Skip to main content

Table 1 Overall analytic approach

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

Algorithm choice

Loss function

Data manipulation

Modeling approach

LASSO

Mean squared error (MSE)

Original data

One-stage approach

Random forest

Mean absolute error (MAE)

Log data

Two-stage approach

Multilayer perceptron

Mean relative error (MRE)

Truncated data

 
  1. This table guides the analytic approach in this study. We compared different algorithm choices, loss functions, data manipulations and modeling approaches
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us