Ivan Kergourlay

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.

Information retrieval in context using various health terminologies

Information retrieval is a branch of computer science concerned with the acquisition, storage, search and selection of information. From the user point of view, the access to information can be carried out in a deliberate way through an information retrieval system, or in a passive way through an information filtration system. CISMeF (Catalogue and Index of the French-speaking Medical Sites) is a health portal aiming to catalogue and index the most important French-speaking institutional health information sources in order to make them available to health professionals, medical students and the general public. The Internet resources were manually indexed and have remained mono-terminological from 1995 to 2007 originally based exclusively on the MeSH thesaurus (Medical Subject Headings). Categorization allows a contextual information retrieval parameterized according to the users needs. In 2007, the CISMeF team directed its objectives towards a multi-terminological universe by the integration of the medical data heterogeneous sources into its back-office. To date, the practical application is the creation of a bilingual (French/English) drug information portal in order to facilitate the user information retrieval about drugs.

Codage standardisé de données médicales textuelles à l’aide d’un serveur multi-terminologique de santé: Exemple d’application en épidémiologie hospitalière

Currently, extraction of data for epidemiological surveillance is severely limited by the lack of standardised structuring of medical records. The objective of this study is to describe a semi-automatic method for standardized coding of textual medical records for epidemiological use. In the context of the ALADIN-DTH research project, we are planning to develop a tool for detecting nosocomial infections. With that goal in mind we will ask physicians to manually code 2,000 hospital medical records using different appropriate medical terminologies (ICD10, SNOMED 3.5, ATC, CCAM, MeSH). A French automatic Multi-Terminology Health Concept Extractor (French acronym: ECMT) can offer a choice of labels and codes of different terminologies. This tool can be called on a distant server via an Internet connection thanks to an XML service. Among 3,450 medical expressions queried by users, the ECMT has proposed relevant codes for 70,5% of them (original formulation) and 87,7% of them after correction of the formulation by the annotator, this result ranging from 51,3% (bacteriological examinations) to 96,4% (symptoms/diagnoses). A multi-terminology health concept extractor is an interesting tool for standardized coding of textual data for epidemiological use.

Accuracy of using natural language processing methods for identifying healthcare-associated infections

OBJECTIVE There is a growing interest in using natural language processing (NLP) for healthcare-associated infections (HAIs) monitoring. A French project consortium, SYNODOS, developed a NLP solution for detecting medical events in electronic medical records for epidemiological purposes. The objective of this study was to evaluate the performance of the SYNODOS data processing chain for detecting HAIs in clinical documents. MATERIALS AND METHODS The collection of textual records in these hospitals was carried out between October 2009 and December 2010 in three French University hospitals (Lyon, Rouen and Nice). The following medical specialties were included in the study: digestive surgery, neurosurgery, orthopedic surgery, adult intensive-care units. Reference Standard surveillance was compared with the results of automatic detection using NLP. Sensitivity on 56 HAI cases and specificity on 57 non-HAI cases were calculated. RESULTS The accuracy rate was 84% (n = 95/113). The overall sensitivity of automatic detection of HAIs was 83.9% (CI 95%: 71.7-92.4) and the specificity was 84.2% (CI 95%: 72.1-92.5). The sensitivity varies from one specialty to the other, from 69.2% (CI 95%: 38.6-90.9) for intensive care to 93.3% (CI 95%: 68.1-99.8) for orthopedic surgery. The manual review of classification errors showed that the most frequent cause was an inaccurate temporal labeling of medical events, which is an important factor for HAI detection. CONCLUSION This study confirmed the feasibility of using NLP for the HAI detection in hospital facilities. Automatic HAI detection algorithms could offer better surveillance standardization for hospital comparisons.