Prognosis of conversion of mild cognitive impairment to Alzheimer's dementia by voxel-wise Cox regression based on FDG PET data

Abstract

AimThe value of 18F-fluorodeoxyglucose (FDG) PET for the prognosis of conversion from mild cognitive impairment (MCI) to Alzheimer's dementia (AD) is controversial. In the present work, the identification of cerebral metabolic patterns with significant prognostic value for conversion of MCI patients to AD is investigated with voxel-based Cox regression, which in contrast to common categorical comparisons also utilizes time information.MethodsFDG PET data of 544 MCI patients from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database were randomly split into two equally-sized datasets (training and test). Within a median follow-up duration of 47 months (95% CI: 46–48 months) 181 patients developed AD. In the training dataset, voxel-wise Cox regressions were used to identify regions associated with conversion of MCI to AD. These were compared to regions identified by a classical group comparison (analysis of covariance (ANCOVA) with statistical parametric mapping (SPM) 8) between converters and non-converters (both adjusted for apolipoprotein E (APOE) genotype, mini-mental state examination (MMSE) score, age, sex and education). In the test dataset, normalized FDG uptake within significant brain regions from voxel-wise Cox- and ANCOVA analyses (Cox- and ANCOVA- regions of interest (ROI), respectively) and clinical variables APOE status, MMSE score and education were tested in different Cox models (adjusted for age, sex) including: (1) only clinical variables, (2) only normalized FDG uptake in ANCOVA-ROI, (3) only normalized FDG uptake from Cox-ROI, (4) clinical variables plus FDG uptake in ANCOVA-ROI, (5) clinical variables plus FDG uptake from Cox-ROI.ResultsConversion-related regions with relative hypometabolism comprised parts of the temporo-parietal and posterior cingulate cortex/precuneus for voxel-wise ANCOVA, plus frontal regions for voxel-wise Cox regression (both p < .01, false discovery rate (FDR) corrected). The clinical-only model (1) and the models based on normalized FDG uptake from Cox-ROI only (2) and ANCOVA-ROI only (3) all significantly predicted conversion to AD (Wald Test (WT): p < .001). The clinical model (1) was significantly improved by adding imaging information in model (4) (Akaike information criterion (AIC) relative likelihood (RL) (1) vs (4): RL < 0.018). There were no significant differences between models (2) and (3), as well as (4) and (5).ConclusionsVoxel-wise Cox regression identifies conversion-related patterns of cerebral glucose metabolism, but is not superior to classical group contrasts in this regard. With imaging information from both FDG PET patterns, the prediction of conversion to AD was improved.

The Power of EEG to Predict Conversion from Mild Cognitive Impairment and Subjective Cognitive Decline to Dementia

“…It is difficult to compare our results with studies exam ining MRI, FDG and amyloid PET, and CSF biomarkers as predictors of conversion to dementia, because different populations and different statistical methods are used. Recently, one study using a machine learning program to evaluate structural brain changes using MRI as predictors of conversion reported very high AUC, and another study using voxelbased FDGPET also reported very good re sults [19,21]. Best results are though reported from stud ies using various biomarkers in combination [24,25].…”

“…Older age, poor er cognition, APOE ε4 allele carrier status, and hyper tension are found to increase the conversion rate to de mentia [15]. The use of various MRI and PET methods and cerebrospinal fluid (CSF) examination, measuring concentrations of amyloidβ, phosphorylated and total tau proteins, as well as other proteins, including inflam matory markers, have shown to be helpful in predicting patients with MCI and SCD who will convert to demen tia, especially to AD [16][17][18][19][20][21][22]. A recent Cochrane review, however, does not support the use of βamyloid PET as biomarker for AD, but studies examining the combina tion of cognitive tests with CSF proteins, MRI, and FDGPET have shown excellent results in identifying people with MCI that would convert to dementia [23][24][25].…”

Mitochondria dysfunction in the pathogenesis of Alzheimer’s disease: recent advances

“…The extent and topography of glucose hypometabolism correlated with symptom severity and also reflected the regional distribution of impaired synaptic activity and density in AD [16,17]. Accepted as a hallmark of the disease, cerebral glucose hypometabolism assessed with FDG-PET is now used as a common biomarker for early detection of AD and can predict the conversion from MCI to AD with reasonable sensitivity and accuracy [18,19], which underscores the critical role of impaired energy metabolism in the course of AD.…”

Image Based Data Mining Using Per-voxel Cox Regression

“…In this work, we have performed permutation testing to assess statistical significance using the max-T method proposed by Chen et al (9). In similar work by Sörensen et al (17), a false discovery rate (FDR) approach was used to adjust analytical p-values derived from the Cox model fitting. While this may be appropriate in that analysis, we feel that the use of a full permutation is preferable in our analysis, due to the presence of strong correlation between neighboring voxels in a dose distribution, which must be carefully taken into account in FDR.…”