Multimodal Predictive Modeling: Scalable Imaging Informed Approaches to Predict Future Brain Health

Abstract

BackgroundPredicting future brain health is a complex endeavor that often requires integrating diverse data sources. The neural patterns and interactions iden-tified through neuroimaging serve as the fundamental basis and early indica-tors that precede the manifestation of observable behaviors or psychological states. New MethodIn this work, we introduce a multimodal predictive modeling approach that leverages an imaging-informed methodology to gain insights into fu-ture behavioral outcomes. We employed three methodologies for evalua-tion: an assessment-only approach using support vector regression (SVR), a neuroimaging-only approach using random forest (RF), and an image-assisted method integrating the static functional network connectivity (sFNC) matrix from resting-state functional magnetic resonance imaging (rs-fMRI) alongside assessments. The image-assisted approach utilized a partially con-ditional variational autoencoder (PCVAE) to predict brain health constructs in future visits from the behavioral data alone. ResultsOur performance evaluation indicates that the image-assisted method ex-cels in handling conditional information to predict brain health constructs in subsequent visits and their longitudinal changes. These results suggest that during the training stage, the PCVAE model effectively captures relevant in-formation from neuroimaging data, thereby potentially improving accuracy in making future predictions using only assessment data. Comparison with Existing MethodsThe proposed image-assisted method outperforms traditional assessment-only and neuroimaging-only approaches by effectively integrating neuroimag-ing data with assessment factors, ConclusionThis study underscores the potential of neuroimaging-informed predictive modeling to advance our comprehension of the complex relationships between cognitive performance and neural connectivity. HighlightsO_LIMultifaceted perspective for studying longitudinal brain health changes. C_LIO_LIShowcases the versatility of methodologies through assessment-only, neuroimaging-only, and image-assisted predictive approaches. C_LIO_LIProvides predictive insights by revealing the neural patterns corresponding to alterations in behavior. C_LI Graphical Abstract