Can Algorithms Identify High-Risk Alzheimer's Patients?
Researchers might more precisely test possible drugs for treating Alzheimer's if they study groups of people living with similar types of cognitive impairment, according to findings reported in the journal Scientific Reports.
"Everyone thinks Alzheimer's is one disease, but it's not," stated P. Murali Doraiswamy, director of the neurocognitive disorders program at Duke Health and a leader of the study. "There are many subgroups [of cognitive impairment]. If you enroll all different types of people in a trial, but your drug is targeting only one biological pathway, of course the people who don't have that abnormality are not going to respond to the drug, and the trial is going to fail."
Using a "clustering algorithm" to sort through data from two large studies of the Alzheimer's Disease Neuroimaging Initiative, Doraiswamy, Dragan Gamberger of the Rudjer Boskovic Institute in Croatia, and other researchers identified patients with significant cognition decline and patients who experienced little — or even no — decline in symptoms. Using what Doraiswamy called "unbiased tools, such as data mining," scientists can analyze all sorts of information at once — sex, lifestyle, genetics — "to identify those who are truly at the greatest risk."