Distributed support vector machine in master-slave mode

A Machine-Learning Approach to Developing a Predictive Signature Based on Transcriptome Profiling of Ground-Glass Opacities for Accurate Classification and Exploring the Immune Microenvironment of Early-Stage LUAD

Screening for early-stage lung cancer with low-dose computed tomography is recommended for high-risk populations; consequently, the incidence of pure ground-glass opacity (pGGO) is increasing. Ground-glass opacity (GGO) is considered the appearance of early lung cancer, and there remains an unmet clinical need to understand the pathology of small GGO (<1 cm in diameter). The objective of this study was to use the transcriptome profiling of pGGO specimens <1 cm in diameter to construct a pGGO-related gene risk signature to predict the prognosis of early-stage lung adenocarcinoma (LUAD) and explore the immune microenvironment of GGO. pGGO-related differentially expressed genes (DEGs) were screened to identify prognostic marker genes with two machine learning algorithms. A 15-gene risk signature was constructed from the DEGs that were shared between the algorithms. Risk scores were calculated using the regression coefficients for the pGGO-related DEGs. Patients with Stage I/II LUAD or Stage IA LUAD and high-risk scores had a worse prognosis than patients with low-risk scores. The prognosis of high-risk patients with Stage IA LUAD was almost identical to that of patients with Stage II LUAD, suggesting that treatment strategies for patients with Stage II LUAD may be beneficial in high-risk patients with Stage IA LUAD. pGGO-related DEGs were mainly enriched in immune-related pathways. Patients with high-risk scores and high tumor mutation burden had a worse prognosis and may benefit from immunotherapy. A nomogram was constructed to facilitate the clinical application of the 15-gene risk signature. Receiver operating characteristic curves and decision curve analysis validated the predictive ability of the nomogram in patients with Stage I LUAD in the TCGA-LUAD cohort and GEO datasets.

Applications of Machine Learning in miRNA Discovery and Target Prediction

MicroRNA (miRNA) is a small non-coding molecule that is involved in gene regulation and RNA silencing by complementary on their targets. Experimental methods for target prediction can be time-consuming and expensive. Thus, the application of the computational approach is implicated to enlighten these complications with experimental studies. However, there is still a need for an optimized approach in miRNA biology. Therefore, machine learning (ML) would initiate a new era of research in miRNA biology towards potential diseases biomarker. In this article, we described the application of ML approaches in miRNA discovery and target prediction with functions and future prospective. The implementation of a new era of computational methodologies in this direction would initiate further advanced levels of discoveries in miRNA.

Metacognitive Training Modulates Default-Mode Network Homogeneity During 8-Week Olanzapine Treatment in Patients With Schizophrenia

BACKGROUND

Previous studies have revealed the efficacy of metacognitive training for schizophrenia. However, the underlying mechanisms of metacognitive training on brain function alterations, including the default-mode network (DMN), remain unknown. The present study explored treatment effects of metacognitive training on functional connectivity of the brain regions in the DMN.

METHODS

Forty-one patients with schizophrenia and 20 healthy controls were scanned using resting-state functional magnetic resonance imaging. Patients were randomly assigned to drug plus psychotherapy (DPP) and drug therapy (DT) groups. The DPP group received olanzapine and metacognitive training, and the DT group received only olanzapine for 8 weeks. Network homogeneity (NH) was applied to analyze the imaging data, and pattern classification techniques were applied to test whether abnormal NH deficits at baseline might be used to discriminate patients from healthy controls. Abnormal NH in predicting treatment response was also examined in each patient group.

RESULTS

Compared with healthy controls, patients at baseline showed decreased NH in the bilateral ventral medial prefrontal cortex (MPFC), right posterior cingulate cortex (PCC)/precuneus, and bilateral precuneus and increased NH in the right cerebellum Crus II and bilateral superior MPFC. NH values in the right PCC/precuneus increased in the DPP group after 8 weeks of treatment, whereas no substantial difference in NH value was observed in the DT group. Support vector machine analyses showed that the accuracy, sensitivity, and specificity for distinguishing patients from healthy controls were more than 0.7 in the NH values of the right PCC/precuneus, bilateral ventral MPFC, bilateral superior MPFC, and bilateral precuneus regions. Support vector regression analyses showed that high NH levels at baseline in the bilateral superior MPFC could predict symptomatic improvement of positive and negative syndrome scale (PANSS) after 8 weeks of DPP treatment. No correlations were found between alterations in the NH values and changes in the PANSS scores/cognition parameters in the patients.

CONCLUSION

This study provides evidence that metacognitive training is related to the modulation of DMN homogeneity in schizophrenia.