This code preprocesses a large volume of historical clinical trials data into labelled datasets for outlier detection. Six off-the-shelf fully-unsupervised outlier detection algorithms are compared, and a handful of model selection techniques based on ensembling and meta-learning are compared.
Do Ensembling and Meta-Learning Improve Outlier Detection in Randomized Controlled Trials?
Walter Nelson, Jonathan Ranisau, Jeremy Petch
Machine Learning for Health, 2023
BibTeX:
TODO