Gaussian process classification of Alzheimer's disease and mild cognitive impairment from resting-state fMRI

Selection bias in the reported performances of AD classification pipelines

The last decade has seen a great proliferation of supervised learning pipelines for individual diagnosis and prognosis in Alzheimer's disease. As more pipelines are developed and evaluated in the search for greater performance, only those results that are relatively impressive will be selected for publication. We present an empirical study to evaluate the potential for optimistic bias in classification performance results as a result of this selection. This is achieved using a novel, resampling-based experiment design that effectively simulates the optimisation of pipeline specifications by individuals or collectives of researchers using cross validation with limited data. Our findings indicate that bias can plausibly account for an appreciable fraction (often greater than half) of the apparent performance improvement associated with the pipeline optimisation, particularly in small samples. We discuss the consistency of our findings with patterns observed in the literature and consider strategies for bias reduction and mitigation.

•

Demonstration and measurement of selection bias in AD classification experiments

•

Bias accounts for much of the performance improvement seen with pipeline optimisation.

•

Assessment of key risk factors and guidance on best research practices

•

Evidence of selection bias in results collected by a recent literature review

Classifying Cognitive Profiles Using Machine Learning with Privileged Information in Mild Cognitive Impairment

Early diagnosis of dementia is critical for assessing disease progression and potential treatment. State-or-the-art machine learning techniques have been increasingly employed to take on this diagnostic task. In this study, we employed Generalized Matrix Learning Vector Quantization (GMLVQ) classifiers to discriminate patients with Mild Cognitive Impairment (MCI) from healthy controls based on their cognitive skills. Further, we adopted a “Learning with privileged information” approach to combine cognitive and fMRI data for the classification task. The resulting classifier operates solely on the cognitive data while it incorporates the fMRI data as privileged information (PI) during training. This novel classifier is of practical use as the collection of brain imaging data is not always possible with patients and older participants. MCI patients and healthy age-matched controls were trained to extract structure from temporal sequences. We ask whether machine learning classifiers can be used to discriminate patients from controls and whether differences between these groups relate to individual cognitive profiles. To this end, we tested participants in four cognitive tasks: working memory, cognitive inhibition, divided attention, and selective attention. We also collected fMRI data before and after training on a probabilistic sequence learning task and extracted fMRI responses and connectivity as features for machine learning classifiers. Our results show that the PI guided GMLVQ classifiers outperform the baseline classifier that only used the cognitive data. In addition, we found that for the baseline classifier, divided attention is the only relevant cognitive feature. When PI was incorporated, divided attention remained the most relevant feature while cognitive inhibition became also relevant for the task. Interestingly, this analysis for the fMRI GMLVQ classifier suggests that (1) when overall fMRI signal is used as inputs to the classifier, the post-training session is most relevant; and (2) when the graph feature reflecting underlying spatiotemporal fMRI pattern is used, the pre-training session is most relevant. Taken together these results suggest that brain connectivity before training and overall fMRI signal after training are both diagnostic of cognitive skills in MCI.

Classification of patients with MCI and AD from healthy controls using directed graph measures of resting-state fMRI

Brain network alterations in patients with Alzheimer's disease (AD) has been the subject of much investigation, but the biological mechanisms underlying these alterations remain poorly understood. Here, we aim to identify the changes in brain networks in patients with AD and mild cognitive impairment (MCI), and provide an accurate algorithm for classification of these patients from healthy control subjects (HC) by using a graph theoretical approach and advanced machine learning methods. Multivariate Granger causality analysis was performed on resting-state functional magnetic resonance imaging (rs-fMRI) data of 34 AD, 89 MCI, and 45 HC to calculate various directed graph measures. The graph measures were used as the original feature set for the machine learning algorithm. Filter and wrapper feature selection methods were applied to the original feature set to select an optimal subset of features. An accuracy of 93.3% was achieved for classification of AD, MCI, and HC using the optimal features and the naïve Bayes classifier. We also performed a hub node analysis and found that the number of hubs in HC, MCI, and AD were 12, 10, and 9, respectively, suggesting that patients with AD experience disturbance of critical communication areas in their brain network as AD progresses. The findings of this study provide insight into the neurophysiological mechanisms underlying MCI and AD. The proposed classification method highlights the potential of directed graph measures of rs-fMRI data for identification of the early stage of AD.

A semi-mechanism approach based on MRI and proteomics for prediction of conversion from mild cognitive impairment to Alzheimer's disease

Mild cognitive impairment (MCI) is a precursor phase of Alzheimer’s disease (AD). As current treatments may be effective only at the early stages of AD, it is important to track MCI patients who will convert to AD. The aim of this study is to develop a high performance semi-mechanism based approach to predict the conversion from MCI to AD and improve our understanding of MCI-to-AD conversion mechanism. First, analysis of variance (ANOVA) test and lasso regression are employed to identify the markers related to the conversion. Then the Bayesian network based on selected markers is established to predict MCI-to-AD conversion. The structure of Bayesian network suggests that the conversion may start with fibrin clot formation, verbal memory impairment, eating pattern changing and hyperinsulinemia. The Bayesian network achieves a high 10-fold cross-validated prediction performance with 96% accuracy, 95% sensitivity, 65% specificity, area under the receiver operating characteristic curve of 0.82 on data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. The semi-mechanism based approach provides not only high prediction performance but also clues of mechanism for MCI-to-AD conversion.

Predicting individual brain maturity using dynamic functional connectivity

Neuroimaging-based functional connectivity (FC) analyses have revealed significant developmental trends in specific intrinsic connectivity networks linked to cognitive and behavioral maturation. However, knowledge of how brain functional maturation is associated with FC dynamics at rest is limited. Here, we examined age-related differences in the temporal variability of FC dynamics with data publicly released by the Nathan Kline Institute (NKI; n = 183, ages 7-30) and showed that dynamic inter-region interactions can be used to accurately predict individual brain maturity across development. Furthermore, we identified a significant age-dependent trend underlying dynamic inter-network FC, including increasing variability of the connections between the visual network, default mode network (DMN) and cerebellum as well as within the cerebellum and DMN and decreasing variability within the cerebellum and between the cerebellum and DMN as well as the cingulo-opercular network. Overall, the results suggested significant developmental changes in dynamic inter-network interaction, which may shed new light on the functional organization of typical developmental brains.