Time series ai model for acute kidney injury detection based on a multicenter distributed research network: development and verification study

HIGHLIGHTS

• What: The authors aimed detect the early occurrence of AKI by applying the interpretable LSTM-based model on a EHR-based time series in patients who took nephrotoxic drugs using a DRN. The principal findings are as follows: First, this study provides an interpretation of the temporal importance of variables for predicting AKI, and the models also achieved high performance, with an average AUC of 0.92%. This study shows the high performance of the IMV-LSTM method for AKI prediction using hospital EHR-based time series data.
• Who: Heo et al and colleagues from . . .
  

   

  

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

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

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