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 1,027 records · Page 57Linked to original sources

Toward a medical linguistic knowledge base.

This paper presents the design of a Medical Linguistic Knowledge Base (MLKB). This MLKB is intended to be the multilingual recipient for all the declarative knowledge about languages. It includes words, their syntax and their conceptual representation, typology of concepts of the domain, rules for semantic analysis and conceptual schemata. For that purpose, Sowa's conceptual graphs are considered as an adequate knowledge representation. The MLKB will be an enormous body of information, and the difficulty to feed it and to validate it appears immediately. Therefore, it is necessary to start an international initiative to merge efforts from different groups.

Language↗

On the linguistic representation of medical information: natural language, controlled language, and formal language.

Language is indispensable for the representation of medical information. We classified the methods of linguistic representation into three items: natural language, controlled language, and formal language. The characteristics of these are discussed; we focus especially on the preparation of data and data quality. We present the perspective that linguistic research in medical informatics can be considered as an effort to convert natural language into formal language and vice versa. The problems related to the conversion and the role of controlled language in medical linguistics are discussed in detail.

Language↗

Automatic recognition of medical terminology (immunology).

This paper discusses a novel approach to automatically recognizing medical terminology, applied to Immunology texts. This approach is based on a computational linguistic analysis of medical terminology which for the first time accounts satisfactorily for the neoclassical lexicon in English.

Allergy and Immunology↗

Identifying concepts in medical knowledge.

The barrier word method of identifying nominal phrases in text, using a very long barrier word list, was evaluated in two different sets of text. In a sample of 10 paragraphs from the Medical Knowledge Self-Assessment Program of the American College of Physicians, the yield of nominal phrases as a percent of total chunks isolated was 66%. Some 500,000 chunks were isolated from Principles and Practice of Oncology (PPO). 38% of these chunk-occurrences were of chunks which matched to 10,000 concept names in Meta-1.4, the most recent version of the UMLS Metathesaurus. 50 paragraphs from PPO were chosen at random. Co-occurrences of concepts in those paragraphs were reviewed. 42 of the paragraphs had unique or infrequently occurring co-occurrences which described closely the major thrust of the paragraph.

Medical Oncology↗

A study on the impact of database design on clinical information systems.

This paper reports on a research project which aims at addressing one of the most crucial problems in clinical computing--the relation between clinical data and database design and their impacts on Clinical Information Systems. The discussion will focus on a research project that is currently being conducted in a number of acute care hospitals at Melbourne, Australia to investigate the database design for the Emergency Department Information System (EDIS), a subset of the Clinical Information System (CIS).

Australia↗

Automated classification of encounter notes in a computer based medical record.

Harvard Community Health Plan is exploring emerging information technologies for means to use the text portion of its 25 year old computerized medical record system. The Center for Intelligent Information Retrieval is developing systems to answer the question: to what extent can automated information systems replace manual chart review of encounter notes? INQUERY, a probabilistic inference net information retrieval system, and FIGLEAF, an inductive decision tree text classifier are applied to the problem of classifying electronic encounter notes to identify acute exacerbations in pediatric asthmatics. Both systems achieve average precisions of greater than 80%, with a new enhancement to INQUERY's relevance feedback, the top performer. Refinement of the systems and plans for their integration are discussed.

Asthma↗

Cognitive design for sharing medical knowledge models.

By building a medical conceptual model inside the galen project, a methodology has been defined to deal with both operative goals and deep and unsolved problems about knowledge. This knowledge sharing oriented approach exploits existing medical coding systems such as knowledge sources and enables us to represent their concepts in a wider cognitive context referring to ontological theories. The tasks of cognitive ergonomy, quasi-naturalness of language, versatility, and flexibility seem to be supported through some functions, such as viewpoint, context, and sign, which act as spin-off points to knowledge or information which is not modeled.

Artificial Intelligence↗

Advanced patient information systems and medical concept representation.

With ubiquitous networked computer based patient information systems, the conventional technology reaches a sound barrier: problems of recall and precision curtail the efficiency gains in data retrieval as the number of data sources and the amount of data in them increases; concerns for privacy protection meet the limits of conventional means as the entropy of the data collections and the number of persons implicated by them increases. We propose that these shortcomings will require additional features for advanced patient information systems, and that medical concept representation has a key role in overcoming these deficiencies. After substantiating the evidence for the need, we outline a means for improvement through medical concept representation. We conclude by discussing the current state of alternatives for medical concept representation and propose that the methodology for resolution of the identified impediments is available.

Ethics, Medical↗

Information retrieval in medicine: the SAPHIRE experience.

Information retrieval systems are proliferating in biomedical settings, but many problems in indexing, retrieval, and evaluation of systems continue to exist. The SAPHIRE Project was undertaken to seek solutions to these problems. This paper summarizes the evaluation studies that have been done with SAPHIRE, highlighting the lessons learned and laying out the challenges ahead to all medical information retrieval efforts.

Abstracting and Indexing↗

Information retrieval maps for biomedical research.

Integration of computer-based information sources should be useful for biomedical research. An information retrieval map is a graphical representation of a set of expert rules for integrating computer-based information sources based on the data connections among those information sources. The use and implementation of an information retrieval map for sequence alignment is described.

Computer Communication Networks↗

Preliminary assessment of the effect of more informative (structured) abstracts on citation retrieval from MEDLINE.

OBJECTIVE: To compare the recall and precision of citation retrieval from MEDLINE when searching in journals containing traditional abstracts with journals containing abstracts prepared according to the guidelines of more informative abstracts (MIAs) for clinical journal articles. DESIGN: Analytic survey of operating characteristics of MeSH terms and textwords selected to detect studies meeting basic methodological criteria for direct clinical use in general adult medicine in priority journals with and without MIAs. MEASURES: The sensitivity, specificity, and precision of search terms were determined by comparison with a manual review of all articles (the gold standard) in 10 internal and general medicine journals for 1986 and 1991. The performance of each search term was compared before and after the implementation of MIAs and in two journal sets with and without MIAs in 1991. RESULTS: The sensitivity of some terms increased with the use of MIAs and also increased by the same amount in journals with usual abstracts in 1991 compared to 1986. The use of MIAs had the greatest impact in the areas of etiology and prognosis. Many MeSH and textwords had comparable performance before and after the implementation of MIAs and between journals with and without MIAs in 1991. CONCLUSIONS: More informative abstracts improved the retrieval properties of some, but not all, textwords and medical subject headings. Further work may be needed to enhance the effects of MIAs on bibliographic retrieval.

Abstracting and Indexing↗

LUCID: a semi-automated ICD-9 encoding system.

The natural language approach to diagnosis encoding will certainly become a widespread technique during the second half of this decade. Accessing standard codes by numbers and keywords will be more and more considered a loss of time and efficiency. We present a demonstration of a natural language based encoding system for ICD, called LUCID, which considerably alleviates the burden of coding with ICD classification and enhances the quality of the encoded list of diagnoses. This tool, delivered on a PC platform, is very convivial and provides a versatile interface to any existing application based on Microsoft Windows standards.

Abstracting and Indexing↗

SNOMED-encoded surgical pathology databases: a tool for epidemiologic investigation.

Pathology departments have invested considerable energy, sometimes extending over several decades, toward coding their anatomic pathology reports. As a result of these labors, there is now a vast amount of electronically coded data from surgical pathology reports, holding a wealth of information relevant to virtually every recognized pathologic entity. The original intent of the Systematized Nomenclature of Medicine (SNOMED) was to prepare population-based disease data from pathology reports, but no such studies have emerged in the medical literature. This is due in part to the nonuniform, idiosyncratic, and incomplete manner in which most SNOMED databases are constructed. Automatic (computer-driven) coding provides uniformity and completeness of SNOMED databases and offers the possibility of customized recoding for an entire collection of reports using any nomenclature and any set of coding algorithms. In prior investigations, we described a computer program that SNOMED-codes surgical pathology reports, and we provided an analysis of a large surgical pathology SNOMED database. In this report, we describe the importance of coded surgical pathology databases for research, teaching, hospital administration, and public health, and we explain the functional differences between coded databases and free-text collections of surgical pathology data. Surgical pathology departments and vendors of laboratory information systems can ensure that surgical report files can be automatically coded or recoded with any chosen nomenclature by adhering to simple guidelines.

Disease↗

SPIRS, WinSPIRS, and OVID: a comparison of three MEDLINE-on-CD-ROM interfaces.

Three MEDLINE-on-CD-ROM interfaces are compared: SPIRS (version 3.11) and WinSPIRS (version 1.0) from SilverPlatter and OVID (version 3.0, DOS and Windows interfaces) from CD Plus Technologies. Though the database is the same, there are substantial differences among the interfaces in the way these data are presented and can be searched. These different approaches are discussed, and a detailed comparative table is included. It is obvious that all three interfaces are quite good yet none of them is perfect; each has desirable and unfortunate features. Together, they offer an enormous range of possibilities. Users would benefit if most of the better features (e.g., easy menu, free-text retrieval, pre-exploded thesaurus terms) were implemented in future versions of these interfaces and if system operators were given greater latitude to determine the system defaults appropriate to their specific situations and customers.

CD-ROM↗

Navigating through a document-centered electronic medical record: a mock-up based on WWW technology.

Current WWW technology facilitates the development of "hypertext" applications. A hospital-wide study of users' requirements in France led to a document-centered approach to the patient Electronic Medical Record (EMR). In order to refine such a specification, and taking advantage of WWW technology, we have developed a running mock-up of a document-based EMR from an actual paper-based patient record. Synthesis documents were added and linked to original replicated paper documents to form a hypertextual EMR. The mock-up has been presented to health care professional boards to gather their remarks and wishes, and then enhanced accordingly. The current version reflects (part of) their requirements for an EMR, and is presented in this paper.

Clinical Medicine↗

Achieving automated narrative text interpretation using phrases in the electronic medical record.

Stereotypic phrases are used by clinicians throughout the medical record, as seen in an analysis of our COSTAR medical record database. These phrases are often associated with an underling semantic concept; for example the phrase CLEAR LUNGS may be linked with the concept "normal lung exam" for a particular physician. Formalizing these associations with concepts from the UMLS using the MEDPhrase application allowed us to automate interpretation of narrative text within our electronic medical record.

Information Storage and Retrieval↗

The PEN&PAD data entry system: from prototype to practical system.

This paper describes some of the issues addressed in the transition of the PEN&PAD from prototype clinical workstation to practical data entry system for use by general practitioners in the UK. Background and motivation of the PEN&PAD and GALEN projects are presented before the operation of the PEN&PAD user interface is described. A number of issues which have arisen in the development of the PEN&PAD Data Entry System are discussed.

Humans↗