Search PubMed⌕ Search

Biomedical subjects

J R Scherrer

Publications and source records attributed to J R Scherrer.

At least 55 records · Page 3Linked to original sources
PubMed1995

Analysis of medical texts based on a sound medical model.

Automatic understanding of natural language is a complex task due to the presence of ambiguities. In particular, semantic ambiguities which are often immediately and unconsciously solved by human beings, are raised when analyzing natural language sentences by computer. The latter has to know the implicit and contextual information in order to resolve these difficulties. Nowadays in medicine, a considerable effort is deployed to model semantic contents of the medical domain. Such a task is usually performed separately from linguistic considerations. The goal of this paper is to highlight the key issues of basing a medical language processing system on a sound semantic model. To illustrate the requirements and advantages of such a conceptual approach to the analysis process, the experiment conducted to adjust the RECIT analyzer to the GALEN model is shown.

Models, Theoretical↗
PubMed1995

Multilingual natural language generation as part of a medical terminology server.

Re-usable and sharable, and therefore language-independent concept models are of increasing importance in the medical domain. The GALEN project (Generalized Architecture for Languages Encyclopedias and Nomenclatures in Medicine) aims at developing language-independent concept representation systems as the foundations for the next generation of multilingual coding systems. For use within clinical applications, the content of the model has to be mapped to natural language. A so-called Multilingual Information Module (MM) establishes the link between the language-independent concept model and different natural languages. This text generation software must be versatile enough to cope at the same time with different languages and with different parts of a compositional model. It has to meet, on the one hand, the properties of the language as used in the medical domain and, on the other hand, the specific characteristics of the underlying model and its representation formalism. We propose a semantic-oriented approach to natural language generation that is based on linguistic annotations to a concept model. This approach is realized as an integral part of a Terminology Server, built around the concept model and offering different terminological services for clinical applications.

Language↗
PubMed1995

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↗
PubMed1995

Word segmentation processing: a way to exponentially extend medical dictionaries.

One of the most critical problems of automatic natural language processing (NLP) is the size of the medical lexicons. The set of compound medical words and the continual creation of new terms renders medical lexicons exhaustive beyond question. The structure of such dictionaries usually consists of two parts: 1) the morphological and sometimes syntactical information necessary to identify, on a grapheme level, a given word in a sentence, and 2) the part often devoted to conceptual knowledge associated with the recognized word. It is only when these two prerequisites are fulfilled that an attempt to understand the meaning of a whole expression is possible. The approach developed in this paper is a pragmatic way to rapidly increase the lexico-semantic part of medical dictionaries. We developed a semi-automatic tool, as a prototype to demonstrate the feasibility of this approach. This tool is able to translate almost any diagnosis expressed in French into its equivalent in the ICD-9CM coding scheme.

Dictionaries, Medical as Topic↗
PubMed1995

Recurrent infections in children observed throughout electronic medical record.

This paper shows the usefulness of routinely collected structured clinical findings in an computerized patient record. Medical observations are collected as detailed clinical findings, without any interpretation, according to a time structure, visit by visit. In the present example, the role of the microbial colonization is studied in relationship with infected organs and other processes which could facilitate the infection.

Child↗
PubMed1995

Fifteen years of medical encoding in the Diogene HIS.

Obtaining good quality encoded medical information is a major issue for patient documentation, hospital management, and epidemiological statistics. In this paper, the experience of encoding medical information in Geneva since 1978 is described, following 1988 IMIA WG6 recommendations: "There is a need to enhance the involvement of physicians and other health care professionals in the original entry of medical and other relevant data to increase its accuracy and quality".

Hospital Information Systems↗
PubMed1995

Constructing clinical applications: the GALEN approach.

A common problem for developers of clinical applications is coping with the diversity of medical language. Medical language as it is used all over the world varies widely, while the referents for these words stay essentially the same. Software developers must reconcile this diversity with the practical necessity of producing applications that are usable in a variety of hospitals, while ensuring that information can be shared between applications. Existing approaches center around coding and classification schemes, but these approaches must be supplemented by a range of sophisticated terminological services in order for the language barriers to be overcome. To address this, the GALEN project is developing an application called the Terminology Server to provide such a range of terminological services (e.g., conceptual and multilingual services). The software is built upon a re-usable core model of medical terminology. This paper reports on the development of a clinical application called the SCUI (Structured Clinical User Interface) which draws on these GALEN technologies and illustrates an innovative approach to the construction of future clinical applications. The SCUI was specifically developed and tested in the context of infectious diseases to satisfy the demands made by the medical intensive care unit on the Geneva Hospital's microbiology laboratory.

Clinical Laboratory Information Systems↗
PubMed1995

Hospital network: a low cost PC-based solution.

A new shell has been developed for Windows 3.1 that allows the use of low-cost PCs and their local processing power within a large hospital network, while conserving a good security and maintenance level.

Computer Security↗
PubMed1995

Representing clinical narratives using conceptual graphs.

The analysis of medical narratives and the generation of natural language expressions are strongly dependent on the existence of an adequate representation language. Such a language has to be expressive enough in order to handle the complexity of human reasoning in the domain. Sowa's Conceptual Graphs (CG) are an answer, and this paper presents a multilingual implementation, using French, English and German. Current developments demonstrate the feasibility of an approach to natural Language Understanding where semantic aspects are dominant, in contrast to syntax driven methods. The basic idea is to aggregate blocks of words according to semantic compatibility rules, following a method called Proximity Processing. The CG representation is gradually built, starting from single words in a semantic lexicon, to finally give a complete representation of the sentence under the form of a single CG. The process is dependent on specific rules of the medical domain, and for this reason is largely controlled by the declarative knowledge of the medical Linguistic Knowledge Base.

Artificial Intelligence↗
PubMed1994

Impact of the acute cardiac ischemia time-insensitive predictive instrument (ACI-TIPI) on the speed of triage decision making for emergency department patients presenting with chest pain: a controlled clinical trial.

OBJECTIVE: Emergency department (ED) triage for acute cardiac ischemia in the primary teaching hospital in Geneva, Switzerland, is very accurate, but at the cost of very long ED stays. Thus, the authors sought: 1) to determine the impact of the acute cardiac ischemia time-insensitive predictive instrument (ACI-TIPI), incorporated into a computerized electrocardiograph, on length of stay and speed of triage decision making for ED patients presenting with symptoms suggesting acute cardiac ischemia, and 2) to study the ACI-TIPI's impact on physicians of different training levels. DESIGN: A seven-month prospective clinical trial with alternating-month experimental and control periods. SETTING: An urban major teaching hospital in Geneva, Switzerland. PARTICIPANTS: Patients over the age of 18 years presenting to the ED with chest pain or other symptoms suggesting acute cardiac ischemia (acute myocardial infarction or unstable angina pectoris). Emergency department physicians, classified as novice (those in their first ED rotations) and experienced (those in their second or later ED rotations). Patients staying overnight in the ED (n = 111) were excluded from the analysis. INTERVENTION: During the experimental months, the computerized electrocardiograph printed the ACI-TIPI probability of acute cardiac ischemia at the top of each subject's electrocardiogram. During control months, the probability was not provided. MEASUREMENTS AND MAIN RESULTS: Among the 418 study subjects, for patients with acute ischemia seen by novice clinicians, the use of the ACI-TIPI decreased ED time from presentation to triage decision and ED release by 0.7 hour (19%) (p = 0.007). Subgroup analyses for patients with acute myocardial infarction, patients with unstable angina pectoris, and patients given thrombolytic therapy also showed analogous decreases in ED time consistent with this finding. Other key determinants of ED length of stay included: age, whether the coronary care unit was full, whether patients received thrombolytic therapy, and whether admission was during the night shift. The experimental and control groups did not differ in triage disposition appropriateness or mortality. CONCLUSIONS: For ED patients with acute cardiac ischemia evaluated by novice clinicians, the ACI-TIPI substantially speeded ED decision making and triage. The suggestion of an impact on different cardiac ischemia subgroups and mortality deserves further larger clinical trials.

Coronary Care Units↗
PubMed1994

Sharing and communicating health care information: summary and recommendations.

Sharing and communicating information is a fundamental task in modern medicine. The health care system of the western world is based on teamwork of professionals who participate in the care of patients. Exchange of information (not just data) requires the communicating parties to agree on a communication channel, an exchange protocol, and a common language. The language includes an alphabet, words, phrases, and symbols that express and assign meaning, understood by all. The most common forms of communication are the spoken word and the paper-based patient record. Computers and communication systems improve the sharing of health care information by overcoming the limitations imposed by the dimensions of time and location. However, natural language is still too complex and too ambiguous for current computing devices to handle the complex interactions between health care professional and patients. A simpler 'language' is needed that uses domain specific vocabularies (and/or codes), well-defined exchange protocols for data, information, knowledge, and, in the future, perhaps even wisdom. This simpler 'language' is expected to handle most of the routine information exchange but not eliminate natural language. It is essential that health care information systems preserve and incorporate natural language expressions and integrate them with structured vocabularies. Today, agreeing on standard data exchange protocols and domain specific vocabularies and codes is our greatest challenge. However, standards alone are not sufficient. Acceptance of the standards by the health care professionals, verifications in clinical environments, and implementation agreements by the medical informatics industry are essential. The group on 'Sharing and Communication of Health Care Information' addressed the issues raised above and unanimously recommends a number of steps that will improve the sharing of information. In addition, specific recommendations are offered to governments, health care institutions, and to developers of health care information systems.

Communication↗
PubMed1994

New opportunities for processing the OSI-7 layer protocols using parallel processing (transputers).

The attractiveness of the OSI-7 layer model is closely dependent upon a highly ambitious intent to promote a series of quasi-universal standards to coordinate the communication between heterogeneous applications, whatever the distributed architectures might be. However, a major criticism of the OSI-model is the performance and the handling of the presentation layer. This paper deals with the evaluation of parallel processing techniques operating at the upper levels of the OSI-model using transputers in a parallel co-processor. It is shown that the performance problem is highly dependent on the structure of the protocol stack and its implementation. With the object-oriented modularization of the protocol stack, an architecture of a possible co-processor using transputers is considered and its performance is considered adequate. An ideal configuration is briefly presented. A final performance appraisal of the parallelism effect is discussed with some insight into the future.

Computer Communication Networks↗
PubMed1994

GAMES II Project: a general architecture for medical knowledge-based systems.

GAMES II aims at developing a comprehensive and commercially viable methodology to avoid problems ordinarily occurring in KBS development. GAMES II methodology proposes to design a KBS starting from an epistemological model of medical reasoning (the Select and Test Model). The design is viewed as a process of adding symbol level information to the epistemological model. The architectural framework provided by GAMES II integrates the use of different formalisms and techniques providing a large set of tools. The user can select the most suitable one for representing a piece of knowledge after a careful analysis of its epistemological characteristics. Special attention is devoted to the tools dealing with knowledge acquisition (both manual and automatic). A panel of practicing physicians are assessing the medical value of such a framework and its related tools by using it in a practical application.

Artificial Intelligence↗
PubMed1994

A classification of one-dimensional electrophoresis gels using wave packet decomposition.

A classification of one-dimensional electrophoresis gels was achieved using a fast approximation of the Karhunen-Loève transformation. The algorithm was based on wave packet decomposition theory, using in particular quadrature mirror filters derived from orthogonal bases of wavelets. Bacterial proteins from two different species of staphylococci were separated by SDS-PAGE electrophoresis. The gel images were analyzed by computer and the protein bands were clustered, after an orthogonal projection onto a space of lower dimension, by standard statistical methods.

Algorithms↗
PubMed1994

Natural language processing of medical texts within the HELIOS environment.

A large number of hospital applications are potentially interested in natural language processing since they currently heavily depend on an efficient use of a huge amount of textual information. The need for systems that are able to accept multiple European languages is of paramount interest, as language barriers can be a strong impediment for large-scale communication in Europe, in particular regarding telemedicine. In the context of the AIM project HELIOS, the Natural Language Processing (NLP) component offers a large variety of medical services according to natural language free input. It allows the multilingual analysis of medical texts (currently in English, French and German) and the storage of the meaning of these texts under a deep knowledge representation that can be queried whenever it is needed. In addition, it provides facilities to handle knowledge source embedded into the conceptual typologies and into the dictionaries. This article aims at describing all these functionalities and their integration into the environment of the HELIOS project.

Artificial Intelligence↗
PubMed1994

Medical office automation integrated into the distributed architecture of a hospital information system.

Patient histories, discharge summaries, and medical consultant reports are made up of written texts. Therefore, the gathering and archiving of these texts in machine-readable form has many characteristics of computer-based medical records. In Geneva, approximately 1,540 PCs are connected to the Hospital Information System DIOGENE 2, with the possibility of accessing all the functions offered by the system without losing any of their MS-DOS word processing capabilities. The UNIDOC system, presented in this paper, takes all these features into account, a real marriage of technologies between the MS-DOS environment and the distributed client-server architecture. The INGRES database management system supports the entire archiving process of the medical patient texts, structured by prelabelled paragraphs and automatically indexed. Both the quality and accessibility of the records are enhanced, while the archiving capacity is neither too limited nor too expensive.

Archives↗