No abstract

Background: Alzheimer’s disease (AD) is a severe health problem. Challenges still remain in early diagnosis. Objective: The objective of this study was to build a Stacking framework for multi-classification of AD by a combination of neuroimaging and clinical features to improve the performance. Methods: The data we used were from the Alzheimer’s Disease Neuroimaging Initiative database with a total of 493 subjects, including 125 normal control (NC), 121 early mild cognitive impairment, 109 late mild cognitive impairment (LMCI), and 138 AD. We selected structural magnetic resonance imaging (sMRI) features by voting strategy. The imaging features, demographic information, Mini-Mental State Examination, and Alzheimer’s Disease Assessment Scale-Cognitive Subscale were combined together as classification features. We proposed a two-layer Stacking ensemble framework to classify four types of people. The first layer represented support vector machine, random forests, adaptive boosting, and gradient boosting decision tree; the second layer was a logistic regression classifier. Additionally, we analyzed performance of only sMRI feature and combined features and compared the proposed model with four base classifiers. Results: The Stacking model combined with sMRI and non-imaging features outshined four base classifiers with an average accuracy of 86.96% . Compared with using sMRI data alone, sMRI combined with non-imaging features significantly improved diagnostic accuracy, especially in NC versus LMCI and LMCI versus AD by 14.08% . Conclusion: The Stacking framework we used can improve performance in diagnosis of AD using combined features.

Background: Identifying individuals with mild cognitive impairment (MCI) who are at increased risk of Alzheimer’s Disease (AD) in cognitive screening is important for early diagnosis and prevention of AD. Objective: This study aimed at proposing a screening strategy based on landmark models to provide dynamic predictive probabilities of MCI-to-AD conversion according to longitudinal neurocognitive tests. Methods: Participants were 312 individuals who had MCI at baseline. The longitudinal neurocognitive tests were the Mini–Mental State Examination, Alzheimer Disease Assessment Scale–Cognitive 13 items, Rey Auditory Verbal Learning Test immediate, learning, and forgetting, and Functional Assessment Questionnaire. We constructed three types of landmark models and selected the optimal landmark model to dynamically predict 2-year probabilities of conversion. The dataset was randomly divided into training set and validation set at a ratio of 7:3. Results: The FAQ, RAVLT-immediate, and RAVLT-forgetting were significant longitudinal neurocognitive tests for MCI-to-AD conversion in all three landmark models. We considered Model 3 as the final landmark model (C-index = 0.894, Brier score = 0.040) and selected Model 3c (FAQ and RAVLT-forgetting as neurocognitive tests) as the optimal landmark model (C-index = 0.898, Brier score = 0.027). Conclusion: Our study shows that the optimal landmark model is feasible to identify the risk of MCI-to-AD conversion, which can be implemented in cognitive screening.