Author: Christopher M. Petrilli; Simon A. Jones; Jie Yang; Harish Rajagopalan; Luke F. O'Donnell; Yelena Chernyak; Katie Tobin; Robert J. Cerfolio; Fritz Francois; Leora I. Horwitz
Title: Factors associated with hospitalization and critical illness among 4,103 patients with COVID-19 disease in New York City Document date: 2020_4_11
ID: 8prg1goh_22
Snippet: is the (which was not peer-reviewed) The copyright holder for this preprint . https://doi.org/10.1101/2020.04.08.20057794 doi: medRxiv preprint has similar characteristics and outcomes. We used the decision tree classifier from Python 3.7.4 scikit-learn library. We chose to maximize information gain (which minimizes entropy) for each branch split in the classification tasks. We also pruned the trees to prevent overfitting by limiting the maximum .....
Document: is the (which was not peer-reviewed) The copyright holder for this preprint . https://doi.org/10.1101/2020.04.08.20057794 doi: medRxiv preprint has similar characteristics and outcomes. We used the decision tree classifier from Python 3.7.4 scikit-learn library. We chose to maximize information gain (which minimizes entropy) for each branch split in the classification tasks. We also pruned the trees to prevent overfitting by limiting the maximum depth, minimum samples in a leaf, and minimum sample splits. For both models, we split the data into a training set (80%) and hold-out set (20%). For the admission model, we ran 48 iterations to achieve optimal parameters. For the complications model, we ran 64 iterations.
Search related documents:
Co phrase search for related documents- classification task and hold set: 1
- decision tree and information gain: 1, 2, 3, 4
- decision tree and optimal parameter: 1
Co phrase search for related documents, hyperlinks ordered by date