Unstructured Information Management Research Articles

A systematic review of text mining approaches applied to various application areas in the biomedical domain

PurposeThis work shows the results of a systematic literature review on biomedical text mining. The purpose of this study is to identify the different text mining approaches used in different application areas of the biomedical domain, the common tools used and the challenges of biomedical text mining as compared to generic text mining algorithms. This study will be of value to biomedical researchers by allowing them to correlate text mining approaches to specific biomedical application areas. Implications for future research are also discussed.Design/methodology/approachThe review was conducted following the principles of the Kitchenham method. A number of research questions were first formulated, followed by the definition of the search strategy. The papers were then selected based on a list of assessment criteria. Each of the papers were analyzed and information relevant to the research questions were extracted.FindingsIt was found that researchers have mostly harnessed data sources such as electronic health records, biomedical literature, social media and health-related forums. The most common text mining technique was natural language processing using tools such as MetaMap and Unstructured Information Management Architecture, alongside the use of medical terminologies such as Unified Medical Language System. The main application area was the detection of adverse drug events. Challenges identified included the need to deal with huge amounts of text, the heterogeneity of the different data sources, the duality of meaning of words in biomedical text and the amount of noise introduced mainly from social media and health-related forums.Originality/valueTo the best of the authors’ knowledge, other reviews in this area have focused on either specific techniques, specific application areas or specific data sources. The results of this review will help researchers to correlate most relevant and recent advances in text mining approaches to specific biomedical application areas by providing an up-to-date and holistic view of work done in this research area. The use of emerging text mining techniques has great potential to spur the development of innovative applications, thus considerably impacting on the advancement of biomedical research.

Clinical concept normalization with a hybrid natural language processing system combining multilevel matching and machine learning ranking.

Normalizing clinical mentions to concepts in standardized medical terminologies, in general, is challenging due to the complexity and variety of the terms in narrative medical records. In this article, we introduce our work on a clinical natural language processing (NLP) system to automatically normalize clinical mentions to concept unique identifier in the Unified Medical Language System. This work was part of the 2019 n2c2 (National NLP Clinical Challenges) Shared-Task and Workshop on Clinical Concept Normalization. We developed a hybrid clinical NLP system that combines a generic multilevel matching framework, customizable matching components, and machine learning ranking systems. We explored 2 machine leaning ranking systems based on either ensemble of various similarity features extracted from pretrained encoders or a Siamese attention network, targeting at efficient and fast semantic searching/ranking. Besides, we also evaluated the performance of a general-purpose clinical NLP system based on Unstructured Information Management Architecture. The systems were evaluated as part of the 2019 n2c2 challenge, and our original best system in the challenge obtained an accuracy of 0.8101, ranked fifth in the challenge. The improved system with newly designed machine learning ranking based on Siamese attention network improved the accuracy to 0.8209. We demonstrate the successful practice of combining multilevel matching and machine learning ranking for clinical concept normalization. Our results indicate the capability and interpretability of our proposed approach, as well as the limitation, suggesting the opportunities of achieving better performance by combining general clinical NLP systems.

Clinical trial cohort selection based on multi-level rule-based natural language processing system.

Identifying patients who meet selection criteria for clinical trials is typically challenging and time-consuming. In this article, we describe our clinical natural language processing (NLP) system to automatically assess patients' eligibility based on their longitudinal medical records. This work was part of the 2018 National NLP Clinical Challenges (n2c2) Shared-Task and Workshop on Cohort Selection for Clinical Trials. The authors developed an integrated rule-based clinical NLP system which employs a generic rule-based framework plugged in with lexical-, syntactic- and meta-level, task-specific knowledge inputs. In addition, the authors also implemented and evaluated a general clinical NLP (cNLP) system which is built with the Unified Medical Language System and Unstructured Information Management Architecture. The systems were evaluated as part of the 2018 n2c2-1 challenge, and authors' rule-based system obtained an F-measure of 0.9028, ranking fourth at the challenge and had less than 1% difference from the best system. While the general cNLP system didn't achieve performance as good as the rule-based system, it did establish its own advantages and potential in extracting clinical concepts. Our results indicate that a well-designed rule-based clinical NLP system is capable of achieving good performance on cohort selection even with a small training data set. In addition, the investigation of a Unified Medical Language System-based general cNLP system suggests that a hybrid system combining these 2 approaches is promising to surpass the state-of-the-art performance.

Natural language processing of radiology reports for identification of skeletal site-specific fractures

BackgroundOsteoporosis has become an important public health issue. Most of the population, particularly elderly people, are at some degree of risk of osteoporosis-related fractures. Accurate identification and surveillance of patient populations with fractures has a significant impact on reduction of cost of care by preventing future fractures and its corresponding complications.MethodsIn this study, we developed a rule-based natural language processing (NLP) algorithm for identification of twenty skeletal site-specific fractures from radiology reports. The rule-based NLP algorithm was based on regular expressions developed using MedTagger, an NLP tool of the Apache Unstructured Information Management Architecture (UIMA) pipeline to facilitate information extraction from clinical narratives. Radiology notes were retrieved from the Mayo Clinic electronic health records data warehouse. We developed rules for identifying each fracture type according to physicians’ knowledge and experience, and refined these rules via verification with physicians. This study was approved by the institutional review board (IRB) for human subject research.ResultsWe validated the NLP algorithm using the radiology reports of a community-based cohort at Mayo Clinic with the gold standard constructed by medical experts. The micro-averaged results of sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1-score of the proposed NLP algorithm are 0.930, 1.0, 1.0, 0.941, 0.961, respectively. The F1-score is 1.0 for 8 fractures, and above 0.9 for a total of 17 out of 20 fractures (85%).ConclusionsThe results verified the effectiveness of the proposed rule-based NLP algorithm in automatic identification of osteoporosis-related skeletal site-specific fractures from radiology reports. The NLP algorithm could be utilized to accurately identify the patients with fractures and those who are also at high risk of future fractures due to osteoporosis. Appropriate care interventions to those patients, not only the most at-risk patients but also those with emerging risk, would significantly reduce future fractures.

A natural language processing algorithm to extract characteristics of subdural hematoma from head CT reports.

Subdural hematoma (SDH) is the most common form of traumatic intracranial hemorrhage, and radiographic characteristics of SDH are predictive of complications and patient outcomes. We created a natural language processing (NLP) algorithm to extract structured data from cranial computed tomography (CT) scan reports for patients with SDH. CT scan reports from patients with SDH were collected from a single center. All reports were based on cranial CT scan interpretations by board-certified attending radiologists. Reports were then coded by a pair of physicians for four variables: number of SDH, size of midline shift, thickness of largest SDH, and side of largest SDH. Inter-rater reliability was assessed. The annotated reports were divided into training (80%) and test (20%) datasets. Relevant information was extracted from text using a pattern-matching approach, due to the lack of a mention-level gold-standard corpus. Then, the NLP pipeline components were integrated using the Apache Unstructured Information Management Architecture. Output performance was measured as algorithm accuracy compared to the data coded by the two ED physicians. A total of 643 scans were extracted. The NLP algorithm accuracy was high: 0.84 for side of largest SDH, 0.88 for thickness of largest SDH, and 0.92 for size of midline shift. A NLP algorithm can structure key data from non-contrast head CT reports with high accuracy. The NLP is a potential tool to detect important radiographic findings from electronic health records, and, potentially, add decision support capabilities.

Argo as a platform for integrating distinct biodiversity analytics tools into workflows for building graph databases

Together with the increasingly growing amount of available data on biodiversity comes the proliferation of various informatics tools aimed at the collection, management and analysis of biodiversity-relevant knowledge. Consequently, we have seen how several data formats and programming languages or environments have come into use, giving rise to a problem in interoperability should anyone wish to combine the outputs of distinct tools, or to integrate them into one solution. Argo (Rak et al. 2012), an online text mining workbench based on the Unstructured Information Management Architecture (UIMA) interoperability standard, offers a means for seamlessly unifying various tools and resources into customisable text processing workflows. Among many other features, Argo provides: (1) a library of diverse tools, i.e., UIMA components, each of which is dedicated to a specific task such as loading datasets or gazetteers of interest (e.g., the Biodiversity Term Inventory), recognition of species names and their semantically related terms (Nguyen et al. 2017); (2) a graphical interface for designing workflows using components as building blocks; (3) an environment for executing and monitoring the progress of workflows; and (4) a user-interactive annotation editor for manually revising or validating results of automated processing. Recently, Argo has been extended to provide support for incorporating into workflows external web services conforming with the Representational State Transfer (REST) protocol. Taking advantage of these features, we demonstrate how we combine in-house tools and resources for named entity recognition (Batista-Navarro et al. 2017) with externally developed ones, e.g., EXTRACT (Pafilis et al. 2016), in order to build text mining workflows for populating neo4j graph databases with biodiversity-relevant knowledge. To provide a few exemplars, we focus on use cases that seek to leverage various sources of literature to capture fine-grained information on the habitat and reproductive conditions of: (1) a subset of plants catalogued in World Flora Online (Jackson and Miller 2015), and (2) tropical trees belonging to the Dipterocarpaceae family.

Integrating UIMA annotators in a web-based text processing framework.

The Unstructured Information Management Architecture (UIMA) [1] framework is a growing platform for natural language processing (NLP) applications. However, such applications may be difficult for non-technical users deploy. This project presents a web-based framework that wraps UIMA-based annotator systems into a graphical user interface for researchers and clinicians, and a web service for developers. An annotator that extracts data elements from lung cancer radiology reports is presented to illustrate the use of the system. Annotation results from the web system can be exported to multiple formats for users to utilize in other aspects of their research and workflow. This project demonstrates the benefits of a lay-user interface for complex NLP applications. Efforts such as this can lead to increased interest and support for NLP work in the clinical domain.

Unstructured Social Media Data Mining System Based on Emotional Database and Unstructured Information Management Architecture Framework

Unstructured Social Media Data Mining System Based on Emotional Database and Unstructured Information Management Architecture Framework

Congestive heart failure information extraction framework for automated treatment performance measures assessment.

This paper describes a new congestive heart failure (CHF) treatment performance measure information extraction system - CHIEF - developed as part of the Automated Data Acquisition for Heart Failure project, a Veterans Health Administration project aiming at improving the detection of patients not receiving recommended care for CHF. CHIEF is based on the Apache Unstructured Information Management Architecture framework, and uses a combination of rules, dictionaries, and machine learning methods to extract left ventricular function mentions and values, CHF medications, and documented reasons for a patient not receiving these medications. The training and evaluation of CHIEF were based on subsets of a reference standard of various clinical notes from 1083 Veterans Health Administration patients. Domain experts manually annotated these notes to create our reference standard. Metrics used included recall, precision, and the F 1 -measure. In general, CHIEF extracted CHF medications with high recall (>0.990) and good precision (0.960-0.978). Mentions of Left Ventricular Ejection Fraction were also extracted with high recall (0.978-0.986) and precision (0.986-0.994), and quantitative values of Left Ventricular Ejection Fraction were found with 0.910-0.945 recall and with high precision (0.939-0.976). Reasons for not prescribing CHF medications were more difficult to extract, only reaching fair accuracy with about 0.310-0.400 recall and 0.250-0.320 precision. This study demonstrated that applying natural language processing to unlock the rich and detailed clinical information found in clinical narrative text notes makes fast and scalable quality improvement approaches possible, eventually improving management and outpatient treatment of patients suffering from CHF.

Efficient identification of nationally mandated reportable cancer cases using natural language processing and machine learning.

To help cancer registrars efficiently and accurately identify reportable cancer cases. The Cancer Registry Control Panel (CRCP) was developed to detect mentions of reportable cancer cases using a pipeline built on the Unstructured Information Management Architecture - Asynchronous Scaleout (UIMA-AS) architecture containing the National Library of Medicine's UIMA MetaMap annotator as well as a variety of rule-based UIMA annotators that primarily act to filter out concepts referring to nonreportable cancers. CRCP inspects pathology reports nightly to identify pathology records containing relevant cancer concepts and combines this with diagnosis codes from the Clinical Electronic Data Warehouse to identify candidate cancer patients using supervised machine learning. Cancer mentions are highlighted in all candidate clinical notes and then sorted in CRCP's web interface for faster validation by cancer registrars. CRCP achieved an accuracy of 0.872 and detected reportable cancer cases with a precision of 0.843 and a recall of 0.848. CRCP increases throughput by 22.6% over a baseline (manual review) pathology report inspection system while achieving a higher precision and recall. Depending on registrar time constraints, CRCP can increase recall to 0.939 at the expense of precision by incorporating a data source information feature. CRCP demonstrates accurate results when applying natural language processing features to the problem of detecting patients with cases of reportable cancer from clinical notes. We show that implementing only a portion of cancer reporting rules in the form of regular expressions is sufficient to increase the precision, recall, and speed of the detection of reportable cancer cases when combined with off-the-shelf information extraction software and machine learning.

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

BackgroundChemical 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.ResultsWe 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.

Anatomic and advanced adenoma detection rates as quality metrics determined via natural language processing.

The objectives of this study were to use an open-source natural language-processing tool (NLP) to accurately assess total, anatomic (left and right colon), and advanced adenoma detection rates (ADRs) and to determine how these metrics differ between high- and low-performing endoscopists. An NLP tool was developed using the Apache Unstructured Information Management Architecture and queried all procedure records for screening colonoscopies performed in patients aged 50-75 years at a single institution from April 1998 to December 2013. Validation was performed on 200 procedures and associated pathology reports. The total, left colon, right colon, and advanced ADRs were calculated and physicians were stratified by total ADR (<20% and ≥20%). Comparisons of colonoscopy characteristics and ADR comparisons (advanced, left, right, and right/left ratio) were determined by t-tests and Wilcoxon rank-sum tests. The total ADR for 34,998 screening colonoscopies from 1998 to 2013 was 20.3%, as determined via NLP. The institutional left and right colon ADRs were 10.1% and 12.5%, respectively. The overall advanced ADR was 4.4%. Endoscopists with total ADRs ≥20% had higher left (12.4%) and right colon (16.4%) ADRs than endoscopists with ADRs <20% (left ADR=5.6%, right ADR=5.8%). Endoscopists with ADRs ≥20% had higher individual right/left ADR ratios than those with low ADRs (1.4 (interquartile range (IQR) 0.4) vs. 1.0 (IQR 0.4), P=0.02). There was a moderate positive correlation between advanced ADR detection and both right (Spearman's rho=0.5, P=0.05) and left colon (Spearman's rho=0.4, P=0.03) ADRs. Institutions should consider the use of anatomic and advanced ADRs determined via natural language processing as a refined measure of colonoscopy quality. The ability to continuously monitor and provide feedback on colonoscopy quality metrics may encourage endoscopists to refine technique, resulting in overall improvements in adenoma detection.

An Unstructured Information Management Architecture Approach to Text Analytics of Cancer Blogs

In this research the authors explore the potential of the Unstructured Information Management Architecture (UIMA) platform in text analytics of cancer blogs. The application is developed using the UIMA open source platform. They use the text analytics methods of categorization, clustering, taxonomic classification, and others to identify and analyze the patterns in cancer blog postings. The authors establish a comprehensive UIMA methodology for developing text analytics applications for the analysis of cancer blogs. Additional insights are extracted through the development of categories or keywords contained in the blogs, the development of a taxonomy and the examination of relationships among the categories. The application has the potential for generalizability and implementation with health content in other blogs and social media. It has the potential to provide insight and decision support for cancer management and to facilitate the efficient and relevant search for information on cancer.

MedXN: an open source medication extraction and normalization tool for clinical text.

We developed the Medication Extraction and Normalization (MedXN) system to extract comprehensive medication information and normalize it to the most appropriate RxNorm concept unique identifier (RxCUI) as specifically as possible. Medication descriptions in clinical notes were decomposed into medication name and attributes, which were separately extracted using RxNorm dictionary lookup and regular expression. Then, each medication name and its attributes were combined together according to RxNorm convention to find the most appropriate RxNorm representation. To do this, we employed serialized hierarchical steps implemented in Apache's Unstructured Information Management Architecture. We also performed synonym expansion, removed false medications, and employed inference rules to improve the medication extraction and normalization performance. An evaluation on test data of 397 medication mentions showed F-measures of 0.975 for medication name and over 0.90 for most attributes. The RxCUI assignment produced F-measures of 0.932 for medication name and 0.864 for full medication information. Most false negative RxCUI assignments in full medication information are due to human assumption of missing attributes and medication names in the gold standard. The MedXN system (http://sourceforge.net/projects/ohnlp/files/MedXN/) was able to extract comprehensive medication information with high accuracy and demonstrated good normalization capability to RxCUI as long as explicit evidence existed. More sophisticated inference rules might result in further improvements to specific RxCUI assignments for incomplete medication descriptions.

CODA: Computer-aided ontology development architecture

This paper introduces CODA (Computer-aided Ontology Development Architecture), which is both an architecture and an associated framework supporting the transformation of unstructured and semi-structured content into RDF (Resource Description Framework) datasets. The purpose of CODA is to support the entire process that ranges from data extraction and transformation to identity resolution. The final objective is to feed semantic repositories with knowledge extracted from unstructured content. The motivation behind CODA lies in the large effort and design issues required for developing knowledge acquisition systems using content analytics frameworks such as UIMA™ (Unstructured Information Management Architecture) and GATE (General Architecture for Text Engineering). Therefore, CODA extends UIMA with facilities and a powerful language for projection and transformation of UIMA-annotated content into RDF. The proposed platform is oriented towards a wide range of beneficiaries, from semantic applications developers to final users that can easily plug CODA components into compliant desktop tools. We describe and discuss the features of CODA through the article, and we conclude by reporting on the adoption of the CODA framework in the context of a usage scenario, related to knowledge acquisition in the agricultural domain.

Classify the Search Result Based on IBM OminiFind Edition and UIMA

A method is proposed which uses the IBM OmniFind Enterprise Edition combined with IBM open source of unstructured information management architecture of Unstructured Information Management Architecture (UIMA), to realize the IBM OmniFind Enterprise Edition semantic search engine search and result classification. This method makes the search space and function more widely, which can not only meet the higher demand of the part of the user, but also increase the competitiveness of the client application.

Comprehensive temporal information detection from clinical text: medical events, time, and TLINK identification

Temporal information detection systems have been developed by the Mayo Clinic for the 2012 i2b2 Natural Language Processing Challenge. To construct automated systems for EVENT/TIMEX3 extraction and temporal link (TLINK) identification from clinical text. The i2b2 organizers provided 190 annotated discharge summaries as the training set and 120 discharge summaries as the test set. Our Event system used a conditional random field classifier with a variety of features including lexical information, natural language elements, and medical ontology. The TIMEX3 system employed a rule-based method using regular expression pattern match and systematic reasoning to determine normalized values. The TLINK system employed both rule-based reasoning and machine learning. All three systems were built in an Apache Unstructured Information Management Architecture framework. Our TIMEX3 system performed the best (F-measure of 0.900, value accuracy 0.731) among the challenge teams. The Event system produced an F-measure of 0.870, and the TLINK system an F-measure of 0.537. Our TIMEX3 system demonstrated good capability of regular expression rules to extract and normalize time information. Event and TLINK machine learning systems required well-defined feature sets to perform well. We could also leverage expert knowledge as part of the machine learning features to further improve TLINK identification performance.

Research on BIM-based Construction Domain Text Information Management

Construction project produces a large amount of unstructured information throughout the whole lifecycle, most of them is text information. Building information modeling (BIM) can support lifecycle information management of construction project, so BIM-based construction domain text information integration management can improve the efficiency and quality of project management to a large extent. The concept of BIM and its implementation platform, as well as the data exchange standard, i.e. industry foundation class (IFC), are introduced firstly. Then this paper puts forward a systematic unstructured construction domain text information management system framework, and the implementation of BIM-based text information integration methodology: the unstructured text information is transformed to structured information by means of text mining to facilitate information retrieval and ranking; then the text information is classified according to the IFC standard, and is associated with entities in BIM to realize the integration of text information and BIM. Finally, this paper takes contract document as an example for verification. The proposed method can improve text information management ability and efficiency of construction domain.

A common type system for clinical natural language processing

BackgroundOne challenge in reusing clinical data stored in electronic medical records is that these data are heterogenous. Clinical Natural Language Processing (NLP) plays an important role in transforming information in clinical text to a standard representation that is comparable and interoperable. Information may be processed and shared when a type system specifies the allowable data structures. Therefore, we aim to define a common type system for clinical NLP that enables interoperability between structured and unstructured data generated in different clinical settings.ResultsWe describe a common type system for clinical NLP that has an end target of deep semantics based on Clinical Element Models (CEMs), thus interoperating with structured data and accommodating diverse NLP approaches. The type system has been implemented in UIMA (Unstructured Information Management Architecture) and is fully functional in a popular open-source clinical NLP system, cTAKES (clinical Text Analysis and Knowledge Extraction System) versions 2.0 and later.ConclusionsWe have created a type system that targets deep semantics, thereby allowing for NLP systems to encapsulate knowledge from text and share it alongside heterogenous clinical data sources. Rather than surface semantics that are typically the end product of NLP algorithms, CEM-based semantics explicitly build in deep clinical semantics as the point of interoperability with more structured data types.

Automated extraction of ejection fraction for quality measurement using regular expressions in Unstructured Information Management Architecture (UIMA) for heart failure

Left ventricular ejection fraction (EF) is a key component of heart failure quality measures used within the Department of Veteran Affairs (VA). Our goals were to build a natural language processing system to extract the EF from free-text echocardiogram reports to automate measurement reporting and to validate the accuracy of the system using a comparison reference standard developed through human review. This project was a Translational Use Case Project within the VA Consortium for Healthcare Informatics. We created a set of regular expressions and rules to capture the EF using a random sample of 765 echocardiograms from seven VA medical centers. The documents were randomly assigned to two sets: a set of 275 used for training and a second set of 490 used for testing and validation. To establish the reference standard, two independent reviewers annotated all documents in both sets; a third reviewer adjudicated disagreements. System test results for document-level classification of EF of <40% had a sensitivity (recall) of 98.41%, a specificity of 100%, a positive predictive value (precision) of 100%, and an F measure of 99.2%. System test results at the concept level had a sensitivity of 88.9% (95% CI 87.7% to 90.0%), a positive predictive value of 95% (95% CI 94.2% to 95.9%), and an F measure of 91.9% (95% CI 91.2% to 92.7%). An EF value of <40% can be accurately identified in VA echocardiogram reports. An automated information extraction system can be used to accurately extract EF for quality measurement.