R. Baud - Academia.edu (original) (raw)
Papers by R. Baud
Studies in health technology and informatics, 2004
OBJECTIVES To cope with medical terms, which present a high variability of expression through a s... more OBJECTIVES To cope with medical terms, which present a high variability of expression through a single natural language, in the sense that any term may be reformulated in hundred of different ways. METHODS A typology of term variants is presented as a systematic approach in order to favour the implementation of an exhaustive solution. Then, an algorithm able to handle all variants is designed. RESULTS Using MetaMap, single terms are analyzed with a success rate varying between 68 and 88 %; the algorithm presented in this paper improves this situation. CONCLUSIONS This experience shows that a semantic driven method, based on a thesaurus, provides a satisfactory solution to the problem of variability of a single term. The presented typology is representative of most variants in a language.
Medinfo. MEDINFO, 1995
Re-usable and sharable, and therefore language-independent concept models are of increasing impor... more 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...
Expert Systems and Decision Support in Medicine, 1988
In der Praxis ist die Verschlusselung von Diagnosen mit Schwierigkeiten verbunden. Manuelle Versc... more In der Praxis ist die Verschlusselung von Diagnosen mit Schwierigkeiten verbunden. Manuelle Verschlusselung ist fur Arzte unattraktiv. Beim Einsatz von spezialisiertem Personal entstehen Kommunikationsprobleme und eine starke Abhangigkeit von der Qualifikation des Personals. Fur Systeme zur automatischen Verschlusselung sind die komplexen Probleme bei der Verarbeitung naturlicher Sprache zu losen.
Medical and nursing staff are busy people and their turnover in a teaching hospital is high. Teac... more Medical and nursing staff are busy people and their turnover in a teaching hospital is high. Teaching them the use of a computer station in a variety of applications belonging to a Medical Information System has to be very short and efficient. Data collection and retrieval has to be simple and accurate. Users training and permanent support may be an overwhelming task in a large hospital because of the numerous employees, the numerous medical departments, and long distances between groups of terminals running the same application. The tree branching logic of a frame selection system and a specially designed video-telephone station have been implemented at the University Hospital of Geneva as key elements actually reducing nurses and doctors initial training to a minimum. Numerical data are presented on the number of users, their training periods, and their activity on terminals.
Morphologie, 2006
ABSTRACT La publication en 1998 de « Terminologia. Anatomica » représentait une étape relativemen... more ABSTRACT La publication en 1998 de « Terminologia. Anatomica » représentait une étape relativement importante dans l’adoption d’un langage anatomique universellement compréhensible. Un peu plus de 7 000 termes anatomiques ont été compulsés en latin par un comité élu à cet effet et approuvés par une soixantaine de sociétés anatomiques dans le monde. La liste de ces termes était accompagnée d’une liste de noms équivalents en anglais. Elle a déjà servi de base à la rédaction de listes officielles en plusieurs langues vernaculaires. Une terminologie française officielle est d’ailleurs en cours de réalisation. Cependant, si l’existence de termes officiels communs satisfait les anatomistes et les enseignants, il n’en va généralement pas de même pour les cliniciens. Il arrive même souvent que chaque spécialité utilise un vocabulaire clinique qui lui est propre. De plus, un des objectifs de l’Organisation Mondiale de la Santé (OMS) est de promouvoir la transparence des dossiers médicaux au moyen d’outils informatiques indépendants des contingences linguistiques. Or il apparaît très vite, dès qu’on s’attaque à une tâche pareille, que ce sont les termes anatomiques prennent une place importante à la base de tels outils. Une équipe de chercheurs menée par Cornelius Rosse à Seattle a donc développé, au cours des 10 dernières années, un modèle descriptif, le Foundational Model of Anatomy (FMA), qui détaille les entités constituant le corps humain en fonction de leurs rapports topographiques. Ce modèle comporte actuellement 70 000 concepts, qui peuvent être explorés de manière automatique à partir de leurs interrelations. Un projet se dessine maintenant visant à rendre compatibles avec le FMA une version future de la Terminologie Anatomique (et Histologique). Il s’agit d’accorder les termes formels utilisés dans l’enseignement académique de la médecine avec les dénominations variées employées dans les nombreux jargons de l’usage clinique, et cela, quelle que soit la langue des utilisateurs.
International Journal of Bio-Medical Computing, 1996
The UNIDOC system of computer-based medical records that was developed and made operational withi... more The UNIDOC system of computer-based medical records that was developed and made operational within the DIOGENE-2 Hospital Information System (HIS), is based upon a fully standardized and distributed open systems architecture. It should also be emphasized that UNIDOC illustrates a feasible marriage of the two technologies, UNIX and MS-DOS, is in many respects successful enough to be recommended as a sound general solution to medical office integration into a HIS.
Proceedings / AMIA ... Annual Symposium. AMIA Symposium, 2001
Content extraction from medical texts is achievable today by linguistic applications, in so far a... more Content extraction from medical texts is achievable today by linguistic applications, in so far as sufficient domain knowledge is available. Such knowledge represents a model of the domain and is hard to collect with sufficient depth and good coverage, despite numerous attempts. To leverage this task is a priority in order to benefit from the awaited linguistic tools. The light model is designed with this goal in mind. Syntactic and lexical information are generally available with large lexicons. A domain model should add the necessary semantic information. The authors have designed a light knowledge model for the collection of semantic information on the basis of the recognized syntactical and lexical attributes. It has been tailored for the acquisition of enough semantic information in order to retrieve terms of a controlled vocabulary from free texts, as for example, to retrieve Mesh terms from patient records.
Proceedings / AMIA ... Annual Symposium. AMIA Symposium, 2001
We report on the comparison of two systems for correcting spelling errors resulting in non-existe... more We report on the comparison of two systems for correcting spelling errors resulting in non-existent words (i.e. not listed in any lexicon). Both systems aim at improving edition of medical reports. Unlike traditional systems, based on word language models, both semantic and syntactic contexts are considered here. Both systems share the same string-to-string edit distance module, and the same contextual disambiguation principles. The differences between the two systems are located at the user interaction level: while the first system is using exclusively the left context, simulating the underlining of every mis-spelling at the end of every word typing, the second system uses the left as well as the right context and simulate a post-edition correction, when asked by the author. Our conclusion shows the improvements brought by the second approach.
Medinfo. MEDINFO, 1995
This paper presents the design of a Medical Linguistic Knowledge Base (MLKB). This MLKB is intend... more 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.
Lecture Notes in Medical Informatics, 1985
This paper presents an exhaustive analysis of patients flow (admissions, transfers and discharges... more This paper presents an exhaustive analysis of patients flow (admissions, transfers and discharges) during one year at the University Hospital of Geneva. Specific characteristics of different medical specialities are enlighted, such as: admission mode, duration of stay, age of patients, rate of transfers, etc.
Lecture Notes in Computer Science, 2001
Page 1. S. Quaglini, P. Barahona, and S. Andreassen (Eds.): AIME 2001, LNAI 2101, pp. 249257, 20... more Page 1. S. Quaglini, P. Barahona, and S. Andreassen (Eds.): AIME 2001, LNAI 2101, pp. 249257, 2001. © Springer-Verlag Berlin Heidelberg 2001 Using Part-of-Speech and Word-Sense Disambiguation for Boosting String-Edit Distance Spelling Correction ...
Lecture Notes in Computer Science, 1995
Researchers in the Artificial Intelligence in Medicine community are facing the challenge to desi... more Researchers in the Artificial Intelligence in Medicine community are facing the challenge to design and develop clinical systems which are intuitive to use and adequately expressive. This paper reports on a Structured Clinical User Interface (SCUI) which achieves this goal by using technologies developed in the Galen project: a new formalism to represent models of terminology coupled with a server
Studies in health technology and informatics, 2004
OBJECTIVES To cope with medical terms, which present a high variability of expression through a s... more OBJECTIVES To cope with medical terms, which present a high variability of expression through a single natural language, in the sense that any term may be reformulated in hundred of different ways. METHODS A typology of term variants is presented as a systematic approach in order to favour the implementation of an exhaustive solution. Then, an algorithm able to handle all variants is designed. RESULTS Using MetaMap, single terms are analyzed with a success rate varying between 68 and 88 %; the algorithm presented in this paper improves this situation. CONCLUSIONS This experience shows that a semantic driven method, based on a thesaurus, provides a satisfactory solution to the problem of variability of a single term. The presented typology is representative of most variants in a language.
Medinfo. MEDINFO, 1995
Re-usable and sharable, and therefore language-independent concept models are of increasing impor... more 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...
Expert Systems and Decision Support in Medicine, 1988
In der Praxis ist die Verschlusselung von Diagnosen mit Schwierigkeiten verbunden. Manuelle Versc... more In der Praxis ist die Verschlusselung von Diagnosen mit Schwierigkeiten verbunden. Manuelle Verschlusselung ist fur Arzte unattraktiv. Beim Einsatz von spezialisiertem Personal entstehen Kommunikationsprobleme und eine starke Abhangigkeit von der Qualifikation des Personals. Fur Systeme zur automatischen Verschlusselung sind die komplexen Probleme bei der Verarbeitung naturlicher Sprache zu losen.
Medical and nursing staff are busy people and their turnover in a teaching hospital is high. Teac... more Medical and nursing staff are busy people and their turnover in a teaching hospital is high. Teaching them the use of a computer station in a variety of applications belonging to a Medical Information System has to be very short and efficient. Data collection and retrieval has to be simple and accurate. Users training and permanent support may be an overwhelming task in a large hospital because of the numerous employees, the numerous medical departments, and long distances between groups of terminals running the same application. The tree branching logic of a frame selection system and a specially designed video-telephone station have been implemented at the University Hospital of Geneva as key elements actually reducing nurses and doctors initial training to a minimum. Numerical data are presented on the number of users, their training periods, and their activity on terminals.
Morphologie, 2006
ABSTRACT La publication en 1998 de « Terminologia. Anatomica » représentait une étape relativemen... more ABSTRACT La publication en 1998 de « Terminologia. Anatomica » représentait une étape relativement importante dans l’adoption d’un langage anatomique universellement compréhensible. Un peu plus de 7 000 termes anatomiques ont été compulsés en latin par un comité élu à cet effet et approuvés par une soixantaine de sociétés anatomiques dans le monde. La liste de ces termes était accompagnée d’une liste de noms équivalents en anglais. Elle a déjà servi de base à la rédaction de listes officielles en plusieurs langues vernaculaires. Une terminologie française officielle est d’ailleurs en cours de réalisation. Cependant, si l’existence de termes officiels communs satisfait les anatomistes et les enseignants, il n’en va généralement pas de même pour les cliniciens. Il arrive même souvent que chaque spécialité utilise un vocabulaire clinique qui lui est propre. De plus, un des objectifs de l’Organisation Mondiale de la Santé (OMS) est de promouvoir la transparence des dossiers médicaux au moyen d’outils informatiques indépendants des contingences linguistiques. Or il apparaît très vite, dès qu’on s’attaque à une tâche pareille, que ce sont les termes anatomiques prennent une place importante à la base de tels outils. Une équipe de chercheurs menée par Cornelius Rosse à Seattle a donc développé, au cours des 10 dernières années, un modèle descriptif, le Foundational Model of Anatomy (FMA), qui détaille les entités constituant le corps humain en fonction de leurs rapports topographiques. Ce modèle comporte actuellement 70 000 concepts, qui peuvent être explorés de manière automatique à partir de leurs interrelations. Un projet se dessine maintenant visant à rendre compatibles avec le FMA une version future de la Terminologie Anatomique (et Histologique). Il s’agit d’accorder les termes formels utilisés dans l’enseignement académique de la médecine avec les dénominations variées employées dans les nombreux jargons de l’usage clinique, et cela, quelle que soit la langue des utilisateurs.
International Journal of Bio-Medical Computing, 1996
The UNIDOC system of computer-based medical records that was developed and made operational withi... more The UNIDOC system of computer-based medical records that was developed and made operational within the DIOGENE-2 Hospital Information System (HIS), is based upon a fully standardized and distributed open systems architecture. It should also be emphasized that UNIDOC illustrates a feasible marriage of the two technologies, UNIX and MS-DOS, is in many respects successful enough to be recommended as a sound general solution to medical office integration into a HIS.
Proceedings / AMIA ... Annual Symposium. AMIA Symposium, 2001
Content extraction from medical texts is achievable today by linguistic applications, in so far a... more Content extraction from medical texts is achievable today by linguistic applications, in so far as sufficient domain knowledge is available. Such knowledge represents a model of the domain and is hard to collect with sufficient depth and good coverage, despite numerous attempts. To leverage this task is a priority in order to benefit from the awaited linguistic tools. The light model is designed with this goal in mind. Syntactic and lexical information are generally available with large lexicons. A domain model should add the necessary semantic information. The authors have designed a light knowledge model for the collection of semantic information on the basis of the recognized syntactical and lexical attributes. It has been tailored for the acquisition of enough semantic information in order to retrieve terms of a controlled vocabulary from free texts, as for example, to retrieve Mesh terms from patient records.
Proceedings / AMIA ... Annual Symposium. AMIA Symposium, 2001
We report on the comparison of two systems for correcting spelling errors resulting in non-existe... more We report on the comparison of two systems for correcting spelling errors resulting in non-existent words (i.e. not listed in any lexicon). Both systems aim at improving edition of medical reports. Unlike traditional systems, based on word language models, both semantic and syntactic contexts are considered here. Both systems share the same string-to-string edit distance module, and the same contextual disambiguation principles. The differences between the two systems are located at the user interaction level: while the first system is using exclusively the left context, simulating the underlining of every mis-spelling at the end of every word typing, the second system uses the left as well as the right context and simulate a post-edition correction, when asked by the author. Our conclusion shows the improvements brought by the second approach.
Medinfo. MEDINFO, 1995
This paper presents the design of a Medical Linguistic Knowledge Base (MLKB). This MLKB is intend... more 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.
Lecture Notes in Medical Informatics, 1985
This paper presents an exhaustive analysis of patients flow (admissions, transfers and discharges... more This paper presents an exhaustive analysis of patients flow (admissions, transfers and discharges) during one year at the University Hospital of Geneva. Specific characteristics of different medical specialities are enlighted, such as: admission mode, duration of stay, age of patients, rate of transfers, etc.
Lecture Notes in Computer Science, 2001
Page 1. S. Quaglini, P. Barahona, and S. Andreassen (Eds.): AIME 2001, LNAI 2101, pp. 249257, 20... more Page 1. S. Quaglini, P. Barahona, and S. Andreassen (Eds.): AIME 2001, LNAI 2101, pp. 249257, 2001. © Springer-Verlag Berlin Heidelberg 2001 Using Part-of-Speech and Word-Sense Disambiguation for Boosting String-Edit Distance Spelling Correction ...
Lecture Notes in Computer Science, 1995
Researchers in the Artificial Intelligence in Medicine community are facing the challenge to desi... more Researchers in the Artificial Intelligence in Medicine community are facing the challenge to design and develop clinical systems which are intuitive to use and adequately expressive. This paper reports on a Structured Clinical User Interface (SCUI) which achieves this goal by using technologies developed in the Galen project: a new formalism to represent models of terminology coupled with a server