Research conducted by Boston University School of Medicine (BUSM) published in the Journal of Alzheimer's Disease examined data from the Framingham Heart Study (FHS) to identify new combinations of risk factors that are linked to increased risk of dementia in later life.
"This study is the first step in applying machine learning approaches to identifying new combinations of factors that are linked to increased risk of dementia later in life. "By focusing on modifiable risk factors, we are hoping to identify disease risk factors that are amenable to change, enabling the possibility of preventing dementia," says corresponding author, Dr Rhoda Au, professor of anatomy and neurobiology.
Using data collected from FHS between 1979 and 1983, researchers identified patterns to determine who was ultimately diagnosed with dementia.
Expectedly, older age was strongly linked dementia as was being 'widowed.' Surprisingly, so was lower BMI while having experienced less sleep at mid-life could also increase risk.
"We wanted to identify information that any physician or even non-physician has easy access to in determining potential increased future risk for dementia. Most dementia screening tools require specialised training or testing, but the front line for screening are primary care physicians or family members. This was also an initial attempt to apply machine learning methods to identify risk factors," continues Au.