From electronic health records to terminology base: A novel knowledge base enrichment approach.

Enriching terminology base (TB) is an important and continuous process, since formal term can be renamed and new term alias emerges all the time. As a potential supplementary for TB enrichment, electronic health record (EHR) is a fundamental source for clinical research and practise. The task to align the set of external terms in EHRs to TB can be regarded as entity alignment without structure information. Conventional approaches mainly use internal structural information of multiple knowledge bases (KBs) to map entities and their counterparts among KBs. However, the external terms in EHRs are independent clinical terms, which lack of interrelations. To achieve entity alignment in this case, we proposed a novel automatic TB enrichment approach, named semantic & structure embeddings-based relevancy prediction (S2ERP). To obtain the semantic embedding of external terms, we fed them with formal entity into a pre-trained language model. Meanwhile, a graph convolutional network was used to obtain the structure embeddings of the synonyms and hyponyms in TB. Afterwards, S2ERP combines both embeddings to measure the relevancy. Experimental results on clinical indicator TB, collected from 38 top-class hospitals of Shanghai Hospital Development Center, showed that the proposed approach outperforms baseline methods by 14.16% in Hits@1.

Weight-based multiple empirical kernel learning with neighbor discriminant constraint for heart failure mortality prediction.

Heart Failure (HF) is one of the most common causes of hospitalization and is burdened by short-term (in-hospital) and long-term (6-12 month) mortality. Accurate prediction of HF mortality plays a critical role in evaluating early treatment effects. However, due to the lack of a simple and effective prediction model, mortality prediction of HF is difficult, resulting in a low rate of control. To handle this issue, we propose a Weight-based Multiple Empirical Kernel Learning with Neighbor Discriminant Constraint (WMEKL-NDC) method for HF mortality prediction. In our method, feature selection by calculating the F-value of each feature is first performed to identify the crucial clinical features. Then, different weights are assigned to each empirical kernel space according to the centered kernel alignment criterion. To make use of the discriminant information of samples, neighbor discriminant constraint is finally integrated into multiple empirical kernel learning framework. Extensive experiments were performed on a real clinical dataset containing 10, 198 in-patients records collected from Shanghai Shuguang Hospital in March 2009 and April 2016. Experimental results demonstrate that our proposed WMEKL-NDC method achieves a highly competitive performance for HF mortality prediction of in-hospital, 30-day and 1-year. Compared with the state-of-the-art multiple kernel learning and baseline algorithms, our proposed WMEKL-NDC is more accurate on mortality prediction Moreover, top 10 crucial clinical features are identified together with their meanings, which are very useful to assist clinicians in the treatment of HF disease.

Incorporating dictionaries into deep neural networks for the Chinese clinical named entity recognition.

Clinical named entity recognition aims to identify and classify clinical terms such as diseases, symptoms, treatments, exams, and body parts in electronic health records, which is a fundamental and crucial task for clinical and translational research. In recent years, deep neural networks have achieved significant success in named entity recognition and many other natural language processing tasks. Most of these algorithms are trained end to end, and can automatically learn features from large scale labeled datasets. However, these data-driven methods typically lack the capability of processing rare or unseen entities. Previous statistical methods and feature engineering practice have demonstrated that human knowledge can provide valuable information for handling rare and unseen cases. In this paper, we propose a new model which combines data-driven deep learning approaches and knowledge-driven dictionary approaches. Specifically, we incorporate dictionaries into deep neural networks. In addition, two different architectures that extend the bi-directional long short-term memory neural network and five different feature representation schemes are also proposed to handle the task. Computational results on the CCKS-2017 Task 2 benchmark dataset show that the proposed method achieves the highly competitive performance compared with the state-of-the-art deep learning methods.

Representation learning for clinical time series prediction tasks in electronic health records.

BACKGROUND: Electronic health records (EHRs) provide possibilities to improve patient care and facilitate clinical research. However, there are many challenges faced by the applications of EHRs, such as temporality, high dimensionality, sparseness, noise, random error and systematic bias. In particular, temporal information is difficult to effectively use by traditional machine learning methods while the sequential information of EHRs is very useful. METHOD: In this paper, we propose a general-purpose patient representation learning approach to summarize sequential EHRs. Specifically, a recurrent neural network based denoising autoencoder (RNN-DAE) is employed to encode inhospital records of each patient into a low dimensional dense vector. RESULTS: Based on EHR data collected from Shuguang Hospital affiliated to Shanghai University of Traditional Chinese Medicine, we experimentally evaluate our proposed RNN-DAE method on both mortality prediction task and comorbidity prediction task. Extensive experimental results show that our proposed RNN-DAE method outperforms existing methods. In addition, we apply the "Deep Feature" represented by our proposed RNN-DAE method to track similar patients with t-SNE, which also achieves some interesting observations. CONCLUSION: We propose an effective unsupervised RNN-DAE method to summarize patient sequential information in EHR data. Our proposed RNN-DAE method is useful on both mortality prediction task and comorbidity prediction task.

The complete chloroplast genome sequence of Begonia ferox, an endangered species in China.

Begonia ferox C.I Peng & Yan Liu (2013) was rated as endangered according to Red List of Chinese Plants. In this study, we report the complete chloroplast genome of B. ferox. The chloroplast genome is 169,114 bp in length as the circular, with the GC content of 35.5%, composed by a large single-copy (LSC) region of 75,887 bp, a small single-copy (SSC) region of 18,105 bp, and two inverted repeat regions (IRs) of 37,561 bp in each. The genome comprises 174 encoded genes in total, including 114 protein-coding genes, eight ribosomal RNA genes, and 52 transfer RNA genes. Phylogenetic analysis indicated that B. ferox is genetically closest to B. gulongshanensis.

Multiple Partial Empirical Kernel Learning with Instance Weighting and Boundary Fitting.

By dividing the original data set into several sub-sets, Multiple Partial Empirical Kernel Learning (MPEKL) constructs multiple kernel matrixes corresponding to the sub-sets, and these kernel matrixes are decomposed to provide the explicit kernel functions. Then, the instances in the original data set are mapped into multiple kernel spaces, which provide better performance than single kernel space. It is known that the instances in different locations and distributions behave differently. Therefore, this paper defines the weight of instance in accordance with the location and distribution of the instances. According to the location, the instances can be categorized into intrinsic instances, boundary instances and noise instances. Generally, the boundary instances, as well as the minority instances in the imbalanced data set, are assigned high weight. Meanwhile, a regularization term, which regulates the classification hyperplane to fit the distribution trend of the class boundary, is constructed by the boundary instances. Then, the weight of instance and the regularization term are introduced into MPEKL to form an algorithm named Multiple Partial Empirical Kernel Learning with Instance Weighting and Boundary Fitting (IBMPEKL). Experiments demonstrate the good performance of IBMPEKL and validate the effectiveness of the instance weighting and boundary fitting.

Heparanase potentiates the invasion and migration of pancreatic cancer cells via epithelial­to­mesenchymal transition through the Wnt/ß­catenin pathway.

Mounting evidence indicates that there exists an association between heparanase (HPSE) and several physiological and pathological mechanisms in humans. However, the dynamics of the mechanisms involved in the regulation of HPSE expression in pancreatic cancer (PC) remain unclear. The aim of the present study was to assess the levels of HPSE in PC tissues and cell lines by western blotting and reverse transcription­quantitative PCR (RT­qPCR) analysis. Wound healing and Transwell assays were conducted to examine the effects of HPSE on migration and invasion in sh­NC and sh­HPSE PC cell lines. In addition, tumor growth was assessed in a mouse xenograft model in vivo. The expression levels of epithelial­to­mesenchymal transition (EMT)­related biomarkers and the involvement of the Wnt/ß­catenin pathway were assessed by analyzing the results of western blot and RT­qPCR assays. The results indicated that the expression of HPSE was substantially higher in PC tissues and cell lines, whereas experimental knockdown of HPSE suppressed the rates of migration and invasion of PC cells. Western blotting was used to assess the expression of EMT biomarkers and determine the function of HPSE in EMT. Furthermore, our results indicated that downregulation of HPSE expression decreased the expression of Wnt/ß­catenin associated proteins. In conclusion, HPSE appears to be a good candidate as a molecular target for the treatment of PC based on the finding of the present study.

Assessment of surface water quality in Lushan: a world heritage sites in China.

Surface water is one of the important landscape resources in tourist attractions. Due to tourism activities, the surface water quality (SWQ) in scenic was often damaged. An example of the Lushan Scenic, the SWQ, was analyzed and evaluated by water sampling and laboratory analysis methods. The results explained that the SWQ of Lushan Scenic was seriously damaged. The comprehensive index explained that the SWQ of seven sampling dots was from mild pollution to extreme pollution. The main pollutants were ammonia nitrogen, total nitrogen, and total phosphorus, and the TN and TP were the most serious. According to the data of tourists in 2017, the emergency water capacity stored by reservoirs was 32.5 days if there was no raining in Lushan Scenic. The main factors affecting the SWQ were tourism activities, such as tourists, hotels, restaurants, and other commercial activities, and pollutants discharged from domestic water were not completely treated in Lushan Scenic.

Upregulation of DUSP14 Affects Proliferation, Invasion and Metastasis, Potentially via Epithelial-Mesenchymal Transition and Is Associated with Poor Prognosis in Pancreatic Cancer.

BACKGROUND: There is a growing number of evidence which report the relationship of the dual-specificity phosphatases 14 (DUSP14) with physiological and pathological mechanisms in the human body. However, it is still not known what if any role DUSP14 plays in pancreatic cancer. MATERIALS AND METHODS: The study evaluates the levels of DUSP14 in the pancreatic cancer tissues and cell lines using Western blotting and qRT-PCR to assess the levels of the DUSP14 and epithelial-mesenchymal transition (EMT) biomarkers. After the DUSP14 was blocked, the following assays were performed: colony formation, assessments of scratch wound and transwell to examine the effects of DUSP14 on the proliferation, migration and invasion of the pancreatic cancer. RESULTS: Results showed that there was a significant increase in the level of DUSP14 expression both in the pancreatic cancer tissues and cell lines. Experimental downregulation of DUSP14 induced the inhibition of the capacity of proliferation, migration and invasion of the pancreatic cancer cells. Western blotting analyses showed changes in the levels of expression of the EMT biomarkers, which helped to determine the function of DUSP14 in EMT. CONCLUSION: In conclusion, we suggest that DUSP14 is a novel molecular target that can be used for the treatment of pancreatic cancer.

Memetic Search for Identifying Critical Nodes in Sparse Graphs.

Critical node problems (CNPs) involve finding a set of critical nodes from a graph whose removal results in optimizing a predefined measure over the residual graph. As useful models for a variety of practical applications, these problems are computationally challenging. In this paper, we study the classic CNP and introduce an effective memetic algorithm for solving CNP. The proposed algorithm combines a double backbone-based crossover operator (to generate promising offspring solutions), a component-based neighborhood search procedure (to find high-quality local optima), and a rank-based pool updating strategy (to guarantee a healthy population). Extensive evaluations on 42 synthetic and real-world benchmark instances show that the proposed algorithm discovers 24 new upper bounds and matches 15 previous best-known bounds. We also demonstrate the relevance of our algorithm for effectively solving a variant of the classic CNP, called the cardinality-constrained CNP. Finally, we investigate the usefulness of each key algorithmic component.

Chinese Clinical Named Entity Recognition Using Residual Dilated Convolutional Neural Network With Conditional Random Field.

Clinical named entity recognition (CNER) is a fundamental and crucial task for clinical and translation research. In recent years, deep learning methods have achieved significant success in CNER tasks. However, these methods depend greatly on recurrent neural networks (RNNs), which maintain a vector of hidden activations that are propagated through time, thus causing too much time to train models. In this paper, we propose a residual dilated convolutional neural network with the conditional random field (RD-CNN-CRF) for the Chinese CNER, which makes the model asynchronous in computation and thus speeding up the training period dramatically. To be more specific, Chinese characters and dictionary features are first projected into dense vector representations, then they are fed into the residual dilated convolutional neural network to capture contextual features. Finally, a conditional random field is employed to capture dependencies between neighboring tags and obtain the optimal tag sequence for the entire sequence. Computational results on the CCKS-2017 Task 2 benchmark dataset show that our proposed RD-CNN-CRF method competes favorably with state-of-the-art RNN-based methods both in terms of computational performance and training time.

[Histopathological study on the healing of orthodontic implant-bone interface adjacent to extraction].

OBJECTIVE: Osseointegration of orthodontic microscrew implant is influenced by tooth extraction. This study aims to evaluate the safety margin of the osseointegration of orthodontic implants by investigating the healing process of the implant-bone interface through histopathological studies and quantitative determination. METHODS: Twelve male beagles were selected and randomly divided into four groups. An orthodontic microscrew was implanted beside the tooth extraction area. Animals were killed in 1, 3, 8, and, 12 weeks to investigate tissue response. Histomorphological observation and bone implant contact ratio (BIC) tests were performed at different healing time after implantation. RESULTS: A new bone was formed on the implant-bone interface of the control group. Bone resorptions were also detected in the experimental group 3 weeks after implantation. The BIC level of the control groups increased during the first 8 weeks; no change was observed anymore after the 8th week. On the other hand, the BIC value in the experimental group decreased in the first 3 weeks. It then increased rapidly and reached its peak of 80.08% in the 8th week. No significant difference wa s found between the experimental and control groups in the first 3 weeks. After the 3rd week, the BIC value of the experimental group (44.35%) was lower than that of the control group (55.46%) (P < 0.01). CONCLUSION: The healing process after implantation was influenced by tooth extraction. Bone resorption was detected at an early stage. However, vigorous bone remodeling was observed subsequently.