Predicting in-hospital length of stay: a two-stage modeling approach to account for highly skewed data

HIGHLIGHTS

• who: Zhenhui Xu from the We abstracted data from the Duke University Health System (DUHS) electronic health record (EHR) systemDUHS consists of three hospitals, tertiary care center and , community hospitals-and has had an integrated EPIC EHR system since, . Data Case definition have published the research work: Predicting in-hospital length of stay: a two-stage modeling approach to account for highly skewed data, in the Journal: (JOURNAL)
• what: The authors compare different loss-functions (mean squared error mean absolute error mean relative error) algorithms (LASSO Random Forests multilayer perceptron) and data transformations (log and . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.