Search

IntroductionThyroid cancer is the most prevalent endocrine malignancy, with its global incidence increasing annually in recent years. Papillary carcinoma is the most common subtype, frequently accompanied by cervical lymph node metastasis early on. Central lymph node metastasis (CLNM) is particularly the common metastasis form in this subtype, and the presence of lymph node metastasis correlates strongly with tumor recurrence. However, effective preoperative assessment methods for CLNM in patients with papillary thyroid carcinoma (PTC) remain lacking.MethodsData from 400 patients diagnosed with PTC between January 1, 2018, and January 1, 2022, at the Shandong Provincial Hospital were retrospectively analyzed. This data included clinicopathological information of the patients, such as thyroid function, BRAF V600E mutation, whether complicated with Hashimoto’s thyroiditis, and the presence of capsular invasion. Univariate and multivariate logistic regression analyses were performed to assess the risk factors associated with cervical CLNM in patients with PTC. Subsequently, a clinical prediction model was constructed, and prognostic risk factors were identified based on univariate and multivariate Cox regression analyses.ResultsUnivariate and multivariate analyses identified that age >45 years (P=0.014), body mass index ≥25 (P=0.008), tumor size ≥1 cm (P=0.001), capsular invasion (P=0.001), and the presence of BRAF V600E mutation (P45 years, body mass index ≥25, tumor size ≥1 cm, BRAF V600E mutation, and capsular invasion are the related risk factors for CLNM in patients with PTC. For patients with clinically nodal-negative (cN0) papillary thyroid microcarcinoma, accurately identifying the BRAF V600E mutation is essential for guiding the central lymph node dissection approach and subsequent treatments.

In the Knowledge Grounded Dialogue (KGD) generation, the explicit modeling of instance-variety of knowledge specificity and its seamless fusion with the dialogue context remains challenging. This paper presents an innovative approach, the Knowledge Interpolated conditional Variational auto-encoder (KIV), to address these issues. In particular, KIV introduces a novel interpolation mechanism to fuse two latent variables: independently encoding dialogue context and grounded knowledge. This distinct fusion of context and knowledge in the semantic space enables the interpolated latent variable to guide the decoder toward generating more contextually rich and engaging responses. We further explore deterministic and probabilistic methodologies to ascertain the interpolation weight, capturing the level of knowledge specificity. Comprehensive empirical analysis conducted on the Wizard-of-Wikipedia and Holl-E datasets verifies that the responses generated by our model performs better than strong baselines, with notable performance improvements observed in both automatic metrics and manual evaluation.

Neural attention mechanism has achieved many successes in various tasks in natural language processing. However, existing neural attention models based on a densely connected network are loosely related to the attention mechanism found in psychology and neuroscience. Motivated by the finding in neuroscience that human possesses the template-searching attention mechanism, we propose to use convolution operation to simulate attentions and give a mathematical explanation of our neural attention model. We then introduce a new network architecture, which combines a recurrent neural network with our convolution-based attention model and further stacks an attention-based neural model to build a hierarchical sentiment classification model. The experimental results show that our proposed models can capture salient parts of the text to improve the performance of sentiment classification at both the sentence level and the document level.