Dataset Information

Enhancing clinical concept extraction with contextual embeddings.

ABSTRACT: OBJECTIVE:Neural network-based representations ("embeddings") have dramatically advanced natural language processing (NLP) tasks, including clinical NLP tasks such as concept extraction. Recently, however, more advanced embedding methods and representations (eg, ELMo, BERT) have further pushed the state of the art in NLP, yet there are no common best practices for how to integrate these representations into clinical tasks. The purpose of this study, then, is to explore the space of possible options in utilizing these new models for clinical concept extraction, including comparing these to traditional word embedding methods (word2vec, GloVe, fastText). MATERIALS AND METHODS:Both off-the-shelf, open-domain embeddings and pretrained clinical embeddings from MIMIC-III (Medical Information Mart for Intensive Care III) are evaluated. We explore a battery of embedding methods consisting of traditional word embeddings and contextual embeddings and compare these on 4 concept extraction corpora: i2b2 2010, i2b2 2012, SemEval 2014, and SemEval 2015. We also analyze the impact of the pretraining time of a large language model like ELMo or BERT on the extraction performance. Last, we present an intuitive way to understand the semantic information encoded by contextual embeddings. RESULTS:Contextual embeddings pretrained on a large clinical corpus achieves new state-of-the-art performances across all concept extraction tasks. The best-performing model outperforms all state-of-the-art methods with respective F1-measures of 90.25, 93.18 (partial), 80.74, and 81.65. CONCLUSIONS:We demonstrate the potential of contextual embeddings through the state-of-the-art performance these methods achieve on clinical concept extraction. Additionally, we demonstrate that contextual embeddings encode valuable semantic information not accounted for in traditional word representations.

SUBMITTER: Si Y

PROVIDER: S-EPMC6798561 | biostudies-literature | 2019 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Enhancing clinical concept extraction with contextual embeddings.

Si Yuqi Y Wang Jingqi J Xu Hua H Roberts Kirk K

Journal of the American Medical Informatics Association : JAMIA 20191101 11

<h4>Objective</h4>Neural network-based representations ("embeddings") have dramatically advanced natural language processing (NLP) tasks, including clinical NLP tasks such as concept extraction. Recently, however, more advanced embedding methods and representations (eg, ELMo, BERT) have further pushed the state of the art in NLP, yet there are no common best practices for how to integrate these representations into clinical tasks. The purpose of this study, then, is to explore the space of possi ...[more]

PMID: 31265066

Similar Datasets

Project description:Extracting concepts (such as drugs, symptoms, and diagnoses) from clinical narratives constitutes a basic enabling technology to unlock the knowledge within and support more advanced reasoning applications such as diagnosis explanation, disease progression modeling, and intelligent analysis of the effectiveness of treatment. The recent release of annotated training sets of de-identified clinical narratives has contributed to the development and refinement of concept extraction methods. However, as the annotation process is labor-intensive, training data are necessarily limited in the concepts and concept patterns covered, which impacts the performance of supervised machine learning applications trained with these data. This paper proposes an approach to minimize this limitation by combining supervised machine learning with empirical learning of semantic relatedness from the distribution of the relevant words in additional unannotated text. The approach uses a sequential discriminative classifier (Conditional Random Fields) to extract the mentions of medical problems, treatments and tests from clinical narratives. It takes advantage of all Medline abstracts indexed as being of the publication type "clinical trials" to estimate the relatedness between words in the i2b2/VA training and testing corpora. In addition to the traditional features such as dictionary matching, pattern matching and part-of-speech tags, we also used as a feature words that appear in similar contexts to the word in question (that is, words that have a similar vector representation measured with the commonly used cosine metric, where vector representations are derived using methods of distributional semantics). To the best of our knowledge, this is the first effort exploring the use of distributional semantics, the semantics derived empirically from unannotated text often using vector space models, for a sequence classification task such as concept extraction. Therefore, we first experimented with different sliding window models and found the model with parameters that led to best performance in a preliminary sequence labeling task. The evaluation of this approach, performed against the i2b2/VA concept extraction corpus, showed that incorporating features based on the distribution of words across a large unannotated corpus significantly aids concept extraction. Compared to a supervised-only approach as a baseline, the micro-averaged F-score for exact match increased from 80.3% to 82.3% and the micro-averaged F-score based on inexact match increased from 89.7% to 91.3%. These improvements are highly significant according to the bootstrap resampling method and also considering the performance of other systems. Thus, distributional semantic features significantly improve the performance of concept extraction from clinical narratives by taking advantage of word distribution information obtained from unannotated data.

Project description:The availability of annotated corpora has facilitated the application of machine learning algorithms to concept extraction from clinical notes. However, high expenditure and labor are required for creating the annotations. A potential alternative is to reuse existing corpora from other institutions by pooling with local corpora, for training machine taggers. In this paper we have investigated the latter approach by pooling corpora from 2010 i2b2/VA NLP challenge and Mayo Clinic Rochester, to evaluate taggers for recognition of medical problems. The corpora were annotated for medical problems, but with different guidelines. The taggers were constructed using an existing tagging system MedTagger that consisted of dictionary lookup, part of speech (POS) tagging and machine learning for named entity prediction and concept extraction. We hope that our current work will be a useful case study for facilitating reuse of annotated corpora across institutions.We found that pooling was effective when the size of the local corpus was small and after some of the guideline differences were reconciled. The benefits of pooling, however, diminished as more locally annotated documents were included in the training data. We examined the annotation guidelines to identify factors that determine the effect of pooling.The effectiveness of pooling corpora, is dependent on several factors, which include compatibility of annotation guidelines, distribution of report types and size of local and foreign corpora. Simple methods to rectify some of the guideline differences can facilitate pooling. Our findings need to be confirmed with further studies on different corpora. To facilitate the pooling and reuse of annotated corpora, we suggest that - i) the NLP community should develop a standard annotation guideline that addresses the potential areas of guideline differences that are partly identified in this paper; ii) corpora should be annotated with a two-pass method that focuses first on concept recognition, followed by normalization to existing ontologies; and iii) metadata such as type of the report should be created during the annotation process.

Project description:Objective:We learn contextual embeddings for emergency department (ED) chief complaints using Bidirectional Encoder Representations from Transformers (BERT), a state-of-the-art language model, to derive a compact and computationally useful representation for free-text chief complaints. Materials and methods:Retrospective data on 2.1 million adult and pediatric ED visits was obtained from a large healthcare system covering the period of March 2013 to July 2019. A total of 355 497 (16.4%) visits from 65 737 (8.9%) patients were removed for absence of either a structured or unstructured chief complaint. To ensure adequate training set size, chief complaint labels that comprised less than 0.01%, or 1 in 10 000, of all visits were excluded. The cutoff threshold was incremented on a log scale to create seven datasets of decreasing sparsity. The classification task was to predict the provider-assigned label from the free-text chief complaint using BERT, with Long Short-Term Memory (LSTM) and Embeddings from Language Models (ELMo) as baselines. Performance was measured as the Top-k accuracy from k?=?1:5 on a hold-out test set comprising 5% of the samples. The embedding for each free-text chief complaint was extracted as the final 768-dimensional layer of the BERT model and visualized using t-distributed stochastic neighbor embedding (t-SNE). Results:The models achieved increasing performance with datasets of decreasing sparsity, with BERT outperforming both LSTM and ELMo. The BERT model yielded Top-1 accuracies of 0.65 and 0.69, Top-3 accuracies of 0.87 and 0.90, and Top-5 accuracies of 0.92 and 0.94 on datasets comprised of 434 and 188 labels, respectively. Visualization using t-SNE mapped the learned embeddings in a clinically meaningful way, with related concepts embedded close to each other and broader types of chief complaints clustered together. Discussion:Despite the inherent noise in the chief complaint label space, the model was able to learn a rich representation of chief complaints and generate reasonable predictions of their labels. The learned embeddings accurately predict provider-assigned chief complaint labels and map semantically similar chief complaints to nearby points in vector space. Conclusion:Such a model may be used to automatically map free-text chief complaints to structured fields and to assist the development of a standardized, data-driven ontology of chief complaints for healthcare institutions.

Project description:BACKGROUND:Data sharing has been a big challenge in biomedical informatics because of privacy concerns. Contextual embedding models have demonstrated a very strong representative capability to describe medical concepts (and their context), and they have shown promise as an alternative way to support deep-learning applications without the need to disclose original data. However, contextual embedding models acquired from individual hospitals cannot be directly combined because their embedding spaces are different, and naive pooling renders combined embeddings useless. OBJECTIVE:The aim of this study was to present a novel approach to address these issues and to promote sharing representation without sharing data. Without sacrificing privacy, we also aimed to build a global model from representations learned from local private data and synchronize information from multiple sources. METHODS:We propose a methodology that harmonizes different local contextual embeddings into a global model. We used Word2Vec to generate contextual embeddings from each source and Procrustes to fuse different vector models into one common space by using a list of corresponding pairs as anchor points. We performed prediction analysis with harmonized embeddings. RESULTS:We used sequential medical events extracted from the Medical Information Mart for Intensive Care III database to evaluate the proposed methodology in predicting the next likely diagnosis of a new patient using either structured data or unstructured data. Under different experimental scenarios, we confirmed that the global model built from harmonized local models achieves a more accurate prediction than local models and global models built from naive pooling. CONCLUSIONS:Such aggregation of local models using our unique harmonization can serve as the proxy for a global model, combining information from a wide range of institutions and information sources. It allows information unique to a certain hospital to become available to other sites, increasing the fluidity of information flow in health care.

Project description:A massive number of biological entities, such as genes and mutations, are mentioned in the biomedical literature. The capturing of the semantic relatedness of biological entities is vital to many biological applications, such as protein-protein interaction prediction and literature-based discovery. Concept embeddings-which involve the learning of vector representations of concepts using machine learning models-have been employed to capture the semantics of concepts. To develop concept embeddings, named-entity recognition (NER) tools are first used to identify and normalize concepts from the literature, and then different machine learning models are used to train the embeddings. Despite multiple attempts, existing biomedical concept embeddings generally suffer from suboptimal NER tools, small-scale evaluation, and limited availability. In response, we employed high-performance machine learning-based NER tools for concept recognition and trained our concept embeddings, BioConceptVec, via four different machine learning models on ~30 million PubMed abstracts. BioConceptVec covers over 400,000 biomedical concepts mentioned in the literature and is of the largest among the publicly available biomedical concept embeddings to date. To evaluate the validity and utility of BioConceptVec, we respectively performed two intrinsic evaluations (identifying related concepts based on drug-gene and gene-gene interactions) and two extrinsic evaluations (protein-protein interaction prediction and drug-drug interaction extraction), collectively using over 25 million instances from nine independent datasets (17 million instances from six intrinsic evaluation tasks and 8 million instances from three extrinsic evaluation tasks), which is, by far, the most comprehensive to our best knowledge. The intrinsic evaluation results demonstrate that BioConceptVec consistently has, by a large margin, better performance than existing concept embeddings in identifying similar and related concepts. More importantly, the extrinsic evaluation results demonstrate that using BioConceptVec with advanced deep learning models can significantly improve performance in downstream bioinformatics studies and biomedical text-mining applications. Our BioConceptVec embeddings and benchmarking datasets are publicly available at https://github.com/ncbi-nlp/BioConceptVec.

Dataset Information

Enhancing clinical concept extraction with contextual embeddings.

Publications

Enhancing clinical concept extraction with contextual embeddings.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets