prescale_fit: Fit and apply brain imaging prescaling

prescale_fitR Documentation

Fit and apply brain imaging prescaling

Description

Fit and apply a prescaling of magnetic resonance imaging (MRI) data from different sites, especially relevant for fMRI, where different devices can have varying units of measurement.

Usage

prescale_fit(dat, site, cov = NULL, n.min = 10, impute_missing_cov = FALSE,
             verbose = TRUE)
prescale_apply(combat_parameters, dat, site, cov = NULL, verbose = TRUE)

Arguments

dat

matrix or data.frame with the MRI data (e.g., ROIs, voxels, vertexes, etc.).

site

factor specifying the site of each individual.

cov

matrix or data.frame with the covariates.

combat_parameters

a list of combat parameters returned by prescale_fit.

n.min

(optional) number specifying the minimum size of a site to be analyzed.

impute_missing_cov

(optional) logical, whether to impute missing covariates.

verbose

(optional) logical, whether to print some messages during execution.

Details

prescale_fit function finds a prescaling parameter for each site so that, after calling prescale_apply, the voxelwise-median standard deviation after removing the effects of covariates is 1 (in the training data, but it might not be the case in new data).

Value

prescale_fit returns a list of parameters for prescale_apply; prescale_apply returns the list of parameters plus the prescaled data (item dat.combat)

Author(s)

Joaquim Radua

References

Neural correlates of human fear conditioning and sources of variability: A mega-analysis and normative modeling study of fMRI data from 2,199 individuals, to be submitted.

See Also

combat_fit, and lmm_fit

Examples

raw_mri = combat_example[,6:19]
site = factor(combat_example$site)

# Fit and apply prescale to prescale mri data across sites
mod = as.matrix(combat_example[,c("disorder", "age", "sex")])
prescaling = prescale_fit(raw_mri, site, mod)
prescaled_mri = prescale_apply(prescaling, raw_mri, site, mod)$dat.combat

combat.enigma documentation built on Oct. 30, 2024, 9:13 a.m.