Abstract #1279

A Multiblock Partial Least Squares Correlation Framework for Covariate Adjustment and Interpretation of Latent Associations in Multimodal Data

Warda T. Syeda¹, Bjørn H. Ebdrup^1,2,3, Cassandra M.J. Wannan¹, Micah Cearns¹, Rigas Soldatos¹, Antonia Merritt¹, Mahesh Jayaram ¹, Andrew Zalesky ¹, Jayachandra M. Raghava^2,4, Birgitte Fagerlund ², Egill Rostrup ², Birte Glenthøj ^2,3, Leigh A. Johnston^5,6, Chad Bousman ^1,7, Ian Everall⁸, Efstratios Skafidas ^1,9, and Christos Pantelis^1,9

¹Melbourne Neuropsychiatry Centre, The University of Melbourne, Parkville, Australia, ²Center for Neuropsychiatric Schizophrenia Research and Center for Clinical Intervention and Neuropsychiatric Schizophrenia Research, Mental Health Centre Glostrup, Copenhagen University Hospital, Glostrup, Denmark, ³Faculty of Health and Medical Sciences, Department of Clinical Medicine, University of Copenhagen, Denmark, Denmark, ⁴Functional Imaging Unit, Department of Clinical Physiology, Nuclear Medicine and PET, Rigshospitalet, Glostrup, Denmark, ⁵Department of Biomedical Engineering, The University of Melbourne, Melbourne, Australia, ⁶Melbourne Brain Centre Imaging Unit, The University of Melbourne, Parkville, Australia, ⁷Departments of Medical Genetics, Psychiatry, and Physiology & Pharmacology, University of Calgary, Calgary, AB, Canada, ⁸Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, United Kingdom, ⁹Electrical and Electronic Engineering Department, The University of Melbourne, Parkville, Australia

Partial least squares (PLS) methods enable identification of multimodal patterns of latent associations between neuroimaging, cognitive, functional and clinical measures. Here, we propose a multiblock PLS correlation (MB-PLS-C) technique to enable covariate representation in the latent space and an interpretation framework to assess results from PLS-C analyses in clinical contexts. We investigate latent structure-cognition patterns in a multivariate dataset of individuals with treatment-resistant schizophrenia and healthy controls using the proposed MB-PLS-C method, and compare with standard PLS-C with and without covariate adjustment through residualization.

This abstract and the presentation materials are available to members only; a login is required.

Join Here