Search Results for author: George Thoma

Found 1 papers, 1 papers with code

Neural networks versus Logistic regression for 30 days all-cause readmission prediction

1 code implementation22 Dec 2018 Ahmed Allam, Mate Nagy, George Thoma, Michael Krauthammer

Among the deep learning approaches, a recurrent neural network (RNN) combined with conditional random fields (CRF) model (RNNCRF) achieved the best performance in readmission prediction with 0. 642 AUC (95% CI, 0. 640-0. 645).

Management Readmission Prediction +1

Cannot find the paper you are looking for? You can Submit a new open access paper.