No abstract

Respiratory sound classification refers to identifying adventitious sounds from given recordings automatically. Due to the difficulty of collection and the expensive manual annotation, there are only limited samples available, which impacts on learning better models. Meanwhile, a majority of these models do not explicitly encourage intra-class compactness and inter-class separability between the learned embeddings, leading to the difficulty of identifying several samples and a reduced generalization performance. To address the problems, we propose a contrastive embedding learning method, where the input is a contrastive tuple. And the composite input strategy provides more possible network inputs. By the comparison among the samples in the tuple, we can learn the slight differences among the similar samples, and the easilyconfused samples are more likely to be identified. In the embedding space, we explicitly promote the intra-class compactness and inter-class separability, thereby the generalization performance is improved. Our method is evaluated on ICBHI 2017, and the classification score is increased from 75.61% of a conventional cross-entropy network to 78.18%, outperforming the state-of-the-art methods.

This study investigates the protective effect of Erigeron breviscapus injection, a classic traditional Chinese medicine most typically used by Chinese minority to treat stroke, on cerebral ischemia–reperfusion injury and the related signaling pathways. Use network pharmacology methods to study the relationship between E. breviscapus (Vant.) Hand-Mazz. and ischemic stroke, predict the mechanism and active ingredients of E. breviscapus (Vant.) Hand-Mazz. in improving ischemic stroke disease. We study the protective effect of E. breviscapus injection on blood–brain barrier (BBB) injuries induced by cerebral ischemia in rats by regulating the ROS/RNS-MMPs-TJs signaling pathway. The rat model of focal cerebral ischemia–reperfusion injury has been prepared using the wire-suppository method. Firstly, the efficacy of E. breviscapus injection, Scutellarin and 3,5-dicaffeoylquinic acid in protecting BBB injury caused by cerebral ischemia has been evaluated. Secondly, the following two methods have been used to study the mechanism of E. breviscapus injection in regulating the ROS/RNS-MMPS-TJS signaling pathway: real-time PCR and western blot for the determination of iNOS, MMP-9, claudin-5, occludin, ZO-1 mRNA and protein expression in brain tissue. We find that PI3K-Akt signaling pathway predicted by network pharmaology affects the blood–brain barrier function, so we chose the blood–brain barrier-related MMP-9, claudin-5, iNOS, occludin and ZO-1 proteins are used for research. The results of our research show that 3 drugs can reduce the rate of cerebral infarction in rats, relieve the abnormal neuroethology of rats, reduce the degree of brain tissue lesion, increase the number of the Nissl corpuscle cells and repair the neuron ultrastructure in injured rats. At the same time, it can obviously reduce the ultrastructure damage of the BBB in rats. All three drugs significantly reduced the content of Evans blue in the ischemic brain tissue caused by cerebral ischemia in rats with BBB injury. In addition, E. breviscapus injection, Scutellarin and 3,5-dicaffeoylquinic acid can decrease the protein expression of iNOS and MMP-9 in rat ischemic brain tissue. In addition, 3,5-dicaffeoylquinic acid can increase the protein expression of claudin-5. We conclude that E. breviscapus injection, Scutellarin and 3,5-dicaffeoylquinic acid have obvious therapeutic effects on BBB and neuron injury induced by cerebral ischemia in rats. Our results from studying the mechanism of action show that E. breviscapus injection and Scutellarin inhibited the activation of MMP-9 by inhibiting the synthesis of iNOS, 3,5-dicaffeoylquinic acid inhibits the expression and activation of MMP-9 by inhibiting the activation of iNOS and reducing the generation of free radicals, thus reducing the degradation of important cytoskeleton connexin claudin-5 in the tight junction (TJ) structure by inhibiting the expression and activation of MMP-9. Finally BBB structure integrity was protected.

BackgroundSerum carcinoembryonic antigen (CEA) is an important biomarker for diagnosis, prognosis, recurrence, metastasis monitoring, and the evaluation of the effect of chemotherapy in colorectal cancer (CRC). However, few studies have focused on the role of early postoperative CEA in the prognosis of stage II CRC.MethodsPatients with stage II CRC diagnosed between January 2007 and December 2015 were included. Receiver operating characteristic (ROC) curves were used to obtain the cutoff value of early postoperative CEA, CEA ratio and CEA absolute value. The areas under curves (AUCs) were used to estimate the predictive abilities of the CEA and T stage. The stepwise regression method was used to screen the factors included in the Cox regression analysis. Before and after propensity score (PS) - adjusted Cox regression and sensitivity analysis were used to identify the relationship between early postoperative CEA and prognosis. Meta-analysis was performed to verify the results. Kaplan-Meier survival curves were used to estimate the effects of CEA on prognosis.ResultsWe included 1081 eligible patients. ROC curves suggested that the cutoff value of early postoperative CEA was 3.66 ng/ml (P <0.001) and the AUC showed early postoperative CEA was the most significant prognostic marker in stage II CRC (P = 0.0189). The Cox regression and sensitivity analysis before and after adjusting for PS both revealed elevated early postoperative CEA was the strongest independent prognostic factor of OS, DFS, and CSS (P < 0.001). Survival analysis revealed that patients with elevated early postoperative CEA had lower OS (53.62% VS 84.16%), DFS (50.03% VS 86.75%), and CSS (61.77% VS 90.30%) than patients with normal early postoperative CEA (P < 0.001). When the postoperative CEA was positive, the preoperative CEA level showed no significant effect on the patient’s prognosis (all P-values were > 0.05). Patients with a CEA ratio ≤0.55 or CEA absolute value ≤-0.98 had a worse prognosis (all P-values were < 0.001). Survival analysis suggested that adjuvant chemotherapy for stage II CRC patients with elevated early postoperative CEA may improve the CSS (P = 0.040).ConclusionsEarly postoperative CEA was a better biomarker for prognosis of stage II CRC patients than T stage and preoperative CEA, and has the potential to become a high-risk factor to guide the prognosis and treatment of stage II CRC patients.

With ecological problems and energy crises intensifying today, greening is essential to sustainable development. Compared with other types of buildings, hospital buildings account for a relatively larger proportion of building energy consumption. In order to realize the rapid cycle optimization of a green hospital project in the design stage and improve the green grade of the building, a pre-evaluation Building Information Model (BIM) of green hospital building performance was established in this study. Firstly, the literature review and expert consultation established the building performance pre-evaluation index system for green hospitals. Then, BIM technology is taken to extract data needed for building a performance pre-evaluation system, and the Cloud Model and the Matter–Element Extension Theory are used to build models. The final green grade calculation is realized in MATLAB. Finally, the Maluan Bay Hospital is taken as an example to test the applicability and effectiveness of the proposed model. The results show that the green hospital building performance pre-evaluation model has advantages of simulation, cyclic optimization and fuzzy quantification, which can effectively guide the design and construction of a green hospital.