Search

The identification of railway safety risk is important in ensuring continuous and stable railway operations. Most works fail to consider the important relation between detected objects. In addition, poor domain semantics directly degrades the final performance due to difficulty in understanding railway text. To solve these challenging issues, we introduce the triple knowledge from knowledge graph to model the railway safety risk with the knowledge interconnection mode. Afterward, we recast the identification of railway safety risk as the relation extraction task, and propose a novel and effective Domain Semantics-Enhanced Relation Extraction (DSERE) model. Specifically, we design a domain semantics-enhanced transformer mechanism that automatically enhances the railway semantics from a dedicated railway lexicon. We further introduce piece-wise convolution neural networks to explore the fine-grained features contained in the structure of triple knowledge. With the domain semantics and fine-grained features, our model can fully understand the domain text and thus improve the performance of relation classification. Finally, the DSERE model is used to identify the railway safety risk of south zone of China Railway, and achieves 81.84% AUC and 76.00% F1 scores on the real-world dataset showing the superiority of our proposed model.

Chemotherapy followed by donor lymphocyte infusion (DLI) is a promising treatment for relapsed acute myeloid leukemia (AML) and myelodysplastic syndrome (MDS) after allogeneic hematopoietic stem cell transplantation (allo-HSCT). However, the best strategy for administering this therapy is still unclear. This study sought to explore the efficacy and safety of chidamide and CAG (cytarabine, aclarubicin and granulocyte colony-stimulating factor) (CCAG) regimen followed by DLI in relapsed AML/MDS after allo-HSCT. This was a single-arm, phase II trial in patients with relapsed AML/MDS after allo-HSCT. CCAG regimen followed by DLI was given according to the inclusion and exclusion criteria. Twenty adult patients were enrolled. The median follow-up time was 12 months. The complete remission (CR) rate was 45% and the partial remission (PR) rate was 5%. The 1-year overall survival (OS) was 56.7% (95% confidence interval (95% CI), 31.6-75.6%), and the median OS was 19 months. The one-year disease-free survival (DFS) was 83.3% (95% CI, 27.3-97.5%). Patients relapsing more than 6 months after HSCT and achieving CR/PR after CCAG plus DLI regimen attained significantly higher survival rates. The cumulative incidence of grade III-IV acute graft-versus-host disease (aGVHD) was 9.4%. There was no treatment-related mortality (TRM). These data suggest that CCAG plus DLI regimen is safe and induces durable remission and superior survival in patients with relapsed AML/MDS after allo-HSCT. Trial registration number: ChiCTR.org identifier: ChiCTR1800017740 and date of registration: August 12, 2018.