done early in the disease process, the researchers noted.
"Individuals might present with similar symptoms to each other, but using SuStaIn we can find that they belong to different subgroups," Dr. Sandra Young, of the imaging center, said. "This allows us to predict more accurately how their disease will progress and diagnose it earlier."
The researchers are studying ways to apply the algorithm to other diseases. Last month, they presented their findinsg at the European Respiratory Society Conference on chronic obstructive pulmonary disease in Paris.
"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," Schott said. "As well as providing new insights into dementia, this work demonstrates the huge potential of SuStaIn to delineate disease subtypes in a range of other medical contexts."
COMMENTS