A5023539531- Pharmaceutical Practices and Patient Outcomes
- Healthcare Systems and Practices
- Pharmacovigilance and Adverse Drug Reactions
- Electronic Health Records Systems
- Health, Medicine and Society
- Biomedical Text Mining and Ontologies
- Health Systems, Economic Evaluations, Quality of Life
- Clinical practice guidelines implementation
- Data Quality and Management
- Artificial Intelligence in Healthcare
- Machine Learning in Healthcare
- Healthcare Technology and Patient Monitoring
- Atrial Fibrillation Management and Outcomes
- Suicide and Self-Harm Studies
- Pharmacy and Medical Practices
- Data-Driven Disease Surveillance
- ECG Monitoring and Analysis
- Quality and Safety in Healthcare
- Orthopedic Surgery and Rehabilitation
- Patient Safety and Medication Errors
- Poisoning and overdose treatments
- Acute Ischemic Stroke Management
- Hip disorders and treatments
- Venous Thromboembolism Diagnosis and Management
- Semantic Web and Ontologies
Université de Lille
2016-2025
Centre Hospitalier Universitaire de Lille
2016-2025
Evaluation des technologies de santé et des pratiques médicales
2015-2025
Santé Publique France
2010-2024
Centre de Recherche en Informatique
2018-2024
Technologies pour la Santé
2011-2023
Inserm
2022
Unité de Technologies Chimiques et Biologiques pour la Santé
2020
Institut thématique Santé Publique
2017
Université Lille Nord de France
2011-2016
Adverse drug events (ADEs) are a public health issue. Their detection usually relies on voluntary reporting or medical chart reviews. The objective of this paper is to automatically detect cases ADEs by data mining. 115,447 complete past hospital stays extracted from six French, Danish, and Bulgarian hospitals using common model including diagnoses, administrations, laboratory results, free-text records. Different kinds outcomes traced, supervised rule induction methods (decision trees...
AimsRemote monitoring of cardiac implantable electronic devices is a growing standard; yet, remote follow-up and management alerts represents time-consuming task for physicians or trained staff. This study evaluates an automatic mechanism based on artificial intelligence tools to filter atrial fibrillation (AF) their medical significance.
Managers, physicians and researchers need to study patient's path for purposes of management, quality care research. We present the proof concept use a flow diagram, Sankey visualize trajectory population that experienced an event. This representation was tested with two case studies in populations from anesthesia data warehouse Lille University Hospital. For 551 patients undergoing pancreaticoduodenectomy, diagram helped us identify atypical paths patient being transferred too late...
To demonstrate that radiologists, with the help of artificial intelligence (AI), are able to better classify screening mammograms into correct breast imaging reporting and data system (BI-RADS) category, as a secondary objective, explore impact AI on cancer detection mammogram interpretation time.A multi-reader, multi-case study cross-over design, was performed, including 314 mammograms. Twelve radiologists interpreted examinations in two sessions delayed by 4 weeks wash-out period without...
ABSTRACT Studies on the fracture risk in presarcopenic and sarcopenic patients report contradictory results. The objective was to assess whether presarcopenia sarcopenia are associated with an increase risk. We conducted a retrospective study using UK Biobank cohort European Working Group Sarcopenia Older People 2 (EWGSOP2) criteria. Muscle strength evaluated hand-grip (HGS) muscle mass skeletal index (SMI; from bioimpedance analysis). Presarcopenia defined through two definitions available...
ABSTRACT Borderline personality disorder (BPD) is a frequent with high mental health care utilization. This study aims to describe BPD hospitalization in France: using the French national hospitals database from 2013 2022, regarding sociodemographic factors and characteristics. In total, this included 121,235 patients. The sex ratio was 1.76 female for 1 male. median age at 33 years. Most hospitalizations concerned patients around 30 years old, were voluntary, full‐time, public facilities,...
<h3>Importance</h3> The risk of postoperative pulmonary embolism has been reported to be highest during the first 5 weeks after surgery. However, how long excess persists remains unknown. <h3>Objective</h3> To assess duration and magnitude late among cancer-free middle-aged patients by type <h3>Design, Setting, Participants</h3> Case-crossover analysis compute respective risks 6 types surgery using data from a French national inpatient database, which covers total 203 million stays over an...
Abstract Background Common data models (CDMs) enable to be standardized, and facilitate exchange, sharing, storage, particularly when the have been collected via distinct, heterogeneous systems. Moreover, CDMs provide tools for quality assessment, integration into models, visualization, analysis. The observational medical outcome partnership (OMOP) provides a CDM organizing standardizing databases. not only but also (and especially OMOP model) extends range of available statistical analyses....
Dehydration secondary to gastroenteritis is one of the most common reasons for office visits and hospital admissions. The indicator commonly used estimate dehydration status acute weight loss. Post-illness gain considered as gold-standard determine true level widely loss in research. To value post-illness a gold standard dehydration, we conducted prospective cohort study which 293 children, aged 1 month 2 years, with diarrhea were followed 7 days during 3-year period. main outcome measures...
Traditional surveillance systems produce estimates of influenza-like illness (ILI) incidence rates, but with 1- to 3-week delay. Accurate real-time monitoring for influenza outbreaks could be useful making public health decisions. Several studies have investigated the possibility using internet users' activity data and different statistical models predict epidemics in near real time. However, very few hospital big data.Here, we compared electronic records (EHRs) identify best approach (data...
Infliximab (IFX) was the first anti-tumor necrosis factor (TNFα) antibody to be used in treatment of severe chronic inflammatory diseases, such as Crohn's disease and rheumatoid arthritis. A number serious adverse drug reactions are known associated with IFX use; they include infections, malignancies, injection site reactions. Although a few case reports have described potential psychiatric events (including suicide attempts manic episodes), latter barely mentioned IFX's summary product...
Incidence of complications following obstetrical anal sphincter injury (OASI) during vaginal delivery are poorly defined. They only studied in high level maternities, small cohorts, all stages perineal tear or low-income countries. The aim our study was to describe after primary OASI repair a French maternity wards at short and midterm assess factors associated with complication occurrence. We conducted historical cohort using the nationwide claim database (PMSI) from January 2013 December...
Introduction The aim of this study was to identify factors associated with the results smoking cessation attempts. Methods Data were collected in Clermont-Ferrand from a clinic between 1999 and 2009 (1,361 patients). Smoking considered success when patients abstinent 6 months after beginning cessation. Multivariate logistic regression used investigate association abstinence different factors. Results significant history depression (ORadjusted = 0.57, p 0.003), state at initial consultation...
Medical coding is used for a variety of activities, from observational studies to hospital billing. However, comorbidities tend be under-reported by medical coders. The aim this study was develop an algorithm detect in electronic health records (EHR) using clinical data warehouse (CDW) and knowledge database. We enriched the Theriaque pharmaceutical database with French national Comorbidities List identify drugs associated at least one major comorbid condition diagnoses drug indication....