Prediction of conversion from mild cognitive impairment to Alzheimer's disease dementia based upon biomarkers and neuropsychological test performance

Abstract

The current study tested the accuracy of primary MRI and cerebrospinal fluid (CSF) biomarker candidates and neuropsychological tests for predicting the conversion from mild cognitive impairment (MCI) to Alzheimer's disease (AD) dementia. In a cross-validation paradigm, predictor models were estimated in the training set of AD (N = 81) and elderly control subjects (N = 101). A combination of CSF t-tau/Aβ(1-4) ratio and MRI biomarkers or neuropsychological tests (free recall and trail making test B (TMT-B)) showed the best statistical fit in the AD vs. HC comparison, reaching a classification accuracy of up to 64% when applied to the prediction of MCI conversion (3.3-year observation interval, mean = 2.3 years). However, several single-predictor models showed a predictive accuracy of MCI conversion comparable to that of any multipredictor model. The best single predictors were right entorhinal cortex (prediction accuracy = 68.5% (95% CI (59.5, 77.4))) and TMT-B test (prediction accuracy 64.6% (95% CI (55.5, 73.4%))). In conclusion, short-term conversion to AD is predicted by single marker models to a comparable degree as by multimarker models in amnestic MCI subjects.

Fig. 1

Flow chart of number of patients undergoing the test under evaluation (index test) and the reference test. HCV, Hippocampus volume; ERC, Entorhinal cortical thickness.

Fig. 2

Distribution of MCI-AD converters (green triangles) vs. MCI nonAD (red circles) as a function of left hippocampus volume (ln) and CSF tau/Aβ_1-42 ratio (A) and for the entorhinal cortex (mm³) vs. CSF tau/Aβ_1-42 ratio (B). The lines show the risk zones for classification as MCI converters or MCI nonconverters. The risk of MCI conversion associated with the left hippocampus volume (A) or left entorhinal cortical thickness (B) is labeled as percentages on each line. The arrow points in the direction of risk increase associated with a decrease in the MRI measures (inset in A and B). Note that an increase in the CSF tau/Aβ_1-42 ratio as indicated by the slope of the lines, but a decrease in left hippocampus volume (A) or left entorhinal cortical thickness (B) indicated by the height of the lines is associated with an increased risk of MCI-AD conversion.

Fig. 3

Bootstrapped mean of the total overall classification accuracy and 95% CI for the 24 rank ordered models of highest CAC each of 1-, 2-, 3-, and 4-predictor models for the classification of MCI conversion within a 2-year interval. For identification of models see supplementary Table 1, where the models are identified by their corresponding rank.