Julien Grosjean

Aligning Biomedical Terminologies in French: Towards Semantic Interoperability in Medical Applications

In health, there exist practically as many different terminologies, controlled vocabularies, thesauri and classification systems as there are fields of application. In fact, terminologies play important roles in clinical data capture, annotation, reporting, information integration, indexing and retrieval. These knowledge sources havemostly different formats and purposes. For example, among many other knowledge sources, the Systematized NOmenclature of MEDicine International (SNOMED Int) is used for clinical coding, the French CCAM for procedures, the 10th revision of the International Classification of Diseases (ICD10) and the Anatomical Therapeutic Chemical (ATC) Classification for drugs are used for epidemiological and medico-economic purposes and the Medical Subject Headings (MeSH) thesaurus for indexing bibliographic databases. Given the great number of terminologies, existing tools, such as search engines, coding systems or decision support systems, are limited in dealing with “syntactic” and “semantic” divergences in spite of their great storage capacity and quick processing of data. Faced with this reality and the increasing need to allow cooperation with/between the various health actors and their related health information systems, it appears necessary to link and connect these terminologies to make them “interoperable”. The objective is to allow the different actors to speak the same language while using different representations of the same things. As it is essential to render these terminologies “interoperable”, this involves establishing a joint semantic repository to allow effective interaction with a minimum loss of meaning. This semantic interoperability requires a shared model, i.e. a common representation of terms and concepts, whatever the original terminology or repository is but it also requires the development of methods to allow connection between equivalent terms or relations from each terminology.

A Search Engine to Access PubMed Monolingual Subsets: Proof of Concept and Evaluation in French

Background PubMed contains numerous articles in languages other than English. However, existing solutions to access these articles in the language in which they were written remain unconvincing. Objective The aim of this study was to propose a practical search engine, called Multilingual PubMed, which will permit access to a PubMed subset in 1 language and to evaluate the precision and coverage for the French version (Multilingual PubMed-French). Methods To create this tool, translations of MeSH were enriched (eg, adding synonyms and translations in French) and integrated into a terminology portal. PubMed subsets in several European languages were also added to our database using a dedicated parser. The response time for the generic semantic search engine was evaluated for simple queries. BabelMeSH, Multilingual PubMed-French, and 3 different PubMed strategies were compared by searching for literature in French. Precision and coverage were measured for 20 randomly selected queries. The results were evaluated as relevant to title and abstract, the evaluator being blind to search strategy. Results More than 650,000 PubMed citations in French were integrated into the Multilingual PubMed-French information system. The response times were all below the threshold defined for usability (2 seconds). Two search strategies (Multilingual PubMed-French and 1 PubMed strategy) showed high precision (0.93 and 0.97, respectively), but coverage was 4 times higher for Multilingual PubMed-French. Conclusions It is now possible to freely access biomedical literature using a practical search tool in French. This tool will be of particular interest for health professionals and other end users who do not read or query sufficiently in English. The information system is theoretically well suited to expand the approach to other European languages, such as German, Spanish, Norwegian, and Portuguese.

Improving information retrieval by meta-modelling medical terminologies

This work aims at improving information retrieval in a health gateway by meta-modelling multiple terminologies related to medicine. The meta-model is based on meta-terms that gather several terms semantically related. Meta-terms, initially modelled for the MeSH thesaurus, are extended for other terminologies such as IC10 or SNOMED Int. The usefulness of this model and the relevance of information retrieval is evaluated and compared in the case of one and multiple terminologies. The results show that exploiting multiple terminologies contributes to increase recall but lowers precision.

Evaluating alignment quality between iconic language and reference terminologies using similarity metrics.

BackgroundVisualization of Concepts in Medicine (VCM) is a compositional iconic language that aims to ease information retrieval in Electronic Health Records (EHR), clinical guidelines or other medical documents. Using VCM language in medical applications requires alignment with medical reference terminologies. Alignment from Medical Subject Headings (MeSH) thesaurus and International Classification of Diseases – tenth revision (ICD10) to VCM are presented here. This study aim was to evaluate alignment quality between VCM and other terminologies using different measures of inter-alignment agreement before integration in EHR.MethodsFor medical literature retrieval purposes and EHR browsing, the MeSH thesaurus and the ICD10, both organized hierarchically, were aligned to VCM language. Some MeSH to VCM alignments were performed automatically but others were performed manually and validated. ICD10 to VCM alignment was entirely manually performed. Inter-alignment agreement was assessed on ICD10 codes and MeSH descriptors, sharing the same Concept Unique Identifiers in the Unified Medical Language System (UMLS). Three metrics were used to compare two VCM icons: binary comparison, crude Dice Similarity Coefficient (DSCcrude), and semantic Dice Similarity Coefficient (DSCsemantic), based on Lin similarity. An analysis of discrepancies was performed.ResultsMeSH to VCM alignment resulted in 10,783 relations: 1,830 of which were manually performed and 8,953 were automatically inherited. ICD10 to VCM alignment led to 19,852 relations. UMLS gathered 1,887 alignments between ICD10 and MeSH. Only 1,606 of them were used for this study. Inter-alignment agreement using only validated MeSH to VCM alignment was 74.2% [70.5-78.0]CI95%, DSCcrude was 0.93 [0.91-0.94]CI95%, and DSCsemantic was 0.96 [0.95-0.96]CI95%. Discrepancy analysis revealed that even if two thirds of errors came from the reviewers, UMLS was nevertheless responsible for one third.ConclusionsThis study has shown strong overall inter-alignment agreement between MeSH to VCM and ICD10 to VCM manual alignments. VCM icons have now been integrated into a guideline search engine (http://www.cismef.org) and a health terminologies portal (http://www.hetop.eu).

Development, dissemination, and applications of a new terminological resource the Q-Code taxonomy for professional aspects of General Practice / Family Medicine.

Abstract Background: While documentation of clinical aspects of General Practice/Family Medicine (GP/FM) is assured by the International Classification of Primary Care (ICPC), there is no taxonomy for the professional aspects (context and management) of GP/FM. Objectives: To present the development, dissemination, applications, and resulting face validity of the Q-Codes taxonomy specifically designed to describe contextual features of GP/FM, proposed as an extension to the ICPC. Development: The Q-Codes taxonomy was developed from Lamberts’ seminal idea for indexing contextual content (1987) by a multi-disciplinary team of knowledge engineers, linguists and general practitioners, through a qualitative and iterative analysis of 1702 abstracts from six GP/FM conferences using Atlas.ti software. A total of 182 concepts, called Q-Codes, representing professional aspects of GP/FM were identified and organized in a taxonomy. Dissemination: The taxonomy is published as an online terminological resource, using semantic web techniques and web ontology language (OWL) (http://www.hetop.eu/Q). Each Q-Code is identified with a unique resource identifier (URI), and provided with preferred terms, and scope notes in ten languages (Portuguese, Spanish, English, French, Dutch, Korean, Vietnamese, Turkish, Georgian, German) and search filters for MEDLINE and web searches. Applications: This taxonomy has already been used to support queries in bibliographic databases (e.g., MEDLINE), to facilitate indexing of grey literature in GP/FM as congress abstracts, master theses, websites and as an educational tool in vocational teaching, Conclusions: The rapidly growing list of practical applications provides face-validity for the usefulness of this freely available new terminological resource.

Un modèle de données adapté à la recherche d’information dans le dossier patient informatisé: Étude, conception et évaluation

Background: Electronic Health Records (EHRs) have an important role in medical decision making and are considered as being a major part of medical support system. To ensure this role effectively, the information must be easily found, even in voluminous and large number of EHRs. This requires to develop search capabilities for EHR information retrieval (IR). Methods: To perform this, we propose a data model adapted to IR. The data analysis of EHRs of the Rouen University Hospital led us to consider them as being a set of informational elements linked by temporal and conceptual relationships. This model consists of two main entities to manage the information elements and their metadata. After implementation, we have evaluated the capacity of the proposed model to take into account all data from the EHRs and its adaptation to IR. Results: We have performed 25 queries on EHR (20 correspond to single patient and 5 to multi-patients). The results in 19 cases (including 3 partial results) were evaluated as successful. These results confirm the ability of the model to take into account most of relevant data of EHR in IR and clearly show the differences in complexity of queries between the initial and our model of IR. Conclusion: The preliminary evaluation of the data model we have developed has shown its adaptation to IR in EHR. Nevertheless, further work on larger sets is needed to confirm this.