A trichotomy method for defining homogeneous subgroups in a dementia population

Abstract

Abstract Introduction Diagnosis of dementia in the aging brain is confounded by the presence of multiple pathologies. Mixed dementia (MX), a combination of Alzheimer's disease (AD) proteins with vascular disease (VD), is frequently found at autopsy, and has been difficult to diagnose during life. This report develops a method for separating the MX group and defining preclinical AD (presence of AD factors with normal cognition) and preclinical VD subgroups (presence of white matter damage with normal cognition). Methods Clustering was based on three diagnostic axes: (1) AD factor (ADF) derived from cerebrospinal fluid proteins (Aβ42 and pTau), (2) VD factor (VDF) calculated from mean free water and peak width of skeletonized mean diffusivity in the white matter, and (3) Cognition (Cog) based on memory and executive function. The trichotomy method was applied to an Alzheimer's Disease Neuroimaging Initiative cohort (N = 538). Results Eight biologically defined subgroups were identified which included the MX group with both high ADF and VDF (9.3%) and a preclinical VD group (3.9%), and a preclinical AD group (13.6%). Cog is significantly associated with both ADF and VDF, and the partial‐correlation remains significant even when the effect of the other variable is removed (r(Cog, ADF/VDF removed) = 0.46, p < 10−28 and r(Cog, VDF/ADF removed) = 0.24, p < 10−7). Discussion The trichotomy method creates eight biologically characterized patient groups, which includes MX, preclinical AD, and preclinical VD subgroups. Further longitudinal studies are needed to determine the utility of the 3‐way clustering method with multimodal biological biomarkers.