A heterogeneous graph convolutional attention network method for classification of autism spectrum disorder.

BACKGROUND: Autism spectrum disorder (ASD) is a serious developmental disorder of the brain. Recently, various deep learning methods based on functional magnetic resonance imaging (fMRI) data have been developed for the classification of ASD. Among them, graph neural networks, which generalize deep neural network models to graph structured data, have shown great advantages. However, in graph neural methods, because the graphs constructed are homogeneous, the phenotype information of the subjects cannot be fully utilized. This affects the improvement of the classification performance. METHODS: To fully utilize the phenotype information, this paper proposes a heterogeneous graph convolutional attention network (HCAN) model to classify ASD. By combining an attention mechanism and a heterogeneous graph convolutional network, important aggregated features can be extracted in the HCAN. The model consists of a multilayer HCAN feature extractor and a multilayer perceptron (MLP) classifier. First, a heterogeneous population graph was constructed based on the fMRI and phenotypic data. Then, a multilayer HCAN is used to mine graph-based features from the heterogeneous graph. Finally, the extracted features are fed into an MLP for the final classification. RESULTS: The proposed method is assessed on the autism brain imaging data exchange (ABIDE) repository. In total, 871 subjects in the ABIDE I dataset are used for the classification task. The best classification accuracy of 82.9% is achieved. Compared to the other methods using exactly the same subjects in the literature, the proposed method achieves superior performance to the best reported result. CONCLUSIONS: The proposed method can effectively integrate heterogeneous graph convolutional networks with a semantic attention mechanism so that the phenotype features of the subjects can be fully utilized. Moreover, it shows great potential in the diagnosis of brain functional disorders with fMRI data.

Perspectives and experiences of Chinese nurses on quality improvement initiatives: A mixed-methods study.

AIM: To investigate Chinese nurses' views and experiences in relation to quality improvement implementation, as well as to determine the impact of contextual factors on nursing quality improvement initiatives. BACKGROUND: Nurses play a major role in carrying out quality improvement initiatives. Contextual factors influence the implementation and success of quality improvement initiatives. Studies that investigated the impact of contextual factors on Chinese nurses' practice in quality improvement remain limited. METHODS: A sequential explanatory mixed-methods design was used for this study. A quantitative cross-sectional survey was used to assess the context of quality improvement initiatives. Simple random sampling was used to recruit quality improvement teams. The sample included 356 nurses from tertiary teaching hospitals; 291 (81.7%) of them completed questionnaires. Nursing managers and nurses (n = 18) were purposively selected to participate in semi-structured interviews; their experiences and perceptions regarding the contextual factors of quality improvement initiatives were obtained. RESULTS: In the quantitative phase, the "microsystem" (mean=5.24) and "QI team" (mean = 4.97) contexts were reported as supportive contexts. The organizational context was weak, with a mean score of 3.92. In the qualitative phase, three themes related to the contextual challenges emerged: (1) nurses' attitudes and satisfaction, (2) team efficacy, and (3) organizational infrastructure and culture. CONCLUSIONS: Efforts to elevate organizational culture and reward systems are needed in Chinese hospitals. Further education aimed at increasing skills and knowledge should be provided, to ensure effective quality improvement implementation. IMPLICATIONS FOR NURSING MANAGEMENT: During quality improvement initiatives, management tasks should focus on increasing nurses' satisfaction, solving skill and knowledge deficits, and clarifying nurses' roles in relation to quality improvement.

Classification of ADHD with bi-objective optimization.

Attention Deficit Hyperactive Disorder (ADHD) is one of the most common diseases in school aged children. In this paper, we consider using fMRI data with classification techniques to aid the diagnosis of ADHD and propose a bi-objective ADHD classification scheme based on L1-norm support vector machine (SVM). In our classification model, two objectives, namely, the margin of separation and the empirical error are considered at the same time. Then the normal boundary intersection (NBI) method of Das and Dennis is used to solve the bi-objective optimization problem. A representative nondominated set which reflects the entire trade-off information between the two objectives is obtained. Each representative nondominated point in the set corresponds to an efficient classifier. Finally a decision maker can choose a final efficient classifier from the set according to the performance of each classifier. Our scheme avoids the trial and error process for regularization hyper-parameter selection. Experimental results show that our bi-objective optimization classification scheme for ADHD diagnosis performs considerably better than some traditional classification methods.

Integrative Multi-omics Analysis to Characterize Herpes Virus Infection Increases the Risk of Alzheimer's Disease.

Evidence suggests that herpes virus infection is associated with an increased risk of Alzheimer's disease (AD), and innate and adaptive immunity plays an important role in the association. Although there have been many studies, the mechanism of the association is still unclear. This study aims to reveal the underlying molecular and immune regulatory network through multi-omics data and provide support for the study of the mechanism of infection and AD in the future. Here, we found that the herpes virus infection significantly increased the risk of AD. Genes associated with the occurrence and development of AD and genetically regulated by herpes virus infection are mainly enrichment in immune-related pathways. The 22 key regulatory genes identified by machine learning are mainly immune genes. They are also significantly related to the infiltration changes of 3 immune cell in AD. Furthermore, many of these genes have previously been reported to be linked, or potentially linked, to the pathological mechanisms of both herpes virus infection and AD. In conclusion, this study contributes to the study of the mechanisms related to herpes virus infection and AD, and indicates that the regulation of innate and adaptive immunity may be an effective strategy for preventing and treating herpes virus infection and AD. Additionally, the identified key regulatory genes, whether previously studied or newly discovered, may serve as valuable targets for prevention and treatment strategies.

Joint-tissue integrative analysis identifies high-risk genes for Parkinson's disease.

The loss of dopaminergic neurons in the substantia nigra and the abnormal accumulation of synuclein proteins and neurotransmitters in Lewy bodies constitute the primary symptoms of Parkinson's disease (PD). Besides environmental factors, scholars are in the early stages of comprehending the genetic factors involved in the pathogenic mechanism of PD. Although genome-wide association studies (GWAS) have unveiled numerous genetic variants associated with PD, precisely pinpointing the causal variants remains challenging due to strong linkage disequilibrium (LD) among them. Addressing this issue, expression quantitative trait locus (eQTL) cohorts were employed in a transcriptome-wide association study (TWAS) to infer the genetic correlation between gene expression and a particular trait. Utilizing the TWAS theory alongside the enhanced Joint-Tissue Imputation (JTI) technique and Mendelian Randomization (MR) framework (MR-JTI), we identified a total of 159 PD-associated genes by amalgamating LD score, GTEx eQTL data, and GWAS summary statistic data from a substantial cohort. Subsequently, Fisher's exact test was conducted on these PD-associated genes using 5,152 differentially expressed genes sourced from 12 PD-related datasets. Ultimately, 29 highly credible PD-associated genes, including CTX1B, SCNA, and ARSA, were uncovered. Furthermore, GO and KEGG enrichment analyses indicated that these genes primarily function in tissue synthesis, regulation of neuron projection development, vesicle organization and transportation, and lysosomal impact. The potential PD-associated genes identified in this study not only offer fresh insights into the disease's pathophysiology but also suggest potential biomarkers for early disease detection.

Gestational diabetes mellitus aggravates adverse perinatal outcomes in women with intrahepatic cholestasis of pregnancy.

PURPOSE: To evaluate the effect of intrahepatic cholestasis of pregnancy (ICP) with gestational diabetes mellitus (GDM) on perinatal outcomes and establish a prediction model of adverse perinatal outcomes in women with ICP. METHODS: This multicenter retrospective cohort study included the clinical data of 2,178 pregnant women with ICP, including 1,788 women with ICP and 390 co-occurrence ICP and GDM. The data of all subjects were collected from hospital electronic medical records. Univariate and multivariate logistic regression analysis were used to compare the incidence of perinatal outcomes between ICP with GDM group and ICP alone group. RESULTS: Baseline characteristics of the population revealed that maternal age (p < 0.001), pregestational weight (p = 0.01), pre-pregnancy BMI (p < 0.001), gestational weight gain (p < 0.001), assisted reproductive technology (ART) (p < 0.001), and total bile acid concentration (p = 0.024) may be risk factors for ICP with GDM. Furthermore, ICP with GDM demonstrated a higher association with both polyhydramnios (OR 2.66) and preterm labor (OR 1.67) compared to ICP alone. Further subgroup analysis based on the severity of ICP showed that elevated total bile acid concentrations were closely associated with an increased risk of preterm labour, meconium-stained amniotic fluid, and low birth weight in both ICP alone and ICP with GDM groups. ICP with GDM further worsened these outcomes, especially in women with severe ICP. The nomogram prediction model effectively predicted the occurrence of preterm labour in the ICP population. CONCLUSIONS: ICP with GDM may result in more adverse pregnancy outcomes, which are associated with bile acid concentrations.

Classification of ASD based on fMRI data with deep learning.

Autism spectrum disorder (ASD) is a neuro-developmental disorder that affects the social abilities of patients. Studies have shown that a small number of abnormal functional connections (FCs) exist in the cerebral hemisphere of ASD patients. The identification of these abnormal FCs provides a biological ground for the diagnosis of ASD. In this paper, we propose a combined deep feature selection (DFS) and graph convolutional network method to classify ASD. Firstly, in the DFS process, a sparse one-to-one layer is added between the input and the first hidden layer of a multilayer perceptron, thus each functional connection (FC) feature can be weighted and a subset of FC features can be selected accordingly. Then based on the selected FCs and the phenotypic information of subjects, a graph convolutional network is constructed to classify ASD and typically developed controls. Finally, we test our proposed method on the ABIDE database and compare it with some other methods in the literature. Experimental results indicate that the DFS can effectively select critical FC features for classification according to the weights of input FC features. With DFS, the performance of GCN classifier can be improved dramatically. The proposed method achieves state-of-the-art performance with an accuracy of 79.5% and an area under the receiver operating characteristic curve (AUC) of 0.85 on the preprocessed ABIDE dataset; it is superior to the other methods. Further studies on the top-ranked thirty FCs obtained by DFS show that these FCs are widespread over the cerebral hemisphere, and the ASD group appears a significantly higher number of weak connections compared to the typically developed group.

Classification of ADHD with fMRI data and multi-objective optimization.

BACKGROUND AND OBJECTIVE: Dataset imbalance is an important problem in neuroimaging. Imbalanced datasets would cause the performance degradation of a classifier by utilizing imbalanced learning, which tends to overfocus on the majority class. In this paper, we consider an imbalanced neuroimaging classification problem, namely, classification of attention deficit hyperactivity disorder (ADHD) using resting-state functional magnetic resonance imaging. METHODS: We propose a multi-objective classification scheme based on support vector machine (SVM). Our scheme addresses the imbalanced dataset problem by using a three objective SVM model with the positive and negative empirical errors being handled explicitly and separately. Moreover, an interactive multi-objective method incorporating the decision maker's preference is adopted, thus a preferred subset of pareto optimal classifiers for decision making can be obtained. RESULTS: The proposed scheme is assessed on five datasets from the ADHD- 200 consortium. Numerical results show that the proposed multi-objective scheme considerably outperforms some traditional classification methods in the literature. CONCLUSION: The proposed multi-objective classification scheme avoids hyper-parameter selection, it effectively addresses dataset imbalanced problem from algorithm level. The scheme can not only be used in the diagnosis of ADHD but also in the diagnosis of other diseases, such as Alzheimer and Autism etc.