Background:
Diagnosing Alzheimer’s disease (AD) in its earliest stages is important for
therapeutic and support planning. Similarly, being able to predict who will convert from mild cognitive
impairment (MCI) to AD would have clinical implications.
Objectives:
The goals of this study were to identify features from the Alzheimer’s Disease Neuroimaging
Initiative (ADNI) database associated with the conversion from MCI to AD, and to characterize the
temporal evolution of that conversion.
Methods:
We screened the publically available ADNI longitudinal database for subjects with MCI who
have developed AD (cases: n=305), and subjects with MCI who have remained stable (controls: n=250).
Analyses included 1,827 features from laboratory assays (n=12), quantitative MRI scans (n=1,423), PET
studies (n=136), medical histories (n=72), and neuropsychological tests (n=184). Statistical longitudinal
models identified features with significant differences in longitudinal behavior between cases and matched
controls. A multiple-comparison adjusted log-rank test identified the capacity of the significant predictive
features to predict early conversion.
Results:
411 features (22.5%) were found to be statistically different between cases and controls at the
time of AD diagnosis; 385 features were statistically different at least 6 months prior to diagnosis, and 28
features distinguished early from late conversion, 20 of which were obtained from neuropsychological
tests. In addition, 69 features (3.7%) had statistically significant changes prior to AD diagnosis.
Conclusion:
Our results characterized features associated with disease progression from MCI to AD, and,
in addition, the log-rank test identified features which are associated with the risk of early conversion.
Semi-automatic liver segmentation based on probabilistic models and anatomical constraints