Biomedical subjects

Marc Cuggia

Publications and source records attributed to Marc Cuggia.

10 recordsLinked to original sources

PubMed2006

A model for a regional health information network sharing clinical information between professionals in Britanny.

The purpose of this paper is to present a generic model of information system supporting healthcare networks for health professionals in Brittany. This model is aimed to develop cooperation between hospital professionals, primary care and practitioners whatever the specific pathology, by providing tools for exchanging and sharing medical-related data. The model is designed based on the heterogeneity factors revealed by a prospective survey. It includes secured exchange of nominative medical data, all other information and activities being accessible by a Web portal. Other associated tools are a synchronous collaborative platform, and a e-learning module. The first implementation, currently in use by the professionals, is presented for the existing neurology healthcare networks.

France↗

PubMed2005

Indexing method of digital audiovisual medical resources with semantic Web integration.

Digitalization of audiovisual resources and network capability offer many possibilities which are the subject of intensive work in scientific and industrial sectors. Indexing such resources is a major challenge. Recently, the Motion Pictures Expert Group (MPEG) has developed MPEG-7, a standard for describing multimedia content. The goal of this standard is to develop a rich set of standardized tools to enable efficient retrieval from digital archives or the filtering of audiovisual broadcasts on the Internet. How could this kind of technology be used in the medical context? In this paper, we propose a simpler indexing system, based on the Dublin Core standard and compliant to MPEG-7. We use MeSH and the UMLS to introduce conceptual navigation. We also present a video-platform which enables encoding and gives access to audiovisual resources in streaming mode.

Abstracting and Indexing↗

PubMed2005

An Improved Publication Process for the UMVF.

The "Université Médicale Virtuelle Francophone" (UMVF) is a federation of French medical schools. Its main goal is to share the production and use of pedagogic medical resources generated by academic medical teachers. We developed an Open-Source application based upon a workflow system which provides an improved publication process for the UMVF. For teachers, the tool permits easy and efficient upload of new educational resources. For web masters it provides a mechanism to easily locate and validate the resources. For both the teachers and the web masters, the utility provides the control and communication functions that define a workflow system.For all users, students in particular, the application improves the value of the UMVF repository by providing an easy way to find a detailed description of a resource and to check any resource from the UMVF to ascertain its quality and integrity, even if the resource is an old deprecated version. The server tier of the application is used to implement the main workflow functionalities and is deployed on certified UMVF servers using the PHP language, an LDAP directory and an SQL database. The client tier of the application provides both the workflow and the search and check functionalities and is implemented using a Java applet through a W3C compliant web browser. A unique signature for each resource, was needed to provide security functionality and is implemented using the MD5 Digest algorithm. The testing performed by Rennes and Lille verified the functionality and conformity with our specifications.

Education, Medical↗

PubMed2004

Predicting survival causes after out of hospital cardiac arrest using data mining method.

BACKGROUND: The prognosis of life for patients with heart failure remains poor. By using data mining methods, the purpose of this study was to evaluate the most important criteria for predicting patient survival and to profile patients to estimate their survival chances together with the most appropriate technique for health care. METHODS: Five hundred and thirty three patients who had suffered from cardiac arrest were included in the analysis. We performed classical statistical analysis and data mining analysis using mainly Bayesian networks. RESULTS: The mean age of the 533 patients was 63 (+/- 17) and the sample was composed of 390 (73 %) men and 143 (27 %) women. Cardiac arrest was observed at home for 411 (77 %) patients, in a public place for 62 (12 %) patients and on a public highway for 60 (11 %) patients. The belief network of the variables showed that the probability of remaining alive after heart failure is directly associated to five variables: age, sex, the initial cardiac rhythm, the origin of the heart failure and specialized resuscitation techniques employed. CONCLUSIONS: Data mining methods could help clinicians to predict the survival of patients and then adapt their practices accordingly. This work could be carried out for each medical procedure or medical problem and it would become possible to build a decision tree rapidly with the data of a service or a physician. The comparison between classic analysis and data mining analysis showed us the contribution of the data mining method for sorting variables and quickly conclude on the importance or the impact of the data and variables on the criterion of the study. The main limit of the method is knowledge acquisition and the necessity to gather sufficient data to produce a relevant model.

Bayes Theorem↗

PubMed2003

Automatic concept extraction from spoken medical reports.

OBJECTIVE: The objective of this project is to investigate methods whereby a combination of speech recognition and automated indexing methods substitute for current transcription and indexing practices. METHODS: We based our study on existing speech recognition software programs and on NOMINDEX, a tool that extracts MeSH concepts from medical text in natural language and that is mainly based on a French medical lexicon and on the UMLS. For each document, the process consists of three steps: (1) dictation and digital audio recording, (2) speech recognition, (3) automatic indexing. The evaluation consisted of a comparison between the set of concepts extracted by NOMINDEX after the speech recognition phase and the set of keywords manually extracted from the initial document. The method was evaluated on a set of 28 patient discharge summaries extracted from the MENELAS corpus in French, corresponding to in-patients admitted for coronarography. RESULTS: The overall precision was 73% and the overall recall was 90%. Indexing errors were mainly due to word sense ambiguity and abbreviations. A specific issue was the fact that the standard French translation of MeSH terms lacks diacritics. A preliminary evaluation of speech recognition tools showed that the rate of accurate recognition was higher than 98%. Only 3% of the indexing errors were generated by inadequate speech recognition. DISCUSSION: We discuss several areas to focus on to improve this prototype. However, the very low rate of indexing errors due to speech recognition errors highlights the potential benefits of combining speech recognition techniques and automatic indexing.

Abstracting and Indexing↗

PubMed2003

Medical pedagogical resources management.

The main objective of this work is to help the management of training resources for students using a pedagogical network available at the Medical School of Rennes. With the increase of the number of connections and the number of medical documents available on this network, the management of new contents requires a lot of efforts for the webmaster. In order to improve the management of the resources, we implemented an automatic web engine for teachers, able to manage the links for the most interesting resources for their practice.

Computer-Assisted Instruction↗

PubMed2003

Indexing method of digital audiovisual medical resources with semantic Web integration.

Digitalization of audio-visual resources combined with the performances of the networks offer many possibilities which are the subject of intensive work in the scientific and industrial sectors. Indexing such resources is a major challenge. Recently, the Motion Pictures Expert Group (MPEG) has been developing MPEG-7, a standard for describing multimedia content. The good of this standard is to develop a rich set of standardized tools to enable fast efficient retrieval from digital archives or filtering audiovisual broadcasts on the internet. How this kind of technologies could be used in the medical context? In this paper, we propose a simpler indexing system, based on Dublin Core standard and complaint to MPEG-7. We use MeSH and UMLS to introduce conceptual navigation. We also present a video-platform with enables to encode and give access to audio-visual resources in streaming mode.

Abstracting and Indexing↗

PubMed2003

Development of an indexing search engine for the UMVF: proposal for an indexing method based on Dublin Core and XML.

The UMVF (French Virtual Medical University) has many heterogeneous resources hosted by the servers of university partners of the project. One of its objectives is to develop an efficient tool to perform a single search on these resources. We first defined a standardized and interoperable indexing method. For each document, an XML file containing information on the fifteen elements of Dublin Core was created. We checked its structure and content with a DTD. If the XML file was valid, its data were then integrated into a central database from which the engine carried out a search. We tested our tool successfully with the resources hosted by the Rennes Laboratory of Medical Informatics in cooperation with the Radiology Medical Campus [1]. Our method allows the standardization of the production of information by the various servers and it conforms to the constraints of the semantic Web owing to the technologies chosen.

Abstracting and Indexing↗

PubMed2002

Combining voice recognition and automatic indexing of medical reports.

Medical records have been evolving from the traditional paper-based records to digital ones, from the method of dictating reports and transcription to voice recognition systems. The transition to digital operations will not be complete until we have the ability to combine voice recognition with automated indexing of texts. This paper introduces the methods we used to evaluate existing voice recognition software programs and presents NOMINDEX, a system that turns a medical text into MeSH codes, using the French ADM lexical database. Those systems were applied to 28 patient discharge summaries in French, produced after a coronarography, and extracted from the MENELAS corpus of texts. Using the best configuration for voice recognition, the rate of accurate recognition exceeds 98 percent. Among the indexing concepts assigned by NOMINDEX, 25 percent were not pertinent and 12 percent of the relevant concepts were missing. Most errors were related to confusion between common language and medical language, and to the coverage of the ADM lexical database. Best results would be expected with a more comprehensive lexical resource In addition, only 3 percent of the errors generated by inadequate voice recognition that remained in the configuration that performed better, impacted on automatic indexing by NOMINDEX.

Abstracting and Indexing↗

PubMedDate not supplied

[Monoclonal gammopathies of undetermined significance and their progression over time. Retrospective study of 190 patients].

INTRODUCTION: Monoclonal gammopathies of undetermined significance (MGUS) occur in up to 1% of persons aged 50 years or older. The risk of its progression to multiple myeloma or related disorders is also approximately 1% per year. OBJECTIVES: Our study had two aims: to describe the risk of malignant progression of patients examined in our center for MGUS, and to identify predictors of this malignant progression. METHODS: We retrospectively reviewed the medical records of patients with MGUS seen in our center from 1980 through 1995. Information about progression came either from the medical file or from responses to questionnaires sent to patients' general practitioners. RESULTS: The study included 190 patients. Median follow-up was 84 months (range: 12-240 months). MGUS remained stable for 128 patients (67.37%), whose median follow-up was 96 months. Malignant transformations occurred in 41 patients (21.58%). The median interval from diagnosis of MGUS to diagnosis of a lymphoplasma cell proliferative disorder was 49 months. The cumulative probability of progression was 13.05% at 5 years and 25.14% at 10 years. The initial concentration of serum monoclonal protein was a significant predictor of progression (threshold value: 15 g/L). DISCUSSION: The cumulative probability of progression in our study is higher than that observed elsewhere. Our results may well be biased by the short follow-up period and selective referrals. CONCLUSION: The initial concentration of serum monoclonal protein is a significant predictor of malignant progression of MGUS.

Adult↗