面向中医临床现病史文本的命名实体抽取方法研究

目的：中医临床病历作为重要的临床数据,以文本的形式记录了医生和患者交互的整个过程。目前,在大数据的背景下,针对临床病历所涵盖的主体问题信息如现病史的分析利用相关研究仍有所欠缺。因此,本文针对中医临床病历中的现病史部分展开症状术语抽取方法研究,为临床病历的进一步使用奠定基础。方法：首先通过随机挑选与专家审核的方式获得了12367份现病史数据,按照疾病种类分成了两组实验,其中糖尿病组包含了4838份数据,脾胃病组7529份数据,以及合并后的混合组12367份数据。并整理出了一份涵盖22996个词的症状术语字典。然后选取滑动窗口特征、词的前后缀特征、词典特征等5种特征模板,使用CRFs 模型开展症状术语命名实体抽取实验。结果：在实验结果评价标准（准确率、召回率和F1 值）上的表现：在开放测试上的评价结果为（0.83、0.8、0.82）、（0.9、0.9、0.89）和（0.88、0.87、0.87）;在十重交叉验证上的评价结果为（0.83、0.82、0.83）、（0.95、0.95、0.95）和（0.93、0.92、0.92）。结论：CRFs模型作为一种优秀的序列标注算法,适用于现病史文本的症状术语命名实体抽取任务。     

Medical Knowledge Extraction and Analysis from Electronic Medical Records Using Deep Learning

Objectives Medical knowledge extraction (MKE) plays a key role in natural language processing (NLP) research in electronic medical records (EMR), which are the important digital carriers for recording medical activities of patients. Named entity recognition (NER) and medical relation extraction (MRE) are two basic tasks of MKE. This study aims to improve the recognition accuracy of these two tasks by exploring deep learning methods.Methods This study discussed and built two application scenes of bidirectional long short-term memory combined conditional random field (BiLSTM-CRF) model for NER and MRE tasks. In the data preprocessing of both tasks, a GloVe word embedding model was used to vectorize words. In the NER task, a sequence labeling strategy was used to classify each word tag by the joint probability distribution through the CRF layer. In the MRE task, the medical entity relation category was predicted by transforming the classification problem of a single entity into a sequence classification problem and linking the feature combinations between entities also through the CRF layer.Results Through the validation on the I2B2 2010 public dataset, the BiLSTM-CRF models built in this study got much better results than the baseline methods in the two tasks, where the F1-measure was up to 0.88 in NER task and 0.78 in MRE task. Moreover, the model converged faster and avoided problems such as overfitting.Conclusion This study proved the good performance of deep learning on medical knowledge extraction. It also verified the feasibility of the BiLSTM-CRF model in different application scenarios, laying the foundation for the subsequent work in the EMR field.     

Inhibition of PI3K and calcineurin suppresses chemoattractant receptor-homologous molecule expressed on Th2 cells (CRTH2)-dependent responses of Th2 lymphocytes to prostaglandin D(2)

Interaction of prostaglandin D2 (PGD2) with chemoattractant receptor-homologous molecule expressed on Th2 cells (CRTH2) triggers chemotaxis and pro-inflammatory cytokine production by Th2 lymphocytes. We have investigated the role of inhibitors of various cell-signalling pathways on the responses of human CRTH2+ CD4+ Th2 cells to PGD2. Phosphatidylinositol 3-kinase (PI3K) and Ca2+/calcineurin/nuclear factor of activated T cells (NFAT) pathways were activated by PGD2 in Th2 cells in a CRTH2-dependent manner. Inhibition of the PI3K pathway with LY294002 significantly reduced both PGD2-induced cell migration and cytokine (interleukin-4, interleukin-5 and interleukin-13) production. The inhibitory effect of LY294002 on cell migration is likely to be related to cytoskeleton reorganization as it showed a similar potency on PGD2-induced actin polymerization. The calcineurin inhibitors, tacrolimus (FK506) and cyclosporin A, had no effect on cell migration but completely blocked both cytokine production and the nuclear translocation of NFATc1 suggesting that Ca2+/calcineurin/NFAT is involved in CRTH2-dependent cytokine production but not chemotaxis. The promotion of NFAT nuclear location by PI3K activation may be mediated by negative regulation of glycogen synthase kinase-3beta (GSK3beta), since the PGD2-stimulated increase in phospho-GSK3beta was down-regulated by LY294002, and inhibition of GSK3beta by SB216763 enhanced PGD2-induced Th2 cytokine production and reversed the inhibitory effect of LY294002. These data suggest that PI3K and Ca2+/calcineurin/NFAT signalling pathways are critically involved in pro-inflammatory responses of Th2 cells to PGD2.     

Coreference analysis in clinical notes: a multi-pass sieve with alternate anaphora resolution modules

Objective

This paper describes the coreference resolution system submitted by Mayo Clinic for the 2011 i2b2/VA/Cincinnati shared task Track 1C. The goal of the task was to construct a system that links the markables corresponding to the same entity.

Materials and methods

The task organizers provided progress notes and discharge summaries that were annotated with the markables of treatment, problem, test, person, and pronoun. We used a multi-pass sieve algorithm that applies deterministic rules in the order of preciseness and simultaneously gathers information about the entities in the documents. Our system, MedCoref, also uses a state-of-the-art machine learning framework as an alternative to the final, rule-based pronoun resolution sieve.

Results

The best system that uses a multi-pass sieve has an overall score of 0.836 (average of B³, MUC, Blanc, and CEAF F score) for the training set and 0.843 for the test set.

Discussion

A supervised machine learning system that typically uses a single function to find coreferents cannot accommodate irregularities encountered in data especially given the insufficient number of examples. On the other hand, a completely deterministic system could lead to a decrease in recall (sensitivity) when the rules are not exhaustive. The sieve-based framework allows one to combine reliable machine learning components with rules designed by experts.

Conclusion

Using relatively simple rules, part-of-speech information, and semantic type properties, an effective coreference resolution system could be designed. The source code of the system described is available at https://sourceforge.net/projects/ohnlp/files/MedCoref.     

A study of active learning methods for named entity recognition in clinical text

ObjectivesNamed entity recognition (NER), a sequential labeling task, is one of the fundamental tasks for building clinical natural language processing (NLP) systems. Machine learning (ML) based approaches can achieve good performance, but they often require large amounts of annotated samples, which are expensive to build due to the requirement of domain experts in annotation. Active learning (AL), a sample selection approach integrated with supervised ML, aims to minimize the annotation cost while maximizing the performance of ML-based models. In this study, our goal was to develop and evaluate both existing and new AL methods for a clinical NER task to identify concepts of medical problems, treatments, and lab tests from the clinical notes.MethodsUsing the annotated NER corpus from the 2010 i2b2/VA NLP challenge that contained 349 clinical documents with 20,423 unique sentences, we simulated AL experiments using a number of existing and novel algorithms in three different categories including uncertainty-based, diversity-based, and baseline sampling strategies. They were compared with the passive learning that uses random sampling. Learning curves that plot performance of the NER model against the estimated annotation cost (based on number of sentences or words in the training set) were generated to evaluate different active learning and the passive learning methods and the area under the learning curve (ALC) score was computed.ResultsBased on the learning curves of F-measure vs. number of sentences, uncertainty sampling algorithms outperformed all other methods in ALC. Most diversity-based methods also performed better than random sampling in ALC. To achieve an F-measure of 0.80, the best method based on uncertainty sampling could save 66% annotations in sentences, as compared to random sampling. For the learning curves of F-measure vs. number of words, uncertainty sampling methods again outperformed all other methods in ALC. To achieve 0.80 in F-measure, in comparison to random sampling, the best uncertainty based method saved 42% annotations in words. But the best diversity based method reduced only 7% annotation effort.ConclusionIn the simulated setting, AL methods, particularly uncertainty-sampling based approaches, seemed to significantly save annotation cost for the clinical NER task. The actual benefit of active learning in clinical NER should be further evaluated in a real-time setting.     

英汉冠名疾病名称解释与囯际疾病分类编码的临床应用——附计算机智能检索

病案管理进行疾病分类编码时难度最大的是对英汉冠名疾病进行选择编码。为了提高病案管理人员对英汉冠名疾病编码的速度及准确率,本项目组收集了英语冠名疾病三千多个,汉语命名的疾病近五千条,内容丰富、直观,操作方便,设有多渠道检索功能,是前所未有的将临床医学、医学基础理论与囯际疾病分类编码相结合的实用性工具。     

Extracting postmarketing adverse events from safety reports in the vaccine adverse event reporting system (VAERS) using deep learning

ObjectiveAutomated analysis of vaccine postmarketing surveillance narrative reports is important to understand the progression of rare but severe vaccine adverse events (AEs). This study implemented and evaluated state-of-the-art deep learning algorithms for named entity recognition to extract nervous system disorder-related events from vaccine safety reports.Materials and MethodsWe collected Guillain-Barré syndrome (GBS) related influenza vaccine safety reports from the Vaccine Adverse Event Reporting System (VAERS) from 1990 to 2016. VAERS reports were selected and manually annotated with major entities related to nervous system disorders, including, investigation, nervous_AE, other_AE, procedure, social_circumstance, and temporal_expression. A variety of conventional machine learning and deep learning algorithms were then evaluated for the extraction of the above entities. We further pretrained domain-specific BERT (Bidirectional Encoder Representations from Transformers) using VAERS reports (VAERS BERT) and compared its performance with existing models.Results and ConclusionsNinety-one VAERS reports were annotated, resulting in 2512 entities. The corpus was made publicly available to promote community efforts on vaccine AEs identification. Deep learning-based methods (eg, bi-long short-term memory and BERT models) outperformed conventional machine learning-based methods (ie, conditional random fields with extensive features). The BioBERT large model achieved the highest exact match F-1 scores on nervous_AE, procedure, social_circumstance, and temporal_expression; while VAERS BERT large models achieved the highest exact match F-1 scores on investigation and other_AE. An ensemble of these 2 models achieved the highest exact match microaveraged F-1 score at 0.6802 and the second highest lenient match microaveraged F-1 score at 0.8078 among peer models.     

Named nursing: in whose best interest?

This paper explores certain influences and issues surrounding the implementation and application of the named nurse concept. The author critically examines the proposals that primary nursing increases job satisfaction, cost effectiveness and quality of care, and suggests that as primary nursing appears to be the template for named nursing, these are factors which may have influenced the former British government's decision to implement the concept of named nursing. Owing to problems regarding the reliability and validity of much of the research, the author draws the conclusion that the direct extrapolation from one concept (such as primary nursing) to another (such as named nursing) is perhaps open to question. The author also analyses other issues related to the implementation and use of the named nurse concept including advocacy and accountability, and proposes that the introduction of individualized care, and in particular named nursing, perhaps serves the drive towards the professionalization of nursing first, and the patient second, and if so questions whether there is a need to reconsider the aim of nursing.     

UMLS-based data augmentation for natural language processing of clinical research literature

ObjectiveThe study sought to develop and evaluate a knowledge-based data augmentation method to improve the performance of deep learning models for biomedical natural language processing by overcoming training data scarcity.Materials and MethodsWe extended the easy data augmentation (EDA) method for biomedical named entity recognition (NER) by incorporating the Unified Medical Language System (UMLS) knowledge and called this method UMLS-EDA. We designed experiments to systematically evaluate the effect of UMLS-EDA on popular deep learning architectures for both NER and classification. We also compared UMLS-EDA to BERT.ResultsUMLS-EDA enables substantial improvement for NER tasks from the original long short-term memory conditional random fields (LSTM-CRF) model (micro-F1 score: +5%, + 17%, and +15%), helps the LSTM-CRF model (micro-F1 score: 0.66) outperform LSTM-CRF with transfer learning by BERT (0.63), and improves the performance of the state-of-the-art sentence classification model. The largest gain on micro-F1 score is 9%, from 0.75 to 0.84, better than classifiers with BERT pretraining (0.82).ConclusionsThis study presents a UMLS-based data augmentation method, UMLS-EDA. It is effective at improving deep learning models for both NER and sentence classification, and contributes original insights for designing new, superior deep learning approaches for low-resource biomedical domains.     

命名实体识别在中医药领域研究进展

介绍中医药领域命名实体识别的研究现状,分析中医药领域命名实体识别的数据特征、评价指标和应用情况,阐述中医药领域命名实体识别研究的难点和不足,并提出展望。