Data harmonization

Data harmonization improves prediction performance for diabetes status in silico.

“the integrated dataset retained predictive signal relative to cohort-specific models and improved performance for the smaller cohort”

In silicoin integrated cohort dataset

Integrating Longitudinal Cohorts for Population Health Research: Mainland and Island-based Puerto Rican Diabetes Study

medRxiv·11 Oct 2026Preprint

Data harmonization decreases artifactual differences in brain network measurement in silico.

“Harmonization approaches accounting for protocol and scanner-model differences alleviate some of the artifactual differences in brain network measurement.”

In silico

Systematic fMRI signal differences across cohorts alter lifespan connectome trajectories

bioRxiv : the preprint server for biology·16 Jan 2026Preprint