A4 Refereed article in a conference publication
Multi-site External Sets Harmonization with M-ComBat: An Application to Functional Connectivity in a Normative Framework
Authors: Won Sampaio, Inês; Tassi, Emma; Bianchi, Anna M.; Borgwardt, Stefan; Kambeitz, Joseph; Kambeitz-Ilankovic, Lana; Meisenzahl, Eva; Salokangas, Raimo K. R.; Upthegrove, Rachel; Wood, Stephen J.; Koutsouleris, Nikolaos; Brambilla, Paolo; Maggioni, Eleonora
Editors: N/A
Conference name: IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering
Publication year: 2024
Book title : 2024 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE)
First page : 400
Last page: 404
ISBN: 979-8-3503-7801-6
eISBN: 979-8-3503-7800-9
DOI: https://doi.org/10.1109/MetroXRAINE62247.2024.10796816(external)
Web address : https://ieeexplore.ieee.org/document/10796816(external)
Multi-site neuroimaging datasets are difficult to integrate due to confounding site effects. ComBat has been a widely used statistical-based model for this type of harmonization. Nevertheless, it suffers some drawbacks which prevent its application in external validation frameworks in machine learning (ML) analyses. First, ComBat relies on all current sites to estimate model parameters, leading to the necessity of re-fitting the model when data from new unseen sites is added. Then, it requires the inclusion of biological information of interest (e.g. diagnosis) in the model fitting process, which is incompatible with the harmonization of samples with unknown outcomes, a necessary condition to develop AI applications based on predictive models to be employed in clinical settings. In this work, we propose to solve the former issues by employing modified ComBat (M-ComBat) in a normative framework (NM-ComBat). To assess its harmonization efficacy, we compared four different ComBat variations, including its standard application (S-ComBat), M-ComBat, and the normative variation of the latter, NS-ComBat and NM-ComBat, in harmonizing a multi-site functional connectivity (FC) dataset. Our results show that NM-ComBat enabled the successful harmonization of external datasets, successfully eliminating site effects from data, while preserving biological covariates of interest, such as age, sex, and diagnosis. These results paved the way for the application of ComBat in ML analysis and external validation frameworks, contributing to the generalizability of developed models and their potential clinical applicability.
Funding information in the publication:
This study was partially supported by EBRAINS-Italy, project funded under the National Recovery and Resilience Plan (NRRP), Mission 4, “Education and Research” - Component 2, “From research to Business” Investiment 3.1 - Call for tender No. 3264 of Dec 28, 2021 of Italian Ministry of University and Research (MUR) funded by the European Union – NextGenerationEU, with award number: Project code IR0000011, Concession Decree No. 117 of June 21,2022 adopted by the Italian Ministry of University and Research, CUP B51E22000150006, Project title “EBRAINSItaly (European Brain ReseArch INfrastructureS-Italy) and by the European Union- FP7 project PRONIA (“Personalized Prognostic Tools for Early Psychosis Management”, grant number 602152). EM was supported by the Italian Ministry of University and Research (PRIN 2022, grant n. 2022RXM3H7) and by the Italian Ministry of Health (grant n. GR-2018-12367789). PB was partially supported by the Italian Ministry of University and Research (Dipartimenti di Eccellenza Program 2023–2027 - Dept of Pathophysiology and Transplantation, University of Milan), the Italian Ministry of Health (Hub Life Science- Diagnostica Avanzata, HLS-DA, PNC-E3-2022-23683266– CUP: C43C22001630001 / MI-0117; Ricerca Corrente 2024) and by the Fondazione Cariplo (grant n° 2019–3416).
