Mild Cognitive Impairment Classification Research Articles

Neural biomarker diagnosis and prediction to mild cognitive impairment and Alzheimer’s disease using EEG technology

BackgroundElectroencephalogram (EEG) has emerged as a non-invasive tool to detect the aberrant neuronal activity related to different stages of Alzheimer’s disease (AD). However, the effectiveness of EEG in the precise diagnosis and assessment of AD and its preclinical stage, amnestic mild cognitive impairment (MCI), has yet to be fully elucidated. In this study, we aimed to identify key EEG biomarkers that are effective in distinguishing patients at the early stage of AD and monitoring the progression of AD.MethodsA total of 890 participants, including 189 patients with MCI, 330 patients with AD, 125 patients with other dementias (frontotemporal dementia, dementia with Lewy bodies, and vascular cognitive impairment), and 246 healthy controls (HC) were enrolled. Biomarkers were extracted from resting-state EEG recordings for a three-level classification of HC, MCI, and AD. The optimal EEG biomarkers were then identified based on the classification performance. Random forest regression was used to train a series of models by combining participants’ EEG biomarkers, demographic information (i.e., sex, age), CSF biomarkers, and APOE phenotype for assessing the disease progression and individual’s cognitive function.ResultsThe identified EEG biomarkers achieved over 70% accuracy in the three-level classification of HC, MCI, and AD. Among all six groups, the most prominent effects of AD-linked neurodegeneration on EEG metrics were localized at parieto-occipital regions. In the cross-validation predictive analyses, the optimal EEG features were more effective than the CSF + APOE biomarkers in predicting the age of onset and disease course, whereas the combination of EEG + CSF + APOE measures achieved the best performance for all targets of prediction.ConclusionsOur study indicates that EEG can be used as a useful screening tool for the diagnosis and disease progression evaluation of MCI and AD.

Dual Semi-Supervised Learning for Classification of Alzheimer's Disease and Mild Cognitive Impairment Based on Neuropsychological Data.

Deep learning has shown impressive diagnostic abilities in Alzheimer's disease (AD) research in recent years. However, although neuropsychological tests play a crucial role in screening AD and mild cognitive impairment (MCI), there is still a lack of deep learning algorithms only using such basic diagnostic methods. This paper proposes a novel semi-supervised method using neuropsychological test scores and scarce labeled data, which introduces difference regularization and consistency regularization with pseudo-labeling. A total of 188 AD, 402 MCI, and 229 normal controls (NC) were enrolled in the study from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. We first chose the 15 features most associated with the diagnostic outcome by feature selection among the seven neuropsychological tests. Next, we proposed a dual semi-supervised learning (DSSL) framework that uses two encoders to learn two different feature vectors. The diagnosed 60 and 120 subjects were randomly selected as training labels for the model. The experimental results show that DSSL achieves the best accuracy and stability in classifying AD, MCI, and NC (85.47% accuracy for 60 labels and 88.40% accuracy for 120 labels) compared to other semi-supervised methods. DSSL is an excellent semi-supervised method to provide clinical insight for physicians to diagnose AD and MCI.

A Convolutional Neural Network and Graph Convolutional Network Based Framework for AD Classification.

The neuroscience community has developed many convolutional neural networks (CNNs) for the early detection of Alzheimer's disease (AD). Population graphs are thought of as non-linear structures that capture the relationships between individual subjects represented as nodes, which allows for the simultaneous integration of imaging and non-imaging information as well as individual subjects' features. Graph convolutional networks (GCNs) generalize convolution operations to accommodate non-Euclidean data and aid in the mining of topological information from the population graph for a disease classification task. However, few studies have examined how GCNs' input properties affect AD-staging performance. Therefore, we conducted three experiments in this work. Experiment 1 examined how the inclusion of demographic information in the edge-assigning function affects the classification of AD versus cognitive normal (CN). Experiment 2 was designed to examine the effects of adding various neuropsychological tests to the edge-assigning function on the mild cognitive impairment (MCI) classification. Experiment 3 studied the impact of the edge assignment function. The best result was obtained in Experiment 2 on multi-class classification (AD, MCI, and CN). We applied a novel framework for the diagnosis of AD that integrated CNNs and GCNs into a unified network, taking advantage of the excellent feature extraction capabilities of CNNs and population-graph processing capabilities of GCNs. To learn high-level anatomical features, DenseNet was used; a set of population graphs was represented with nodes defined by imaging features and edge weights determined by different combinations of imaging or/and non-imaging information, and the generated graphs were then fed to the GCNs for classification. Both binary classification and multi-class classification showed improved performance, with an accuracy of 91.6% for AD versus CN, 91.2% for AD versus MCI, 96.8% for MCI versus CN, and 89.4% for multi-class classification. The population graph's imaging features and edge-assigning functions can both significantly affect classification accuracy.

An attention-based deep learning approach for the classification of subjective cognitive decline and mild cognitive impairment using resting-state EEG

Objective. This study aims to design and implement the first deep learning (DL) model to classify subjects in the prodromic states of Alzheimer’s disease (AD) based on resting-state electroencephalographic (EEG) signals. Approach. EEG recordings of 17 healthy controls (HCs), 56 subjective cognitive decline (SCD) and 45 mild cognitive impairment (MCI) subjects were acquired at resting state. After preprocessing, we selected sections corresponding to eyes-closed condition. Five different datasets were created by extracting delta, theta, alpha, beta and delta-to-theta frequency bands using bandpass filters. To classify SCD vs MCI and HC vs SCD vs MCI, we propose a framework based on the transformer architecture, which uses multi-head attention to focus on the most relevant parts of the input signals. We trained and validated the model on each dataset with a leave-one-subject-out cross-validation approach, splitting the signals into 10 s epochs. Subjects were assigned to the same class as the majority of their epochs. Classification performances of the transformer were assessed for both epochs and subjects and compared with other DL models. Main results. Results showed that the delta dataset allowed our model to achieve the best performances for the discrimination of SCD and MCI, reaching an Area Under the ROC Curve (AUC) of 0.807, while the highest results for the HC vs SCD vs MCI classification were obtained on alpha and theta with a micro-AUC higher than 0.74. Significance. We demonstrated that DL approaches can support the adoption of non-invasive and economic techniques as EEG to stratify patients in the clinical population at risk for AD. This result was achieved since the attention mechanism was able to learn temporal dependencies of the signal, focusing on the most discriminative patterns, achieving state-of-the-art results by using a deep model of reduced complexity. Our results were consistent with clinical evidence that changes in brain activity are progressive when considering early stages of AD.

Screening for Mild Cognitive Impairment Using a Machine Learning Classifier and the Remote Speech Biomarker for Cognition: Evidence from Two Clinically Relevant Cohorts.

Modern prodromal Alzheimer's disease (AD) clinical trials might extend outreach to a general population, causing high screen-out rates and thereby increasing study time and costs. Thus, screening tools that cost-effectively detect mild cognitive impairment (MCI) at scale are needed. Develop a screening algorithm that can differentiate between healthy and MCI participants in different clinically relevant populations. Two screening algorithms based on the remote ki:e speech biomarker for cognition (ki:e SB-C) were designed on a Dutch memory clinic cohort (N = 121) and a Swedish birth cohort (N = 404). MCI classification was each evaluated on the training cohort as well as on the unrelated validation cohort. The algorithms achieved a performance of AUC 0.73 and AUC 0.77 in the respective training cohorts and AUC 0.81 in the unseen validation cohorts. The results indicate that a ki:e SB-C based algorithm robustly detects MCI across different cohorts and languages, which has the potential to make current trials more efficient and improve future primary health care.

An Effective Test (EOmciSS) for Screening Older Adults With Mild Cognitive Impairment in a Community Setting: Development and Validation Study

Early detection of mild cognitive impairment (MCI) symptoms is an important step to its diagnosis and intervention. We developed a new screening test called "Efficient Online MCI Screening System" (EOmciSS) for use in community-dwelling older adults. It is a self-paced cognitive test to be completed within 10 minutes on tablets or smartphones in homes or care centers for older adults. This study aims to test the validity of EOmciSS for identifying community-dwelling older adults with MCI risks. Participants (N=827) completed EOmciSS and other screening tests for MCI. The psychometric properties tested were "subscale item difficulty," "discriminative index," "internal consistency," and "construct validity." We also tested between-group discrimination using the cross-validation method in an MCI group and a normal cognitive function (NCF) group. A total of 3 accuracy factors and 1 reaction time factor explained the structure of the 20 item factors. The difficulty level of accuracy factors (ie, "trail making," "clock drawing," "cube copying," "delayed recall") was 0.63-0.99, whereas that of the reaction time factor was 0.77-0.95. The discriminative index of the medium-to-high-difficulty item factors was 0.39-0.97. The internal consistency (Cronbach α) ranged from .41 (for few item factors) to .96. The training data set contained 9 item factors (CC-Acc1, P<.001; CD-Acc1, P=.07; CD-Acc2, P=.06; CD-Acc3, P<.001; TM-Acc4, P=.07; DR-Acc1, P=.03; RS, P=.06; DR-RT1, P=.02; and DR-RT2, P=.05) that were significant predictors for an MCI classification versus NCF classification. Depressive symptoms were identified as significant factors (P<.001) influencing the performance of participants, and were an integral part of our test system. Age (P=.15), number of years of education (P=.18), and proficiency in using an electronic device (P=.39) did not significantly influence the scores nor classification of participants. Application of the MCI/NCF cutoff score (7.90 out of 9.67) to the validation data set yielded an area under the curve of 0.912 (P<.001; 95% CI 0.868-0.955). The sensitivity was 84.9%, specificity was 85.1%, and the Youden index was 0.70. EOmciSS was valid and reliable for identifying older adults with significant risks of MCI. Our results indicate that EOmciSS has higher sensitivity and specificity than those of the Computer-Administered Neuropsychological Screen for Mild Cognitive Impairment and the Computerized Cognitive Screen. The user interface, online operation, and self-paced format allowed the test system to be operated by older adults or their caregivers in different settings (eg, home or care centers for older adults). Depressive symptoms should be an integral part in future MCI screening systems because they influence the test performance and, hence, MCI risk. Chinese Clinical Trial Registry ChiCTR2000039411; http://www.chictr.org.cn/showprojen.aspx?proj=62903.

Virtual reality-based monitoring test for MCI: A multicenter feasibility study.

As the significance of the early diagnosis of mild cognitive impairment (MCI) has emerged, it is necessary to develop corresponding screening tools with high ecological validity and feasible biomarkers. Virtual reality (VR)-based cognitive assessment program, which is close to the daily life of the older adults, can be suitable screening tools for MCI with ecological validity and accessibility. Meanwhile, dehydroepiandrosterone (DHEA) has been observed at a low concentration in the older adults with dementia or cognitive decline, indicating its potential as a biomarker of MCI. This study aimed to determine the efficacy and usability of a VR cognitive assessment program and salivary DHEA for screening MCI. The VR cognitive assessment program and the traditional Montreal Cognitive Assessment (MOCA) test were performed on 12 patients with MCI and 108 healthy older adults. The VR program operates in a situation of caring for a grandchild, and evaluates the memory, attention, visuospatial, and executive functions. An analysis of covariance (ANCOVA), a partial correlation analysis, and receiving operating characteristic (ROC) curve analysis were conducted for statistical analysis. According to the ANCOVA, no significant difference in MOCA scores was found between the normal and MCI groups (F = 2.36, p = 0.127). However, the VR total score of the MCI group was significantly lower than that of the normal group (F = 8.674, p = 0.004). There was a significant correlation between the MOCA and VR scores in the total and matched subdomain scores. The ROC curve analysis also showed a larger area under the curve (AUC) for the VR test (0.765) than for the MOCA test (0.598), and the sensitivity and specificity of the VR program were 0.833 and 0.722, respectively. Salivary DHEA was correlated with VR total (R 2 = 0.082, p = 0.01) and attention scores (R 2 = 0.086, p = 0.009). The VR cognitive test was as effective as the traditional MOCA test in the MCI classification and safe enough for older adults to perform, indicating its potential as a diagnostic tool. It has also been shown that salivary DHEA can be used as a biomarker for MCI.

A Dimension Centric Proximate Attention Network and Swin Transformer for Age-Based Classification of Mild Cognitive Impairment From Brain MRI

A Dimension Centric Proximate Attention Network and Swin Transformer for Age-Based Classification of Mild Cognitive Impairment From Brain MRI

S-02-3: A REVIEW AND NEW INSIGHTS FROM THE SPRINT MIND TRIAL DATA

Background: Proven treatments for reducing the risk of mild cognitive impairment (MCI) and dementia have been lacking. The impact of intensive treatment of hypertension on the incidence of Mild Cognitive Impairment (MCI) and dementia was tested in the Systolic Blood Pressure Intervention Trial (SPRINT-MIND) by prospectively assessing the effect of intensive blood pressure control to a target systolic blood pressure of &lt;120 mmHg versus a standard target (&lt;140 mmHg). This presentation reviews the SPRINT results demonstrating a reduction in risk of developing dementia and MCI and presents additional data on the reliability of the MCI and dementia diagnosis. We will also provide preliminary evidence for differential cognitive benefit from specific antihypertensive medicines and evidence for lack of benefit after onset of cognitive impairment Results: At one year, mean systolic blood pressure was 121.4 mmHg in the intensive-treatment group and 136.2 mmHg in the standard-treatment group. Treatment was stopped on 8/20/2015 due to CVD benefit after a median follow up of 3.26 years, but cognitive assessment continued. Participant mean age was 67.9 years (35.6% women) and 8,626 (92.1%) completed at least one follow-up cognitive assessment. There was a significantly lower rate of adjudicated incident MCI (HR 0.81, CI 0.67–0.97) and a non-significant reduction in probable dementia (HR 0.83, CI 0.69–1.04). The combined outcome of MCI plus probable all cause dementia was significantly lower (HR 0.85, CI 0.74–0.97) in the intensive versus standard treatment group. Most cases occurred in persons over age 70. At 2 years, MCI classification was 10X more likely to transition to dementia than normal cognition and 30% of classified as MCI reverted to normal, consistent with other large epidemiologic studies of MCI trajectory Conclusions: Among ambulatory adults at increased risk for CVD but without diabetes, treating to a SBP target &lt; 120 mmHg compared to a target of &lt; 140 mmHg reduces the risk of incident MCI and combined MCI/probable dementia. Reduction of dementia risk by cardiovascular interventions is feasible in the elderly population.

Comparing Multi-Dimensional fNIRS Features Using Bayesian Optimization-Based Neural Networks for Mild Cognitive Impairment (MCI) Detection.

The diagnosis of mild cognitive impairment (MCI), a prodromal stage of Alzheimer's disease (AD), is essential for initiating timely treatment to delay the onset of AD. Previous studies have shown the potential of functional near-infrared spectroscopy (fNIRS) for diagnosing MCI. However, preprocessing fNIRS measurements requires extensive experience to identify poor-quality segments. Moreover, few studies have explored how proper multi-dimensional fNIRS features influence the classification results of the disease. Thus, this study outlined a streamlined fNIRS preprocessing method to process fNIRS measurements and compared multi-dimensional fNIRS features with neural networks in order to explore how temporal and spatial factors affect the classification of MCI and cognitive normality. More specifically, this study proposed using Bayesian optimization-based auto hyperparameter tuning neural networks to evaluate 1D channel-wise, 2D spatial, and 3D spatiotemporal features of fNIRS measurements for detecting MCI patients. The highest test accuracies of 70.83%, 76.92%, and 80.77% were achieved for 1D, 2D, and 3D features, respectively. Through extensive comparisons, the 3D time-point oxyhemoglobin feature was proven to be a more promising fNIRS feature for detecting MCI by using an fNIRS dataset of 127 participants. Furthermore, this study presented a potential approach for fNIRS data processing, and the designed models required no manual hyperparameter tuning, which promoted the general utilization of fNIRS modality with neural network-based classification to detect MCI.

Prescreening MCI and Dementia Using Shank-Mounted IMU During TUG Task

Detection of mild cognitive impairment (MCI) and dementia (DEM) is an important topic because, unless it is treated early, MCI can progress to DEM, which is an untreatable disease. This article proposes a timed-up-and-go (TUG) task features analysis and classification of MCI and DEM using inertial measurement units (IMUs) in wearable devices. Our goal is to create a generalized model that can be used for preclinical screening. As a result, rather than classifying only one subtype of DEM, such as Alzheimer’s disease (AD) or Parkinson’s disease (PD), we classify all subtypes as DEM. We also utilize feature selection methods on features from TUG tasks to optimize the MCI and DEM classification performance. From the results, our generalized model can outperform other works in normal control (NC)-MCI&DEM classification with an accuracy of 86.94% and sensitivity of 97.40%. For NC-DEM classification, the performance of our generalized model is slightly lower than that of specific-subtype models (e.g., NC versus AD). However, our generalized model can outperform the specific-subtype models when using a diverse variety of subtypes. It is a reasonable tradeoff, and it can be a good first step toward a future where the patient can preclinically self-screening the cognitive impairments using wearable devices in free-living environments. This could allow patients to notice the cognitive impairment early on and seek a comprehensive diagnosis from a doctor.

Classification of mild cognitive impairment based on handwriting dynamics and qEEG

Subtle changes in fine motor control and quantitative electroencephalography (qEEG) in patients with mild cognitive impairment (MCI) are important in screening for early dementia in primary care populations. In this study, an automated, non-invasive and rapid detection protocol for mild cognitive impairment based on handwriting kinetics and quantitative EEG analysis was proposed, and a classification model based on a dual fusion of feature and decision layers was designed for clinical decision-marking. Seventy-nine volunteers (39 healthy elderly controls and 40 patients with mild cognitive impairment) were recruited for this study, and the handwritten data and the EEG signals were performed using a tablet and MUSE under four designed handwriting tasks. Sixty-eight features were extracted from the EEG and handwriting parameters of each test. Features selected from both models were fused using a late feature fusion strategy with a weighted voting strategy for decision making, and classification accuracy was compared using three different classifiers under handwritten features, EEG features and fused features respectively. The results show that the dual fusion model can further improve the classification accuracy, with the highest classification accuracy for the combined features and the best classification result of 96.3% using SVM with RBF kernel as the base classifier. In addition, this not only supports the greater significance of multimodal data for differentiating MCI, but also tests the feasibility of using the portable EEG headband as a measure of EEG in patients with cognitive impairment.

A pilot study to investigate postural sway and saccadic eye movements comprehensively for MCI classification

AbstractBackgroundWhile single assessment of postural sway or saccadic eye movements is potentially useful for dementia screening at clinical settings [1, 2], multimodal assessment of the two movements could improve the screening accuracy [3‐5]. We have developed a novel comprehensive assessment system of posture and saccades, with integrated additional cognitive tasks of visuospatial memory and spatial orientation. We hypothesised that the new system would improve the classification of mild cognitive impairment (MCI).Method23 older adults joined the experiment and were split into two group based on the score of Montreal Cognitive Assessment (MoCA) [6]: 20 healthy older adults (HA) (70.35±4.93 years, 11 men / 9 women) and 3 older adults with MCI (74.7±4.04 years, 1 man / 2 women). The assessment system consists of stabilometer (GP‐5000, ANIMA Corporation, Japan) and a head‐mounted display virtual reality (VR) technology (VIVE Pro Eye, HTC Corporation, Taiwan). We measured postural sway and pro‐ or anti‐saccadic eye movements simultaneously in each of three different VR environments: #1) no additional cognitive task, #2) with visuospatial memory task, and #3) with spatial orientation task. We compared the parameters of saccades and postural sway between HA and MCI groups.ResultHA group achieved the MoCA score of 27.2±1.64, while MCI group scored 20.3±2.08 (P=0.006). Our analysis did not find significant differences between the two groups in all parameters. However, we observed moderate effect on standard deviation of centre of pressure in medio‐lateral direction in two test conditions: 1) the condition with pro‐saccade and visuospatial memory tasks (P=0.14; effect size = 0.32) and 2) the condition with anti‐saccade and spatial orientation tasks (P=0.09; effect size = 0.36).ConclusionModerate effect was observed on postural sway behaviours in the two test conditions. Since these conditions theoretically activate wider areas of the brain, our comprehensive assessment approach could be useful for dementia screening. Future research requires more sample size of MCI population for further analysis.

MCI performance classification improves with a brief vocabulary test

AbstractBackgroundScores on cognitive tests in the bottom 7% of normative distributions are consistent with the possible diagnosis of mild cognitive impairment (MCI). The identification of patients with MCI is improved by correcting for the influence of demographic factors such as Age, Education, and Gender (AEG), on performance. Here, we evaluated whether estimates of premorbid verbal IQ derived from a brief vocabulary test would further improve classification accuracy.MethodWe obtained vocabulary scores from 441 healthy adults (mean age = 65.1 ±14.4) using the 4‐min vocabulary subtest of the California Cognitive Assessment Battery (CCAB). The vocabulary subtest included 24 multiple choice items that adapted in difficulty based on the examinee responses using a 2:1 staircase with adjustable step sizes (Figure 1). Tests were telemedically administered in participants’ homes by an experienced proctor who monitored performance via a web‐based interface.ResultUnlike cognitive measures of fluid intelligence, vocabulary scores improved significantly with Age (r = 0.25, p &lt; 0.001, Figure 2). Scores were also higher for participants with more education and female gender. Vocabulary z‐scores were therefore calculated after correcting for the influence of Age, Education, and Gender. Vocabulary z‐scores correlated significantly with total recall scores on the Bay Area Verbal Learning Test (BAVLT, n = 398 participants, r = 0.35, p &lt; 0.001) and significantly improved model fit when added to AEG regressors (z = 2.1, p&lt; 0.02 one tailed)L the AEG model accounted for 25.6% of BAVLT score variance, whereas the AEG+vocabulary (AEG+V) model accounted for 34.7% of variance. AEG and AEG+V models classified different participants in the MCI performance range: 44% of participants in the lowest 7% of scores in the AEG+V model fell within the normal range in the AEG model, while 32% of participants classified as MCI in the AEG model fell within the normal range on the AEG+V model (Figure 3).ConclusionThe current results suggest that a brief vocabulary test improves MCI classification accuracy among older participants.

Multi-label classification of Alzheimer's disease stages from resting-state fMRI-based correlation connectivity data and deep learning

Alzheimer's disease is a neurodegenerative condition that gradually impairs cognitive abilities. Recently, various neuroimaging modalities and machine learning methods have surfaced to diagnose Alzheimer's disease. Resting-state fMRI is a neuroimaging modality that has been widely utilized to study brain activity related to neurodegenerative diseases. In literature, the previous studies are limited to the binary classification of Alzheimer's disease and Mild Cognitive Impairment. The application of computer-aided diagnosis for the numerous advancing phases of Alzheimer's disease, on the other hand, remains understudied. This research analyzes and presents methods for multi-label classification of six Alzheimer's stages using rs-fMRI and deep learning. The proposed model solves the multi-class classification problem by extracting the brain's functional connectivity networks from rs-fMRI data and employing two deep learning approaches, Stacked Sparse Autoencoder and Brain Connectivity Graph Convolutional Network. The suggested models' results were assessed using the k-fold cross-validation approach, and an average accuracy of 77.13% and 84.03% was reached for multi-label classification using Stacked Sparse Autoencoders and Brain Connectivity Based Convolutional Network, respectively. An analysis of brain regions was also performed by using the network's learned weights, leading to the conclusion that the precentral gyrus, frontal gyrus, lingual gyrus, and supplementary motor area are the significant brain regions of interest.

On Disharmony in Batch Normalization and Dropout Methods for Early Categorization of Alzheimer’s Disease

Alzheimer’s disease (AD) is a global health issue that predominantly affects older people. It affects one’s daily activities by modifying neural networks in the brain. AD is categorized by the death of neurons, the creation of amyloid plaques, and the development of neurofibrillary tangles. In clinical settings, an early diagnosis of AD is critical to limit the problems associated with it and can be accomplished using neuroimaging modalities, such as magnetic resonance imaging (MRI) and positron emission tomography (PET). Deep learning (DL) techniques are widely used in computer vision and related disciplines for various tasks such as classification, segmentation, detection, etc. CNN is a sort of DL architecture, which is normally useful to categorize and extract data in the spatial and frequency domains for image-based applications. Batch normalization and dropout are commonly deployed elements of modern CNN architectures. Due to the internal covariance shift between batch normalization and dropout, the models perform sub-optimally under diverse scenarios. This study looks at the influence of disharmony between batch normalization and dropout techniques on the early diagnosis of AD. We looked at three different scenarios: (1) no dropout but batch normalization, (2) a single dropout layer in the network right before the softmax layer, and (3) a convolutional layer between a dropout layer and a batch normalization layer. We investigated three binaries: mild cognitive impairment (MCI) vs. normal control (NC), AD vs. NC, AD vs. MCI, one multiclass AD vs. NC vs. MCI classification problem using PET modality, as well as one binary AD vs. NC classification problem using MRI modality. In comparison to using a large value of dropout, our findings suggest that using little or none at all leads to better-performing designs.

Multimodal magnetic resonance imaging for Alzheimer's disease diagnosis using hybrid features extraction and ensemble support vector machines

AbstractMagnetic resonance imaging (MRI) is increasingly used in the diagnosis of Alzheimer's disease (AD) in order to identify abnormalities in the brain. Indeed, cortical atrophy, a powerful biomarker for AD, can be detected using structural MRI (sMRI), but it cannot detect impairment in the integrity of the white matter (WM) preceding cortical atrophy. The early detection of these changes is made possible by the novel MRI modality known as diffusion tensor imaging (DTI). In this study, we integrate DTI and sMRI as complementary imaging modalities for the early detection of AD in order to create an effective computer‐assisted diagnosis tool. The fused Bag‐of‐Features (BoF) with Speeded‐Up Robust Features (SURF) and modified AlexNet convolutional neural network (CNN) are utilized to extract local and deep features. This is applied to DTI scalar metrics (fractional anisotropy and diffusivity metric) and segmented gray matter images from T1‐weighted MRI images. Then, the classification of local unimodal and deep multimodal features is first performed using support vector machine (SVM) classifiers. Then, the majority voting technique is adopted to predict the final decision from the ensemble SVMs. The study is directed toward the classification of AD versus mild cognitive impairment (MCI) versus cognitively normal (CN) subjects. Our proposed method achieved an accuracy of 98.42% and demonstrated the robustness of multimodality imaging fusion.

Machine Learning Workflow to Explain Black-Box Models for Early Alzheimer’s Disease Classification Evaluated for Multiple Datasets

Hard-to-interpret black-box Machine Learning (ML) was often used for early Alzheimer’s Disease (AD) detection. To interpret eXtreme Gradient Boosting (XGBoost), Random Forest (RF), and Support Vector Machine (SVM) black-box models, a workflow based on Shapley values was developed. All models were trained on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset and evaluated for an independent ADNI test set, as well as the external Australian Imaging and Lifestyle flagship study of Ageing (AIBL), and Open Access Series of Imaging Studies (OASIS) datasets. Shapley values were compared to intuitively interpretable Decision Trees (DTs), and Logistic Regression (LR), as well as natural and permutation feature importances. To avoid the reduction of the explanation validity caused by correlated features, forward selection and aspect consolidation were implemented. Some black-box models outperformed DTs and LR. The forward-selected features correspond to brain areas previously associated with AD. Shapley values identified biologically plausible associations with moderate-to-strong correlations with feature importances. The most important RF features to predict AD conversion were the volume of the amygdalae and a cognitive test score. Good cognitive test performances and large brain volumes decreased the AD risk. The models trained using cognitive test scores significantly outperformed brain volumetric models (p<0.05). Cognitive Normal (CN) vs. AD models were successfully transferred to external datasets. In comparison to previous work, improved performances for ADNI and AIBL were achieved for CN vs. Mild Cognitive Impairment (MCI) classification using brain volumes. The Shapley values and the feature importances showed moderate-to-strong correlations.

A transfer learning approach based on gradient boosting machine for diagnosis of Alzheimer's disease.

Early detection of Alzheimer’s disease (AD) during the Mild Cognitive Impairment (MCI) stage could enable effective intervention to slow down disease progression. Computer-aided diagnosis of AD relies on a sufficient amount of biomarker data. When this requirement is not fulfilled, transfer learning can be used to transfer knowledge from a source domain with more amount of labeled data than available in the desired target domain. In this study, an instance-based transfer learning framework is presented based on the gradient boosting machine (GBM). In GBM, a sequence of base learners is built, and each learner focuses on the errors (residuals) of the previous learner. In our transfer learning version of GBM (TrGB), a weighting mechanism based on the residuals of the base learners is defined for the source instances. Consequently, instances with different distribution than the target data will have a lower impact on the target learner. The proposed weighting scheme aims to transfer as much information as possible from the source domain while avoiding negative transfer. The target data in this study was obtained from the Mount Sinai dataset which is collected and processed in a collaborative 5-year project at the Mount Sinai Medical Center. The Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset was used as the source domain. The experimental results showed that the proposed TrGB algorithm could improve the classification accuracy by 1.5 and 4.5% for CN vs. MCI and multiclass classification, respectively, as compared to the conventional methods. Also, using the TrGB model and transferred knowledge from the CN vs. AD classification of the source domain, the average score of early MCI vs. late MCI classification improved by 5%.

УМЕРЕННЫЕ КОГНИТИВНЫЕ НАРУШЕНИЯ В ПРАКТИКЕ ВРАЧА-НЕВРОЛОГА

Cognitive impairment and dementia are an relevant problem of modern neurology and psychiatry, which is explained by their wide prevalence, as well as the predicted increase in the number of patients in the future. However, dementia in most cases does not occur acutely, its development is preceded by a long period when cognitive impairments do not disrupt the patient’s everyday and professional life yet. Such cognitive impairments are called “pre-dementia” and are divided into subjective, subtle, and mild. With subjective cognitive impairment, patients present complaints; however, neuropsychological testing does not reveal decreased cognitive functions. Subtle cognitive impairment is accompanied by a decrease in cognitive functions when using highly sensitive scales. This article provides an overview of current data on the definition, classification, diagnosis, and treatment of mild cognitive impairment (MCI) from the point of view of the evidence-based medicine for timely diagnostics of the state and its effective correction. In patients with MCI, in addition to complaints of cognitive deficit, it is detected during screening neuropsychological testing; but unlike dementia, it does not impair the patient’s functionality. MCI is a leading risk factor for future dementia. However, according to research, cognitive deficits can not only progress, but also stabilize and even regress. In this regard, it is important to identify patients with MCI on time, establish nosological affiliation for correcting risk factors and prescribing treatment. The most common causes of MCI can be neurodegenerative disorders (primarily Alzheimer’s disease) and cerebrovascular diseases. The authors present the diagnostic value of popular scales such as the Mini-Mental State Examination, the Montreal Cognitive Assessment Scale and the 3-CT test in the diagnosis of MCI. The possibilities of using biomarkers, such as the determination of beta-amyloid and tau-protein in the cerebrospinal fluid, and the detection of signs of neuronal damage during neuroimaging of the brain, are discussed. It is stated that the most proven methods of influencing cognitive deficits in MCI are non-drug measures.