New artificial intelligence tools can predict, with 92% accuracy, which consumers will develop dementia. The tools are four different machine-learning algorithms: logistic regression (LR), support vector machine (SVM), random forest (RF), and gradient-boosted trees (XGB). These algorithms are meant to classify whether a participant falls into class 0 (predicted to remain dementia-free 29 months from baseline) or class 1 (predicted to experience incident dementia within 29 months of baseline), based on variables recorded at an individual’s first memory clinic visit. The tools were used at National Alzheimer Coordinating Center memory clinics between 2005 and 2015.
The . . .