All ENIGMA protocols are now linked on the ENIGMA GitHub page page. Please check here for the latest amendments and updates!

Anyone is welcome to use these protocols for their projects! If you use the protocols on this site for projects outside of ENIGMA, please include a reference to the ENIGMA main page ( so that your readers and reviewers know about it as well.

ComBat for ENIGMA

ComBat is a function that allows for removal of known batch effects. This modified version of the function for the ENIGMA Consortium also allows to separate functions for fitting and applying the harmonization, and allows missings and constant rows and minor changes in the arguments of the functions to facilitate their use.
Please cite "Increased power by harmonizing structural MRI site differences with the ComBat batch adjustment method in ENIGMA" (Radua et al., NeuroImage 2020)

Estimation of multisite accuracy

The effects of the site may severely bias the accuracy of a multisite machine-learning model, even if the analysts removed them when fitting the model in the 'training set' and when applying the model in the 'test set'. This simple R package estimates the accuracy of a multisite machine-learning model unbiasedly. It currently supports the estimation of sensitivity, specificity, balanced accuracy, the area under the curve, correlation, mean squared error, and hazard ratio for binomial, multinomial, gaussian, and survival (time-to-event) outcomes.
Please cite "Biased accuracy in multisite machine-learning studies due to incomplete removal of the effects of the site" (Solanes et al., Psychiatry Res Neuroimaging 2021)


ENIGMA on social media: