BookTon J. Cleophas, Aeilko H. Zwinderman.
Summary: Machine learning and big data is hot. It is, however, virtually unused in clinical trials. This is so, because randomization is applied to even out multiple variables. Modern medical computer files often involve hundreds of variables like genes and other laboratory values, and computationally intensive methods are required. This is the first publication of clinical trials that have been systematically analyzed with machine learning. In addition, all of the machine learning analyses were tested against traditional analyses. Step by step statistics for self-assessments are included. The authors conclude, that machine learning is often more informative, and provides better sensitivities of testing than traditional analytic methods do.
Contents:
Preface
Traditional and Machine-Learning Methods for Efficacy Analysis
Optimal-Scaling for Efficacy Analysis
Ratio-Statistic for Efficacy Analysis
Ratio-Statistic for Efficacy Analysis
Complex-Samples for Efficacy Analysis
Bayesian-Networks for Efficacy Analysis
Evolutionary-Operations for Efficacy Analysis
Automatic-Newton-Modeling for Efficacy Analysis
High-Risk-Bins for Efficacy Analysis
Balanced-Iterative-Reducing-Hierarchy for Efficacy Analysis
Cluster-Analysis for Efficacy Analysis
Multidimensional-Scaling for Efficacy Analysis
Binary Decision-Trees for Efficacy Analysis
Continuous Decision-Trees for Efficacy Analysis
Automatic-Data-Mining for Efficacy Analysis
Support-Vector-Machines for Efficacy Analysis
Neural-Networks for Efficacy Analysis
Ensembled-Accuracies for Efficacy Analysis
Ensembled-Correlations for Efficacy Analysis
Gamma-Distributions for Efficacy Analysis
Validation with Big Data, a Big Issue
Index.