Multimodal prediction of psychotic-like experiences using Elastic Net modeling: external validation in a clinical sample

Abstract

Psychotic-like experiences (PLEs) represent subtle expressions of vulnerability within the psychosis continuum. Although many studies suggest that these experiences arise from multimodal factors, research comprehensively examining these factors together remains scarce. This thesis examines how different aspects of a environmental exposures, cognitive schemas, and brain structure jointly associate with PLEs in young population. It also explores model’s ability to explain psychosis in a clinical group. After applying variable selection including generalized estimating equations, correlation filtering, Least Absolute Shrinkage and Selection Operator model to 741 variables (i.e., environmental factors, cognitive appraisals, clinical variables, cognitive functioning, and structural brain connectome measures), obtained PLEs predictors (N=27) and covariates (i.e., age, sex, IQ) were included in the classification model based on Elastic Net algorithm for predicting high/low PLEs in 396 healthy participants aged 14-24 (Mage=19.72±2.5). We externally validated PLE-related predictors in a clinical sample comprising first-episode psychosis patients (n=19), their siblings (n=20), and healthy controls (n=19). Important predictors of PLEs included environmental and cognitive appraisals, along with sixteen structural network properties spanning frontal, temporal, occipital, and parietal regions. The model showed moderate accuracy in predicting low versus high PLEs (accuracy = 75%, AUC = 0.750) and demonstrated high specificity (84.2%) in distinguishing siblings from patients. These findings suggest that environmental burden, cognitive schemas, and brain network alterations predict PLEs and partially generalize to clinical psychosis. These variables may reflect intermediate phenotypes across the psychosis spectrum, offering insights into both vulnerability and resilience. This work forms a central empirical chapter of the present dissertation.