PROGNOSTIC VALUE OF AT(N) CLASSIFICATION IN CSF USING CLUSTERING ANALYSIS

Abstract

AbstractBackgroundThe biological definition of Alzheimer’s disease (AD) and the use of biomarkers according to the AT(N) system may improve the clinical characterization of patients and the sequence of events during the clinical course. However, some studies have raised challenges in the clinical application of AT(N) system. Unbiased, data‐driven techniques such as unsupervised machine learning may help optimize it. We aimed to optimize the classification using unsupervised machine learning algorithms (clustering analysis).MethodWe included 421 patients from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort and 165 from our centre. We included subjective memory complaints (SMC), early mild cognitive impairment due to AD (EMCI), late MCI due to AD (LMCI) and MCI without evidence of neurodegeneration (MCI‐NN) patients according to clinical manifestations, neuropsychological test and CSF biomarkers from our center and the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort. We clustered the biomarkers separately and all together using the KMeans algorithm for each cohort and compared them in terms of diagnosis, AT(N) system, biomarker values distribution, and risk of progression to dementia.ResultThe optimal number of clusters for all the biomarkers together was three. These clusters differed significantly in both cohorts according to diagnosis, AT(N) categories, biomarker values distribution, and progression to dementia. We found amyloid biomarkers to be more dichotomic, while Tau biomarkers were more continuous. Intergroup comparisons revealed the following groups: 1) non‐defined or unrelated to AD subjects, with no risk of progression to dementia; 2) early stages and/or more delayed risk of conversion to dementia subjects, and 3) more severe cognitive impairment subjects within the early stages of AD and with faster progression to dementia. Findings were largely similar between the two cohorts.ConclusionThis new 3‐group classification, developed with a data‐driven approach, represents a novel perspective to assess the risk of conversion to dementia in a much more simplified way and is complementary to the AT(N) system classification