Incremental value of biomarker combinations to predict progression of mild cognitive impairment to Alzheimer's dementia

Abstract

Background: The progression of mild cognitive impairment (MCI) to Alzheimer's disease (AD) dementia can be predicted by cognitive, neuroimaging, and cerebrospinal fluid (CSF) markers. Since most biomarkers reveal complementary information, a combination of biomarkers may increase the predictive power. We investigated which combination of the Mini-Mental State Examination (MMSE), Clinical Dementia Rating (CDR)-sum-of-boxes, the word list delayed free recall from the Consortium to Establish a Registry of Dementia (CERAD) test battery, hippocampal volume (HCV), amyloid-beta_1-42 (Aβ42), amyloid-beta_1-40 (Aβ40) levels, the ratio of Aβ42/Aβ40, phosphorylated tau, and total tau (t-Tau) levels in the CSF best predicted a short-term conversion from MCI to AD dementia.

Methods: We used 115 complete datasets from MCI patients of the "Dementia Competence Network", a German multicenter cohort study with annual follow-up up to 3 years. MCI was broadly defined to include amnestic and nonamnestic syndromes. Variables known to predict progression in MCI patients were selected a priori. Nine individual predictors were compared by receiver operating characteristic (ROC) curve analysis. ROC curves of the five best two-, three-, and four-parameter combinations were analyzed for significant superiority by a bootstrapping wrapper around a support vector machine with linear kernel. The incremental value of combinations was tested for statistical significance by comparing the specificities of the different classifiers at a given sensitivity of 85%.

Results: Out of 115 subjects, 28 (24.3%) with MCI progressed to AD dementia within a mean follow-up period of 25.5 months. At baseline, MCI-AD patients were no different from stable MCI in age and gender distribution, but had lower educational attainment. All single biomarkers were significantly different between the two groups at baseline. ROC curves of the individual predictors gave areas under the curve (AUC) between 0.66 and 0.77, and all single predictors were statistically superior to Aβ40. The AUC of the two-parameter combinations ranged from 0.77 to 0.81. The three-parameter combinations ranged from AUC 0.80-0.83, and the four-parameter combination from AUC 0.81-0.82. None of the predictor combinations was significantly superior to the two best single predictors (HCV and t-Tau). When maximizing the AUC differences by fixing sensitivity at 85%, the two- to four-parameter combinations were superior to HCV alone.

Conclusion: A combination of two biomarkers of neurodegeneration (e.g., HCV and t-Tau) is not superior over the single parameters in identifying patients with MCI who are most likely to progress to AD dementia, although there is a gradual increase in the statistical measures across increasing biomarker combinations. This may have implications for clinical diagnosis and for selecting subjects for participation in clinical trials.

Keywords: Alzheimer’s dementia; Amyloid-beta 42; Biomarkers; Hippocampal volume; Mild cognitive impairment; Phospho-tau; Prediction; Tau.

Fig. 1

Patient loss due to missing data. The absolute sample size is given in the rectangles; the loss of sample size due to missing data of the respective measures is given in the diamonds. AD Alzheimer’s disease, CSF cerebrospinal fluid, MCI mild cognitive impairment

Fig. 2

ROC curves of the best single and two- to four-parameter classifiers, based on 100 replicates of a 0.632 bootstrapping algorithm based on support vector machine classifier. A boxplot of areas under the curves (AUCs) for the different classification engines is shown in the insert. The AUC values of the different classification engines were not significantly different from each other. CDR.SB Clinical Dementia Rating–sum-of-boxes, HIPPO hippocampal volume, ttau total tau, ratio42_40 amyloid-beta_1–42/amyloid-beta_1–42 ratio

Fig. 3

Boxplot of specificities at a given sensitivity of 85% for the different predictor combinations. AUC were calculated by 100 replications of a .632 bootstrapping algorithm. p-values for comparing specificities at the given sensitivity demonstrated the single value predictors HCV and total tau were significantly inferior compared to the two-four predictor combinations. None of the predictor combinations were significantly different from each other. CDR.SB Clinical Dementia Rating–sum-of-boxes, HIPPO hippocampal volume, ttau total tau, ratio42_40 amyloid-beta_1–42/amyloid-beta_1–42 ratio