Marco Lorenzi

The paper discusses challenges in federated analysis for multisite neuroinformatics studies and presents solutions from recent projects.

The paper investigates seizure mechanisms in Dravet syndrome, finding that preictal dysfunctions of inhibitory interneurons lead to rebound hyperactivity and low-voltage-fast seizures.

This study benchmarks the accuracy and cost-effectiveness of federated learning and consensus-based learning in medical data analysis, finding that consensus-based learning is more cost-effective with comparable accuracy.

Fed-ComBat harmonizes batch effects in decentralized data, showing comparable results to centralized methods for linear and nonlinear cases.

This study simulates amyloid treatment outcomes in Alzheimer's Disease using multi-modal imaging and clinical data to show that earlier intervention improves clinical endpoints.

The paper detects pre-symptomatic shape changes in the thalamus using spatiotemporal analysis of MRI scans from the GENFI study, finding differences five years before symptoms appear.