A5068096460- Healthcare Systems and Practices
- Total Knee Arthroplasty Outcomes
- Spinal Hematomas and Complications
- Orthopaedic implants and arthroplasty
- Case Reports on Hematomas
- Health, Medicine and Society
- Biomedical Text Mining and Ontologies
- Lung Cancer Treatments and Mutations
- Artificial Intelligence in Healthcare
- Data-Driven Disease Surveillance
- Traffic and Road Safety
- Hemodynamic Monitoring and Therapy
- Hip and Femur Fractures
- Trauma and Emergency Care Studies
- Injury Epidemiology and Prevention
- Neurological Complications and Syndromes
- Vasculitis and related conditions
- Semantic Web and Ontologies
- Machine Learning in Healthcare
- Pneumothorax, Barotrauma, Emphysema
- Retinal and Optic Conditions
- Delphi Technique in Research
- Data Quality and Management
- Health Systems, Economic Evaluations, Quality of Life
- COVID-19 epidemiological studies
Centre Hospitalier Universitaire de Tours
2020-2022
Université de Tours
2021-2022
Hôpital Bretonneau
2021
Université de Rennes
2020
Centre Hospitalier Universitaire de Rennes
2020
Inserm
2020
Anticipating unplanned hospital readmission episodes is a safety and medico-economic issue. We compared statistics (Logistic Regression) machine learning algorithms (Gradient Boosting, Random Forest, Neural Network) for predicting the risk of all-cause, 30-day using data from clinical warehouse Rennes other sources. The dataset included stays based on criteria French national methodology rate (i.e., patients older than 18 years, geolocation, no iterative stays, hospitalization palliative...
Hip arthroplasty represents a large proportion of orthopaedic activity, constantly increasing. Automating monitoring from clinical data warehouses is an opportunity to dynamically monitor devices and patient outcomes allowing improve practices. Our objective was assess quantitative qualitative concordance between claim device supply in order create e-cohort patients undergoing hip replacement. We performed single-centre cohort pilot study, one warehouse French University Hospital, January 1,...
Abstract Introduction Familial hypercholesterolemia (FH) in children and adolescents is a genetic cause of premature coronary heart disease. Early detection patients with FH could improve their management life expectancy. Methods A retrospective observational study was conducted using our university hospital clinical data warehouse including born after 01/01/2000, at least one available lipid profile. Phenotypic diagnosis defined by plasma LDL-C level ≥5 mmol/L (190 mg/dL). Above-threshold...
Abstract Background: Unplanned hospital readmissions are a major healthcare and economic burden. This study compared statistical methods machine learning algorithms for predicting the risk of all-cause 30-day readmission in two French academic hospitals. Methods: The dataset included stays selected from clinical data warehouses (CDW) hospitals (Rennes Tours Academic Hospitals) using criteria national methodology to measure rate (i.e. ≥18-year-old patients, geolocation, no iterative stays,...