Search

BACKGROUND Word embedding technologies are now used in a wide range of applications. However, no formal evaluation and comparison have been made on models produced by the three most famous implementations (Word2Vec, GloVe and FastText). OBJECTIVE The goal of this study is to compare embedding implementations on a corpus of documents produced in a working context, by health professionals. METHODS Models have been trained on documents coming from the Rouen university hospital. This data is not structured and cover a wide range of documents produced in a clinic (discharge summary, prescriptions ...). Four evaluation tasks have been defined (cosine similarity, odd one, mathematical operations and human formal evaluation) and applied on each model. RESULTS Word2Vec had the highest score for three of the four tasks (mathematical operations, odd one similarity and human validation), particularly regarding the Skip-Gram architecture. CONCLUSIONS Even if this implementation had the best rate, each model has its own qualities and defects, like the training time which is very short for GloVe or morphosyntaxic similarity conservation observed with FastText. Models and test sets produced by this study will be the first publicly available through a graphical interface to help advance French biomedical research.

Background Adverse drug reactions (ADRs) are an important cause of morbidity and mortality. Classical Pharmacovigilance process is limited by underreporting which justifies the current interest in new knowledge sources such as social media. The Adverse Drug Reactions from Patient Reports in Social Media (ADR-PRISM) project aims to extract ADRs reported by patients in these media. We identified 5 major challenges to overcome to operationalize the analysis of patient posts: (1) variable quality of information on social media, (2) guarantee of data privacy, (3) response to pharmacovigilance expert expectations, (4) identification of relevant information within Web pages, and (5) robust and evolutive architecture. Objective This article aims to describe the current state of advancement of the ADR-PRISM project by focusing on the solutions we have chosen to address these 5 major challenges. Methods In this article, we propose methods and describe the advancement of this project on several aspects: (1) a quality driven approach for selecting relevant social media for the extraction of knowledge on potential ADRs, (2) an assessment of ethical issues and French regulation for the analysis of data on social media, (3) an analysis of pharmacovigilance expert requirements when reviewing patient posts on the Internet, (4) an extraction method based on natural language processing, pattern based matching, and selection of relevant medical concepts in reference terminologies, and (5) specifications of a component-based architecture for the monitoring system. Results Considering the 5 major challenges, we (1) selected a set of 21 validated criteria for selecting social media to support the extraction of potential ADRs, (2) proposed solutions to guarantee data privacy of patients posting on Internet, (3) took into account pharmacovigilance expert requirements with use case diagrams and scenarios, (4) built domain-specific knowledge resources embeding a lexicon, morphological rules, context rules, semantic rules, syntactic rules, and post-analysis processing, and (5) proposed a component-based architecture that allows storage of big data and accessibility to third-party applications through Web services. Conclusions We demonstrated the feasibility of implementing a component-based architecture that allows collection of patient posts on the Internet, near real-time processing of those posts including annotation, and storage in big data structures. In the next steps, we will evaluate the posts identified by the system in social media to clarify the interest and relevance of such approach to improve conventional pharmacovigilance processes based on spontaneous reporting.

ATC classification is a WHO international classification used to classify drugs. The aim of this paper is to evaluate two lexical methods in English and in French to map ATC to UMLS. Several applications have been impemented to illustrate the use of the ATC mapping in English and French: (a) MeSH translation in Norwegian, (b) Drug Information Portal, and (c) ATC to PubMed tool. Two lexical methods were used to map ATC to UMLS. The first approach used a French natural language processing tool to map French terms of ATC to the French terminologies of UMLS. The second approach used the MetaMap tool to map English terms of ATC to UMLS. The English MetaMap provides slightly more mappings than the French NLP tool (3,170 vs. 2,992). On the other hand, the French NLP tool provides a slightly better precision than MetaMap (88% vs. 86%). Using a manual mapping between ATC and MeSH, the union of the validated mappings between ATC and MeSH provides 2,824 mappings (68.7% of ATC codes of the fifth level). Lexical methods are powerful methods to map health terminologies to the UMLS Metathesaurus. Manual mapping is still necessary to complete the mapping.