Early Prediction of Alzheimer's Disease Using Null Longitudinal Model-Based Classifiers

Abstract

Incipient Alzheimer's Disease (AD) is characterized by a slow onset of clinical symptoms, with pathological brain changes starting several years earlier. Consequently, it is necessary to first understand and differentiate age-related changes in brain regions in the absence of disease, and then to support early and accurate AD diagnosis. However, there is poor understanding of the initial stage of AD; seemingly healthy elderly brains lose matter in regions related to AD, but similar changes can also be found in non-demented subjects having mild cognitive impairment (MCI). By using a Linear Mixed Effects approach, we modelled the change of 166 Magnetic Resonance Imaging (MRI)-based biomarkers available at a 5-year follow up on healthy elderly control (HC, n = 46) subjects. We hypothesized that, by identifying their significant variant (vr) and quasi-variant (qvr) brain regions over time, it would be possible to obtain an age-based null model, which would characterize their normal atrophy and growth patterns as well as the correlation between these two regions. By using the null model on those subjects who had been clinically diagnosed as HC (n = 161), MCI (n = 209) and AD (n = 331), normal age-related changes were estimated and deviation scores (residuals) from the observed MRI-based biomarkers were computed. Subject classification, as well as the early prediction of conversion to MCI and AD, were addressed through residual-based Support Vector Machines (SVM) modelling. We found reductions in most cortical volumes and thicknesses (with evident gender differences) as well as in sub-cortical regions, including greater atrophy in the hippocampus. The average accuracies (ACC) recorded for men and women were: AD-HC: 94.11%, MCI-HC: 83.77% and MCI converted to AD (cAD)-MCI non-converter (sMCI): 76.72%. Likewise, as compared to standard clinical diagnosis methods, SVM classifiers predicted the conversion of cAD to be 1.9 years earlier for females (ACC:72.5%) and 1.4 years earlier for males (ACC:69.0%).

Fig 1. Proposed framework.

(A) HC subjects with normal CSF profile are identified from cutoff values calculated from CSF biomarkers distributions. (B) Longitudinal ROIs of these subjects are modelled using LME approach, variant (vr) and quasi-variant (qvr) ROIs and Y-intercepts (y₀) ROIs values are identified and then null models for both genders are built from these values by applying multivariate modelling. (C) qvr ROIs values of new HC, MCI and AD subjects are used within null models to infer the y₀ values of vr ROIs. Estimated ROIs values ($\widehat{y}$) at different ages are estimated by linear regression by using y₀ and β coefficients of age and education. Residuals are calculated as the difference $y-\widehat{y}$; and finally, SVM classifiers are trained for subject classification and addressing the early diagnosis problem: HC vs MCI, MCI vs. AD and HC vs AD. The full workflow of last two stages is applied separately for each gender.

Fig 2. Boxplot of CSF biomarkers concentrations for dx_csf diagnostic groups.

(a) CSF-Aβ1 − 42; and (b) CSF-τ.