A semi-supervised model is proposed for extracting clinical terms of Traditional Chinese Medicine using feature words. The extraction model is based on BiLSTM-CRF and combined with semi-supervised learning and feature word set, which reduces the cost of manual annotation and leverage extraction results. Experiment results show that the proposed model improves the extraction of five types of TCM clinical terms, including traditional Chinese medicine, symptoms, patterns, diseases and formulas. The best F1-value of the experiment reaches 78.70% on the test dataset. This method can reduce the cost of manual labeling and improve the result in the NER research of TCM clinical terms.

Curcumin, a compound derived from turmeric, is traditionally utilized in East Asian medicine for treating various health conditions, including epilepsy. Despite its involvement in numerous cellular signaling pathways, the specific mechanisms and targets of curcumin in epilepsy treatment have remained unclear. Our study focused on identifying the primary targets and functional pathways of curcumin in the brains of epileptic mice. Using drug affinity responsive target stabilization (DARTS) and affinity chromatography, we identified key targets in the mouse brain, revealing 232 and 70 potential curcumin targets, respectively. Bioinformatics analysis revealed a strong association of these proteins with focal adhesions and cytoskeletal components. Further experiments using DARTS, along with immunofluorescence staining and cell migration assays, confirmed curcumin's ability to regulate the dynamics of focal adhesions and influence cell migration. This study not only advances our understanding of curcumin's role in epilepsy treatment but also serves as a model for identifying therapeutic targets in neurological disorders.

OBJECTIVE: To evaluate the influence of cliriical pathways in the hospitals using the Traditional Chinese Medicine in treatment of stroke in terms of postoperative complications, length of stay (LOS), costs incurred during hospitalization, compared with standard medical care. METHODS: Medline, Embase, China National Knowledge Infrastructure (CNKI) platforms, Wan fang databases and the Cochrane Central Register of Controlled Trials were searched. The search was performed up to August 2014. Each study was assessed independently by two reviewers. The assessment of methodological quality of the included studies was based on the Methodological index for non-randomized studies standard. Meta-analyses were performed using RevMan software, version 5.0. RESULTS: Six studies met the study inclusion criteria and were included in the Meta-analysis for a total sample of 710 patients. The aggregate overall results showed that shorter length of stay in the clinical pathway group was observed during hospital stay was associated with the use of the clinical pathways. No significant differences were found in other effects. CONCLUSION: Regardless the possible limitations, our findings show that clinical pathways can significantly reduce LOS. Although there is no clear evidence that clinical pathways can reduce hospital costs, but the cost of hospitalization path group for each included study were lower than the control group. (C) 2017 JTCM. All rights reserved.