Study of brain morphology change in Alzheimer's disease and amnestic mild cognitive impairment compared with normal controls

Data analysis with Shapley values for automatic subject selection in Alzheimer's disease data sets using interpretable machine learning

BACKGROUND

For the recruitment and monitoring of subjects for therapy studies, it is important to predict whether mild cognitive impaired (MCI) subjects will prospectively develop Alzheimer's disease (AD). Machine learning (ML) is suitable to improve early AD prediction. The etiology of AD is heterogeneous, which leads to high variability in disease patterns. Further variability originates from multicentric study designs, varying acquisition protocols, and errors in the preprocessing of magnetic resonance imaging (MRI) scans. The high variability makes the differentiation between signal and noise difficult and may lead to overfitting. This article examines whether an automatic and fair data valuation method based on Shapley values can identify the most informative subjects to improve ML classification.

METHODS

An ML workflow was developed and trained for a subset of the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. The validation was executed for an independent ADNI test set and for the Australian Imaging, Biomarker and Lifestyle Flagship Study of Ageing (AIBL) cohort. The workflow included volumetric MRI feature extraction, feature selection, sample selection using Data Shapley, random forest (RF), and eXtreme Gradient Boosting (XGBoost) for model training as well as Kernel SHapley Additive exPlanations (SHAP) values for model interpretation.

RESULTS

The RF models, which excluded 134 of the 467 training subjects based on their RF Data Shapley values, outperformed the base models that reached a mean accuracy of 62.64% by 5.76% (3.61 percentage points) for the independent ADNI test set. The XGBoost base models reached a mean accuracy of 60.00% for the AIBL data set. The exclusion of those 133 subjects with the smallest RF Data Shapley values could improve the classification accuracy by 2.98% (1.79 percentage points). The cutoff values were calculated using an independent validation set.

CONCLUSION

The Data Shapley method was able to improve the mean accuracies for the test sets. The most informative subjects were associated with the number of ApolipoproteinE ε4 (ApoE ε4) alleles, cognitive test results, and volumetric MRI measurements.

Relationship between Cortical Thickness and EEG Alterations during Sleep in the Alzheimer's Disease

Recent evidence showed that EEG activity alterations that occur during sleep are associated with structural, age-related, changes in healthy aging brains, and predict age-related decline in memory performance. Alzheimer's disease (AD) patients show specific EEG alterations during sleep associated with cognitive decline, including reduced sleep spindles during NREM sleep and EEG slowing during REM sleep. We investigated the relationship between these EEG sleep alterations and brain structure changes in a study of 23 AD patients who underwent polysomnographic recording of their undisturbed sleep and 1.5T MRI scans. Cortical thickness measures were correlated with EEG power in the sigma band during NREM sleep and with delta- and beta-power during REM sleep. Thinning in the right precuneus correlated with all the EEG indexes considered in this study. Frontal-central NREM sigma power showed an inverse correlation with thinning of the left entorhinal cortex. Increased delta activity at the frontopolar and temporal regions was significantly associated with atrophy in some temporal, parietal, and frontal cortices, and with mean thickness of the right hemisphere. Our findings revealed an association between sleep EEG alterations and the changes to AD patients' brain structures. Findings also highlight possible compensatory processes involving the sources of frontal-central sleep spindles.

Case report of the treatment and experience of mental disorders due to chronic viral encephalitis

Viral encephalitis is a common clinical condition. Its clinical manifestations are variable and include neurological symptoms and psychiatric abnormalities, which makes clinical diagnosis and treatment difficult. To date, there are only a few reported cases on mental symptoms of chronic viral encephalitis. We present a case of a 16-year-old male patient who was previously hospitalised and diagnosed with schizophrenia and treated with aripiprazole 15 mg/day but failed to respond. The patient was then given antiviral therapy and recovered after 2 weeks. Clinicians should be aware of the possbility that chronic mental disorders could be caused by viral encephalitis. In the future, diagnosis of chronic functional mental disorders should include viral encephalitis in the differential diagnosis.

A feasibility study on the association between residential greenness and neurocognitive function in middle-aged Bulgarians

Recent research has indicated that exposure to residential vegetation ("greenness") may be protective against cognitive decline and may support the integrity of the corresponding brain structures. However, not much is known about these effects, especially in less affluent countries and in middle-aged populations. In this study, we investigated the associations between greenness and neurocognitive function. We used a convenience sample of 112 middle-aged Bulgarians and two cognitive tests: the Consortium to Establish a Registry for Alzheimer's Disease Neuropsychological Battery (CERAD-NB) and the Montreal Cognitive Assessment (MoCA). In addition, structural brain imaging data were available for 25 participants. Participants' home address was used to link cognition scores to the normalised difference vegetation index (NDVI), a measure of overall neighbourhood vegetation level (radii from 100 to 1,000 m). Results indicated that higher NDVI was consistently associated with higher CERAD-NB and MoCA scores across radial buffers and adjustment scenarios. Lower waist circumference mediated the effect of NDVI on CERAD-NB. NDVI100-m was positively associated with average cortical thickness across both hemispheres, but these correlations turned marginally significant (P<0.1) after correction for false discovery rate due to multiple comparisons. In conclusion, living in a greener neighbourhood might be associated with better cognitive function in middle-aged Bulgarians, with lower central adiposity partially accounting for this effect. Tentative evidence suggests that greenness might also contribute to structural integrity in the brain regions regulating cognitive functions. Future research should build upon our findings and investigate larger and more representative population groups.

Early Detection of Alzheimer's Disease Using Magnetic Resonance Imaging: A Novel Approach Combining Convolutional Neural Networks and Ensemble Learning

Early detection is critical for effective management of Alzheimer's disease (AD) and screening for mild cognitive impairment (MCI) is common practice. Among several deep-learning techniques that have been applied to assessing structural brain changes on magnetic resonance imaging (MRI), convolutional neural network (CNN) has gained popularity due to its superb efficiency in automated feature learning with the use of a variety of multilayer perceptrons. Meanwhile, ensemble learning (EL) has shown to be beneficial in the robustness of learning-system performance via integrating multiple models. Here, we proposed a classifier ensemble developed by combining CNN and EL, i.e., the CNN-EL approach, to identify subjects with MCI or AD using MRI: i.e., classification between (1) AD and healthy cognition (HC), (2) MCIc (MCI patients who will convert to AD) and HC, and (3) MCIc and MCInc (MCI patients who will not convert to AD). For each binary classification task, a large number of CNN models were trained applying a set of sagittal, coronal, or transverse MRI slices; these CNN models were then integrated into a single ensemble. Performance of the ensemble was evaluated using stratified fivefold cross-validation method for 10 times. The number of the intersection points determined by the most discriminable slices separating two classes in a binary classification task among the sagittal, coronal, and transverse slice sets, transformed into the standard Montreal Neurological Institute (MNI) space, acted as an indicator to assess the ability of a brain region in which the points were located to classify AD. Thus, the brain regions with most intersection points were considered as those mostly contributing to the early diagnosis of AD. The result revealed an accuracy rate of 0.84 ± 0.05, 0.79 ± 0.04, and 0.62 ± 0.06, respectively, for classifying AD vs. HC, MCIc vs. HC, and MCIc vs. MCInc, comparable to previous reports and a 3D deep learning approach (3D-SENet) based on a more state-of-the-art and popular Squeeze-and-Excitation Networks model using channel attention mechanism. Notably, the intersection points accurately located the medial temporal lobe and several other structures of the limbic system, i.e., brain regions known to be struck early in AD. More interestingly, the classifiers disclosed multiple patterned MRI changes in the brain in AD and MCIc, involving these key regions. These results suggest that as a data-driven method, the combined CNN and EL approach can locate the most discriminable brain regions indicated by the trained ensemble model while the generalization ability of the ensemble model was maximized to successfully capture AD-related brain variations early in the disease process; it can also provide new insights into understanding the complex heterogeneity of whole-brain MRI changes in AD. Further research is needed to examine the clinical implication of the finding, capability of the advocated CNN-EL approach to help understand and evaluate an individual subject's disease status, symptom burden and progress, and the generalizability of the advocated CNN-EL approach to locate the most discriminable brain regions in the detection of other brain disorders such as schizophrenia, autism, and severe depression, in a data-driven way.