PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Natural Language Processing”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

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

At least 271 records · Page 15Linked to original sources
PubMed1995

Effective access to distributed heterogeneous medical text databases.

INQUERY is an advanced text information retrieval system developed by the Information Retrieval Laboratory of the University of Massachusetts in Amherst. It is based on Bayesian inference networks, which are probabilistic models for reasoning with multiple sources of uncertain evidence. The evidence, in this case, is the presence or absence of words and/or phrases in a document. Evidence is combined into belief that a document is relevant. The INQUERY retrieval engine has been developed with the support of ARPA, NSF, and industrial funding. It has a number of unique features and has achieved excellent results in the TIPSTER and TREC evaluations. Informatics research and application development using INQUERY has recently begun in the medical domain, including a new ARPA initiative concerned with clinical text. The features that we will focus on in this demonstration are: Automatic processing of natural language queries, including the extraction of phrases and specific medical concepts such as drug doses; Document selection through automatic relevance feedback and routing techniques, including the construction of complex queries using the INQUERY query language; The integration of conventional database techniques with text analysis and retrieval; Automatic thesaurus generation and query expansion using the PhraseFinder system; Distributed database access, including automatic database selection and merging of local searches; this will be demonstrated using a collection of medical databases; Retrieval based on passages, rather than whole documents.

Bayes Theorem↗
PubMed1996

Structured data entry in ORCA: the strengths of two models combined.

The capture of patient data in a structured format receives increasing attention. Data can be extracted from free text using natural language processing techniques, but it can also be collected in a structured fashion at the time of data entry. The latter has the advantage that completeness and unambiguity can be promoted by offering predefined terms and options for description of findings. The paper discusses two models for supporting structured data entry. In the direct model, there is an immediate relationship between the terms and options for data entry and the structure of the underlying database. In the indirect model, terms and options for data entry are based on a controlled vocabulary and not directly related to the structure in which actual data is represented. Both models have been utilized by ORCA (Open Record for CAre). We discuss the pros and cons of these two models in relation to the type of patient data and the task involved. It is concluded that a strategic combination of both models has more strengths and less weaknesses than the use of each model only.

Data Collection↗
PubMed2004

Really, is medical sublanguage that different? Experimental counter-evidence from tagging medical and newspaper corpora.

We compare the performance of two part-of-speech taggers trained on a German newspaper corpus for mixed types of medical documents. TnT, a tagger based on a statistical language model, outperforms Brill's rule-based tagger, and supplied with additional lexicon resources matches state-of-the-art performance figures (close to 97% accuracy) on the medical corpus. We explain this unexpected result by focusing on the statistically significant part-of-speech type overlap between the newspaper training set and the medical test set. At least at that level, sublanguage differences seem to vanish. Thus, statistical off-the-shelf part-of-speech taggers can immediately be reused for medical language processing

Natural Language Processing↗
PubMed1991

A Medical Text Analysis System for German--syntax analysis.

Much information about patients is stored in free text. Hence, the computerized processing of medical language data has been a well-known goal of medical informatics resulting in different paradigms. In Göttingen, a Medical Text Analysis System for German (abbr. MediTAS) has been under development for some time, trying to combine and to extend these paradigms. This article concentrates on the automated syntax analysis of German medical utterances. The investigated text material consists of 8,790 distinct utterances extracted from the summary sections of about 18,400 cytopathological findings reports. The parsing is based upon a new approach called Left-Associative Grammar (LAG) developed by Hausser. By extending considerably the LAG approach, most of the grammatical constructions occurring in the text material could be covered.

Electronic Data Processing↗
PubMed2004

Doublet method for very fast autocoding.

BACKGROUND: Autocoding (or automatic concept indexing) occurs when a software program extracts terms contained within text and maps them to a standard list of concepts contained in a nomenclature. The purpose of autocoding is to provide a way of organizing large documents by the concepts represented in the text. Because textual data accumulates rapidly in biomedical institutions, the computational methods used to autocode text must be very fast. The purpose of this paper is to describe the doublet method, a new algorithm for very fast autocoding. METHODS: An autocoder was written that transforms plain-text into intercalated word doublets (e.g. "The ciliary body produces aqueous humor" becomes "The ciliary, ciliary body, body produces, produces aqueous, aqueous humor"). Each doublet is checked against an index of doublets extracted from a standard nomenclature. Matching doublets are assigned a numeric code specific for each doublet found in the nomenclature. Text doublets that do not match the index of doublets extracted from the nomenclature are not part of valid nomenclature terms. Runs of matching doublets from text are concatenated and matched against nomenclature terms (also represented as runs of doublets). RESULTS: The doublet autocoder was compared for speed and performance against a previously published phrase autocoder. Both autocoders are Perl scripts, and both autocoders used an identical text (a 170+ Megabyte collection of abstracts collected through a PubMed search) and the same nomenclature (neocl.xml, containing over 102,271 unique names of neoplasms). In side-by-side comparison on the same computer, the doublet method autocoder was 8.4 times faster than the phrase autocoder (211 seconds versus 1,776 seconds). The doublet method codes 0.8 Megabytes of text per second on a desktop computer with a 1.6 GHz processor. In addition, the doublet autocoder successfully matched terms that were missed by the phrase autocoder, while the phrase autocoder found no terms that were missed by the doublet autocoder. CONCLUSIONS: The doublet method of autocoding is a novel algorithm for rapid text autocoding. The method will work with any nomenclature and will parse any ascii plain-text. An implementation of the algorithm in Perl is provided with this article. The algorithm, the Perl implementation, the neoplasm nomenclature, and Perl itself, are all open source materials.

Abstracting and Indexing↗
PubMedDate not supplied

A continuous-speech interface to a decision support system: I. Techniques to accommodate for misrecognized input.

OBJECTIVE: Develop a continuous-speech interface that allows flexible input of clinical findings into a medical diagnostic application. DESIGN: The authors' program allows users to enter clinical findings using their own vernacular. It displays from the diagnostic program's controlled vocabulary a list of terms that most closely matches the input, and allows the user to select the single best term. The interface program includes two components: a speech-recognition component that converts utterances into text strings, and a language-processing component that matches recognized text strings with controlled-vocabulary terms. The speech-recognition component is composed of commercially available speech-recognition hardware and software, and developer-created grammars, which specify the language to be recognized. The language-processing component is composed of a translator, which extracts a canonical form from both recognized text strings and controlled-vocabulary terms, and a matcher, which measures the similarity between the two canonical forms. RESULTS: The authors discovered that grammars constructed by a physician, who could anticipate how users might speak findings, supported speech recognition better than did grammars constructed programmatically from the controlled vocabulary. However, this programmatic method of grammar construction was more time efficient and better supported long-term maintenance of the grammars. The authors also found that language-processing techniques recovered some of the information lost due to speech misrecognition, but were dependent on the completeness of supporting synonym dictionaries. CONCLUSIONS: The authors' program demonstrated the feasibility of using continuous speech to enter findings into a medical application. However, improvements in speech-recognition technology and language-processing techniques are needed before natural continuous speech becomes an acceptable input modality for clinical applications.

Diagnosis, Computer-Assisted↗
PubMed2004

Extracting human protein interactions from MEDLINE using a full-sentence parser.

MOTIVATION: The living cell is a complex machine that depends on the proper functioning of its numerous parts, including proteins. Understanding protein functions and how they modify and regulate each other is the next great challenge for life-sciences researchers. The collective knowledge about protein functions and pathways is scattered throughout numerous publications in scientific journals. Bringing the relevant information together becomes a bottleneck in a research and discovery process. The volume of such information grows exponentially, which renders manual curation impractical. As a viable alternative, automated literature processing tools could be employed to extract and organize biological data into a knowledge base, making it amenable to computational analysis and data mining. RESULTS: We present MedScan, a completely automated natural language processing-based information extraction system. We have used MedScan to extract 2976 interactions between human proteins from MEDLINE abstracts dated after 1988. The precision of the extracted information was found to be 91%. Comparison with the existing protein interaction databases BIND and DIP revealed that 96% of extracted information is novel. The recall rate of MedScan was found to be 21%. Additional experiments with MedScan suggest that MEDLINE is a unique source of diverse protein function information, which can be extracted in a completely automated way with a reasonably high precision. Further directions of the MedScan technology improvement are discussed. AVAILABILITY: MedScan is available for commercial licensing from Ariadne Genomics, Inc.

Abstracting and Indexing↗
PubMed1999

How knowledge drives understanding--matching medical ontologies with the needs of medical language processing.

In this article, we introduce a knowledge-based approach to medical text understanding. From an in-depth consideration of deep sentence and text understanding we distill basic requirements for an adequate knowledge representation framework. These requirements are then matched with currently available medical ontologies (thesauri, terminologies, etc.). A fundamental trade-off is recognized between large-scale conceptual coverage on the one hand, and formal mechanisms for integrity preservation and conceptual expressiveness on the other hand. We discuss various shortcomings of the most wide-spread ontologies to capture medical knowledge in-the-large. As a result, we argue for the need of a formally sound and expressive model along the lines of KL-ONE-style terminological representation systems in the format of description logics. These provide an adequate methodology for designing more sophisticated, flexible medical ontologies serving the needs of 'deep' knowledge applications which are by no means restricted to medical language processing.

Artificial Intelligence↗
PubMed2003

Interactions of the hippocampal system and the prefrontal cortex in learning language-like rules.

One of the most influential views on the hippocampal function suggests that this brain region is critically involved in relational memory processing, that is, binding converging inputs to mediate the representation of relationships among the constituents of episodes. It has been proposed that this binding is automatic and obligatory during learning and remembering In addition, neuroimaging studies have highlighted the importance of the prefrontal cortex, in learning, memory, and language processing. However, the posited importance of hippocampal-prefrontal interaction remains to be empirically tested. In the present study we used functional magnetic resonance imaging to examine in detail this interaction by assessing learning-related changes in hemodynamic activity during artificial language acquisition. It has been shown previously that artificial grammar systems might be learned by evaluating pattern-based relations in word sequences and generalizing beyond specific word order, that is, rule abstraction. During scanning, participants learned an artificial language whose miniature grammar meets the universal principles of a natural language. Increased proficiency level of the artificial language is associated with decreased left hippocampal activity. In contrast, we observed an increased recruitment of the left inferior frontal gyrus (Broca's area), a region that contributes to syntax processing in natural language. The present results, therefore, indicate a learning-related change in brain circuitry underlying relational processes of language learning, with a transition from a similarity-based learning system in the medial temporal lobes to a language-related processing system in the left prefrontal cortex.

Adult↗
PubMedDate not supplied

Effects of acoustic degradation on syntactic processing: implications for the nature of the resource system used in language processing.

This study investigated the effect of noise masking on on-line syntactic processing. Ninety college students were tested on measures of working memory and on-line sentence comprehension. Subjects were divided equally into three listening conditions: no noise masking, -3 dB signal-to-noise ratio (S:N), -4.5 dB S:N. The auditory moving windows (AMW) paradigm was used to measure on-line sentence processing. In the AMW paradigm, subjects pressed a button for the successive presentation of each phrase in two types of sentences (syntactically simple and complex), and listening times were recorded for each phrase. Previous studies have shown that the verb in the more complex sentence type is the most capacity demanding portion of the sentence. Listening times were longer overall with increased noise masking, and listening times were longer overall at the verb of the harder sentence type. However, the increase at the verb was not larger with increased noise masking. All three groups showed similar effects of syntactic structure in the on-line data. The on-line syntactic effects were not due to problems in word recognition. Correlational analyses did not indicate a relationship between the increase in processing time at the capacity demanding region of the harder sentence types and any of the measures of working memory capacity in any of the three listening conditions. Results indicate that on-line sentence processing is not affected by noise masking if lexical access (e.g., word recognition) remains intact.

Adolescent↗
PubMedDate not supplied

The LBI-method for automated indexing of diagnoses by using SNOMED. Part 1. Design and realization.

We present a simple, formal, lexicon-based method for automated indexing of diagnoses based on the Systematized Nomenclature of Medicine (SNOMED II), called the LBI-method. Part 1 gives an introduction to the LBI-method and presents its realization as application system SALBIDH. The underlying model states that a diagnosis is represented by a set of indices of any nomenclature. The LBI-method is defined as a composition of functions, which in turn define the 3 steps of the LBI-method: preprocessing, morphological analysis, and semantic analysis. Part 2 will focus on the design and the results of an evaluation study to judge the quality of the LBI-method. In this evaluation study the quality of automated indexing was examined as well as the quality of the retrieval of patient data by using automated indexed diagnoses.

Abstracting and Indexing↗
PubMed2001

Using narrative reports to support a digital library.

The vast amount of information collected and stored in clinical systems can be a significant challenge in the integration of digital libraries and electronic medical records, especially the selection of clinical data to be used in the search, retrieval, and summarization processes. In this study, we describe the use of information retrieval measures with natural language processor output to identify critical information in narrative reports. Our hypothesis is that clinical data that occur often in narrative reports are less important to clinicians than findings that occur rarely. We used the information retrieval methods to analyze one year of discharge summaries. We then conducted a performance study, using physicians as subject. Results show that the methods can be used for filtering critical information from reports. Further studies need to be done on evaluation of the method based on an evaluation of the system performance in the context of a digital library.

Humans↗
PubMed1994

Automatic encoding into SNOMED III: a preliminary investigation.

The Linguistic String Project (LSP) medical language processing (MLP) system converts narrative clinical reports into database tables of patient data. A procedure for mapping the output of the LSP MLP system into SNOMED III codes was developed. Preliminary results and further requirements are discussed.

Abstracting and Indexing↗
PubMed1994

Ambiguity resolution while mapping free text to the UMLS Metathesaurus.

We propose a method for resolving ambiguities encountered when mapping free text to the UMLS Metathesaurus. Much of the research in medical informatics involves the manipulation of free text. The Metathesaurus contains extensive information which supports solutions to problems encountered while processing such text. After discussing the process of mapping free text to the Metathesaurus and describing the ambiguities which are often the result of such mapping, we provide examples of rules designed to eliminate mapping ambiguities. These rules refer to the context in which the ambiguity occurs and crucially depend on semantic types obtained from the Metathesaurus. We have conducted a preliminary test of the methodology and the results obtained indicate that the rules successfully resolve ambiguity around 80% of the time.

Abstracting and Indexing↗
PubMed1996

The expert surgical assistant. An intelligent virtual environment with multimodal input.

Virtual Reality has made computer interfaces more intuitive but not more intelligent. This paper shows how an expert system can be coupled with multimodal input in a virtual environment to provide an intelligent simulation tool or surgical assistant. This is accomplished in three steps. First, voice and gestural input is interpreted and represented in a common semantic form. Second, a rule-based expert system is used to infer context and user actions from this semantic representation. Finally, the inferred user actions are matched against steps in a surgical procedure to monitor the user's progress and provide automatic feedback. In addition, the system can respond immediately to multimodal commands for navigational assistance and/or identification of critical anatomical structures. To show how these methods are used we present a prototype sinus surgery interface. The approach described here may easily be extended to a wide variety of medical and non-medical training applications by making simple changes to the expert system database and virtual environment models. Successful implementation of an expert system in both simulated and real surgery has enormous potential for the surgeon both in training and clinical practice.

Artificial Intelligence↗
PubMed2000

The automation of coding.

Automated coding is a rapidly growing technology. The implications of this technology for the clinical, business, and research areas of health care today are dramatic. Before a health care organization chooses an automated coding system it is important that the implications of each of the various types as well as the vocabulary to be chosen are understood. This article will discuss three types of automated coding systems that are currently available, but it will not discuss the merits of the various vocabularies available for use in an automated coding system.

Abstracting and Indexing↗