A5015302815- Heart Failure Treatment and Management
- Cardiovascular Function and Risk Factors
- Ultrasound in Clinical Applications
- Cardiac Valve Diseases and Treatments
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Hemodynamic Monitoring and Therapy
- Bayesian Methods and Mixture Models
- Cardiac Imaging and Diagnostics
- Machine Learning in Healthcare
- Cardiomyopathy and Myosin Studies
- Hormonal Regulation and Hypertension
- Hemoglobinopathies and Related Disorders
- Data Mining Algorithms and Applications
- Statistical Methods and Inference
- Ion Transport and Channel Regulation
- Artificial Intelligence in Healthcare
- Advanced Clustering Algorithms Research
French Clinical Research Infrastructure Network
2020-2022
Centre d'Investigation Clinique Pierre Drouin
2020-2022
Défaillance Cardiovasculaire Aiguë et Chronique
2020-2022
Université de Lorraine
2020
Inserm
2020
Abstract The choice of the most appropriate unsupervised machine-learning method for “heterogeneous” or “mixed” data, i.e. with both continuous and categorical variables, can be challenging. Our aim was to examine performance various clustering strategies mixed data using simulated real-life data. We conducted a benchmark analysis “ready-to-use” tools in R comparing 4 model-based (Kamila algorithm, Latent Class Analysis, Model [LCM] Clustering by Mixture Modeling) 5...
This study sought to identify homogenous echocardiographic phenotypes in community-based cohorts and assess their association with outcomes.Asymptomatic cardiac dysfunction leads a high risk of long-term cardiovascular morbidity mortality; however, better classification asymptomatic individuals remains challenge.Echocardiographic were identified using K-means clustering the first generation STANISLAS (Yearly non-invasive follow-up Health status Lorraine insured inhabitants) cohort (N = 827;...
Background: Heart failure with preserved ejection fraction (HFpEF) is a heterogeneous syndrome for which clear evidence of effective therapies lacking. Understanding factors determine this heterogeneity may be helped by better phenotyping. An unsupervised statistical approach applied to large set biomarkers identify distinct HFpEF phenotypes.Methods: Relevant proteomic were analyzed in 392 patients included Metabolic Road Diastolic HF (MEDIA-DHF). We performed an cluster analysis define...
Many patients with heart failure preserved ejection fraction (HFpEF) are women. Exploring mechanisms underlying the sex differences may improve our understanding of pathophysiology HFpEF. Studies focusing on in circulating proteins HFpEF scarce. A total 415 were analyzed 392 included The Metabolic Road to Diastolic Heart Failure: Failure study (MEDIA-DHF). Sex these assessed using adjusted logistic regression analyses. associations between candidate and cardiovascular (CV) death or CV...
Background Congestion score index (CSI), a semiquantitative evaluation of congestion on chest radiography (CXR), is associated with outcome in patients heart failure (HF). However, its diagnostic value admitted for acute dyspnea has yet to be evaluated. Methods and findings The CSI HF (AHF; adjudicated from patients’ discharge files) was studied the Pathway dyspneic Emergency (PARADISE) cohort, including aged 18 years or older emergency department (ED) Nancy University Hospital (France)...
Abstract Aims Activation of the renin–angiotensin–aldosterone system plays an important role in pathophysiology heart failure (HF) and has been associated with poor prognosis. There are limited data on associations renin aldosterone levels clinical profiles, treatment response, study outcomes patients HF. Methods results We analysed 2,039 available baseline BIOSTAT‐CHF (a systems BIOlogy to Tailored Treatment Chronic Heart Failure). The primary outcome was composite all‐cause mortality or HF...