PEOPLE@HES-SO Verzeichnis der Mitarbeitenden und Kompetenzen

Web Intelligence for Rare Disease

Rolle: Mitarbeiter

Financement: HES-SO Rectorat; 549,Information et documentation; Etat de Genève; Canton de Vaud; Interreg France Suisse; Innobridge; Management des villes et du territoire; 549,Information et documentation

Description du projet : Développement de deux grands types de fonctionnalités-clés d'une plateforme de veille existante, Webso/Inelio, à savoir : 1. Des fonctionnalités de traitement automatique des informations utiles issues de la veille : classification automatique, cartographie et résumés automatiques. Ces fonctionnalités de traitement automatique seront adaptées en priorité aux compétences technologiques représentatives de la région transfrontalière, à savoir les micro techniques, la mécatronique et mécanique de précision au service des secteurs de l'horlogerie, des medtech, biotech, cleantech et de l'aéronautique. Ces fonctionnalités doivent pouvoir réellement accélérer le traitement des informations et aider les entreprises à résoudre leurs problèmes de surinformation. 2. Des fonctionnalités de suivi de e-reputation : un module d'optimisation du référencement (SEO) permettant aux entreprises de suivre le positionnement de leur propre site ainsi que celui de leurs concurrents, un module d'analytique, et un module d'"analyse du sentiment" (sentiment analysis). Précision du modèle d'affaires de la plateforme développée à travers la réalisation d'une étude de marché, et définition d'un modèle d'affaires spécifique en direction des structures d'aide/de soutien, des associations ou fédérations professionnelles et de toute entité chargée d'aider les entreprises à innover.

Forschungsteam innerhalb von HES-SO: Gaudinat Arnaud , Rota Mathias , Bregnard Thierry , Segessemann Alain , Madinier Hélène , Berger Bastien

Durée du projet: 01.07.2016 - 31.01.2018

Montant global du projet: 310'361 CHF

Statut: Abgeschlossen

epSOS 2 ' Smart Open Services for European Patients - Open eHealth Initiative for a European Large Scale Pilot of Patient Summary and Electronic Prescription ' Extension

Rolle: Mitarbeiter

Requérant(e)s: 549,Information et documentation, Ruch Patrick, 549,Information et documentation

Financement: HES-SO Rectorat

Description du projet : Background: Modern healthcare relies on a sound methodological approach combining experimental observations and statistical analysis. The so-called evidence-based medicine collects empirical observations to confirm or infirm a given clinical hypothesis. Unfortunately, clinical practice guidelines, which constitute the main clinical decisionsupport instrument, cover only a fraction of what a physician is likely to observe in practice. This problem is especially acute for rare diseases (RD) because physicians are then confronted with cases they have rarely met during their professional history. Although individually rare, physicians are very likely to meet patients suffering from RDs as rare diseases are estimated to affect about 8% of the patients. It has been shown that in such a context, where information is sparse, that health-related contents of the web, provided it is powered with appropriate access engines, can provide an effective source of evidence for both the medical practitioner and the patient. Objective: The WeIRD project aims to provide the informational instruments needed to navigate, search and ultimately question the web evidence space of RD by providing access to high-quality specific contents helpful to help diagnosing RD. Deliverables: The project must deliver the following deliverables: 1. a library of web documents (WeIRD-Library), harvested from legacy sources (case report, knowledge bases such as Orphanet, OMIM, Swiss-Prot, locus-specific databases'), to comprehensively store all information relevant for RD; 2. a decision-support system (WeIRD-DSS) to help end-users answering medical questions. In WeIRD-DSS, each answer will be provided with a set of links to legacy sources so that erroneous answers can be easily discarded; thus iteratively improving the knowledge base of the WeIRD-DSS. Methods: the system will use advanced information retrieval and text mining methods to holistically crawl, index and finally analyze all the explicit and implicit knowledge available on Rare Diseases. Evaluation: 1. The evaluation will be using the Cranfield paradigm including to assess the best acquisition channels for health-related information; 2. Assess the best data acquisition channels for health-related information. Exploitation and availability: the resulting web services and interfaces will be publicly available for clinicians, researchers and patients. Depending on the success, it could become an SIB (Swiss Institute of Bioinformatics) infrastructure resource.

Forschungsteam innerhalb von HES-SO: Gaudinat Arnaud , Mottin Luc , Ruch Patrick

Partenaires académiques: 549,Information et documentation; Ruch Patrick, 549,Information et documentation

Durée du projet: 01.05.2015 - 30.11.2017

Montant global du projet: 183'000 CHF

Statut: Abgeschlossen

Web stratégie et Observation

Rolle: Mitarbeiter

Requérant(e)s: 549,Information et documentation, Ruch Patrick, 549,Information et documentation

Financement: Koordinationsorgan Bund-Kantone

Description du projet : The European Commission and 23 participating Member and other States in co-operation with national eHealth Competence Centres intend to extend the presently running epSOS I Large Scale Pilot by another 24 month, with an overlap period starting on January 1st 2011, to Dec. 2013. Key goals are to - Improve healthcare quality and safety for citizens when in another European country - Advance towards pan-European agreements for interoperability - Defragment European services and ICT solutions markets - Address interoperability in a more global way by working with international organisations and considering major world markets such as that of the USA. Results achieved so far and the outcomes expected till the end of the presently running phase I of the project concern the definition of an interoperable eHealth service infrastructure, which interconnects national solutions. The approach, which is based on advanced and distinct use cases and associated infrastructural components, aims to deliver both a methodological process and durable implementation building blocks. These building blocks will form the basis for a longer term, pan-European approach to develop interoperable eHealth supported healthcare service solutions. The concrete objectives to be pursued in the epSOS enlargement are as follows: - Continue support for the engagement of presently already involved Member States, and integrate new countries and international actors - Consolidate, scale up and operationalise further the epSOS building blocks and services - Refine and extend the functional requirements of the epSOS core services: patient summary and ePrescription - Assess, test and - if feasible - pilot new epSOS services like the integration with 112 emergency services, integration with European Health Insurance Card (EHIC) processes or patient access to their data - Assess epSOS services and related interoperability approaches in the context of similar activities across the Atlantic. The overall budget for the second phase of the project is estimated at ' 14.5m; the funding requested from the EC amounts to ' 7m. It is foreseen to establish both a 'Coordination activity reserve fund' and a 'Reserve fund for joint activities' to cover the full costs of project coordination and administration as well as some subcontracting to be undertaken by the project coordinator. Editorial note epSOS 1 refers to the existing contract running since July 2008. epSOS 2 refers to the content of this proposal.

Forschungsteam innerhalb von HES-SO: Gaudinat Arnaud , Ruch Patrick

Partenaires académiques: 549,Information et documentation; Ruch Patrick, 549,Information et documentation

Durée du projet: 01.01.2011 - 31.12.2014

Montant global du projet: 102'000 CHF

Statut: Abgeschlossen

Rolle: Mitarbeiter

Financement: HES-SO Rectorat; 549,Information et documentation; 549,Information et documentation

Description du projet : L'objectif du projet est le développement d'un prototype de veille utilisable par des PME, ainsi que l'identification d'un modèle d'affaires pour la finalisation, la distribution et la commercialisation de cet outil qui seront réalisées par une entreprise privée et dont le produit permettra à la HEG de se positionner comme prestataire de veille.

Forschungsteam innerhalb von HES-SO: Gaudinat Arnaud , Madinier Hélène , Ruch Patrick

Partenaires académiques: Reflex Sàrl

Partenaires professionnels: Menth Electronique; B+G & Partners SA; Remarq SA

Durée du projet: 01.01.2013 - 31.10.2014

Montant global du projet: 214'000 CHF

Statut: Abgeschlossen

2022

La veille Web 3.0 :

Professioneller Artikel ArODES

la veille de l’information à l’ère de la blockchain

Arnaud Gaudinat

Hors-Texte, 2022, no 122, pp. 73-85

2021

Indirectly named entity recognition

Wissenschaftlicher Artikel ArODES

Alexis Kauffmann, François-Claude Rey, Iana Atanassova, Arnaud Gaudinat, Peter Greenfield, Hélène Madinier, Sylviane Cardet

Journal of computer-assisted linguistic research, 2021, vol. 5, pp. 27-46

Zusammenfassung:

We define here indirectly named entities, as a term to denote multiword expressions referring to known named entities by means of periphrasis. While named entity recognition is a classical task in natural language processing, little attention has been paid to indirectly named entities and their treatment. In this paper, we try to address this gap, describing issues related to the detection and understanding of indirectly named entities in texts. We introduce a proof of concept for retrieving both lexicalised and non-lexicalised indirectly named entities in French texts. We also show example cases where this proof of concept is applied, and discuss future perspectives. We have initiated the creation of a first lexicon of 712 indirectly named entity entries that is available for future research.

2019

Public libraries in Switzerland :

Wissenschaftlicher Artikel ArODES

RDA and the FRBRization watershed

Elisa Banfi, Arnaud Gaudinat

Library Management, 2019, vol. 40, issue 1-2, pp. 98-112

Zusammenfassung:

Purpose :The purpose of this paper is to investigate how Swiss public libraries are experiencing a normative revolution connected to new cataloging standards, such as RDA and the FRBRization of catalogs. Design/methodology/approach :Thanks to semi-structured interviews, the paper analyzes the current positioning of Swiss public libraries on the “bibliographic transition” issue by using a case study of the network of municipal libraries in Geneva. Findings :In Switzerland, the federal and multi-linguistic structure of the library networks increases the organizational obstacles to the adoption of new cataloging principles and formats. At the local level, the Swiss municipal libraries have to cope with this complexity to transform their structures and continue to offer competitive and effective services to their users. Practical implications : The paper proposes six scenarios of technology watershed for the analyzed case study and their consequences for cataloging standards and rules. Social implications : The paper shows how the adoption of technological and conceptual innovations has to be done in the face of real organizational and administrative constraints, especially in the case of public lending libraries. Originality/value : The paper analyzes at the empirical and theoretical levels how, especially in Switzerland, the variety of governance levels and linguistic areas have made strategizing more complex for public lending libraries.

2017

Improving average ranking precision in user searches for biomedical research datasets

Wissenschaftlicher Artikel ArODES

Douglas Teodoro, Luc Mottin, Julien Gobeill, Arnaud Gaudinat, Thérèse Vachon, Patrick Ruch

Database, 2017, vol. 2017, pp. 1-18

Zusammenfassung:

Availability of research datasets is keystone for health and life science study reproducibility and scientific progress. Due to the heterogeneity and complexity of these data, a main challenge to be overcome by research data management systems is to provide users with the best answers for their search queries. In the context of the 2016 bioCADDIE Dataset Retrieval Challenge, we investigate a novel ranking pipeline to improve the search of datasets used in biomedical experiments. Our system comprises a query expansion model based on word embeddings, a similarity measure algorithm that takes into consideration the relevance of the query terms, and a dataset categorisation method that boosts the rank of datasets matching query constraints. The system was evaluated using a corpus with 800k datasets and 21 annotated user queries. Our system provides competitive results when compared to the other challenge participants. In the official run, it achieved the highest infAP among the participants, being +22.3% higher than the median infAP of the participant’s best submissions. Overall, it is ranked at top 2 if an aggregated metric using the best official measures per participant is considered. The query expansion method showed positive impact on the system’s performance increasing our baseline up to +5.0% and +3.4% for the infAP and infNDCG metrics, respectively. Our similarity measure algorithm seems to be robust, in particular compared to Divergence From Randomness framework, having smaller performance variations under different training conditions. Finally, the result categorization did not have significant impact on the system’s performance. We believe that our solution could be used to enhance biomedical dataset management systems. The use of data driven expansion methods, such as those based on word embeddings, could be an alternative to the complexity of biomedical terminologies. Nevertheless, due to the limited size of the assessment set, further experiments need to be performed to draw conclusive results.

2016

Le plaisir de tout conserver sans modération :

Professioneller Artikel ArODES

une question de taille ?

Arnaud Gaudinat

Arbido, 2016, no 3

Zusammenfassung:

Pourquoi jeter lorsqu’on peut conserver? Exit le papier physique et les mètres linéaires. L’ère du numérique a tout chamboulé. L’espace dans les nuages est infini, c’est la promesse de la loi Kryder qui prédit empiriquement le doublement de la densité de stockage tous les ans depuis 60 ans. Mais conserver l’information c’est bien, la retrouver c’est encore mieux et indispensable. Google trouve plutôt bien son chemin parmi plus de 1000 milliards de documents décentralisés. Alors pourquoi devrions-nous perdre du temps à trier, archiver, sélectionner, effacer nos centaines d’emails, de photos et autres documents? Ici sont présentés quelques idées, repères et exemples relatifs à la problématique de la conservation de toute l’information numérique plutôt que de son élimination.

2015

The SIB Swiss institute of bioinformatics’ resources :

Wissenschaftlicher Artikel ArODES

focus on curated databases

Patrick Ruch, Luc Mottin, Julien Gobeill, Emilie Pasche, Arnaud Gaudinat

Nucleic Acids Research, November 2015, Vol. 44, no.4, pp. 27-37

Zusammenfassung:

The SIB Swiss Institute of Bioinformatics (www. isb-sib.ch) provides world-class bioinformatics databases, software tools, services and training to the international life science community in academia and industry. These solutions allow life scientists to turn the exponentially growing amount of data into knowledge. Here, we provide an overview of SIB’s resources and competence areas, with a strong focus on curated databases and SIB’s most popular and widely used resources. In particular, SIB’s Bioinformatics resource portal ExPASy features over 150 resources, including UniProtKB/Swiss-Prot, ENZYME, PROSITE, neXtProt, STRING, UniCarbKB, SugarBindDB, SwissRegulon, EPD, arrayMap, Bgee, SWISS-MODEL Repository, OMA, OrthoDB and other databases, which are briefly described in this article.

Deep Question Answering for protein annotation

Wissenschaftlicher Artikel ArODES

Julien Gobeill, Arnaud Gaudinat, Emilie Pasche, Dina Vishnyakova, Pascale Gaudet, Amos Bairoch, Patrick Ruch

Database : the journal of biological databases and curation, 2015

Zusammenfassung:

Biomedical professionals have access to a huge amount of literature, but when they use a search engine, they often have to deal with too many documents to efficiently find the appropriate information in a reasonable time. In this perspective, question-answering (QA) engines are designed to display answers, which were automatically extracted from the retrieved documents. Standard QA engines in literature process a user question, then retrieve relevant documents and finally extract some possible answers out of these documents using various named-entity recognition processes. In our study, we try to answer complex genomics questions, which can be adequately answered only using Gene Ontology (GO) concepts. Such complex answers cannot be found using state-of-the-art dictionary- and redundancy-based QA engines. We compare the effectiveness of two dictionary-based classifiers for extracting correct GO answers from a large set of 100 retrieved abstracts per question. In the same way, we also investigate the power of GOCat, a GO supervised classifier. GOCat exploits the GOA database to propose GO concepts that were annotated by curators for similar abstracts. This approach is called deep QA, as it adds an original classification step, and exploits curated biological data to infer answers, which are not explicitly mentioned in the retrieved documents. We show that for complex answers such as protein functional descriptions, the redundancy phenomenon has a limited effect. Similarly usual dictionary-based approaches are relatively ineffective. In contrast, we demonstrate how existing curated data, beyond information extraction, can be exploited by a supervised classifier, such as GOCat, to massively improve both the quantity and the quality of the answers with a +100% improvement for both recall and precision.

2012

An advanced search engine for patent analytics in medicinal chemistry

Wissenschaftlicher Artikel ArODES

Emilie Pasche, Julien Gobeill, Douglas Teodoro, Arnaud Gaudinat, Dina Vishnyakova, Christian Lovis, Patrick Ruch

Studies in health technology and informatics, 2012, vol. 180, p. 204-209,

Classification and prioritization of biomedical literature for the comparative toxicogenomics database

Wissenschaftlicher Artikel ArODES

Dina Vishnyakova, Emilie Pasche, Julien Gobeill, Arnaud Gaudinat, Christian Lovis, Patrick Ruch

Studies in health technology and informatics, 2012, vol. 180, p. 210-214,

A user-friendly interface for health-related patent retrieval

Wissenschaftlicher Artikel ArODES

Emilie Pasche, Julien Gobeill, Douglas Teodoro, Arnaud Gaudinat, Dina Vishnyakova, Lovis Christian, Patrick Ruch

Studies in health technology and informatics, 2012, vol. 174, p. 121-125,

2011

Using multimodal mining to drive clinical guidelines development

Wissenschaftlicher Artikel ArODES

Emilie Pasche, Julien Gobeill, Douglas Teodoro, Dina Vishnyakova, Arnaud Gaudinat, Patrick Ruch, Christian Lovis

Studies in health technology and informatics, 2011, vol. 169, p. 477-481,

Improving the transparency of health information found on the internet through the honcode: a comparative study

Wissenschaftlicher Artikel ArODES

Sabine Laversin, Vincent Baujard, Arnaud Gaudinat, Maria-Ana Simonet, Célia Boyer

Studies in health technology and informatics, 2011, vol. 169, p. 654-658,

2024

Global taxonomy of stablecoins

Konferenz ArODES

Christophe Lebrun, Oetske Leroux-Frankhauser, Natkamon Tovanich, Thibault Vatter, Arnaud Gaudinat

Proceedings of the 5th International Conference on mathematical research for blockchain economy

2019

Utilisation de méthodes de traitement automatique du langage pour assister la traduction de terminologies dans le cadre du projet EXPAND

Konferenz ArODES

Luc Mottin, Anaïs Mottaz, Arnaud Gaudinat, Stéphane Spahni, Adrian Schmid, Stefan Wyss, Patrick Ruch

Actes de TALMED 2019 : Symposium satellite francophone sur le traitement automatique des langues dans le domaine biomédical

Zusammenfassung:

L’Union Européenne encourage de nombreux projets pilotes dans le domaine de la santé afin de promouvoir les échanges transfrontaliers. epSOS, puis EXPAND, sont deux de ces projets ayant conduit à l’élaboration du Master Value Sets Catalogue (MVC), une compilation de terminologies hautement compatibles avec un ensemble de documents médicaux communs aux états membres du projet. Outre le développement de cette terminologie, le projet EXPAND avait pour but de maintenir une traduction de cette terminologie dans la langue officielle de chaque État-membre, ainsi que son transcodage vis-à-vis des standards terminologiques nationaux. Ce papier présente donc le système semi-automatisé déployé en Suisse pour assister le développement et la mise-à-jour des différentes terminologies concernées. Chacune des étapes de traduction et de validation sont décrites, ainsi que les différents problèmes rencontrés, inhérents au traitement automatique de concepts médicaux.

2017

Accessing reliable health information on the Web :

Konferenz ArODES

a review of the HON approach

Celia Boyer, Arnaud Gaudinat, Allan Hanbury, Ron D. Appel, Marion Ball, Michel Carpentier, Jan H. Van Bemmel, Jean-Paul Bergmans, Denis Hochstrasser, Donald Lindberg, Randolph Miller, Jean-Claude Peterschmitt, Charles Safran, Michèle Thonnet, Antoine Geissbuhler

Proceedings of the 16th World Congress on Medical and Health Informatics (MedInfo2017)

Zusammenfassung:

Accessing online health content of high quality and reliability presents challenges. Laypersons cannot easily differentiate trustworthy content from misinformed or manipulated content. This article describes complementary approaches for members of the general public and health professionals to find trustworthy content with as little bias as possible. These include the Khresmoi health search engine (K4E), the Health On the Net Code of Conduct (HONcode) and health trust indicator Web browser extensions.

2016

BiTeM at CLEF eHealth Evaluation Lab 2016 Task 2 :

Konferenz ArODES

Multilingual Information Extraction

Luc Mottin, Julien Gobeill, Anaïs Mottaz, Arnaud Gaudinat, Patrick Ruch

CEURS Workshop Proceedings, vol. 1609 - Working Notes of CLEF 2016 - Conference and Labs of the Evaluation forum

Julien Gobeill, Arnaud Gaudinat, Patrick Ruch

Zusammenfassung:

BiTeM/SIB Text Mining (http://bitem.hesge.ch/) is a University re-search group carrying over activities in semantic and text analytics applied to health and life sciences. This paper reports on the participation of our team at the CLEF eHealth 2016 evaluation lab. The processing applied to each evaluation corpus (QUAREO and CépiDC) was originally very similar. Our method is based on an Au-tomatic Text Categorization (ATC) system. First, the system is set with a specific input ontology (French UMLS), and ATC assigns a rank list of related concepts to each document received in input. Then, a second module relocates all of the positive matches in the text, and normalizes the extracted entities. For the CépiDC corpus, the system was loaded with the Swiss ICD-10 GM thesaurus. However a late minute data transformation issue forced us to implement an ad hoc solution based on simple pat-tern matching to comply with the constraints of the CépiDC challenge. We obtained an average precision of 62% on the QUAREO entity extraction (over MEDLINE/EMEA texts, and exact/inexact), 48% on normalizing this entities, and 59% on the CépiDC subtask. Enhancing the recall by expanding the coverage of the terminologies could be an interesting approach to improve this system at moderate labour costs.

2015

Exploiting incoming and outgoing citations for improving Information Retrieval in the TREC 2015 Clinical Decision Support Track

Konferenz ArODES

Proceedings of The 24th Text REtrieval Conference (TREC 2015)

Julien Gobeill, Arnaud Gaudinat, Patrick Ruch

Zusammenfassung:

We investigated two strategies for improving Information Retrieval thanks to incoming and outgoing citations. We first started from settings that worked last year and established a baseline. Then, we tried to rerank this run. The incoming citations’ strategy was to compute the number of incoming citations in PubMed Central, and to boost the score of the articles that were the most cited. The outgoing citations’ strategy was to promote the references of the retrieved documents. Unfortunately, no significant improvement from the baseline was observed.

Instance-based learning for tweet monitoring and categorization

Konferenz ArODES

Experimental IR meets multilinguality, multimodality, and interaction

Patrick Ruch, Julien Gobeill, Arnaud Gaudinat, Emilie Pasche

Zusammenfassung:

The CLEF RepLab 2014 Track was the occasion to investigate the robustness of instance-based learning in a complete system for tweet monitoring and categorization based. The algorithm we implemented was a k-Nearest Neighbors. Dealing with the domain (automotive or banking) and the language (English or Spanish), the experiments showed that the categorizer was not affected by the choice of representation: even with all learning tweets merged into one single Knowledge Base (KB), the observed performances were close to those with dedicated KBs. Interestingly, English training data in addition to the sparse Spanish data were useful for Spanish categorization (+14% for accuracy for automotive, +26% for banking). Yet, performances suffered from an overprediction of the most prevalent category. The algorithm showed the defects of its virtues: it was very robust, but not easy to improve. BiTeM/SIBtex tools for tweet monitoring are available within the DrugsListener Project page of the BiTeM website (http://bitem.hesge.ch/).

2014

Full-texts representations with medical subject headings, and co-citations network reranking strategies for TREC 2014 clinical decision support track

Konferenz ArODES

In : Proceedings of Text REtrieval Conference (TREC), Washington, USA, November 19-21 2014. 5 p

Patrick Ruch, Julien Gobeill, Arnaud Gaudinat

Instance-based learning for tweet categorization in CLEF REPLAB 2014

Konferenz ArODES

In : Proceedings of Conference and Labs of the Evaluation Forum (CLEF), Sheffield, United Kingdom, 15-18 september 2014. P.1491-1499

2011

Bitem group report for TREC medical records track 2011

Konferenz ArODES

Julien Gobeill, Arnaud Gaudinat, Patrick Ruch, Emilie Pasche, Douglas Teodoro, Dina Vishnyakova

Proceedings of the Twentieth text retrieval conference, TREC, 2011

Bitem group report for TREC chemical IR track 2011

Konferenz ArODES

Julien Gobeill, Arnaud Gaudinat, Patrick Ruch, Emilie Pasche, Douglas Teodoro, Dina Vishnyakova

In : proceedings of the Twentieth text retrieval conference, TREC, 2011