1. This study developed a hierarchical multi-class framework for clinical populations, namely, normal cognition (NC), early mild cognitive impairment (EMCI), late mild cognitive impairment (LMCI), and Alzheimer's disease (AD).
2. Four cortical geometric properties for 148 anatomical structures were extracted, namely, cortical thickness (CTh), fractal dimension (FD), gyrification index (GI), and sulcus depth (SD).
3. The combination of selected imaging features and clinical variables improved the multi-class performance using the AdaBoost algorithm, with overall accuracy rates of 0.877 in the temporal validation set.
The article is generally reliable and trustworthy as it provides detailed information on the development of a hierarchical multi-class framework for clinical populations, namely, normal cognition (NC), early mild cognitive impairment (EMCI), late mild cognitive impairment (LMCI), and Alzheimer's disease (AD). The authors have provided evidence to support their claims by citing relevant studies from the literature. Furthermore, they have used a large sample size from the Alzheimer's Disease Neuroimaging Initiative database to develop their model.
However, there are some potential biases that should be noted. For example, the authors have not discussed any possible risks associated with using this framework in clinical practice or explored any counterarguments to their findings. Additionally, they have not presented both sides of the argument equally; instead they have focused mainly on supporting their own claims without considering alternative perspectives or interpretations of their results. Furthermore, there is no mention of any promotional content in the article which could be seen as a potential bias.
In conclusion, while this article is generally reliable and trustworthy due to its detailed information and evidence-based approach to developing a hierarchical multi-class framework for AD diagnosis, there are some potential biases that should be noted such as lack of discussion on possible risks associated with using this framework in clinical practice or exploring counterarguments to their findings.