- Biomedical Text Mining and Ontologies
- Semantic Web and Ontologies
- Electronic Health Records Systems
- Data Visualization and Analytics
- Clinical practice guidelines implementation
- Pharmaceutical Practices and Patient Outcomes
- Natural Language Processing Techniques
- Medication Adherence and Compliance
- Computational Drug Discovery Methods
- Advanced Text Analysis Techniques
- Computational Physics and Python Applications
- linguistics and terminology studies
- Data Quality and Management
- Meta-analysis and systematic reviews
- Health Sciences Research and Education
- Machine Learning in Healthcare
- Marine Bivalve and Aquaculture Studies
- Chronic Disease Management Strategies
- Bioinformatics and Genomic Networks
- Health Systems, Economic Evaluations, Quality of Life
- Artificial Intelligence in Healthcare
- Topic Modeling
- Pharmacovigilance and Adverse Drug Reactions
- Pharmaceutical industry and healthcare
- scientometrics and bibliometrics research
Université Sorbonne Paris Nord
2015-2024
Laboratoire d'Informatique Médicale et d'Ingénierie des Connaissances en e-Santé
2015-2024
Inserm
2015-2024
Sorbonne Université
2015-2024
Institut National de Santé Publique
2024
Université Paris Cité
2012-2023
Sorbonne Paris Cité
2013-2023
Département d'Informatique
2009-2022
Laban/Bartenieff Institute of Movement Studies
2022
Laboratoire de Recherche en Informatique
2020-2021
Case-Based Reasoning (CBR) is a form of analogical reasoning in which the solution for (new) query case determined using database previous known cases with their solutions. Cases similar to are retrieved from database, and then solutions adapted query. In medicine, usually corresponds patient problem consists classifying class diagnostic or therapy. Compared "black box" algorithms such as deep learning, responses CBR systems can be justified easily examples. However, this possibility often...
Measures for controlling antimicrobial resistance are urgently required. We describe here AntibioGame®, a serious game improving the training of medical students in antibiotic use primary care. aimed to design antibiotics teaching and evaluate its usability playability by students. used various gamification techniques (e.g. mascots, avatars, rewards, leader board) cartoon graphics AntibioGame®. This implements clinical case templates built from list learning goals defined team through an...
Each year, the International Medical Informatics Association Yearbook recognizes significant scientific papers, labelled as "best papers", published previous year in subfields of biomedical informatics that correspond to different section topics journal. For each section, about fifteen pre-selected "candidate" best papers are externally peer-reviewed select actual papers. Although based on available literature, little is known pre-selection process.To move toward an explicit formalization...
Clinical guidelines carry medical evidence to the point of practice. As is not always available, many do provide recommendations for all clinical situations encountered in We propose an approach identifying knowledge gaps and exploring physicians' therapeutic decisions with data mining techniques fill these gaps. demonstrate our method by example domain type 2 diabetes. analyzed French national management diabetes identify conditions that are covered or those which recommendations. extracted...
Many medication errors are encountered in drug prescriptions, which would not occur if practitioners could remember the properties. They can refer to monographs find these properties, however long and tedious read during consultation. We propose a two-step approach for facilitating access monographs. The first step, presented here, is design of graphical language, called VCM.The VCM language was designed using small number primitives combinatory rules. evaluated over 11 volunteer general...
VCM (Visualization of Concept in Medicine) is an iconic language for representing key medical concepts by icons. However, the use this with reference terminologies, such as SNOMED CT, will require mapping its icons to terms these terminologies. Here, we present and evaluate a semi-automatic semantic method CT Both are compositional nature; expressed description logic semantics formalized OWL ontology. The proposed involves manual limited number underlying from ontology, followed automatic...
The integration of terminologies is still a challenging problem in medical informatics research and software applications, due to the high number heterogeneous terminologies. In this paper, we present generic API (Application Programming Interface) for multi-terminology multilingual terminology service, PyMedTermino, its open-source implementation Python with 5 terminological resources (ICD10, SNOMED CT, MedDRA, CDF, VCM iconic language) UMLS compendium. This service has been designed...
Drug iatrogeny is important but could be decreased if contraindications, cautions for use, drug interactions and adverse effects of drugs described in monographs were taken into account. However, the physician's time limited during consultations, this information often not consulted. We describe here design "Mister VCM", a graphical interface based on VCM language, facilitating access to monographs. also provide an assessment usability interface. The VCM" was designed by dividing screen two...
Overlapping set visualization is a well-known problem in information visualization. This considers elements and sets containing all or part of the elements, given element possibly belonging to more than one set. A typical example properties 20 amino-acids. complex application visual comparison contraindications adverse effects several similar drugs. The knowledge involved voluminous, each drug has many effects, some them are shared with other In this paper, we present rainbow boxes, novel...
Clinical decision support systems (CDSS) implementing clinical practice guidelines (CPGs) have 2 main limitations: they target only patients for whom CPGs provide explicit recommendations, and their rationale may be difficult to understand. These limitations result in poor CDSS adoption. We designed AntibioHelp® as a antibiotic treatment. It displays the recommended nonrecommended antibiotics, together with properties, weighted by degree of importance outlined CPGs. The aim this study was...
Well-designed medical decision support system (DSS) have been shown to improve health care quality. However, before they can be used in real clinical situations, these systems must extensively tested, ensure that conform the guidelines (CG) on which are based. Existing methods cannot for systematic testing of all possible test cases. We describe here a new exhaustive dynamic verification method. In this method, DSS is considered black box, and Quinlan C4.5 algorithm build tree from an set...
Identifying patients at risk of hereditary cancer based on their family health history is a highly nuanced task. Frequently, are not referred for genetic counseling as providers lack the time and training to collect assess history. Consequently, do receive testing that they need determine preventive steps should take mitigate risk.This study aims automate clinical practice guideline recommendations patient history.We combined chatbots, web application programming interfaces, guidelines,...
Set visualization is a well-known task in information visualization. In biology, it used for comparing visually sets of genes or proteins, typically using Venn diagrams. However, limitations the diagram are well-known: they limited to 6 and difficult read above 4. Many other set techniques have been proposed, but never widely biology. this paper, we introduce RainBio, technique visualizing biology aimed at providing global overview showing size main intersections, proportional way,...