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 181 records · Page 10Linked to original sources
PubMed1990

[Registration of detailed data in the medical record or how to translate "impressions" into measurable observations].

Every medical case record represents a mass of data (texts, pictures, figures, etc.) in an unstructured form. The physician needs to retrieve this data via several access routes: temporal (dependent on date or sequences of events), type of data (diagnostic, treatment, clinical signs, laboratory findings, image descriptors, all with their interrelationships), or depending on the severity of the disease, etc. Retrieval of this data fulfils several functions: circulation of a case record among specialists, assistance in summarizing a long and complex clinical course, comparison of patients, research, and teaching. Three projects are described which have the same aim: structuring of the case record in order to retrieve detailed data on patients as individuals and describe clinical courses on the basis of measurable observations. This structure must be understandable to a computer (directly or indirectly) so that searches and comparisons can be performed automatically. The first project, entitled "indexed paragraph prototype" reproduces the structure of the problem-oriented case record and is designed to input the Medical Outpatients Department's follow-up notes into the computer. The second, "automatic language analysis", aims to exploit two characteristics of medical language, its omnipresence in the case record and its reliability, in view of its status as the spontaneous vehicle of communication between physicians. The third, "collection of clinical signs during consultation", is based on a prospective collection of all elements of clinical observation, structured temporally consultation by consultation. The purpose of precise collection of detailed and measurable observations in individual patients is to identify those among the clinical signs which display the greatest power of discrimination, i.e. those which best serve to predict the case's evolution.

Abstracting and Indexing↗
PubMed1990

[Comparison of 2 series of autopsies observed at Johns-Hopkins Medical Center, Baltimore (JHMI) and at the Neuchâtel Institute of Pathology (INAP)].

We are reporting the first results of a comparative study of 100 consecutive autopsies and their clinical diagnoses, observed at the Johns Hopkins Medical Institutions (JHMI) and at the Institut neuchâtelois d'anatomie pathologique (INAP). The diagnoses of the two series were coded according to the two different systems used currently at the two institutions. The data from Baltimore were automatically classified by a special "key word method" using the categories of the Index Medicus (MeSH = Medical subject headings). We proceeded then to a second recording by SNOMED codes, introduced into the computer system in the same way as we document the autopsy diagnoses in Neuchâtel. The two series could be compared in detail according to topographical, morphological and aetiological parameters. The over-all repartition of the examined cases shows a higher incidence of newborns in Baltimore (23), in Neuchâtel we observed only 7 newborn autopsies. The mean age was inferior in Baltimore (males: 53.5 years for JHMI, 73.1 years for INAP; females: 58.4 years for JHMI, 66.2 years for INAP). The number of diagnoses per autopsy was 31.9 at JHMI, and 50.1 in Neuchâtel. The topographical distribution of clinical and autopsy diagnoses showed a higher frequency of central nervous system lesions in JHMI which might be explained by the activity of a neuropathological division. Findings concerning the morphological categories revealed a higher frequency in JHMI for traumatic abnormalities (7.2% vs 2.5%), malformations (4.3% vs 0.8%), whereas inflammation and fibrosis and degenerative lesions were more often encountered in Neuchâtel. The differences in morphological observations could be attributed to a higher proportion of newborn cases in JHMI with complex malformation syndromes.(ABSTRACT TRUNCATED AT 250 WORDS)

Adolescent↗
PubMed1989

[RGSS-IDJ and its application to cranial computed tomography].

RGSS-IDJ is developed as the Japanese version of Report Generation Support System for Imaging Diagnosis (RGSS-ID), which is a developmental computer system that applies artificial intelligence (AI) methods to a reporting system. Now RGSS-IDJ supports the report generation of cranial computed tomography. A representation scheme called Generalized Finding Representation (GFR) is proposed, to bridge the gap between natural language expressions in the radiographic report and AI methods. GRF for RGSS-IDJ is the same as for RGSS-ID. The basic style for entering the findings on the radiograph is the dialogue system with the routine of query and answering it by selecting items with a mouse. This system encodes the input findings into the network expressions, which are represented as the list form in the LISP computer language. And, it reserves them into the knowledge data base. The content of the report will be able to be utilized for various analyses within AI paradigm. The final radiographic report is made in the natural Japanese language.

Artificial Intelligence↗
PubMed1989

Generation of surgical pathology report using a 5,000-word speech recognizer.

Pressures to decrease both turnaround time and operating costs simultaneously have placed conflicting demands on traditional forms of medical transcription. The new technology of voice recognition extends the promise of enabling the pathologist or other medical professional to dictate a correct report and have it printed and/or transmitted to a database immediately. The usefulness of voice recognition systems depends on several factors, including ease of use, reliability, speed, and accuracy. These in turn depend on the general underlying design of the systems and inclusion in the systems of a specific knowledge base appropriate for each application. Development of a good knowledge base requires close collaboration between a domain expert and a knowledge engineer with expertise in voice recognition. The authors have recently completed a knowledge base for surgical pathology using the Kurzweil VoiceReport 5,000-word system.

Artificial Intelligence↗
PubMed1988

Integrated pathology reporting, indexing, and retrieval system using natural language diagnoses.

Pathology computer systems are making increasing use of natural language diagnoses. The Johns Hopkins Medical Institutions integrated pathology reporting system, a commercial product with extensive, locally added enhancements, covers all information management functions within autopsy and surgical pathology divisions and has on-line linkages to clinical laboratory reports and the medical library's Mini-MEDLINE system. All diagnoses are written in natural language, using a word processor and spelling checker. A security system with personal passwords and different levels of access for different staff members allows reports to be signed out with an electronic signature. The system produces financial reports, overdue case reports, and Boolean searches of the database. Our experience with 128,790 consecutively entered pathology reports suggests that the greater precision of natural language diagnoses makes them the most suitable vehicle for follow-up, retrieval, and systems development functions in pathology.

Artificial Intelligence↗
PubMedDate not supplied

[Methodology for the development of expert systems of viral epidemiology].

The proposed methodology for the elaboration of the base of knowledge uses a tree of the hierarchical entities and a simplified variant of the natural language. The resolution system is based on an extension of the predicate calculation containing, in an explicit way, entities of different nature, and among these the correlations giving the rules of deduction.

Artificial Intelligence↗
PubMed1995

A model for medical knowledge representation application to the analysis of descriptive pathology reports.

A new knowledge-representation system is presented, designed for medical knowledge-based applications and in particular for the analysis of descriptive medical reports. Knowledge is represented at two levels. A definitional level uses a concept-type hierarchy, a relation-type hierarchy, and a set of schematic graphs to define the concepts used and the relations between them, as well as different types of cardinality restrictions on these relations. A set of compositional hierarchies using the classic "has-part" relation as well as a new set-inclusion relation allows concept composition to be precisely defined. An assertional level allows the creation and manipulation of empirical data, in the form of graphs using the concepts, relations, and constraints defined at the definition level. The use of cardinality constraints in graph unification is considered in the context of descriptive medical discourse analysis.

Artificial Intelligence↗
PubMed1993

PALM--a pattern language for molecular biology.

This paper presents a new pattern language, PALM, for describing patterns in molecular biology sequences. The language is intended for representing knowledge about such patterns in a declarative, clear and concise way. It is also shown that its expressive power enables the definition of any regular or context free language, and also higher languages in the Chomsky hierarchy by parameter attachment, variables and procedural attachment. It is also possible to define approximate patterns. The language is rigorously defined, and several examples of its use and expressive power are given.

DNA-Directed DNA Polymerase↗
PubMed1994

A model for structured data entry based on explicit descriptional knowledge.

Clinical narratives in patient records are usually recorded in free text, limiting the use of this information for research, quality assessment, and decision support. This study focuses on the capture of clinical narratives in a structured format by supporting physicans with structured data entry (SDE). We analyzed and made explicit which requirements SDE should meet to be acceptable for the physician on the one hand, and generate unambiguous patient data on the other. Starting from these requirements, we found that in order to support SDE, the knowledge on which it is based needs to be made explicit: we refer to this knowledge as descriptional knowledge. We articulate the nature of this knowledge, and propose a model in which it can be formally represented. The model allows the construction of specific knowledge bases, each representing the knowledge needed to support SDE within a circumscribed domain. Data entry is made possible through a general entry program, of which the behavior is determined by a combination of user input and the content of the applicable domain knowledge base. We clarify how descriptional knowledge is represented, modeled, and used for data entry to achieve SDE, which meets the proposed requirements.

Artificial Intelligence↗
PubMed1994

The component-based architecture of the HELIOS medical software engineering environment.

The constitution of highly integrated health information networks and the growth of multimedia technologies raise new challenges for the development of medical applications. We describe in this paper the general architecture of the HELIOS medical software engineering environment devoted to the development and maintenance of multimedia distributed medical applications. HELIOS is made of a set of software components, federated by a communication channel called the HELIOS Unification Bus. The HELIOS kernel includes three main components, the Analysis-Design and Environment, the Object Information System and the Interface Manager. HELIOS services consist in a collection of toolkits providing the necessary facilities to medical application developers. They include Image Related services, a Natural Language Processor, a Decision Support System and Connection services. The project gives special attention to both object-oriented approaches and software re-usability that are considered crucial steps towards the development of more reliable, coherent and integrated applications.

Computer Communication Networks↗
PubMed1994

Analysing and developing object-oriented medical applications with HELIOS.

The HELIOS project promotes systematic reuse of existing software in a valuable methodological context. In order to reach this goal, the Analysis and Design Development Environment (ADDE) has been realized as a HELIOS component. This component includes the Analysis and Design sub-component (ADT), which supports the Rumbaugh's object-oriented methodology and the Insertion Retrieval Tool (IRT), which implements the reuse. The ADT sub-component enhances the quality of software development permitting a correct analysis, and design and a satisfactory documentation. The IRT Tool is dedicated to reuse by retrieving parts of existing applications (retrieve) and by qualifying elements just created or updated (insertion). A faceted system adapted to the medical domain allows an efficient search among the object database. Both tools contribute to reducing the cost of software development. This paper presents the design and the implementation of these tools in the HELIOS framework.

Database Management Systems↗
PubMed1994

Lexical methods for managing variation in biomedical terminologies.

Access to biomedical terminologies is hampered by the high degree of variability inherent in natural language terms and in the terminologies themselves. The lexicon, lexical programs, databases, and indexes included with the 1994 release of the UMLS Knowledge Sources are designed to help users manage this variability. We describe these resources and illustrate their flexibility and usefulness in providing enhanced access to data in the UMLS Metathesaurus.

Biology↗
PubMed1994

A natural language understanding system combining syntactic and semantic techniques.

A large proportion of the medical record currently available in computerized medical information systems is in the form of free text reports. While the accessibility of this source of data is improved through inclusion in the computerized record, it remains unavailable for automated decision support, medical research, and management of medical delivery systems. Natural language understanding systems (NLUS) designed to encode free text reports represent one approach to making this information available for these uses. Below we describe an experimental NLUS designed to parse the reports of chest radiographs and store the clinical data extracted in a medical data base.

Bayes Theorem↗
PubMed1994

Generating patient-specific interactive natural language explanations.

Patient compliance is a significant problem and is strongly correlated with the patients' understanding of their condition and prescribed treatment. Since doctors typically do not have large amounts of time to educate patients, and impersonal, voluminous patient handouts are largely ineffective, we propose the use of a sophisticated computer-based information system to generate tailored, interactive handouts to communicate with patients. Our system uses text planning and user modeling techniques to generate natural language descriptions of migraine, its symptoms, triggering factors and prescriptions. The system is capable of handling follow-up questions requesting further information, and generating responses in the context of previously supplied information--a capability unavailable in previous patient information systems. The system tailors its interaction to: (i) the class of migraine patients, (ii) the individual patient, and (iii) the previous dialogue. Preliminary evaluation of the system indicates that patients find it useful and informative. More extensive evaluation is in progress.

Computer-Assisted Instruction↗
PubMed1993

Computer auditing of surgical operative reports written in English.

We developed a script-based scheme for automated auditing of natural language surgical operative reports. Suitable operations (appendectomy and breast biopsy) were selected, then audit criteria and operation scripts conforming with our audit criteria were developed. Our LISP parser was context and expectation sensitive. Parsed sentences were represented by semigraph structures and placed in a textual database to improve efficiency. Sentence ambiguities were resolved by matching the narrative textual database to the script textual database and employing the Uniform Medical Language System (UMLS) Knowledge Sources. All audit criteria questions were successfully answered for typical operative reports by matching parsed audit questions to the textual database.

Appendectomy↗
PubMed1993

Modelling for natural language understanding.

Natural Language Understanding (NLU) is a rapidly growing field in medical informatics. Its potential for tomorrow's applications is important. However, it is limited by its ability to ground its components on a solid model of the domain. This opens the way for the emergence of the discipline of medical domain modelling, as part of the vast field of Knowledge Base (KB) engineering. This article aims at describing the current development of a multilingual natural language system, strongly oriented towards the semantics of the domain. Special emphasis is presently given to the task of building a domain model, and to establish direct links with the language platform. The result is a model-driven NLU system. Numerous benefits are expected in the long term.

Artificial Intelligence↗