Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Natural Language Processing”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 235 records · Page 13Linked to original sources
PubMed2021

Automated Extraction of Tumor Staging and Diagnosis Information From Surgical Pathology Reports.

PURPOSE: Typically stored as unstructured notes, surgical pathology reports contain data elements valuable to cancer research that require labor-intensive manual extraction. Although studies have described natural language processing (NLP) of surgical pathology reports to automate information extraction, efforts have focused on specific cancer subtypes rather than across multiple oncologic domains. To address this gap, we developed and evaluated an NLP method to extract tumor staging and diagnosis information across multiple cancer subtypes. METHODS: The NLP pipeline was implemented on an open-source framework called Leo. We used a total of 555,681 surgical pathology reports of 329,076 patients to develop the pipeline and evaluated our approach on subsets of reports from patients with breast, prostate, colorectal, and randomly selected cancer subtypes. RESULTS: Averaged across all four cancer subtypes, the NLP pipeline achieved an accuracy of 1.00 for International Classification of Diseases, Tenth Revision codes, 0.89 for T staging, 0.90 for N staging, and 0.97 for M staging. It achieved an F1 score of 1.00 for International Classification of Diseases, Tenth Revision codes, 0.88 for T staging, 0.90 for N staging, and 0.24 for M staging. CONCLUSION: The NLP pipeline was developed to extract tumor staging and diagnosis information across multiple cancer subtypes to support the research enterprise in our institution. Although it was not possible to demonstrate generalizability of our NLP pipeline to other institutions, other institutions may find value in adopting a similar NLP approach-and reusing code available at GitHub-to support the oncology research enterprise with elements extracted from surgical pathology reports.

Humans↗
PubMed1993

Generic queries for meeting clinical information needs.

This paper describes a model for automated information retrieval in which questions posed by clinical users are analyzed to establish common syntactic and semantic patterns. The patterns are used to develop a set of general-purpose questions called generic queries. These generic queries are used in responding to specific clinical information needs. Users select generic queries in one of two ways. The user may type in questions, which are then analyzed, using natural language processing techniques, to identify the most relevant generic query; or the user may indicate patient data of interest and then pick one of several potentially relevant questions. Once the query and medical concepts have been determined, an information source is selected automatically, a retrieval strategy is composed and executed, and the results are sorted and filtered for presentation to the user. This work makes extensive use of the National Library of Medicine's Unified Medical Language System (UMLS): medical concepts are derived from the Metathesaurus, medical queries are based on semantic relations drawn from the UMLS Semantic Network, and automated source selection makes use of the Information Sources Map. The paper describes research currently under way to implement this model and reports on experience and results to date.

Algorithms↗
PubMed2003

Mining terminological knowledge in large biomedical corpora.

Terminological knowledge of the biomedical domain is important for natural language processing (NLP) and information retrieval (IR) applications, and a number of terminological knowledge sources, such as LocusLink, GeneBank, and the UMLS, already exist. However, because of the tremendous amount of research activity in the field, new terms and symbols are continually being created, many of which are published in the literature, but are not available in any of the other resources. Therefore, effective mining of the literature for new terminology is critical for furthering NLP and IR applications. Abbreviations are widely used in the biomedical domain, and the understanding of abbreviations requires a terminological knowledge base that consists of abbreviations with their associated senses. In previous work, several methods have been developed for automatic construction of abbreviation knowledge bases from parenthetical expressions. However, these methods pair abbreviations and their expansions based on manually crafted patterns or rules. In this paper, we propose an automatic method, which is not based on patterns or rules but is based on the use of collocations, to extract a set of related terms from parenthetical expressions including abbreviations associated with their expansions and other types of related terms such as synonyms, or hyponyms etc. Our method is based on the observation that terms associated with parenthetical expressions i) are usually related, and ii) are often collocations because they tend to co-occur more often than expected by chance. Our method was applied to the collection of MEDLINE abstracts. The method and the results were evaluated using two collections: Berman's handcrafted abbreviation list and the LocusLink collection.

Abstracting and Indexing↗
PubMed1998

Conceptual graph grammar--a simple formalism for sublanguage.

There are a wide variety of computer applications that deal with various aspects of medical language: concept representation, controlled vocabulary, natural language processing, and information retrieval. While technical and theoretical methods appear to differ, all approaches investigate different aspects of the same phenomenon: medical sublanguage. This paper surveys the properties of medical sublanguage from a formal perspective, based on detailed analyses cited in the literature. A review of several computer systems based on sublanguage approaches shows some of the difficulties in addressing the interaction between the syntactic and semantic aspects of sublanguage. A formalism called Conceptual Graph Grammar is presented that attempts to combine both syntax and semantics into a single notation by extending standard Conceptual Graph notation. Examples from the domain of pathology diagnoses are provided to illustrate the use of this formalism in medical language analysis. The strengths and weaknesses of the approach are then considered. Conceptual Graph Grammar is an attempt to synthesize the common properties of different approaches to sublanguage into a single formalism, and to begin to define a common foundation for language-related research in medical informatics.

Computer Graphics↗
PubMed2001

Meeting medical terminology needs--the Ontology-Enhanced Medical Concept Mapper.

This paper describes the development and testing of the Medical Concept Mapper, a tool designed to facilitate access to online medical information sources by providing users with appropriate medical search terms for their personal queries. Our system is valuable for patients whose knowledge of medical vocabularies is inadequate to find the desired information, and for medical experts who search for information outside their field of expertise. The Medical Concept Mapper maps synonyms and semantically related concepts to a user's query. The system is unique because it integrates our natural language processing tool, i.e., the Arizona (AZ) Noun Phraser, with human-created ontologies, the Unified Medical Language System (UMLS) and WordNet, and our computer generated Concept Space, into one system. Our unique contribution results from combining the UMLS Semantic Net with Concept Space in our deep semantic parsing (DSP) algorithm. This algorithm establishes a medical query context based on the UMLS Semantic Net, which allows Concept Space terms to be filtered so as to isolate related terms relevant to the query. We performed two user studies in which Medical Concept Mapper terms were compared against human experts' terms. We conclude that the AZ Noun Phraser is well suited to extract medical phrases from user queries, that WordNet is not well suited to provide strictly medical synonyms, that the UMLS Metathesaurus is well suited to provide medical synonyms, and that Concept Space is well suited to provide related medical terms, especially when these terms are limited by our DSP algorithm.

Algorithms↗
PubMed2005

Application of latent semantic analysis to protein remote homology detection.

MOTIVATION: Remote homology detection between protein sequences is a central problem in computational biology. The discriminative method such as the support vector machine (SVM) is one of the most effective methods. Many of the SVM-based methods focus on finding useful representations of protein sequence, using either explicit feature vector representations or kernel functions. Such representations may suffer from the peaking phenomenon in many machine-learning methods because the features are usually very large and noise data may be introduced. Based on these observations, this research focuses on feature extraction and efficient representation of protein vectors for SVM protein classification. RESULTS: In this study, a latent semantic analysis (LSA) model, which is an efficient feature extraction technique from natural language processing, has been introduced in protein remote homology detection. Several basic building blocks of protein sequences have been investigated as the 'words' of 'protein sequence language', including N-grams, patterns and motifs. Each protein sequence is taken as a 'document' that is composed of bags-of-word. The word-document matrix is constructed first. The LSA is performed on the matrix to produce the latent semantic representation vectors of protein sequences, leading to noise-removal and smart description of protein sequences. The latent semantic representation vectors are then evaluated by SVM. The method is tested on the SCOP 1.53 database. The results show that the LSA model significantly improves the performance of remote homology detection in comparison with the basic formalisms. Furthermore, the performance of this method is comparable with that of the complex kernel methods such as SVM-LA and better than that of other sequence-based methods such as PSI-BLAST and SVM-pairwise.

Algorithms↗
PubMed2005

Domain-specific language models and lexicons for tagging.

Accurate and reliable part-of-speech tagging is useful for many Natural Language Processing (NLP) tasks that form the foundation of NLP-based approaches to information retrieval and data mining. In general, large annotated corpora are necessary to achieve desired part-of-speech tagger accuracy. We show that a large annotated general-English corpus is not sufficient for building a part-of-speech tagger model adequate for tagging documents from the medical domain. However, adding a quite small domain-specific corpus to a large general-English one boosts performance to over 92% accuracy from 87% in our studies. We also suggest a number of characteristics to quantify the similarities between a training corpus and the test data. These results give guidance for creating an appropriate corpus for building a part-of-speech tagger model that gives satisfactory accuracy results on a new domain at a relatively small cost.

Humans↗
PubMed2006

Machine learning and word sense disambiguation in the biomedical domain: design and evaluation issues.

BACKGROUND: Word sense disambiguation (WSD) is critical in the biomedical domain for improving the precision of natural language processing (NLP), text mining, and information retrieval systems because ambiguous words negatively impact accurate access to literature containing biomolecular entities, such as genes, proteins, cells, diseases, and other important entities. Automated techniques have been developed that address the WSD problem for a number of text processing situations, but the problem is still a challenging one. Supervised WSD machine learning (ML) methods have been applied in the biomedical domain and have shown promising results, but the results typically incorporate a number of confounding factors, and it is problematic to truly understand the effectiveness and generalizability of the methods because these factors interact with each other and affect the final results. Thus, there is a need to explicitly address the factors and to systematically quantify their effects on performance. RESULTS: Experiments were designed to measure the effect of "sample size" (i.e. size of the datasets), "sense distribution" (i.e. the distribution of the different meanings of the ambiguous word) and "degree of difficulty" (i.e. the measure of the distances between the meanings of the senses of an ambiguous word) on the performance of WSD classifiers. Support Vector Machine (SVM) classifiers were applied to an automatically generated data set containing four ambiguous biomedical abbreviations: BPD, BSA, PCA, and RSV, which were chosen because of varying degrees of differences in their respective senses. Results showed that: 1) increasing the sample size generally reduced the error rate, but this was limited mainly to well-separated senses (i.e. cases where the distances between the senses were large); in difficult cases an unusually large increase in sample size was needed to increase performance slightly, which was impractical, 2) the sense distribution did not have an effect on performance when the senses were separable, 3) when there was a majority sense of over 90%, the WSD classifier was not better than use of the simple majority sense, 4) error rates were proportional to the similarity of senses, and 5) there was no statistical difference between results when using a 5-fold or 10-fold cross-validation method. Other issues that impact performance are also enumerated. CONCLUSION: Several different independent aspects affect performance when using ML techniques for WSD. We found that combining them into one single result obscures understanding of the underlying methods. Although we studied only four abbreviations, we utilized a well-established statistical method that guarantees the results are likely to be generalizable for abbreviations with similar characteristics. The results of our experiments show that in order to understand the performance of these ML methods it is critical that papers report on the baseline performance, the distribution and sample size of the senses in the datasets, and the standard deviation or confidence intervals. In addition, papers should also characterize the difficulty of the WSD task, the WSD situations addressed and not addressed, as well as the ML methods and features used. This should lead to an improved understanding of the generalizablility and the limitations of the methodology.

Algorithms↗
PubMed2006

Exploring supervised and unsupervised methods to detect topics in biomedical text.

BACKGROUND: Topic detection is a task that automatically identifies topics (e.g., "biochemistry" and "protein structure") in scientific articles based on information content. Topic detection will benefit many other natural language processing tasks including information retrieval, text summarization and question answering; and is a necessary step towards the building of an information system that provides an efficient way for biologists to seek information from an ocean of literature. RESULTS: We have explored the methods of Topic Spotting, a task of text categorization that applies the supervised machine-learning technique naïve Bayes to assign automatically a document into one or more predefined topics; and Topic Clustering, which apply unsupervised hierarchical clustering algorithms to aggregate documents into clusters such that each cluster represents a topic. We have applied our methods to detect topics of more than fifteen thousand of articles that represent over sixteen thousand entries in the Online Mendelian Inheritance in Man (OMIM) database. We have explored bag of words as the features. Additionally, we have explored semantic features; namely, the Medical Subject Headings (MeSH) that are assigned to the MEDLINE records, and the Unified Medical Language System (UMLS) semantic types that correspond to the MeSH terms, in addition to bag of words, to facilitate the tasks of topic detection. Our results indicate that incorporating the MeSH terms and the UMLS semantic types as additional features enhances the performance of topic detection and the naïve Bayes has the highest accuracy, 66.4%, for predicting the topic of an OMIM article as one of the total twenty-five topics. CONCLUSION: Our results indicate that the supervised topic spotting methods outperformed the unsupervised topic clustering; on the other hand, the unsupervised topic clustering methods have the advantages of being robust and applicable in real world settings.

Abstracting and Indexing↗
PubMed2006

Measures of semantic similarity and relatedness in the biomedical domain.

Measures of semantic similarity between concepts are widely used in Natural Language Processing. In this article, we show how six existing domain-independent measures can be adapted to the biomedical domain. These measures were originally based on WordNet, an English lexical database of concepts and relations. In this research, we adapt these measures to the SNOMED-CT ontology of medical concepts. The measures include two path-based measures, and three measures that augment path-based measures with information content statistics from corpora. We also derive a context vector measure based on medical corpora that can be used as a measure of semantic relatedness. These six measures are evaluated against a newly created test bed of 30 medical concept pairs scored by three physicians and nine medical coders. We find that the medical coders and physicians differ in their ratings, and that the context vector measure correlates most closely with the physicians, while the path-based measures and one of the information content measures correlates most closely with the medical coders. We conclude that there is a role both for more flexible measures of relatedness based on information derived from corpora, as well as for measures that rely on existing ontological structures.

Database Management Systems↗
PubMed2005

Improved identification of noun phrases in clinical radiology reports using a high-performance statistical natural language parser augmented with the UMLS specialist lexicon.

OBJECTIVE: The aim of this study was to develop and evaluate a method of extracting noun phrases with full phrase structures from a set of clinical radiology reports using natural language processing (NLP) and to investigate the effects of using the UMLS(R) Specialist Lexicon to improve noun phrase identification within clinical radiology documents. DESIGN: The noun phrase identification (NPI) module is composed of a sentence boundary detector, a statistical natural language parser trained on a nonmedical domain, and a noun phrase (NP) tagger. The NPI module processed a set of 100 XML-represented clinical radiology reports in Health Level 7 (HL7)(R) Clinical Document Architecture (CDA)-compatible format. Computed output was compared with manual markups made by four physicians and one author for maximal (longest) NP and those made by one author for base (simple) NP, respectively. An extended lexicon of biomedical terms was created from the UMLS Specialist Lexicon and used to improve NPI performance. RESULTS: The test set was 50 randomly selected reports. The sentence boundary detector achieved 99.0% precision and 98.6% recall. The overall maximal NPI precision and recall were 78.9% and 81.5% before using the UMLS Specialist Lexicon and 82.1% and 84.6% after. The overall base NPI precision and recall were 88.2% and 86.8% before using the UMLS Specialist Lexicon and 93.1% and 92.6% after, reducing false-positives by 31.1% and false-negatives by 34.3%. CONCLUSION: The sentence boundary detector performs excellently. After the adaptation using the UMLS Specialist Lexicon, the statistical parser's NPI performance on radiology reports increased to levels comparable to the parser's native performance in its newswire training domain and to that reported by other researchers in the general nonmedical domain.

Abstracting and Indexing↗
PubMed1997

Galen-In-Use: an EU Project applied to the development of a new national coding system for surgical procedures: NCAM.

GALEN has developed a language independent common reference model based on a medically oriented ontology and practical tools and techniques for managing healthcare terminology including natural language processing. GALEN-IN-USE is the current phase which applied the modelling and the tools to the development or the updating of coding systems for surgical procedures in different national coding centre co-operating within the European Federation of Coding Centre (EFCC) to create a multilingual knowledge repository for multicultural Europe. NCAM (Nomenclature Commune des Actes Médicaux) is the new French multipurpose coding system for surgical procedures. The labels are processed from the intermediate dissections to the Grail representation and the natural language generation by the electronically related Medical Informatics research centres network of Saint Etienne, Manchester, Geneva and Nijmegen. The national coding centre is able to retrieve the initial labels with different categories of concepts, to compare the professional language proposed by expert clinicians to the French generated controlled vocabulary and to finalize the linguistic labels of the coding system in relation with the meanings of the conceptual system structure.

Electronic Data Processing↗
PubMed1998

Hemispheric specialization for English and ASL: left invariance-right variability.

Functional magnetic resonance imaging (fMRI) was used to compare the cerebral organization during sentence processing in English and in American sign language (ASL). Classical language areas within the left hemisphere were recruited by both English in native speakers and ASL in native signers. This suggests a bias of the left hemisphere to process natural languages independently of the modality through which language is perceived. Furthermore, in contrast to English, ASL strongly recruited right hemisphere structures. This was true irrespective of whether the native signers were deaf or hearing. Thus, the specific processing requirements of the language also in part determine the organization of the language systems of the brain.

Adult↗
PubMed2000

The virtual standardized patient. Simulated patient-practitioner dialog for patient interview training.

We describe the Virtual Standardized Patient (VSP) application, having a computerized virtual person who interacts with medical practitioners in much the same way as actors hired to teach and evaluate patient assessment, diagnosis, and interviewing skills. The VSP integrates technologies from two successful research projects conducted at Research Triangle Institute. AVATALK provides natural language processing, emotion and behavior modeling, and composite facial expression and lip-shape modeling for a natural patient-practitioner dialog. Trauma Patient Simulator provides case-based patient history and trauma casualty data, real-time physiological modeling, interactive patient assessment, 3-D scenario simulation, and instructional record-keeping capabilities. The VSP offers training benefits that include enhanced adaptability, availability, and assessment.

Communication↗
PubMed1995

Integration of speech with natural language understanding.

The integration of speech recognition with natural language understanding raises issues of how to adapt natural language processing to the characteristics of spoken language; how to cope with errorful recognition output, including the use of natural language information to reduce recognition errors; and how to use information from the speech signal, beyond just the sequence of words, as an aid to understanding. This paper reviews current research addressing these questions in the Spoken Language Program sponsored by the Advanced Research Projects Agency (ARPA). I begin by reviewing some of the ways that spontaneous spoken language differs from standard written language and discuss methods of coping with the difficulties of spontaneous speech. I then look at how systems cope with errors in speech recognition and at attempts to use natural language information to reduce recognition errors. Finally, I discuss how prosodic information in the speech signal might be used to improve understanding.

Cognition↗
PubMed1995

Voice-processing technologies--their application in telecommunications.

As the telecommunications industry evolves over the next decade to provide the products and services that people will desire, several key technologies will become commonplace. Two of these, automatic speech recognition and text-to-speech synthesis, will provide users with more freedom on when, where, and how they access information. While these technologies are currently in their infancy, their capabilities are rapidly increasing and their deployment in today's telephone network is expanding. The economic impact of just one application, the automation of operator services, is well over $100 million per year. Yet there still are many technical challenges that must be resolved before these technologies can be deployed ubiquitously in products and services throughout the worldwide telephone network. These challenges include: (i) High level of accuracy. The technology must be perceived by the user as highly accurate, robust, and reliable. (ii) Easy to use. Speech is only one of several possible input/output modalities for conveying information between a human and a machine, much like a computer terminal or Touch-Tone pad on a telephone. It is not the final product. Therefore, speech technologies must be hidden from the user. That is, the burden of using the technology must be on the technology itself. (iii) Quick prototyping and development of new products and services. The technology must support the creation of new products and services based on speech in an efficient and timely fashion. In this paper I present a vision of the voice-processing industry with a focus on the areas with the broadest base of user penetration: speech recognition, text-to-speech synthesis, natural language processing, and speaker recognition technologies. The current and future applications of these technologies in the telecommunications industry will be examined in terms of their strengths, limitations, and the degree to which user needs have been or have yet to be met. Although noteworthy gains have been made in areas with potentially small user bases and in the more mature speech-coding technologies, these subjects are outside the scope of this paper.

Automation↗
PubMed1997

SNOMED RT: a reference terminology for health care.

We describe the framework for SNOMED RT (Reference Terminology), designed to complement the broad coverage of medical concepts in SNOMED with a set of enhanced features that significantly increases its value as a reference terminology for representing clinical data. We describe what is meant by a reference terminology, and differentiate SNOMED RT from specialized terminologies that enable user interfaces, electronic messaging, or natural language processing, as well as from other specialized reference terminologies whose primary purpose is for representing data that is not primarily clinical in nature. We then describe how SNOMED RT represents multiple hierarchies and incorporates description logic. We believe that such a comprehensive set of concepts at multiple levels of granularity, with multiple logic-based subsumption hierarchies can meet the requirements of a reference terminology for health care.

Terminology as Topic↗
PubMed2003

The CardioOP-Data Clas (CDC). Development and application of a thesaurus for content management and multi-user teleteaching in cardiac surgery.

OBJECTIVES: Self-directed and customized medical education programs are gaining importance in health care instruction. We prototypically implemented a repository-driven online computer system (CardioOP) for teleteaching in Heart Surgery. It supports authoring and multiple re-use of multimedia data for different user groups in different instructional applications and therefore requires a process of content management. METHODS: We defined objectives for a terminological system to support semantic, cross-media type annotation and retrieval of learning objects: domain completeness, German (natural) language processing, multi-user concepts, extensibility and maintenance, content based annotation and technical implementation. Existing terminologies (ICD10, READ V3, Snomed III, UMLS 1997, MESH) have been analysed according to these objectives. RESULTS: We found that the analysed terminologies did not meet our criteria sufficiently. Therefore, we developed a domain-specific thesaurus, the CardioOP-DataClas (CDC). The application of the CDC within a database-driven authoring process using specifically developed tools is reported. CONCLUSIONS: Metadata play an important role in the effective discovery and search, access, integration and management of educational multimedia data in medicine but so far, there is no terminology to support content management for instructional multimedia. We prototypically designed and applied a thesaurus for the CardioOP educational system. Additional work is needed to evaluate the system in terms of user-friend-liness, concept coverage and information retrieval performance.

Cardiac Surgical Procedures↗