Table 1.
Demographic data for the 694 ADNI participants, shown across categories of clinical status.
Table 2.
ADNI cognitive instruments used in this study.
Figure 1.
The concept of a probabilistic hypercube is illustrated.
The probability hypercube can be interpreted as a geometrical representation of the output of a set of generative classifiers, each one estimated with different types of data. The set of AD-PS scores corresponding to a given individual define a position inside a unit hypercube. The position inside the hypercube for three individuals is illustrated.
Figure 2.
RLR classifier performances across different types of information and cognitive groups.
Consistent with previous reports, grey matter (GM) tissue was more informative than white matter (WM) and cerebrospinal fluid (CSF). Interestingly, this difference decreases when a group with less severe cognitive decline is compared with the cognitively normal (CN) group.
Figure 3.
The GM, WM and CSF discriminative maps produced by logistic regression with sparsity regularization are overlaid on the study customized template generated by DARTEL.
In each case, nine coronal slices (−82, −68, −52, −38, −22, −8, 8, 22, 38) are shown (neurological convention) in the first, second, and third rows, respectively. The blue areas are associated with AD classification, while the red ones are associated with CN classification.
Table 3.
Median values of classification accuracy, sensitivity and specificity across cognitive groups are presented.
Table 4.
Median AD-PS scores by type of information, SPARE-AD index and total hippocampal volume at baseline are presented.
Table 5.
Results from proportional hazards regression to assess associations with the distribution of times until conversion to AD.
Table 6.
Median values of AD-PS scores, SPARE-AD index and total hippocampal volume were estimated across cognitive status categories for ADNI participants, based on age (<75 yrs., vs. ≥75 yrs.).
Table 7.
Median values of AD-PS scores, SPARE-AD index and total hippocampal volume were estimated across clinical groups by functional status (FAQ≤2 v. >2).
Figure 4.
Two-dimensional probabilistic hypercube views of ADNI data showing AD-PS grey matter (GM) and white matter (WM) scores for 188 cognitively normal (CN – blue stars) and 171 Alzheimer's disease (AD) patients (red circles).
They tended to cluster in different corners, as expected.
Table 8.
Summary of classification reports of CN versus AD subjects based on structural MRI data from different groups.
Table 9.
Summary of classification reports of ncMCI versus cMCI subjects based on structural MRI data from different groups.
Table 10.
Results related to detection of differences between ncMCI from cMCI ADNI participants based on statistical testing and imaging data.