Clinical Relation Extraction Toward Drug Safety Surveillance Using Electronic Health Record Narratives: Classical Learning Versus Deep Learning.

BACKGROUND: Medication and adverse drug event (ADE) information extracted from electronic health record (EHR) notes can be a rich resource for drug safety surveillance. Existing observational studies have mainly relied on structured EHR data to obtain ADE information; however, ADEs are often buried in the EHR narratives and not recorded in structured data. OBJECTIVE: To unlock ADE-related information from EHR narratives, there is a need to extract relevant entities and identify relations among them. In this study, we focus on relation identification. This study aimed to evaluate natural language processing and machine learning approaches using the expert-annotated medical entities and relations in the context of drug safety surveillance, and investigate how different learning approaches perform under different configurations. METHODS: We have manually annotated 791 EHR notes with 9 named entities (eg, medication, indication, severity, and ADEs) and 7 different types of relations (eg, medication-dosage, medication-ADE, and severity-ADE). Then, we explored 3 supervised machine learning systems for relation identification: (1) a support vector machines (SVM) system, (2) an end-to-end deep neural network system, and (3) a supervised descriptive rule induction baseline system. For the neural network system, we exploited the state-of-the-art recurrent neural network (RNN) and attention models. We report the performance by macro-averaged precision, recall, and F1-score across the relation types. RESULTS: Our results show that the SVM model achieved the best average F1-score of 89.1% on test data, outperforming the long short-term memory (LSTM) model with attention (F1-score of 65.72%) as well as the rule induction baseline system (F1-score of 7.47%) by a large margin. The bidirectional LSTM model with attention achieved the best performance among different RNN models. With the inclusion of additional features in the LSTM model, its performance can be boosted to an average F1-score of 77.35%. CONCLUSIONS: It shows that classical learning models (SVM) remains advantageous over deep learning models (RNN variants) for clinical relation identification, especially for long-distance intersentential relations. However, RNNs demonstrate a great potential of significant improvement if more training data become available. Our work is an important step toward mining EHRs to improve the efficacy of drug safety surveillance. Most importantly, the annotated data used in this study will be made publicly available, which will further promote drug safety research in the community.

Understanding Deep Learning Performance through an Examination of Test Set Difficulty: A Psychometric Case Study.

Interpreting the performance of deep learning models beyond test set accuracy is challenging. Characteristics of individual data points are often not considered during evaluation, and each data point is treated equally. We examine the impact of a test set question's difficulty to determine if there is a relationship between difficulty and performance. We model difficulty using well-studied psychometric methods on human response patterns. Experiments on Natural Language Inference (NLI) and Sentiment Analysis (SA) show that the likelihood of answering a question correctly is impacted by the question's difficulty. As DNNs are trained with more data, easy examples are learned more quickly than hard examples.

Neural Tree Indexers for Text Understanding.

Recurrent neural networks (RNNs) process input text sequentially and model the conditional transition between word tokens. In contrast, the advantages of recursive networks include that they explicitly model the compositionality and the recursive structure of natural language. However, the current recursive architecture is limited by its dependence on syntactic tree. In this paper, we introduce a robust syntactic parsing-independent tree structured model, Neural Tree Indexers (NTI) that provides a middle ground between the sequential RNNs and the syntactic tree-based recursive models. NTI constructs a full n-ary tree by processing the input text with its node function in a bottom-up fashion. Attention mechanism can then be applied to both structure and node function. We implemented and evaluated a binary-tree model of NTI, showing the model achieved the state-of-the-art performance on three different NLP tasks: natural language inference, answer sentence selection, and sentence classification, outperforming state-of-the-art recurrent and recursive neural networks .

Neural Semantic Encoders.

We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the understanding of input sequences through read, compose and write operations. NSE can also access multiple and shared memories. In this paper, we demonstrated the effectiveness and the flexibility of NSE on five different natural language tasks: natural language inference, question answering, sentence classification, document sentiment analysis and machine translation where NSE achieved state-of-the-art performance when evaluated on publically available benchmarks. For example, our shared-memory model showed an encouraging result on neural machine translation, improving an attention-based baseline by approximately 1.0 BLEU.

Meta Networks.

Neural networks have been successfully applied in applications with a large amount of labeled data. However, the task of rapid generalization on new concepts with small training data while preserving performances on previously learned ones still presents a significant challenge to neural network models. In this work, we introduce a novel meta learning method, Meta Networks (MetaNet), that learns a meta-level knowledge across tasks and shifts its inductive biases via fast parameterization for rapid generalization. When evaluated on Omniglot and Mini-ImageNet benchmarks, our MetaNet models achieve a near human-level performance and outperform the baseline approaches by up to 6% accuracy. We demonstrate several appealing properties of MetaNet relating to generalization and continual learning.

Self-training in significance space of support vectors for imbalanced biomedical event data.

BACKGROUND: Pairwise relationships extracted from biomedical literature are insufficient in formulating biomolecular interactions. Extraction of complex relations (namely, biomedical events) has become the main focus of the text-mining community. However, there are two critical issues that are seldom dealt with by existing systems. First, an annotated corpus for training a prediction model is highly imbalanced. Second, supervised models trained on only a single annotated corpus can limit system performance. Fortunately, there is a large pool of unlabeled data containing much of the domain background that one can exploit. RESULTS: In this study, we develop a new semi-supervised learning method to address the issues outlined above. The proposed algorithm efficiently exploits the unlabeled data to leverage system performance. We furthermore extend our algorithm to a two-phase learning framework. The first phase balances the training data for initial model induction. The second phase incorporates domain knowledge into the event extraction model. The effectiveness of our method is evaluated on the Genia event extraction corpus and a PubMed document pool. Our method can identify a small subset of the majority class, which is sufficient for building a well-generalized prediction model. It outperforms the traditional self-training algorithm in terms of f-measure. Our model, based on the training data and the unlabeled data pool, achieves comparable performance to the state-of-the-art systems that are trained on a larger annotated set consisting of training and evaluation data.

The CHEMDNER corpus of chemicals and drugs and its annotation principles.

The automatic extraction of chemical information from text requires the recognition of chemical entity mentions as one of its key steps. When developing supervised named entity recognition (NER) systems, the availability of a large, manually annotated text corpus is desirable. Furthermore, large corpora permit the robust evaluation and comparison of different approaches that detect chemicals in documents. We present the CHEMDNER corpus, a collection of 10,000 PubMed abstracts that contain a total of 84,355 chemical entity mentions labeled manually by expert chemistry literature curators, following annotation guidelines specifically defined for this task. The abstracts of the CHEMDNER corpus were selected to be representative for all major chemical disciplines. Each of the chemical entity mentions was manually labeled according to its structure-associated chemical entity mention (SACEM) class: abbreviation, family, formula, identifier, multiple, systematic and trivial. The difficulty and consistency of tagging chemicals in text was measured using an agreement study between annotators, obtaining a percentage agreement of 91. For a subset of the CHEMDNER corpus (the test set of 3,000 abstracts) we provide not only the Gold Standard manual annotations, but also mentions automatically detected by the 26 teams that participated in the BioCreative IV CHEMDNER chemical mention recognition task. In addition, we release the CHEMDNER silver standard corpus of automatically extracted mentions from 17,000 randomly selected PubMed abstracts. A version of the CHEMDNER corpus in the BioC format has been generated as well. We propose a standard for required minimum information about entity annotations for the construction of domain specific corpora on chemical and drug entities. The CHEMDNER corpus and annotation guidelines are available at: http://www.biocreative.org/resources/biocreative-iv/chemdner-corpus/.

Incorporating domain knowledge in chemical and biomedical named entity recognition with word representations.

BACKGROUND: Chemical and biomedical Named Entity Recognition (NER) is an essential prerequisite task before effective text mining can begin for biochemical-text data. Exploiting unlabeled text data to leverage system performance has been an active and challenging research topic in text mining due to the recent growth in the amount of biomedical literature. We present a semi-supervised learning method that efficiently exploits unlabeled data in order to incorporate domain knowledge into a named entity recognition model and to leverage system performance. The proposed method includes Natural Language Processing (NLP) tasks for text preprocessing, learning word representation features from a large amount of text data for feature extraction, and conditional random fields for token classification. Other than the free text in the domain, the proposed method does not rely on any lexicon nor any dictionary in order to keep the system applicable to other NER tasks in bio-text data. RESULTS: We extended BANNER, a biomedical NER system, with the proposed method. This yields an integrated system that can be applied to chemical and drug NER or biomedical NER. We call our branch of the BANNER system BANNER-CHEMDNER, which is scalable over millions of documents, processing about 530 documents per minute, is configurable via XML, and can be plugged into other systems by using the BANNER Unstructured Information Management Architecture (UIMA) interface. BANNER-CHEMDNER achieved an 85.68% and an 86.47% F-measure on the testing sets of CHEMDNER Chemical Entity Mention (CEM) and Chemical Document Indexing (CDI) subtasks, respectively, and achieved an 87.04% F-measure on the official testing set of the BioCreative II gene mention task, showing remarkable performance in both chemical and biomedical NER. BANNER-CHEMDNER system is available at: https://bitbucket.org/tsendeemts/banner-chemdner.