Nicolas Garcelon

Roogle: an information retrieval engine for clinical data warehouse.

High amount of relevant information is contained in reports stored in the electronic patient records and associated metadata. R-oogle is a project aiming at developing information retrieval engines adapted to these reports and designed for clinicians. The system consists in a data warehouse (full-text reports and structured data) imported from two different hospital information systems. Information retrieval is performed using metadata-based semantic and full-text search methods (as Google). Applications may be biomarkers identification in a translational approach, search of specific cases, and constitution of cohorts, professional practice evaluation, and quality control assessment.

The value of using verbs in Medline searches.

New findings are continuously identified thanks to novel diagnostic procedures, among others in medical imaging. It would be useful to retrieve these new findings from literature. The aim of this work is to investigate if using verbs in MEDLINE queries can improve the retrieval of findings. Verbs used in the field of findings were selected: ‘to show’ (an examination shows a finding) and ‘to confirm’ (a finding confirms a diagnosis). For each of these verbs, semantically close verbs were researched on the WordNet website. Then, the extent to which adding these verbs to a query about various radiological pathologies can improve findings retrieval in Medline citations was studied. This method has been tested on two sets of MEDLINE citations regarding the diagnostic imaging of musculo-skeletal disorders. Using appropriate verbs in Medline queries enhances the precision from 53% to 61% and from 53% to 74%, respectively, in our first and second test set. A recall of 74% and 83% was reached in our two experiments. Using relevant verbs can be a rather simple way to improve the retrieval of findings related to diseases and diagnostic procedures from Medline citations.

L’informatisation du signe radiologique

The goal of this article is to present to the radiologist the different theories of the sign and their consequences for sign representation in computer systems. All the theories of the sign are presented, but the most relevant are highlighted in order to explain the great modeling systems currently in use (such as DICOM-SR or the UMLS). The constructivist approach of the notion of disease, the semiosis process, which starting from signs produces new signs, and the structuralist analysis of sign through language are emphasized. The purpose of this analysis is to end up with a consensual representation of the sign that can be understood by human beings and processed by machines. Such a representation, also known as an ontology, is based on a semantic organization of language, thus allowing medicine to become a truly scientific discipline. It aims at disambiguating the symbols given to machines, which will help us in our reasoning.

Methode de creation de bases de connaissances radiologiques utilisant le test de concordance des scripts

Objectifs Proposer et evaluer une methode de creation d’une base de connaissances radiologiques centree sur les plaintes des patients utilisant le test de concordance des scripts. Materiels et methodes Nous utilisons la methode d’elaboration des scripts pour interroger des experts sur les scapulalgies. Ils creent des items : indications (si je pense faire – et qu’alors je trouve – l’effet sur la necessite de demander cet examen est) et diagnostics (si je pense a – et qu’alors je trouve – l’effet sur l’hypothese diagnostique est). Les items obtenus sont ensuite relies comme suit : signe d’appel (indique) examen (montre) signe radiologique (diagnostique) maladie. L’analyse globale des relations a ensuite ete effectuee. Resultats Le reseau semantique est constitue de 131 chainons diagnostics et 89 chainons indications. Les chainons indications sont constitues de 20 examens et de 59 signes d’appel. Les chainons diagnostics sont constitues de 55 diagnostics et 72 signes radiologiques. Le reseau se replie car maladies, signes d’appel et signes radiologiques peuvent partager les memes concepts. Conclusion Le test de concordance des scripts permet d’interroger les experts en suivant leur logique hypotheticodeductive. Le reseau semantique obtenu est une modelisation du processus d’indication et de diagnostic radiologique. Il est utilisable pour des tâches automatisees d’evaluation ou d’expertise.