Ensemble Integration (EI) is a customizable pipeline for generating diverse ensembles of heterogeneous classifiers. The original python implementation of EI can be found in the following repository: https://github.com/GauravPandeyLab/eipy. All EI-derived models were adapted from this implementation, using a fork of EI already included in this repository.
The original data provided by TADPOLE can be read about here: https://tadpole.grand-challenge.org/Data/#Data. To access TADPOLE data, you will need to register with ADNI and apply for access to these data. Once access is granted, you need only to run the 'setup' jupyter notebook to process the data.
All details and code necessary to run EI on TADPOLE data are located in the 'EI_for_TADPOLE' jupyter notebook. Make sure to process the data using the 'setup' notebook first!