Search

Background Bipolar disorder (BPD) is a common mood disorder that is often goes misdiagnosed or undiagnosed. Recently, machine learning techniques have been combined with neuroimaging methods to aid in the diagnosis of BPD. However, most studies have focused on the construction of classifiers based on single-modality MRI. Hence, in this study, we aimed to construct a support vector machine (SVM) model using a combination of structural and functional MRI, which could be used to accurately identify patients with BPD. Methods In total, 44 patients with BPD and 36 healthy controls were enrolled in the study. Clinical evaluation and MRI scans were performed for each subject. Next, image pre-processing, VBM and ReHo analyses were performed. The ReHo values of each subject in the clusters showing significant differences were extracted. Further, LASSO approach was recruited to screen features. Based on selected features, the SVM model was established, and discriminant analysis was performed. Results After using the two-sample t-test with multiple comparisons, a total of 8 clusters were extracted from the data (VBM = 6; ReHo = 2). Next, we used both VBM and ReHo data to construct the new SVM classifier, which could effectively identify patients with BPD at an accuracy of 87.5% (95%CI: 72.5–95.3%), sensitivity of 86.4% (95%CI: 64.0–96.4%), and specificity of 88.9% (95%CI: 63.9–98.0%) in the test data (p = 0.0022). Conclusions A combination of structural and functional MRI can be of added value in the construction of SVM classifiers to aid in the accurate identification of BPD in the clinic.

Background Atrial fibrillation (AF) is one of the most common arrhythmia, which brings huge burden to the individual and the society. However, the mechanism of AF is not clear. This paper aims at screening the key differentially expressed genes (DEGs) of atrial fibrillation and to construct enrichment analysis and protein-protein interaction (PPI) network analysis for these DEGs. Methods The datasets were collected from the Gene Expression Omnibus database to extract data of left atrial appendage (LAA) RNA of patients with or without AF in GSE79768, GSE31821, GSE115574, GSE14975 and GSE41177. Batch normalization, screening of the differential genes and gene ontology analysis were finished by R software. Reactome analysis was used for pathway analysis. STRING platform was utilized for PPI network analysis. At last, we performed reverse transcription-quantitative polymerase chain reaction (RT-qPCR) to validate the expression of key genes in 20 sinus rhythm (SR) LAA tissues and 20 AF LAA tissues. Results A total of 106 DEGs were screened in the merged dataset. Among these DEGs, 74 genes were up-regulated and 32 genes down-regulated. DEGs were mostly enriched in extracellular matrix organization, protein activation cascade and extracellular structure organization. In PPI network, we identified SPP1, COL5A1 and VCAN as key genes which were associated with extracellular matrix. RT-qPCR showed the same expression trend of the three key genes as in our bioinformatics analysis. The expression levels of SPP1, COL5A1 and VCAN were increased in AF tissues compared to SR tissues (P Conclusion According to the analyses which were conducted by bioinformatics tools, genes related to extracellular matrix were involved in pathology of AF and may become the possible targets for the diagnosis and treatment of AF.