COVID-19 Mortality Prediction From Deep Learning in a Large Multistate Electronic Health Record and Laboratory Information System Data Set: Algorithm Development and Validation.
Saranya SankaranarayananJagadheshwar BalanJesse R WalshYanhong WuSara MinnichAmy L PiazzaCollin OsborneGavin R OliverJessica LeskoKathy L BatesKia KhezeliDarci R BlockMargaret A DiGuardoJustin KreuterJohn C O'HoroJohn KalantariEric W KleeMohamed E SalamaBenjamin R KippWilliam George MoriceGarrett JenkinsonPublished in: Journal of medical Internet research (2021)
Our deep learning approach using GRU-D provides an alert system to flag mortality for COVID-19-positive patients by using clinical covariates and laboratory values within a 72-hour window after the first positive nucleic acid test result.
Keyphrases
- deep learning
- electronic health record
- coronavirus disease
- nucleic acid
- sars cov
- clinical decision support
- end stage renal disease
- machine learning
- cardiovascular events
- artificial intelligence
- convolutional neural network
- ejection fraction
- newly diagnosed
- chronic kidney disease
- risk factors
- blood pressure
- prognostic factors
- healthcare
- adverse drug
- coronary artery disease
- cardiovascular disease