Artificial Intelligence To Predict Future Dementia Development
Artificial Intelligence may now help humans predict dementia risks among healthy elders.
In a statement released by the University of Finland, a team of medical doctors and engineers in Finland and Sweden has created a machine learning method that could assess potential dementia threats among cognitively normal individuals from age 65 to 79. The software containing massive amounts of data could also display a detailed risk profile in a visual format designed for easy interpretation.
According to World Health Organization figures, there are 47.5 million dementia patients worldwide in 2015 and it is projected to increase to 75.6 million by 2030. In fact, the number of dementia cases is expected to triple by 2050. Because of these figures, experts have been studying effective measures to prevent the widespread of the cognitive disease.
To address this concern, the team created a dementia risk index based on the data collected from the Cardiovascular Risk Factors, Aging and Dementia (CAIDE) study, which was conducted in Eastern Finland. Participants of the study include cognitively healthy people aged 65-79 who went through a series of detailed health tests such as memory and other cognitive assessments.
The generated dementia risk index was successful in analyzing comprehensive profiles to project the development of dementia up to 10 years later. Predicting factors include age, vascular factors, apolipoprotein E (APOE) genotype, subjective memory complaints and cognition.
"The risk index was designed to support clinical decision making, and we are very keen on exploring its potential practical use," said study's lead author, Alina Solomon, MD, PhD, from the University of Eastern Finland. "The results of our study are very promising," Dr. Solomon added, "as it is the first time this machine learning approach was used for estimating dementia risk in a cognitively normal general population."
This study was published in the Journal of Alzheimer's Disease.