Predicting the cognitive function status in end-stage renal disease patients at a functional subnetwork scale.

Brain functional networks derived from functional magnetic resonance imaging (fMRI) provide a promising approach to understanding cognitive processes and predicting cognitive abilities. The topological attribute parameters of global networks are taken as the features from the overall perspective. It is constrained to comprehend the subtleties and variances of brain functional networks, which fell short of thoroughly examining the complex relationships and information transfer mechanisms among various regions. To address this issue, we proposed a framework to predict the cognitive function status in the patients with end-stage renal disease (ESRD) at a functional subnetwork scale (CFSFSS). The nodes from different network indicators were combined to form the functional subnetworks. The area under the curve (AUC) of the topological attribute parameters of functional subnetworks were extracted as features, which were selected by the minimal Redundancy Maximum Relevance (mRMR). The parameter combination with improved fitness was searched by the enhanced whale optimization algorithm (E-WOA), so as to optimize the parameters of support vector regression (SVR) and solve the global optimization problem of the predictive model. Experimental results indicated that CFSFSS achieved superior predictive performance compared to other methods, by which the mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE) were up to 0.5951, 0.0281 and 0.9994, respectively. The functional subnetwork effectively identified the active brain regions associated with the cognitive function status, which offered more precise features. It not only helps to more accurately predict the cognitive function status, but also provides more references for clinical decision-making and intervention of cognitive impairment in ESRD patients.

Multi-modal feature selection with self-expression topological manifold for end-stage renal disease associated with mild cognitive impairment.

Effectively selecting discriminative brain regions in multi-modal neuroimages is one of the effective means to reveal the neuropathological mechanism of end-stage renal disease associated with mild cognitive impairment (ESRDaMCI). Existing multi-modal feature selection methods usually depend on the Euclidean distance to measure the similarity between data, which tends to ignore the implied data manifold. A self-expression topological manifold based multi-modal feature selection method (SETMFS) is proposed to address this issue employing self-expression topological manifold. First, a dynamic brain functional network is established using functional magnetic resonance imaging (fMRI), after which the betweenness centrality is extracted. The feature matrix of fMRI is constructed based on this centrality measure. Second, the feature matrix of arterial spin labeling (ASL) is constructed by extracting the cerebral blood flow (CBF). Then, the topological relationship matrices are constructed by calculating the topological relationship between each data point in the two feature matrices to measure the intrinsic similarity between the features, respectively. Subsequently, the graph regularization is utilized to embed the self-expression model into topological manifold learning to identify the linear self-expression of the features. Finally, the selected well-represented feature vectors are fed into a multicore support vector machine (MKSVM) for classification. The experimental results show that the classification performance of SETMFS is significantly superior to several state-of-the-art feature selection methods, especially its classification accuracy reaches 86.10%, which is at least 4.34% higher than other comparable methods. This method fully considers the topological correlation between the multi-modal features and provides a reference for ESRDaMCI auxiliary diagnosis.

Nondeformed Ultrasound Image Production Method for Ultrasound-Guided Radiotherapy.

Purpose: During ultrasound (US)-guided radiotherapy, the tissue is deformed by probe pressure, and the US image is limited by changes in tissue and organ position and geometry when the US image is aligned with computed tomography (CT) image, leading to poor alignment. Accordingly, a pixel displacement-based nondeformed US image production method is proposed. Methods: The correction of US image deformation is achieved by calculating the pixel displacement of an image. The positioning CT image (CTstd) is used as the gold standard. The deformed US image (USdef) is inputted into the Harris algorithm to extract corner points for selecting feature points, and the displacement of adjacent pixels of feature points in the US video stream is calculated using the Lucas-Kanade optical flow algorithm. The moving least squares algorithm is used to correct USdef globally and locally in accordance with image pixel displacement to generate a nondeformed US image (USrev). In addition, USdef and USrev were separately aligned with CTstd to evaluate the improvement of alignment accuracy through deformation correction. Results: In the phantom experiment, the overall and local average correction errors of the US image under the optimal probe pressure were 1.0944 and 0.7388 mm, respectively, and the registration accuracy of USdef and USrev with CTstd was 0.6764 and 0.9016, respectively. During the volunteer experiment, the correction error of all 12 patients' data ranged from -1.7525 to 1.5685 mm, with a mean absolute error of 0.8612 mm. The improvement range of US and CT registration accuracy, before and after image deformation correction in the 12 patients evaluated by a normalized correlation coefficient, was 0.1232 to 0.2476. Conclusion: The pixel displacement-based deformation correction method can solve the limitation imposed by image deformation on image alignment in US-guided radiotherapy. Compared with USdef, the alignment results of USrev with CT were better.

Application of Deep Learning in Cancer Prognosis Prediction Model.

As an important branch of artificial intelligence and machine learning, deep learning (DL) has been widely used in various aspects of cancer auxiliary diagnosis, among which cancer prognosis is the most important part. High-accuracy cancer prognosis is beneficial to the clinical management of patients with cancer. Compared with other methods, DL models can significantly improve the accuracy of prediction. Therefore, this article is a systematic review of the latest research on DL in cancer prognosis prediction. First, the data type, construction process, and performance evaluation index of the DL model are introduced in detail. Then, the current mainstream baseline DL cancer prognosis prediction models, namely, deep neural networks, convolutional neural networks, deep belief networks, deep residual networks, and vision transformers, including network architectures, the latest application in cancer prognosis, and their respective characteristics, are discussed. Next, some key factors that affect the predictive performance of the model and common performance enhancement techniques are listed. Finally, the limitations of the DL cancer prognosis prediction model in clinical practice are summarized, and the future research direction is prospected. This article could provide relevant researchers with a comprehensive understanding of DL cancer prognostic models and is expected to promote the research progress of cancer prognosis prediction.

Characterizing Topological Properties of Brain Functional Networks Using Multi-Threshold Derivative for End-Stage Renal Disease with Mild Cognitive Impairment.

Patients with end-stage renal disease (ESRD) experience changes in both the structure and function of their brain networks. In the past, cognitive impairment was often classified based on connectivity features, which only reflected the characteristics of the binary brain network or weighted brain network. It exhibited limited interpretability and stability. This study aims to quantitatively characterize the topological properties of brain functional networks (BFNs) using multi-threshold derivative (MTD), and to establish a new classification framework for end-stage renal disease with mild cognitive impairment (ESRDaMCI). The dynamic BFNs (DBFNs) were constructed and binarized with multiple thresholds, and then their topological properties were extracted from each binary brain network. These properties were then quantified by calculating their derivative curves and expressing them as multi-threshold derivative (MTD) features. The classification results of MTD features were compared with several commonly used DBFN features, and the effectiveness of MTD features in the classification of ESRDaMCI was evaluated based on the classification performance test. The results indicated that the linear fusion of MTD features improved classification performance and outperformed individual MTD features. Its accuracy, sensitivity, and specificity were 85.98 ± 2.92%, 86.10 ± 4.11%, and 81.54 ± 4.27%, respectively. Finally, the feature weights of MTD were analyzed, and MTD-cc had the highest weight percentage of 28.32% in the fused features. The MTD features effectively supplemented traditional feature quantification by addressing the issue of indistinct classification differentiation. It improved the quantification of topological properties and provided more detailed features for diagnosing cognitive disorders.

Multimodal Classification Framework Based on Hypergraph Latent Relation for End-Stage Renal Disease Associated with Mild Cognitive Impairment.

Combined arterial spin labeling (ASL) and functional magnetic resonance imaging (fMRI) can reveal more comprehensive properties of the spatiotemporal and quantitative properties of brain networks. Imaging markers of end-stage renal disease associated with mild cognitive impairment (ESRDaMCI) will be sought from these properties. The current multimodal classification methods often neglect to collect high-order relationships of brain regions and remove noise from the feature matrix. A multimodal classification framework is proposed to address this issue using hypergraph latent relation (HLR). A brain functional network with hypergraph structural information is constructed by fMRI data. The feature matrix is obtained through graph theory (GT). The cerebral blood flow (CBF) from ASL is selected as the second modal feature matrix. Then, the adaptive similarity matrix is constructed by learning the latent relation between feature matrices. Latent relation adaptive similarity learning (LRAS) is introduced to multi-task feature learning to construct a multimodal feature selection method based on latent relation (LRMFS). The experimental results show that the best classification accuracy (ACC) reaches 88.67%, at least 2.84% better than the state-of-the-art methods. The proposed framework preserves more valuable information between brain regions and reduces noise among feature matrixes. It provides an essential reference value for ESRDaMCI recognition.

Detecting slow eye movements using multi-scale one-dimensional convolutional neural network for driver sleepiness detection.

BACKGROUND: Slow eye movements (SEMs), which occurs during eye-closed periods with high time coverage rate during simulated driving process, indicate drivers' sleep onset. NEW METHOD: For the multi-scale characteristics of slow eye movement waveforms, we propose a multi-scale one-dimensional convolutional neural network (MS-1D-CNN) for classification. The MS-1D-CNN performs multiple down-sampling processing branches on the original signal and uses the local convolutional layer to extract the features for each branch. RESULTS: We evaluate the classification performance of this model on ten subjects' standard train-test datasets and continuous test datasets by means of subject-subject evaluation and leave-one-subject-out cross validation, respectively. For the standard train-test datasets, the overall average classification accuracies are about 99.1% and 98.6%, in subject-subject evaluation and leave-one-subject-out cross validation, respectively. For the continuous test datasets, the overall average values of accuracy, precision, recall and F1-score are 99.3%, 98.9%, 99.5% and 99.1% in subject-subject evaluation, are 99.2%, 98.8%, 99.3% and 99.0% in leave-one-subject-out cross validation. COMPARISON WITH EXISTING METHOD: Results of the standard train-test datasets show that the overall average classification accuracy of the MS-1D-CNN is quite higher than the baseline method based on hand-designed features by 3.5% and 3.5%, in subject-subject evaluation and leave-one-subject-out cross validation, respectively. CONCLUSIONS: These results suggest that multi-scale transformation in the MS-1D-CNN model can enhance the representation ability of features, thereby improving classification accuracy. Experimental results verify the good performance of the MS-1D-CNN model, even in leave-one-subject-out cross validation, thus promoting the application of SEMs detection technology for driver sleepiness detection.

Altered spontaneous brain activities in maintenance hemodialysis patients with cognitive impairment and the construction of cognitive function prediction models.

OBJECTIVE: The brain neuromechanism in maintenance hemodialysis patients (MHD) with cognitive impairment (CI) remains unclear. The study aimed to probe the relationship between spontaneous brain activity and CI by using resting-state functional magnetic resonance imaging (rs-fMRI) data. METHODS: Here, 55 MHD patients with CI and 28 healthy controls were recruited. For baseline data, qualitative data were compared between groups using the χ2 test; quantitative data were compared between groups using the independent samples t-test, ANOVA test, Mann-Whitney U-test, or Kruskal-Wallis test. Comparisons of ALFF/fALFF/ReHo values among the three groups were calculated by using the DPABI toolbox, and then analyzing the correlation with clinical variables. p < .05 was considered a statistically significant difference. Furthermore, back propagation neural network (BPNN) was utilized to predict cognitive function. RESULTS: Compared with the MHD-NCI group, the patients with MHD-CI had more severe anemia and higher urea nitrogen levels, lower mALFF values in the left postcentral gyrus, lower mfALFF values in the left inferior temporal gyrus, and greater mALFF values in the right caudate nucleus (p < .05). The above-altered indicators were correlated with MOCA scores. BPNN prediction models indicated that the diagnostic efficacy of the model which inputs were hemoglobin, urea nitrogen, and mALFF value in the left central posterior gyrus was optimal (R2 = 0.8054), validation cohort (R2 = 0.7328). CONCLUSION: The rs-fMRI can reveal the neurophysiological mechanism of cognitive impairment in MHD patients. In addition, it can serve as a neuroimaging marker for diagnosing and evaluating cognitive impairment in MHD patients.

Hypergraph representation of multimodal brain networks for patients with end-stage renal disease associated with mild cognitive impairment.

The structure and function of brain networks (BN) may be altered in patients with end-stage renal disease (ESRD). However, there are relatively few attentions on ESRD associated with mild cognitive impairment (ESRDaMCI). Most studies focus on the pairwise relationships between brain regions, without taking into account the complementary information of functional connectivity (FC) and structural connectivity (SC). To address the problem, a hypergraph representation method is proposed to construct a multimodal BN for ESRDaMCI. First, the activity of nodes is determined by connection features extracted from functional magnetic resonance imaging (fMRI) (i.e., FC), and the presence of edges is determined by physical connections of nerve fibers extracted from diffusion kurtosis imaging (DKI) (i.e., SC). Then, the connection features are generated through bilinear pooling and transformed into an optimization model. Next, a hypergraph is constructed according to the generated node representation and connection features, and the node degree and edge degree of the hypergraph are calculated to obtain the hypergraph manifold regularization (HMR) term. The HMR and L1 norm regularization terms are introduced into the optimization model to achieve the final hypergraph representation of multimodal BN (HRMBN). Experimental results show that the classification performance of HRMBN is significantly better than that of several state-of-the-art multimodal BN construction methods. Its best classification accuracy is 91.0891%, at least 4.3452% higher than that of other methods, verifying the effectiveness of our method. The HRMBN not only achieves better results in ESRDaMCI classification, but also identifies the discriminative brain regions of ESRDaMCI, which provides a reference for the auxiliary diagnosis of ESRD.

Brain Micro-Structural and Functional Alterations for Cognitive Function Prediction in the End-Stage Renal Disease Patients Undergoing Maintenance Hemodialysis.

RATIONALE AND OBJECTIVES: The goal of this study was to investigate the relationship between altered brain micro-structure and function, and cognitive function in patients with end-stage renal disease (ESRD) undergoing maintenance hemodialysis. Specially, diffusion kurtosis imaging (DKI), the resting-state functional connectivity (FC) algorithm, and the least squares support vector regression machine (LSSVRM) were utilized to conduct our study. MATERIALS AND METHODS: A total of 50 patients and 36 matched healthy controls were prospectively enrolled in our study. All subjects completed the Montreal cognitive assessment scale (MoCA) test. DKI and resting-state functional magnetic resonance imaging were measured. Relationship between DKI parameters, FC, and MoCA scores was evaluated. LSSVRM combined with the whale optimization algorithm (WOA) was used to predict cognitive function scores. RESULTS: In ESRD patients, altered DKI metrics were identified in 12 brain regions. Furthermore, we observed changes in FC values based on regions of interest (ROIs) in nine brain regions, involved in default mode network (DMN), frontoparietal network (FPN), and the limbic system. Significant correlations among DKI values, FC values, and MoCA scores were found. To some extent, altered FC showed significant correlations with changed DKI parameters. Furthermore, optimized prediction models were applied to more accurately predict the cognitive function associated with ESRD patients. CONCLUSION: Micro-structural and functional brain changes were found in ESRD patients, which may account for the onset of cognitive impairment in affected patients. These quantitative parameters combined with our optimized prediction model may be helpful to establish more reliable imaging markers to detect and monitor cognitive impairment associated with ESRD.

Abnormal cerebral micro-structures in end-stage renal disease patients related to mild cognitive impairment.

PURPOSE: To investigate the mediating effect of abnormal brain micro-structures on the relationship between clinical risk factors and mild cognitive impairment (MCI), and further predict individual cognitive function in end-stage renal disease (ESRD) patients undergoing maintenance hemodialysis. METHODS: In total, 40 ESRD patients and 30 healthy controls were prospectively enrolled in our study. All subjects completed diffusion kurtosis imaging (DKI) examinations and Montreal cognitive assessment (MoCA) test. Between-group differences in the DKI metrics were analyzed. In addition, the mediating effects of altered brain micro-structures on the association between clinical risk factors and MCI were determined by mediation analysis. Finally, cognitive function was predicted based on DKI metrics and clinical characteristics by applying the optimized least squares support vector regression machine. RESULTS: We observed disrupted brain micro-structures in ESRD patients with MCI, as indicated by significantly altered DKI parameters. Significant correlations were found between the DKI metrics, clinical characteristics, and MoCA scores. In ESRD patients, low hemoglobin level and high serum creatine level were clinical risk factors for MCI. A decreased axial kurtosis value in the left hippocampus may partially mediate the impact of serum creatine on MCI. Furthermore, the prediction model could predict cognitive scores associated with ESRD with relatively high accuracy. CONCLUSION: Aberrant micro-structures partially mediated the association between clinical risk factors and MCI, which is a novel insight into the progression of cognitive dysfunction in ESRD patients. Combined DKI metrics and clinical characteristics could be used as features to efficiently predict cognitive function associated with ESRD.

Aberrant brain gray matter and functional networks topology in end stage renal disease patients undergoing maintenance hemodialysis with cognitive impairment.

Purpose: To characterize the topological properties of gray matter (GM) and functional networks in end-stage renal disease (ESRD) patients undergoing maintenance hemodialysis to provide insights into the underlying mechanisms of cognitive impairment. Materials and methods: In total, 45 patients and 37 healthy controls were prospectively enrolled in this study. All subjects completed resting-state functional magnetic resonance imaging (rs-fMRI) and diffusion kurtosis imaging (DKI) examinations and a Montreal cognitive assessment scale (MoCA) test. Differences in the properties of GM and functional networks were analyzed, and the relationship between brain properties and MoCA scores was assessed. Cognitive function was predicted based on functional networks by applying the least squares support vector regression machine (LSSVRM) and the whale optimization algorithm (WOA). Results: We observed disrupted topological organizations of both functional and GM networks in ESRD patients, as indicated by significantly decreased global measures. Specifically, ESRD patients had impaired nodal efficiency and degree centrality, predominantly within the default mode network, limbic system, frontal lobe, temporal lobe, and occipital lobe. Interestingly, the involved regions were distributed laterally. Furthermore, the MoCA scores significantly correlated with decreased standardized clustering coefficient (γ), standardized characteristic path length (λ), and nodal efficiency of the right insula and the right superior temporal gyrus. Finally, optimized LSSVRM could predict the cognitive scores of ESRD patients with great accuracy. Conclusion: Disruption of brain networks may account for the progression of cognitive dysfunction in ESRD patients. Implementation of prediction models based on neuroimaging metrics may provide more objective information to promote early diagnosis and intervention.

Integrated Prediction Framework for Clinical Scores of Cognitive Functions in ESRD Patients.

The clinical scores are applied to determine the stage of cognitive function in patients with end-stage renal disease (ESRD). However, accurate clinical scores are hard to come by. This paper proposed an integrated prediction framework with GPLWLSV to predict clinical scores of cognitive functions in ESRD patients. GPLWLSV incorporated three parts, graph theoretic algorithm (GTA) and principal component analysis (PCA), whale optimization algorithm with Levy flight (LWOA), and least squares support vector regression machine (LSSVRM). GTA was adopted to extract features from the brain functional networks in ESRD patients, while PCA was used to select features. LSSVRM was built to explore the relationship between the selected features and the clinical scores of ESRD patients. Whale optimization algorithm (WOA) was introduced to select better parameters of the kernel function in LSSVRM; it aims to improve the exploration competence of LSSVRM. Levy flight was used to optimize the ability to jump out of local optima in WOA and improve the convergence of coefficient vectors in WOA, which lead to an increase in the generalization ability and convergence speed of WOA. The results validated that the prediction accuracy of GPLWLSV was higher than that of several comparable frameworks, such as GPSV, GPLSV, and GPWLSV. In particular, the average of root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) between the predicted scores and the actual scores of ESRD patients was 2.40, 2.06, and 9.83%, respectively. The proposed framework not only can predict the clinical scores more accurately but also can capture imaging markers associated with decline of cognitive function. It helps to understand the potential relationship between structural changes in the brain and cognitive function of ESRD patients.

Intravoxel incoherent motion to assess brain microstructure and perfusion in patients with end-stage renal disease.

BACKGROUND AND PURPOSE: This study aimed to investigate the clinical value of intravoxel incoherent motion (IVIM) diffusion-weighted imaging in evaluating the brain microstructure and perfusion changes in end-stage renal disease (ESRD) patients. METHODS: The routine head MRI sequences and IVIM were performed on 40 ESRD patients and 30 healthy subjects. The IVIM was executed with 10 b-values varying from 0 to 1000 seconds/mm2 . All subjects were evaluated on neuropsychological test. Laboratory tests were conducted for ESRD patients. RESULTS: Compared with the control group, increased slow apparent diffusion coefficient values (ADCslow ) were found in the left frontal lobe, hippocampus, bilateral temporal lobe, and the right occipital lobe (p < .05), and increased fast ADC values (ADCfast ) were found in all regions of interest (all p < .001) in ESRD patients. In ESRD patients, ADCfast in right frontal lobe (p = .041) and insular lobe (p = .045) was negatively correlated with the Montreal Cognitive Assessment score (MoCA), and ADCfast in the right parietal lobe (p = .009) and hippocampus (p = .041) had positive correlation with hemoglobin levels. Using receiver operating characteristics (ROC) analysis, ADCfast in the right frontal lobe, insular lobe, hippocampus, and parietal lobe separately showed fair to good efficacy in differentiating ESRD patients from healthy subjects, with the area under the ROC ranging from .853 to .903. CONCLUSIONS: The microstructure and perfusion of the brain were impaired in ESRD patients. ADCfast of the right frontal lobe, insular lobe, hippocampus, and parietal lobe could be effective biomarker for evaluating cognitive impairment in ESRD patients.

Multi-Modal Neuroimaging Neural Network-Based Feature Detection for Diagnosis of Alzheimer's Disease.

Alzheimer's disease (AD) is a neurodegenerative brain disease, and it is challenging to mine features that distinguish AD and healthy control (HC) from multiple datasets. Brain network modeling technology in AD using single-modal images often lacks supplementary information regarding multi-source resolution and has poor spatiotemporal sensitivity. In this study, we proposed a novel multi-modal LassoNet framework with a neural network for AD-related feature detection and classification. Specifically, data including two modalities of resting-state functional magnetic resonance imaging (rs-fMRI) and diffusion tensor imaging (DTI) were adopted for predicting pathological brain areas related to AD. The results of 10 repeated experiments and validation experiments in three groups prove that our proposed framework outperforms well in classification performance, generalization, and reproducibility. Also, we found discriminative brain regions, such as Hippocampus, Frontal_Inf_Orb_L, Parietal_Sup_L, Putamen_L, Fusiform_R, etc. These discoveries provide a novel method for AD research, and the experimental study demonstrates that the framework will further improve our understanding of the mechanisms underlying the development of AD.

Research on Voxel-Based Features Detection and Analysis of Alzheimer's Disease Using Random Survey Support Vector Machine.

Alzheimer's disease (AD) is a degenerative disease of the central nervous system characterized by memory and cognitive dysfunction, as well as abnormal changes in behavior and personality. The research focused on how machine learning classified AD became a recent hotspot. In this study, we proposed a novel voxel-based feature detection framework for AD. Specifically, using 649 voxel-based morphometry (VBM) methods obtained from MRI in Alzheimer's Disease Neuroimaging Initiative (ADNI), we proposed a feature detection method according to the Random Survey Support Vector Machines (RS-SVM) and combined the research process based on image-, gene-, and pathway-level analysis for AD prediction. Particularly, we constructed 136, 141, and 113 novel voxel-based features for EMCI (early mild cognitive impairment)-HC (healthy control), LMCI (late mild cognitive impairment)-HC, and AD-HC groups, respectively. We applied linear regression model, least absolute shrinkage and selection operator (Lasso), partial least squares (PLS), SVM, and RS-SVM five methods to test and compare the accuracy of these features in these three groups. The prediction accuracy of the AD-HC group using the RS-SVM method was higher than 90%. In addition, we performed functional analysis of the features to explain the biological significance. The experimental results using five machine learning indicate that the identified features are effective for AD and HC classification, the RS-SVM framework has the best classification accuracy, and our strategy can identify important brain regions for AD.

GWLS: A Novel Model for Predicting Cognitive Function Scores in Patients With End-Stage Renal Disease.

The scores of the cognitive function of patients with end-stage renal disease (ESRD) are highly subjective, which tend to affect the results of clinical diagnosis. To overcome this issue, we proposed a novel model to explore the relationship between functional magnetic resonance imaging (fMRI) data and clinical scores, thereby predicting cognitive function scores of patients with ESRD. The model incorporated three parts, namely, graph theoretic algorithm (GTA), whale optimization algorithm (WOA), and least squares support vector regression machine (LSSVRM). It was called GTA-WOA-LSSVRM or GWLS for short. GTA was adopted to calculate the area under the curve (AUC) of topological parameters, which were extracted as the features from the functional networks of the brain. Then, the statistical method and Pearson correlation analysis were used to select the features. Finally, the LSSVRM was built according to the selected features to predict the cognitive function scores of patients with ESRD. Besides, WOA was introduced to optimize the parameters in the LSSVRM kernel function to improve the prediction accuracy. The results validated that the prediction accuracy obtained by GTA-WOA-LSSVRM was higher than several comparable models, such as GTA-SVRM, GTA-LSSVRM, and GTA-WOA-SVRM. In particular, the root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) between the predicted scores and the actual scores of patients with ESRD were 0.92, 0.88, and 4.14%, respectively. The proposed method can more accurately predict the cognitive function scores of ESRD patients and thus helps to understand the pathophysiological mechanism of cognitive dysfunction associated with ESRD.

Multi-Modal Feature Selection with Feature Correlation and Feature Structure Fusion for MCI and AD Classification.

Feature selection for multiple types of data has been widely applied in mild cognitive impairment (MCI) and Alzheimer's disease (AD) classification research. Combining multi-modal data for classification can better realize the complementarity of valuable information. In order to improve the classification performance of feature selection on multi-modal data, we propose a multi-modal feature selection algorithm using feature correlation and feature structure fusion (FC2FS). First, we construct feature correlation regularization by fusing a similarity matrix between multi-modal feature nodes. Then, based on manifold learning, we employ feature matrix fusion to construct feature structure regularization, and learn the local geometric structure of the feature nodes. Finally, the two regularizations are embedded in a multi-task learning model that introduces low-rank constraint, the multi-modal features are selected, and the final features are linearly fused and input into a support vector machine (SVM) for classification. Different controlled experiments were set to verify the validity of the proposed method, which was applied to MCI and AD classification. The accuracy of normal controls versus Alzheimer's disease, normal controls versus late mild cognitive impairment, normal controls versus early mild cognitive impairment, and early mild cognitive impairment versus late mild cognitive impairment achieve 91.85 ± 1.42%, 85.33 ± 2.22%, 78.29 ± 2.20%, and 77.67 ± 1.65%, respectively. This method makes up for the shortcomings of the traditional multi-modal feature selection based on subjects and fully considers the relationship between feature nodes and the local geometric structure of feature space. Our study not only enhances the interpretation of feature selection but also improves the classification performance, which has certain reference values for the identification of MCI and AD.

Integration and Segregation of Dynamic Functional Connectivity States for Mild Cognitive Impairment Revealed by Graph Theory Indicators.

Mild cognitive impairment (MCI) is an intermediate stage between normal aging and dementia. Researchers tend to discuss its early state (early MCI, eMCI) due to its high conversion rate of dementia and poor treatment effect in the middle and late stages. Currently, the research on the disease evolution of the brain functional networks of patients with MCI has gradually become a research hotspot. In this study, we compare the differences in dynamic functional connectivity among eMCI, late MCI (lMCI), and normal control (NC) groups, and their graph theory indicators reveal the integration and segregation of functional connectivity states. Firstly, dynamic functional network windows were constructed based on the sliding time window method, and then these window samples were clustered by k-means to extract the functional connectivity states. The differences in the three groups were compared by analyzing the graph theory indicators, such as the participation coefficient, module degree distribution, clustering coefficient, global efficiency, and local efficiency, which distinguish the functional connectivity states. The results reveal that the NC group has the strongest integration and segregation, followed by the eMCI group, and the lMCI group has the weakest integration and segregation. We conclude that with the aggravation of MCI, the integration and segregation of dynamic functional connectivity states tend to decline. The results also reflect that the lMCI group has significantly more brain functional connections in some states, such as IPL.L-MTG.R and DCG.R-SMG.L, than the eMCI group, while the lMCI group has significantly less OLF.L-SPG.L than the NC group.

Constructing Dynamic Brain Functional Networks via Hyper-Graph Manifold Regularization for Mild Cognitive Impairment Classification.

Brain functional networks (BFNs) constructed via manifold regularization (MR) have emerged as a powerful tool in finding new biomarkers for brain disease diagnosis. However, they only describe the pair-wise relationship between two brain regions, and cannot describe the functional interaction between multiple brain regions, or the high-order relationship, well. To solve this issue, we propose a method to construct dynamic BFNs (DBFNs) via hyper-graph MR (HMR) and employ it to classify mild cognitive impairment (MCI) subjects. First, we construct DBFNs via Pearson's correlation (PC) method and remodel the PC method as an optimization model. Then, we use k-nearest neighbor (KNN) algorithm to construct the hyper-graph and obtain the hyper-graph manifold regularizer based on the hyper-graph. We introduce the hyper-graph manifold regularizer and the L1-norm regularizer into the PC-based optimization model to optimize DBFNs and obtain the final sparse DBFNs (SDBFNs). Finally, we conduct classification experiments to classify MCI subjects from normal subjects to verify the effectiveness of our method. Experimental results show that the proposed method achieves better classification performance compared with other state-of-the-art methods, and the classification accuracy (ACC), the sensitivity (SEN), the specificity (SPE), and the area under the curve (AUC) reach 82.4946 ± 0.2827%, 77.2473 ± 0.5747%, 87.7419 ± 0.2286%, and 0.9021 ± 0.0007, respectively. This method expands the MR method and DBFNs with more biological significance. It can effectively improve the classification performance of DBFNs for MCI, and has certain reference value for the research and auxiliary diagnosis of Alzheimer's disease (AD).