Search

Background Adverse drug reactions (ADRs) are statistically characterized within randomized clinical trials and postmarketing pharmacovigilance, but their molecular mechanism remains unknown in most cases. This is true even for hepatic or skin toxicities, which are classically monitored during drug design. Aside from clinical trials, many elements of knowledge about drug ingredients are available in open-access knowledge graphs, such as their properties, interactions, or involvements in pathways. In addition, drug classifications that label drugs as either causative or not for several ADRs, have been established. Methods We propose in this paper to mine knowledge graphs for identifying biomolecular features that may enable automatically reproducing expert classifications that distinguish drugs causative or not for a given type of ADR. In an Explainable AI perspective, we explore simple classification techniques such as Decision Trees and Classification Rules because they provide human-readable models, which explain the classification itself, but may also provide elements of explanation for molecular mechanisms behind ADRs. In summary, (1) we mine a knowledge graph for features; (2) we train classifiers at distinguishing, on the basis of extracted features, drugs associated or not with two commonly monitored ADRs: drug-induced liver injuries (DILI) and severe cutaneous adverse reactions (SCAR); (3) we isolate features that are both efficient in reproducing expert classifications and interpretable by experts (i.e., Gene Ontology terms, drug targets, or pathway names); and (4) we manually evaluate in a mini-study how they may be explanatory. Results Extracted features reproduce with a good fidelity classifications of drugs causative or not for DILI and SCAR (Accuracy = 0.74 and 0.81, respectively). Experts fully agreed that 73% and 38% of the most discriminative features are possibly explanatory for DILI and SCAR, respectively; and partially agreed (2/3) for 90% and 77% of them. Conclusion Knowledge graphs provide sufficiently diverse features to enable simple and explainable models to distinguish between drugs that are causative or not for ADRs. In addition to explaining classifications, most discriminative features appear to be good candidates for investigating ADR mechanisms further. Supplementary Information The online version contains supplementary material available at 10.1186/s12911-021-01518-6.

A strong trend in the software industry is to merge the activities of deployment and operationalization through the DevOps approach, which in the case of artificial intelligence is called Machine Learning Operations (MLOps). We present here a microservices architecture containing the whole pipeline (frontend, backend, data predictions) hosted in Docker containers which exposes a model implemented for opinion prediction in Twitter on the COVID vaccines. This is the first description in the literature of implementing a microservice architecture using TorchServe, a library for serving Pytorch models.

Our objective was to improve the accuracy of bacteria and resistance coding in a hospital case mix database. Data sources consisted of 50,074 files on bacteriological susceptibility tests transmitted with the HPRIM protocol from laboratory management system to electronic health record of the University hospital of Saint Etienne in July 2017. An algorithm was implemented to detect susceptibility tests containing information corresponding to codes whose addition in the case mix database was susceptible to increase the severity level of a diagnosis related group. Among 132 hospital stays fulfilling the conditions, 27 were lacking bacteria and/or resistance codes, and the tariff was increased for 9 stays, with earnings of €54,612. Analyzing Antimicrobial susceptibility tests helps to improve clinical coding and optimize the financial gain.

Since December 2019 and the first reported cases of COVID-19 in Wuhan, China, there have been 199,466,211 confirmed cases of COVID-19 in the World. The WHO defined vaccination hesitancy as one of the top ten threats to global health in 2019. Our objective was thus to identify topics and trends about COVID-19 vaccines from French web forums to understand the perception of the French population on these vaccines before the vaccination campaign started. We performed a topic model analysis on 485 web forums' posts. 10 topics were found. We reviewed 120 posts from 6 of these 10 topics. One topic was about vaccine hesitancy, refusal, and mistrust, and two topics were related to what the users think about the government, the political and economic choices made towards this epidemic.

International audience; Since December 2019 and the first reported cases of COVID-19 in Wuhan, China, there have been 199,466,211 confirmed cases of COVID-19 in the World. The WHO defined vaccination hesitancy as one of the top ten threats to global health in 2019. Our objective was thus to identify topics and trends about COVID-19 vaccines from French web forums to understand the perception of the French population on these vaccines before the vaccination campaign started. We performed a topic model analysis on 485 web forums' posts. 10 topics were found. We reviewed 120 posts from 6 of these 10 topics. One topic was about vaccine hesitancy, refusal, and mistrust, and two topics were related to what the users think about the government, the political and economic choices made towards this epidemic.

International audience; As social media are an interesting source of information for pharmacovigilance, we implemented a novel visualisation method for pharmacovigilance specialists applied to French discussion forums. A word embedding model was trained on posts to facilitate the identification of patterns associated with adverse drug reactions.

Background Medical terminologies are commonly used in medicine. For instance, to answer a pharmacovigilance question, pharmacovigilance specialists (PVS) search in a pharmacovigilance database for reports in relation to a given drug. To do that, they first need to identify all MedDRA terms that might have been used to code an adverse reaction in the database, but terms may be numerous and difficult to select as they may belong to different parts of the hierarchy. In previous studies, three tools have been developed to help PVS identify and group all relevant MedDRA terms using three different approaches: forms, structured query-builder, and icons. Yet, a poor usability of the tools may increase PVS’ workload and reduce their performance. This study aims to evaluate, compare and improve the three tools during two rounds of formative usability evaluation. Methods First, a cognitive walkthrough was performed. Based on the design recommendations obtained from this evaluation, designers made modifications to their tools to improve usability. Once this re-engineering phase completed, six PVS took part in a usability test: difficulties, errors and verbalizations during their interaction with the three tools were collected. Their satisfaction was measured through the System Usability Scale. The design recommendations issued from the tests were used to adapt the tools. Results All tools had usability problems related to the lack of guidance in the graphical user interface (e.g., unintuitive labels). In two tools, the use of the SNOMED CT to find MedDRA terms hampered their use because French PVS were not used to it. For the most obvious and common terms, the icons-based interface would appear to be more useful. For the less frequently used MedDRA terms or those distributed in different parts of the hierarchy, the structured query-builder would be preferable thanks to its great power and flexibility. The form-based tool seems to be a compromise. Conclusion These evaluations made it possible to identify the strengths of each tool but also their weaknesses to address them before further evaluation. Next step is to assess the acceptability of tools and the expressiveness of their results to help identify and group MedDRA terms.

While vaccines are intended to protect people from infectious diseases, public confidence in vaccination has evolved as patients have reservation about vaccination, with a major concern about its safety. Social media may help regulatory authorities to better understand opposition to vaccination and make informed decisions for better promotion of vaccines' benefits towards the public. Our objective was to explore French web forums for potential pharmacovigilance signals associated with human papillomavirus infections (HPV) vaccines. Among 138 posts associated with a signal randomly chosen for manual review, 29% were actually adverse drug reactions to the vaccine described in clinical studies, and only 2 were personal experiences. Only 14% of the reviewed posts described positive opinion about the vaccine whereas 46% were neutral and 40% were negative. While few personal experiences of adverse reactions were actually reported by users, our case study showed a large proportion of negative opinions.

This poster presents a non-exhaustive study of machine learning classification algorithms on pharmacovigilance data. In this study, we have taken into account the patient's clinical data such as medical history, medications taken and their indications for prescriptions, and the observed side effects. From these elements we determine whether the patient case is considered serious or not. We show the performances of the different algorithms by their precision, recall and accuracy as well as their learning curves.

The large-scale use of social media by the population has gained the attention of stakeholders and researchers in various fields. In the domain of pharmacovigilance, this new resource was initially considered as an opportunity to overcome underreporting and monitor the safety of drugs in real time in close connection with patients. Research is still required to overcome technical challenges related to data extraction, annotation, and filtering, and there is not yet a clear consensus concerning the systematic exploration and use of social media in pharmacovigilance. Although the literature has mainly considered signal detection, the potential value of social media to support other pharmacovigilance activities should also be explored. The objective of this paper is to present the main findings and subsequent recommendations from the French research project Vigi4Med, which evaluated the use of social media, mainly web forums, for pharmacovigilance activities. This project included an analysis of the existing literature, which contributed to the recommendations presented herein. The recommendations are categorized into three categories: ethical (related to privacy, confidentiality, and follow-up), qualitative (related to the quality of the information), and quantitative (related to statistical analysis). We argue that the progress in information technology and the societal need to consider patients’ experiences should motivate future research on social media surveillance for the reinforcement of classical pharmacovigilance.

Pharmacogenomics (PGx) studies how individual gene variations impact drug response phenotypes, which makes PGx-related knowledge a key component towards precision medicine. A significant part of the state-of-the-art knowledge in PGx is accumulated in scientific publications, where it is hardly reusable by humans or software. Natural language processing techniques have been developed to guide experts who curate this amount of knowledge. But existing works are limited by the absence of a high quality annotated corpus focusing on PGx domain. In particular, this absence restricts the use of supervised machine learning. This article introduces PGxCorpus, a manually annotated corpus, designed to fill this gap and to enable the automatic extraction of PGx relationships from text. It comprises 945 sentences from 911 PubMed abstracts, annotated with PGx entities of interest (mainly gene variations, genes, drugs and phenotypes), and relationships between those. In this article, we present the corpus itself, its construction and a baseline experiment that illustrates how it may be leveraged to synthesize and summarize PGx knowledge., Measurement(s)gene_variant • response to drug • textual entity • chemical entity • haplotype • gene • Pharmacogenomics • Pharmacogenetics • abbreviation textual entity • Pharmacokinetics • Pharmacodynamics • phenotypeTechnology Type(s)digital curationSample Characteristic - OrganismHomo sapiens Machine-accessible metadata file describing the reported data: 10.6084/m9.figshare.11323724

Resume Objectif Evaluer l’informativite et la qualite des descriptions d’effets indesirables susceptibles d’etre lies au baclofene, dans les forums de discussion francais. Methodes Nous avons evalue la qualite des cas de pharmacovigilance potentiels associes au baclofene dans 22 forums de discussion. Nous avons ensuite compare ces donnees aux cas de pharmacovigilance issus de la base nationale de pharmacovigilance (BNPV), en termes d’informativite concernant le patient, le traitement et l’effet indesirable ainsi que la gravite et le caractere inattendu des effets. Resultats Nous avons identifie 782 cas de pharmacovigilance potentiels parmi 2621 messages issus de forums francais. L’informativite des messages des forums etait significativement inferieure a celle des cas issus de la BNPV, pour l’ensemble des donnees concernant le patient (3 %/6 % vs 88 % pour l’âge/la classe d’âge et 46 % vs 99 % pour le sexe, respectivement), pour la duree de traitement (9 % vs 24 %) et pour l’evolution de l’effet indesirable (1 % vs 64 %, respectivement). Mais l’indication du traitement et sa posologie etaient plus frequemment renseignees dans les forums que dans la BNPV (67 % vs 24 % et 27 % vs 9 %, respectivement). Les cas d’effets indesirables issus des forums sont tres majoritairement non graves, contrairement a ceux issus de la BNPV (38 % vs 0,7 %). La proportion de cas rapportant des effets indesirables inattendus est significativement plus importante dans les forums que dans la BNPV (43,8 % vs 11,6 %). Conclusion L’indication et la posologie etaient plus souvent renseignees dans les messages que dans la BNPV, ce qui fait des forums une ressource interessante pour etudier les conditions d’utilisation du baclofene. Bien que les forums comportent plus d’effets inattendus, leur moindre informativite rend difficile l’evaluation de l’imputabilite. Nous estimons que les forums et la BNPV sont deux sources de donnees complementaires pour la securite d’emploi du baclofene.

International audience; Introduction and Background: Since June 2011, the European legislation allows patients and patients' organizations to report adverse drug reactions (ADRs). In France, in 2017, more than 32,000 ADRs were reported by patients representing 42% of all ADRs collected yearly and an unexpected increase in patient reports (5.8% in 2016). Most of these cases involved the new Levothyrox® formulation (available since March 2017), leading to the "French Levothyrox® Crisis" [1]. To evaluate whether such crises can be predicted by analyzing social media data, the PHARES multidisciplinary consortium carried out the Levothyrox® case study that is described in this abstract. The PHARES project was funded from 2017 to 2019 by the French National Agency for the Safety of Medicines and Health Products (ANSM [2]) with the objective to implement a computerized tool for social media mining. Objectives: Quantitative and qualitative analysis of Levothyrox® mentions in a French web site dedicated to thyroid pathology to investigate whether social media may be useful to predict ADR-related crises. Methods: All posts published in the forums of the "Vivre sans thyroïde" website were collected and annotated automatically using machine learning and natural language processing methods to identify mentions of drugs and potential Adverse Events (AE) [3, 4]. Only posts containing at least one mention of Levothyrox® or levothyroxine were considered as our analysis collection. From this data sample, we first counted the number of posts per each verbatim detected by the annotation algorithm to identify those AEs most mentioned with Levothyrox®. The 100 most mentioned verbatims were then manually reviewed and classified into categories by a pharmacovigilance expert (cf. Table 1). This manual step generated an association list (verbatim -> Category) that we used as a reference to generate the following statistics over the whole collection: the number of posts per category, the number of posts per AE in each category, and the evolution over time of the number of posts per AE and per category and a time-series analysis using change-point analysis method (CPA) [5].Results: As for July 2018, the studied website contained over 900 thousand posts published since 2001. The evolution of the number of AE mentions associated to Levothyrox® from June 2005 to July 2018 shows no particular rise was present before the first declaration to the pharmacovigilance network. The qualitative analysis of the categories selected for this study resulted in: 25% of General AE, 25% of Levothyrox® indication, 18% of neurological and psychiatric effects, 7% of seriousness description ("emergency", "consultation", "crisis") and 5% of cardiovascular effects. The main AEs associated to general effects are "tiredness", "weight gain" and "pain". The CPA method shows a change point one month before the beginning of the crisis.Conclusion and perspectives: To our knowledge, this study is the first retrospective analysis of social media data following a drug health crisis. It concerns a new formulation of a drug used by more than 3 million people in France, leading to thousands of patients' complaints about ADRs. Most of the collected AEs were expected, some of them may be difficult to classify and a human evaluation is still required. The detected change point corresponds to a low variation and further investigations need to be performed.

Medical terminologies are the basis of interoperability in medicine. They allow connecting the various systems and data and facilitate searches in databases. An example is the MedDRA terminology, used in particular for coding drug adverse events. However, these terminologies are often complex and involve a huge number of terms. Consequently, it is difficult to browse them or find the desired terms. Traditional approaches consist of lexical search, with the problems of synonymy and polysemy, or tree-based navigation, but the user often gets "lost" in the tree. Here, we propose a new approach for browsing medical terminologies: the use of pictograms and icons, for formulating the query in complement to a textual search box, and for displaying the search results. We applied this approach to the MedDRA terminology. We present both the methods and search algorithms and the resulting browsing interface, as well as the qualitative opinions of two pharmacovigilance experts.

Social media are proposed as a complementary data source for detection and characterisation of adverse drug reactions. While signal detection algorithms were implemented for generating signals in pharmacovigilance databases, the implementation of a graphical user interface supporting the selection and display of algorithms' results is not documented in the medical literature. Although collecting information on the chronology and the impact of adverse drug reactions is desirable to enable causality and quality assessment of potential signals detected in patients' posts, no tool has been proposed yet to consider such data. We describe here two approaches, and the corresponding tools we implemented for: (1) quantitative approach based on signal detection algorithms, and (2) qualitative approach based on expert review of patient's posts. Future work will focus on implementing other statistical methods, exploring the complementarity of both approaches on a larger scale, and prioritizing the posts to manually evaluate after applying appropriate signal detection methods.

To evaluate the informativity, quality of French discussion forums for evaluation of baclofen safety.We evaluated the quality of potential pharmacovigilance case reports associated to baclofen in 22 French discussion forums. We compared the informativity concerning the patient, treatment, seriousness and expectedness of adverse events described on these posts, with similar information coded in case reports from the French pharmacovigilance database (FPVD).A total of 782 potential case reports were identified among 2621 French language forums' posts. Cases in the FPVD were significantly more informative than web forums' posts for patient information (3%/6% vs. 88% for the age/class of age and 46% vs. 99% for the gender), treatment duration (9% vs. 24%) and outcome of the ADR (1% vs. 64%). But both indication and dose were more frequently retrieved in forums than in the FPVD (67% vs. 24% and 27% vs. 9%, respectively). Cases from web forums were significantly more frequently non-serious than the FPVD's ones (38% vs. 0.7%). Adverse events were significantly more often unexpected in forums than in the FPVD (43.8% vs. 11.6%).Indication and posology were more often documented in posts than in case reports which makes forums an interesting resource for monitoring use of baclofen. While posts contain more unexpected events, informativity is low which makes causality assessment difficult. Nevertheless, we consider forums as a secondary, but complementary source for pharmacovigilance about baclofen.

The aim of this study is to analyze drug mentions in web forums to evaluate the utility of this data source for drug post-marketing studies. We automatically annotated over 60 million posts extracted from 21 French web forums. Drug mentions detected in this corpus were matched to drug names in a French drug database (Theriaque®). Our analysis showed that a high proportion of the most frequent drug mentions in the selected web forums correspond to drugs that are usually prescribed to young women, such as combined oral contraceptives. The most mentioned drugs in our corpus correlated weakly to the most prescribed drugs in France but seemed to be influenced by events widely reported in traditional media. In this article, we conclude that web forums have high potential for post-marketing drug-related studies, such as pharmacovigilance, and observation of drug utilization. However, the bias related to forum selection and the corresponding population representativeness should always be taken into account.

Resume Objectif Proposer une methode de regroupement de termes medical dictionary for regulatory activities (MedDRA) alternative a l’approche habituelle : methode hierarchique (selection de groupements de reference dans MedDRA) et/ou methode textuelle (recherche de chaines de caracteres). Exemple des valvulopathies medicamenteuses. Methodes Liste de termes obtenue par une approche automatisee, basee sur l’interrogation d’une base de connaissances definissant les termes MedDRA au moyen de relations avec des concepts systematized nomenclature of medicine–clinical terms (SNOMED CT), comparee avec la liste de reference obtenue par methode hierarchique et textuelle. Resultats Le premier groupement automatise de termes MedDRA en rapport avec une fibrose, un retrecissement ou une calcification de valve cardiaque, excluant les pathologies congenitales et le deuxieme reprenant les memes criteres en remplacant l’aspect morphologique par l’aspect fonctionnel, presentent respectivement un rappel de 79 % avec une precision de 100 %, et un rappel de 100 % avec une precision de 96 %. Conclusion Une approche alternative aux groupements de reference MedDRA est possible pour les valvulopathies medicamenteuses et pourrait etre etendue a d’autres effets indesirables.

Over a period of 5 years, the Innovative Medicines Initiative PROTECT (Pharmacoepidemiological Research on Outcomes of Therapeutics by a European ConsorTium) project has addressed key research questions relevant to the science of safety signal detection. The results of studies conducted into quantitative signal detection in spontaneous reporting, clinical trial and electronic health records databases are summarised and 39 recommendations have been formulated, many based on comparative analyses across a range of databases (e.g. regulatory, pharmaceutical company). The recommendations point to pragmatic steps that those working in the pharmacovigilance community can take to improve signal detection practices, whether in a national or international agency or in a pharmaceutical company setting. PROTECT has also pointed to areas of potentially fruitful future research and some areas where further effort is likely to yield less.

Background: Searching into the MedDRA terminology is usually limited to a hierarchical search, and/or a string search. Our objective was to compare user performances when using a new kind of user interface enabling semantic queries versus classical methods, and evaluating term selection improvement in MedDRA. Methods: We implemented a forms-based web interface: OntoADR Query Tools (OQT). It relies on OntoADR, a formal resource describing MedDRA terms using SNOMED CT concepts and corresponding semantic relations, enabling terminological reasoning. We then compared time spent on five examples of medical conditions using OQT or the MedDRA web-based browser (MWB), and precision and recall of the term selection. Results: OntoADR Query Tools allows the user to search in MedDRA: One may enter search criteria by selecting one semantic property from a dropdown list and one or more SNOMED CT concepts related to the range of the chosen property. The user is assisted in building his query: he can add criteria and combine them. Then, the interface displays the set of MedDRA terms matching the query. Meanwhile, on average, the time spent on OQT (about 4 min 30 s) is significantly lower (−35%; p < 0.001) than time spent on MWB (about 7 min). The results of the System Usability Scale (SUS) gave a score of 62.19 for OQT (rated as good). We also demonstrated increased precision (+27%; p = 0.01) and recall (+34%; p = 0.02). Computed “performance” (correct terms found per minute) is more than three times better with OQT than with MWB. Discussion: This pilot study establishes the feasibility of our approach based on our initial assumption: performing MedDRA queries on the five selected medical conditions, using terminological reasoning, expedites term selection, and improves search capabilities for pharmacovigilance end users. Evaluation with a larger number of users and medical conditions are required in order to establish if OQT is appropriate for the needs of different user profiles, and to check if conclusions can be extended to other kinds of medical conditions. The application is currently limited by the non-exhaustive coverage of MedDRA by OntoADR, but nevertheless shows good performance which encourages continuing in the same direction.

Background: Formal definitions allow selecting terms (e.g., identifying all terms related to “Infectious disease” using the query “has causative agent organism”) and terminological reasoning (e.g., “hepatitis B” is a “hepatitis” and is an “infectious disease”). However, the standard international terminology Medical Dictionary for Regulatory Activities (MedDRA) used for coding adverse drug reactions in pharmacovigilance databases does not beneficiate from such formal definitions. Our objective was to evaluate the potential of reuse of ontological and non-ontological resources for generating such definitions for MedDRA. Methods: We developed several methods that collectively allow a semiautomatic semantic enrichment of MedDRA: 1) using MedDRA-to-SNOMED Clinical Terms (SNOMED CT) mappings (available in the Unified Medical Language System metathesaurus or other mapping resources, e.g., the MedDRA preferred term “hepatitis B” is associated to the SNOMED CT concept “type B viral hepatitis”) to extract term definitions (e.g., “hepatitis B” is associated with the following properties: has finding site liver structure, has associated morphology inflammation morphology, and has causative agent hepatitis B virus); 2) using MedDRA labels and lexical/syntactic methods for automatic decomposition of complex MedDRA terms (e.g., the MedDRA systems organ class “blood and lymphatic system disorders” is decomposed in blood system disorders and lymphatic system disorders) or automatic suggestions of properties (e.g., the string “cyclic” in preferred term “cyclic neutropenia” leads to the property has clinical course cyclic). Results: The Unified Medical Language System metathesaurus was the main ontological resource reusable for generating formal definitions for MedDRA terms. The non-ontological resources (another mapping resource provided by Nadkarni and Darer in 2010 and MedDRA labels) allowed defining few additional preferred terms. While the Ci4SeR tool helped the curator to define 1,935 terms by suggesting potential supplemental relations based on the parents’ and siblings’ semantic definition, defining manually all MedDRA terms remains expensive in time. Discussion: Several ontological and non-ontological resources are available for associating MedDRA terms to SNOMED CT concepts with semantic properties, but providing manual definitions is still necessary. The ontology of adverse events is a possible alternative but does not cover all MedDRA terms either. Perspectives are to implement more efficient techniques to find more logical relations between SNOMED CT and MedDRA in an automated way.

Background: Social media are currently considered as a potential complementary source of knowledge for drug safety surveillance. Our primary objective was to estimate the frequency of adverse drug reactions (ADRs) experienced by Twitter users. Our secondary objective was to determine whether tweets constitute a valuable and informative source of data for pharmacovigilance purposes, despite limitations on character number per tweet. Research design and methods: We selected a list of 33 drugs subject to careful monitoring due to safety concern in France and Europe, and extracted tweets using the streaming API from 30 September 2014 to 5 April 2015. Two pharmacovigilance centers classified these tweets manually as potential ADR case reports. Results: Among 10,534 tweets, 848 (8.05%) implied or mentioned an ADR without meeting the four FDA criteria required for reporting an ADR, and 289 (2.74%) tweets were classified as ‘case reports.’ Among them 20 (7.27%) tweets mentioned an unexpected ADR and 33 (11.42%) tweets mentioned a serious ADR. Conclusions: With the use of dedicated tools, Twitter could become a complementary source of information for pharmacovigilance, despite a major limitation regarding causality assessment of ADRs in individual tweets, which may improve with the new limitation to 280 characters per tweet.

Resume Objectif Evaluer l’interet d’une recherche dans la base de donnees du programme de medicalisation des systemes d’information (PMSI) pour l’identification des cas de chocs anaphylactiques ou anaphylactoides (CA) medicamenteux. Methodes Extraction des sejours de patients hospitalises au centre hospitalier universitaire de Saint-Etienne du 1 er juillet 2009 au 30 juin 2012 correspondant aux cinq codes de la classification internationale des maladies suivants : T88.6, T88.2, J39.3, T80.5 et T78.2. Resultats Sur 89 sejours repondant aux criteres, 40 (45 %) correspondaient bien a un CA parmi lesquels 16 cas avaient ete declares au centre regional de pharmacovigilance. Le code peu specifique « choc anaphylactique sans precision (T78.2) » etait code pour 57,5 % des cas. Conclusion L’etude confirme l’interet de l’utilisation du PMSI comme outil de veille, en complement de la notification spontanee. Cependant la qualite du codage et sa faible precision entrainent une perte de temps consequente avec le retour au dossier medical.

Graphical abstractDisplay Omitted MedDRA's current format limits accurate and consistent term selection for coding.OntoADR, a formalized ("ontologized") version of MedDRA can improve MedDRA coding and support signal detection.OntoADR is an OWL representation of MedDRA using SNOMED-CT formal definitions.Formalizing MedDRA enables terminological reasoning on terms semantics.The process of formalization of MedDRA can be semi-automated. Although MedDRA has obvious advantages over previous terminologies for coding adverse drug reactions and discovering potential signals using data mining techniques, its terminological organization constrains users to search terms according to predefined categories. Adding formal definitions to MedDRA would allow retrieval of terms according to a case definition that may correspond to novel categories that are not currently available in the terminology. To achieve semantic reasoning with MedDRA, we have associated formal definitions to MedDRA terms in an OWL file named OntoADR that is the result of our first step for providing an "ontologized" version of MedDRA. MedDRA five-levels original hierarchy was converted into a subsumption tree and formal definitions of MedDRA terms were designed using several methods: mappings to SNOMED-CT, semi-automatic definition algorithms or a fully manual way. This article presents the main steps of OntoADR conception process, its structure and content, and discusses problems and limits raised by this attempt to "ontologize" MedDRA.

In France, data derived from hospital information systems are adequate to feed the prospective payment system. The consistency between drugs prescribed to patients and their indications could solve difficulties related to the identification of ICD-10 undercoded chronic diseases as the Parkinson Disease. Our goal was to highlight patients' stays mentioning administration of antiparkinsonian drugs and not coded for Parkinson's disease. Our approach was to parameterize tables of associations between ICD-10 codes and drug identifiers in the Web100T® application that collects medical information in our hospital and displays related inconsistencies for patients' stays. Based on acute care patients' stays of the second semester of 2015, we identified 246 patients corresponding to 253 stays, for which 33% of stays were not coded with the ICD-10 G20 code of the Parkinson's disease. The precision of our approach was 29%. Based on these data we predict roughly 84 patient stays without mention of Parkinson Disease. We plan to extend this study to other drugs and other kinds of data available in the health information system, such as biology or medical devices in order to improve the coding of chronic diseases in our hospital.

To propose an alternative approach for building custom groupings of terms that complements the usual approach based on both hierarchical method (selection of reference groupings in medical dictionary for regulatory activities [MedDRA]) and/or textual method (string search), for case reports extraction from a pharmacovigilance database in response to a safety problem. Here we take cardiac valve fibrosis as an example.The list of terms obtained by an automated approach, based on querying ontology of adverse drug reactions (OntoADR), a knowledge base defining MedDRA terms through relationships with systematized nomenclature of medicine-clinical terms (SNOMED CT) concepts, was compared with the reference list consisting of 53 preferred terms obtained by hierarchical and textual method. Two queries were performed on OntoADR by using a dedicated software: OntoADR query tools. Both queries excluded congenital diseases, and included a procedure or an auscultation method performed on cardiac valve structures. Query 1 also considered MedDRA terms related to fibrosis, narrowing or calcification of heart valves, and query 2 MedDRA terms described according to one of these four SNOMED CT terms: "Insufficiency", "Valvular sclerosis", "Heart valve calcification" or "Heart valve stenosis".The reference grouping consisted of 53 MedDRA preferred terms. Our automated method achieved recall of 79% and precision of 100% for query 1 privileging morphological abnormalities, and recall of 100% and precision of 96% for query 2 privileging functional abnormalities.An alternative approach to MedDRA reference groupings for building custom groupings is feasible for cardiac valve fibrosis. OntoADR is still in development. Its application to other adverse reactions would require significant work for a knowledge engineer to define every MedDRA term, but such definitions could then be queried as many times as necessary by pharmacovigilance professionals.

International audience; Objective: To propose a method to build customized sets of MedDRA terms for the description of a medical condition. We illustrate this method with upper gastrointestinal bleedings (UGIB).Research design and methods: We created a broad list of MedDRA terms related to UGIB and defined a gold standard with the help of experts. MedDRA terms were formally described in a semantic resource named OntoADR. We report the use of two semantic queries that automatically select candidate terms for UGIB. Query 1 is a combination of two SNOMED CT concepts describing both morphology ‘Hemorrhage’ and finding site ‘Upper digestive tract structure’. Query 2 complements Query 1 by taking into account MedDRA terms associated to SNOMED CT concepts describing clinical manifestations ‘Melena’ or ‘Hematemesis’.Results: We compared terms in queries and our gold standard achieving a recall of 71.0% and a precision of 81.4% for query 1 (F1 score 0.76); and a recall of 96.7% and a precision of 77.0% for query 2 (F1 score 0.86).Conclusions: Our results demonstrate the feasibility of applying knowledge engineering techniques for building customized sets of MedDRA terms. Additional work is necessary to improve precision and recall, and confirm the interest of the proposed strategy.

Resume Objectifs La prevention des effets indesirables lies aux medicaments (EIM) est devenue un important enjeu de sante publique. La pharmacovigilance a pour objet l’identification, l’analyse et la prevention des risques lies aux EIM. L’objectif du projet VigiTermes est de developper des methodes innovantes pour une detection plus precoce des EIM. Materiel et methodes Les methodes mises en œuvre appartiennent a l’ingenierie des connaissances, l’ingenierie multilingue, le traitement automatique du langage et a la fouille de texte. Resultats Le principal resultat du projet est la mise en place d’une architecture logicielle destinee a la recherche et l’analyse des articles decrivant les EIM sur le serveur bibliographique PubMed. Il s’agit de la premiere application de ce type destinee a la pharmacovigilance. Les autres resultats sont en rapport avec la detection statistique des signaux, la modelisation des medicaments et des EIM au moyen d’ontologies, la recherche d’information dans les bases de donnees de pharmacovigilance et l’application de methode de traitement automatique des langues en japonais appliquee a des cas de pharmacovigilance. Discussion Des developpements sont en cours afin de mettre les resultats du projet sous forme operationnelle pour une exploitation par les autorites reglementaires et les laboratoires pharmaceutiques. L’amelioration de l’interface graphique devrait faciliter l’aide a la decision pour les professionnels responsables des questions liees a la pharmacovigilance. Conclusion Notre ambition est de continuer l’integration des composants sur la plateforme commune afin de proposer aux pharmacovigilants l’outil le plus complet et le plus efficace pour la detection, ainsi que le suivi et la consolidation des signaux de pharmacovigilance.

Summary Objectives: Several alert systems have been developed to improve the patient safety aspects of clinical information systems (CIS). Most studies have focused on the evaluation of these systems, with little information provided about the methodology leading to system implementation. We propose here an ‘agile’ business rule design framework (BRDF) supporting both the design of alerts for the validation of drug prescriptions and the incorporation of the end user into the design process. Methods: We analyzed the unified process (UP) design life cycle and defined the activities, subactivities, actors and UML artifacts that could be used to enhance the agility of the proposed framework. We then applied the proposed framework to two different sets of data in the context of the Georges Pompidou University Hospital (HEGP) CIS. Results: We introduced two new subactivities into UP: business rule specification and business rule instantiation activity. The pharmacist made an effective contribution to five of the eight BRDF design activities. Validation of the two new subactivities was effected in the context of drug dosage adaption to the patients’ clinical and biological contexts. Pilot experiment shows that business rules modeled with BRDF and implemented as an alert system triggered an alert for 5824 of the 71,413 prescriptions considered (8.16%). Conclusion: A business rule design framework approach meets one of the strategic objectives for decision support design by taking into account three important criteria posing a particular challenge to system designers: 1) business processes, 2) knowledge modeling of the context of application, and 3) the agility of the various design steps.