Algorithm Aims to Predict Dementia Risk with Routine Data
The algorithm is potentially useful for patients aged 60 to 79 years, but not for people older than 80. More research is needed before it can be used.
HealthDay News — Researchers from University College London have developed an algorithm that uses medical data to predict a 5-year risk of dementia, according to a report published online Jan. 21 in BMC Medical.
The algorithm assesses factors like age, sex, social interaction, smoking, body mass index, alcohol use, hypertension, diabetes, stroke, atrial fibrillation, aspirin use, and depression, the study authors said.
The risk score proved accurate when researchers used it to assess the records of 226 140 patients ages 60 to 79, according to Kate Walters, PhD, director of the Centre for Ageing and Population Studies at University College London. But, it was not accurate for judging dementia risk at age 80 or beyond, because by that age the risk of dementia is elevated across the board, she told HealthDay.
"We therefore would not recommend it for people aged 80 years or more, but it is potentially useful for people aged 60 to 79 years," Walters said. "We chose the particular factors as other research has shown in some people that they can be linked to an increased risk of dementia. We have written a simple program to calculate the score."
Walters K, Hardoon S, Petersen I, Iliffe S, Omar RZ, Nazareth I, Rait G. Predicting dementia risk in primary care: devlopment and validation of the Dementia Risk Score using routinely collected data. BMC Medicine. 2016; doi:10.1186/s12916-016-0549-y.