BiMGCL: rumor detection via bi-directional multi-level graph contrastive learning.

The rapid development of large language models has significantly reduced the cost of producing rumors, which brings a tremendous challenge to the authenticity of content on social media. Therefore, it has become crucially important to identify and detect rumors. Existing deep learning methods usually require a large amount of labeled data, which leads to poor robustness in dealing with different types of rumor events. In addition, they neglect to fully utilize the structural information of rumors, resulting in a need to improve their identification and detection performance. In this article, we propose a new rumor detection framework based on bi-directional multi-level graph contrastive learning, BiMGCL, which models each rumor propagation structure as bi-directional graphs and performs self-supervised contrastive learning based on node-level and graph-level instances. In particular, BiMGCL models the structure of each rumor event with fine-grained bidirectional graphs that effectively consider the bi-directional structural characteristics of rumor propagation and dispersion. Moreover, BiMGCL designs three types of interpretable bi-directional graph data augmentation strategies and adopts both node-level and graph-level contrastive learning to capture the propagation characteristics of rumor events. Experimental results on real datasets demonstrate that our proposed BiMGCL achieves superior detection performance compared against the state-of-the-art rumor detection methods.

[Effect of B Lymphocyte-Induced Mature Protein-1 Expression in Bone Marrow Mononuclear Cells on Prognosis of Patients with Multiple Myeloma].

OBJECTIVE: To study the effect of B lymphocyte-induced mature protein-1(Blimp1) expression in bone marrow mononuclear cells on the prognosis of patients with multiple myeloma. METHODS: Forty-eight patients with multiple myeloma from January 2014 to January 2015 were selected. The expression of Blimp1 in the bone marrow of all the patients was measured. According to the median score of Blimp1 expression level, the patients was divided into low expression group (L group, 22 cases) and high expression group (H group, 26 cases). The related influencing factors of different Blimp1 expression levels, the clinical efficacy, immunophenotypic changes and progression-free survival(PFS) were compared between different Blimp1 expression groups. RESULTS: There were no significant differences in sex, age, type, stage and treatment stage between the 2 groups (P> 0.05). The total remission rate of the low expression group was significantly higher than that in the high expression group (P<0.05). However before treatment, there was no significant difference in the positive rate of CD19, CD38, CD56, CD138 and minimal lesion between the 2 groups (P> 0.05); after treatment the positive expression rates of CD38, CD56, CD138 and minimal lesion in the low expression group were significantly lower than those in the high expression group. While the positive expression rate of CD19 was significantly higher than that in high expression group (P<0.05). The PFS of 1, 2 and 3 years in the low expression group was significantly higher than that in the high expression group (P<0.05). CONCLUSION: The MM patients with the high in staging and the larger in diffeculty of treatment possess high Blimp1 expression, however, the therapeutic efficacy and prognosis of MM patients with low Blimp1 expression are significantly better than those of MM patients with high Blimp1 expression.

[Value of patient education in the treatment of allergic rhinitis].

OBJECTIVE: To evaluate the effect of patient education on patients with allergic rhinitis (AR). METHOD: From January 2009 to December 2013, 100 cases of allergic rhinitis were treated. The patients were randomly divided into experimental group or control group by Stochastic tables law,50 patients in control group accepted only drug treatment, 50 patients in experimental group accepted both drug treatment and patient education. The difference in compliance with treatment, treatment effect, incidence of adverse drug reactions and complications, average costs and times of treatment between two groups were evaluated by the rhinoconjunctivitis quality of life questionnaire (RQLQ) score. The independent sample t-test and χ2 test were used for statistical analysis. RESULT: The patients of experimental group showed more positive attitude to treatment compared to the patients of control group (P < 0.01). The average scores of each classification and overall symptoms after treatment in experimental group were lower than those in control group (P < 0.05). The incidence of adverse drug reactions (nose-bleed, dry nose,nasal mucosa ulcer)and complications in patients with AR (asthma, chronic cough, secretory otitis media) in experimental group was lower than that in control group, with statistically differences (P < 0.05). The average times of treatment and costs of diagnosis and treatment(calculation of budesonide nasal spray)in experimental group were significantly lower than those in control group (P < 0.01). The total score for RQLQ and the scores of seven dimensions in experimental group were lower than those in control group (P < 0.05). CONCLUSIONS: Patient education can help the patients with AR to cooperate actively with treatment, to reduce the incidence of adverse drug reactions and AR complications, and to save medical costs and improve the quality of life.