Background Within-day glycemic variability (GV), characterized by frequent and significant fluctuations in blood glucose levels, is a growing concern in hospitalized patients with type 2 diabetes mellitus (T2DM). It is associated with an increased risk of hypoglycemia and potentially higher long-term mortality rates. Robust clinical evidence is needed to determine whether traditional Chinese medicine (TCM) decoctions can be a beneficial addition to the management of within-day GV in this patient population. Methods This retrospective cohort study utilized data from adult inpatients diagnosed with T2DM admitted to the Traditional Chinese Medicine Hospital of Kaifeng. The primary outcome investigated was the association between the use of TCM decoctions and improved stability of within-day GV. Blood glucose variability was assessed using the standard deviation of blood glucose values (SDBG). For each patient, the total number of hospitalization days with SDBG below 2 mmol/L was calculated to represent within-day GV stability. Hospitalization duration served as the secondary outcome, compared between patients receiving TCM decoctions and those who did not. The primary analysis employed a multivariable logistic regression model, with propensity score matching to account for potential confounding variables. Results A total of 1,360 patients were included in the final analysis. The use of TCM decoctions was significantly associated with enhanced stability of within-day GV (OR = 1.77, 95% CI: 1.34-2.33, P < 0.01). This association was most prominent in patients with a diagnosis of deficiency syndrome (predominantly qi-yin deficiency, accounting for 74.8% of cases) and a disease duration of less than 5 years (OR = 2.28, 95% CI: 1.21-4.29, P = 0.03). However, TCM decoctions did not exert a statistically significant effect on hospitalization duration among patients with T2DM (OR = 0.96, 95% CI: 0.91-1.01, P = 0.22). Conclusion This study suggests that TCM decoctions may be effective in improving within-day GV stability in hospitalized patients with T2DM. This effect appears to be most pronounced in patients diagnosed with deficiency syndrome, particularly those with qi-yin deficiency and a shorter disease course. Further investigation is warranted to confirm these findings and elucidate the underlying mechanisms.

This paper addresses the mixture symptom mention problem which appears in the structuring of Traditional Chinese Medicine (TCM). We accomplished this by disassembling mixture symptom mentions with entity relation extraction. Over 2,200 clinical notes were annotated to construct the training set. Then, an end-to-end joint learning model was established to extract the entity relations. A joint model leveraging a multihead mechanism was proposed to deal with the problem of relation overlapping. A pretrained transformer encoder was adopted to capture context information. Compared with the entity extraction pipeline, the constructed joint learning model was superior in recall, precision, and F1 measures, at 0.822, 0.825, and 0.818, respectively, 14% higher than the baseline model. The joint learning model could automatically extract features without any extra natural language processing tools. This is efficient in the disassembling of mixture symptom mentions. Furthermore, this superior performance at identifying overlapping relations could benefit the reassembling of separated symptom entities downstream.

在某政府部门信息系统迁云过程中,论文总结出了2阶段15步迁云法,并从分层、纵深防御思想出发解决上云后的安全问题。然后介绍了迁云流程及取得的成效,分享了迁云的典型案例及迁云经验,为同行提供迁云参考经验。

本文研究利用XGBoost方法对潜在高血脂症进行预测,通过对体检数据进行训练,测试数据集的准确率、召回率以及F1值都较为理想。并通过对比XGBoost、随机森林以及逻辑回归三种方法的预测结果,结果表明XGBoost算法能够更准确的对潜在高血脂症进行预测,可以为潜在高血脂提供强有力的数据支撑。

In recent years, recommendation systems based on collaborative filtering (CF) have achieved a high performance. Most of the existing recommendation systems use similarity measures to determine the suitability of items for users based on latent factor models (LFM). However, these recommendation systems reduce the explainability of recommendations and hide the reasons for recommending specific items. As a result, users tend to distrust the recommendation results. To address this problem, we propose the neural explicit factor model (NEFM). Based on the user-item rating matrix, we propose adding both user-feature attention matrix and an item-feature quality matrix to improve the explainability of user and item vectors. In addition, a feedforward neural network and a one-dimensional convolutional neural network extract features from user, item and the item-feature vector. Finally, a prediction layer performs the inner product of user data, item data, and item features. Experiments on the MovieLens and Yahoo Movies datasets validate the proposed model, and comparisons with similar recommendation models show the higher accuracy and explainability of our proposal.

目的探索一种具有较好扩展性且可检验数据准确性的中医皮肤病"病-证-治"本体的存储方法,为未来开展大规模、高准确性领域本体存储的研究奠定基础。方法在明确中医皮肤病"疾病-证候-治疗"等领域本体及概念间关系的基础上,以资源描述框架（RDF）模型实现领域本体的规范化表达,应用由RDF模型向Neo4j属性图模型映射的规则对领域本体进行映射与存储,结合领域本体对属性的约束设置,最终实现对已存储数据的一致性检验以提高其准确性。结果构建了中医皮肤病"病-证-治"本体及其间关系的RDF模型,实现了由RDF模型向Neo4j属性图模型的映射,并对已存储数据实现了对象属性定义域、值域的数据一致性检验。结论基于Neo4j图数据库构建的中医皮肤病"病-证-治"本体具有扩展性较强、数据准确性较高的特点,本研究为后续进行大规模、高准确性存储中医药领域本体的研究奠定了基础。

随着互联网的迅猛发展,网上健康信息以几何速度增长,其中大量虚假健康信息给人们的生活带来了很大影响,但目前对虚假健康信息文本识别的研究非常缺乏,以往研究主要集中在识别微博上的谣言、伪造商品评论、垃圾邮件及虚假新闻等方面。鉴于此,采用基于词向量的深度神经网络模型和基于双向编码的语言表征模型,对互联网上流传广泛的健康信息文本进行自动分类,识别其中的虚假健康信息。实验中,深度网络模型比传统机器学习模型性能提高10%,融合Word2vec的深度神经网络模型比单独的CNN或Att-BiLSTM模型在分类性能上提高近7%。BERT模型表现最好,准确率高达88.1%。实验结果表明,深度学习可以有效识别虚假健康信息,并且通过大规模语料预训练获得的语言表征模型比基于词向量的深度神经网络模型性能更好。

Label distribution learning (LDL) assumes labels are associated with each instance to some degree and tries to model the relationship between labels and instances. LDL has achieved great success in many applications, but most existing LDL methods are designed for data with complete annotation information. However, in reality, supervised information often be incomplete due to the huge costs of data collection. In this paper, we propose a novel incomplete label distribution learning method based on supervised neighborhood information (IncomLDL-SNI). The proposed method uses partial least squares to project the original data into a supervised feature space where instances with similar labels are likely to be projected together. Then, IncomLDL-SNI utilizes the Euclidean distance to find the nearest neighbors for target samples in the supervised feature space and recovers the missing annotations from the neighborhood label Information. Extensive experiments on various data sets validate the effectiveness of our proposal. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.

随着云计算的广泛应用和医疗数据的爆炸式增长,大部分医疗机构逐步将医疗数据的存储和分析放到云端进行。由于中医电子病历中包含了大量的患者隐私信息,医疗机构通常将电子病历加密后再存储到云服务器上。然而,常规的加密数据无法直