Premium
Subtyping mild cognitive impairment based on imaging and CSF biomarker levels
Author(s) -
Dadar Mahsa,
Shafiee Neda,
Collins Louis,
Camicioli Richard,
Duchesne Simon
Publication year - 2021
Publication title -
alzheimer's and dementia
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 6.713
H-Index - 118
eISSN - 1552-5279
pISSN - 1552-5260
DOI - 10.1002/alz.054129
Subject(s) - oncology , dementia , medicine , biomarker , subtyping , neuroimaging , alzheimer's disease neuroimaging initiative , neuropsychology , cohort , psychology , cognition , disease , neuroscience , biology , biochemistry , computer science , programming language
Background Individuals with mild cognitive impairment (MCI) have variable clinical outcomes, with a proportion converting to dementia in a short follow‐up period. Subtyping MCI subjects based on biomarker levels can provide additional insights on why some individuals progress faster, aiding clinical treatment strategy and facilitating cohort enrichment for clinical trials. Method Data included 562 individuals with MCI from the Alzheimer's Disease Neuroimaging Initiative (ADNI) project with baseline MRI, CSF amyloid beta (Aβ), t‐tau, and p‐tau data and a minimum of one‐year follow‐up information on clinical diagnosis. White matter hyperintensities (WMHs) were segmented using a previously validated random forests classifier (Dadar et al. 2017). SNIPE (Scoring by Nonlocal Image Patch Estimator) was used to measure Alzheimer’s‐disease‐like atrophy patterns in the hippocampi (HC) and entorhinal cortex (EC) (Coupé et al. 2019). CSF Aβ, p‐tau and t‐tau levels were obtained from project files. Agglomerative hierarchical clustering as used to cluster the data based on baseline age, education, APOE4 status, CSF Aβ, p‐tau and t‐tau levels, WMH load, and HC and EC grading scores. We then investigated differences in baseline ADAS13 cognitive scores as well as rate of conversion to dementia between different subtypes. Result Figure 1 shows the clustering dendrogram, splitting the data into three subtypes of 152, 200, and 210 participants, respectively. Figure 2 compares biomarker values across subtypes. Baseline ADAS13 scores and conversion rates were significantly different across all subtypes (p<0.0001). Subtype 1 had the oldest subjects with largest WMH loads (p<0.0001), with a conversion rate of 30.2%. Subtype 2 had the highest conversion rate (70.0%), with significantly lower CSF Aβ and EC grading scores, and higher CSF p‐tau and t‐tau values (p<0.0001). Subtype 3 had the lowest conversion rate (15.2%), with significantly higher HC and EC grading scores and lower age and WMH loads than the other two subtypes (p<0.0001). Conclusion Biomarker‐based subtyping of MCI subjects led to three distinct groups with significantly different clinical outcomes: 1) older individuals with cerebrovascular pathology and moderate conversion rates, 2) individuals with abnormal CSF biomarker levels, hippocampal and entorhinal atrophy, and high conversion rates, and 3) younger individuals without abnormal biomarker levels and low conversion rates.