Initial chest radiographs and artificial intelligence (AI) predict clinical outcomes in COVID-19 patients: analysis of 697 Italian patients.
Junaid MushtaqRenato PennellaSalvatore LavalleAnna ColarietiStephanie SteidlerCarlo M A MartinenghiDiego PalumboAntonio EspositoPatrizia Rovere-QueriniMoreno TresoldiGiovanni LandoniFabio CiceriAlberto ZangrilloFrancesco De CobelliPublished in: European radiology (2020)
• AI system-based score ≥ 30 and a RALE score ≥ 12 at CXRs performed at ED presentation are independent and comparable predictors of death and/or ICU admission in COVID-19 patients. • Other independent predictors are older age, male sex, coronary artery disease, COPD, and neurodegenerative disease. • The comparable performance of the AI system in relation to a radiologist-assessed score in predicting adverse outcomes may represent a game-changer in resource-constrained settings.
Keyphrases
- percutaneous coronary intervention
- artificial intelligence
- coronary artery disease
- coronary artery bypass grafting
- machine learning
- big data
- deep learning
- emergency department
- sars cov
- end stage renal disease
- cardiovascular events
- newly diagnosed
- chronic obstructive pulmonary disease
- ejection fraction
- peritoneal dialysis
- intensive care unit
- physical activity
- heart failure
- type diabetes
- cardiovascular disease
- lung function
- cystic fibrosis
- left ventricular
- case report
- transcatheter aortic valve replacement