Simple models for estimating dementia severity using machine learning

Estimating dementia severity using the Clinical Dementia Rating (CDR) Scale is a two-stage process that currently is costly and impractical in community settings, and at best has an interrater reliability of 80%. Because staging of dementia severity is economically and clinically important, we used Machine Learning (ML) algorithms with an Electronic Medical Record (EMR) to identify simpler models for estimating total CDR scores. Compared to a gold standard, which required 34 attributes to derive total CDR scores, ML algorithms identified models with as few as seven attributes. The classification accuracy varied with the algorithm used with naïve Bayes giving the highest. (76%) The mildly demented severity class was the only one with significantly reduced accuracy (59%). If one groups the severity classes into normal, very mild-to-mildly demented, and moderate-to-severely demented, then classification accuracies are clinically acceptable (85%). These simple models can be used in community settings where it is currently not possible to estimate dementia severity due to time and cost constraints.