Phenotype clustering of hospitalized high-risk patients with COVID-19 - a machine learning approach within the multicentre, multinational PCHF-COVICAV registry.
Mateusz SokolskiSander TrensonKonrad ReszkaSzymon UrbanJustyna M SokolskaTor Biering-SørensenMats C Højbjerg LassenKristoffer Grundtvig SkaarupCarmen BasicZacharias MandalenakisKlemens AblasserPeter P RainerMarkus WallnerValentina A RossiMarzia LilliuGoran LoncarHuseyin A CakmakFrank RuschitzkaAndreas J FlammerPublished in: Cardiology journal (2024)
The ML process has identified three important clinical clusters from hospitalized COVID-19 CV and/or RF patients. The cluster of males with severe CV disease, particularly HF, and multiple RF presenting with increased inflammation had a particularly poor outcome.
Keyphrases
- machine learning
- end stage renal disease
- coronavirus disease
- ejection fraction
- chronic kidney disease
- sars cov
- oxidative stress
- clinical trial
- prognostic factors
- peritoneal dialysis
- randomized controlled trial
- single cell
- heart failure
- study protocol
- case report
- atrial fibrillation
- deep learning
- double blind
- acute heart failure