New prediction tool can determine individual’s 13-year dementia risk at 100% prediction accuracy

A risk score tool can accurately predict an individual’s 13-year dementia risk, according to a study published online Nov. 17 in JAMA Network Open.  Lina Ren, from Shenzhen Mental Health Centre in China, and colleagues developed a point risk score prediction model for dementia using data from a diagnostic study of 444,695 U.K. individuals.

The researchers found that dementia occurrence during the 13 years of follow-up (mean age at baseline, 56.2 years) was 0.7 percent for men and 0.5 percent for women. In the training set, the C statistic of the final multivariate Cox proportional hazards regression model was 0.86 for men and 0.85 for women versus 0.85 for men and 0.87 for women in the testing data set. Some modifiable risk and protective factors were similar between men and women, but they also presented independent risk factors that accounted for 31.7 percent of men developing dementia and 53.35 percent of women developing dementia, according to the weighted population-attributable fraction.  The total point score of the risk score model ranged from −18 to 30 in men versus −17 to 30 in women.  For both genders, the risk score model yielded nearly 100 percent prediction accuracy of 13-year dementia risk.

“The findings of this diagnostic study suggest that a risk score tool can be used for individual prediction of dementia risk that may help individuals to identify their potential risk profile and provide guidance on precise and timely actions to take to prevent or delay dementia,” the Authors write.

REFERENCE:  Health Day News; 18 NOV 2022