No abstract

BackgroundPubMed is the main access to medical literature on the Internet. In order to enhance the performance of its information retrieval tools, primarily non-indexed citations, the authors propose a method: expanding users' queries using Unified Medical Language System' (UMLS) synonyms i.e. all the terms gathered under one unique Concept Unique Identifier.MethodsThis method was evaluated using queries constructed to emphasize the differences between this new method and the current PubMed automatic term mapping. Four experts assessed citation relevance.ResultsUsing UMLS, we were able to retrieve new citations in 45.5% of queries, which implies a small increase in recall. The new strategy led to a heterogeneous 23.7% mean increase in non-indexed citation retrieved. Of these, 82% have been published less than 4 months earlier. The overall mean precision was 48.4% but differed according to the evaluators, ranging from 36.7% to 88.1% (Inter rater agreement was poor: kappa = 0.34).ConclusionsThis study highlights the need for specific search tools for each type of user and use-cases. The proposed strategy may be useful to retrieve recent scientific advancement.

Background Word embedding technologies, a set of language modeling and feature learning techniques in natural language processing (NLP), are now used in a wide range of applications. However, no formal evaluation and comparison have been made on the ability of each of the 3 current most famous unsupervised implementations (Word2Vec, GloVe, and FastText) to keep track of the semantic similarities existing between words, when trained on the same dataset. Objective The aim of this study was to compare embedding methods trained on a corpus of French health-related documents produced in a professional context. The best method will then help us develop a new semantic annotator. Methods Unsupervised embedding models have been trained on 641,279 documents originating from the Rouen University Hospital. These data are not structured and cover a wide range of documents produced in a clinical setting (discharge summary, procedure reports, and prescriptions). In total, 4 rated evaluation tasks were defined (cosine similarity, odd one, analogy-based operations, and human formal evaluation) and applied on each model, as well as embedding visualization. Results Word2Vec had the highest score on 3 out of 4 rated tasks (analogy-based operations, odd one similarity, and human validation), particularly regarding the skip-gram architecture. Conclusions Although this implementation had the best rate for semantic properties conservation, each model has its own qualities and defects, such as the training time, which is very short for GloVe, or morphological similarity conservation observed with FastText. Models and test sets produced by this study will be the first to be publicly available through a graphical interface to help advance the French biomedical research.

To help clinicians read medical texts such as clinical practice guidelines or drug monographs, we proposed an iconic language called VCM. This language can use icons to represent the main medical concepts, including diseases, symptoms, treatments and follow-up procedures, by combining various pictograms, shapes and colors. However, the semantics of this language have not been formalized, and users may create inconsistent icons, e.g. by combining the "tumor" shape and the "sleeping" pictograms into a "tumor of sleeping" icon. This work aims to represent the VCM language using DLs and OWL for evaluating its semantics by reasoners, and in particular for determining inconsistent icons. We designed an ontology for formalized the semantics of VCM icons using the Protégé editor and scripts for translating the VCM lexicon in OWL. We evaluated the ability of the ontology to determine icon consistency for a set of 100 random icons. The evaluation showed good results for determining icon consistency, with a high sensitivity. The ontology may also be useful for the design of mapping between VCM and other medical terminologies, for generating textual labels for icons, and for developing user interfaces for creating VCM icons.