Abstract
In a random 200 septic patient sample, the effect of laboratory values on the risk of death was tested, both traditionally, and with help of machine learning.
Traditional efficacy analysis was composed of
discretization of continuous predictors,
crosstabs with chi-square statistics,
multiple binary logistic regressions.
Machine learning efficacy analysis was composed of support-vector-machine methods.
The machine learning methods provided better sensitivity of testing, and were more informative.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Cleophas, T.J., Zwinderman, A.H. (2019). Support-Vector-Machines for Efficacy Analysis. In: Efficacy Analysis in Clinical Trials an Update. Springer, Cham. https://doi.org/10.1007/978-3-030-19918-0_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-19918-0_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-19917-3
Online ISBN: 978-3-030-19918-0
eBook Packages: Biomedical and Life SciencesBiomedical and Life Sciences (R0)