Predicting Psychosis Progression in Clinical High-Risk Individuals Using Peripheral Transcriptomic and Epigenomic Profiles: A Machine Learning Approach

Advancing the prediction of psychosis in individuals identified as clinically high risk for psychosis (CHRP), a state indicating an elevated risk of developing psychosis, requires the identification of reliable biomarkers. Here, we employ a comprehensive approach using transcriptomic and epigenomic profiling from peripheral blood samples to predict the conversion from high-risk to psychosis in a longitudinal cohort of 56 individuals. We employed ensemble tree-based machine learning techniques, specifically XGBoost and LightGBM models, to analyze and select biomarkers capable of forecasting the conversion to psychosis at one-year and two-year follow-up intervals. The predictive accuracy of these models was robust, with the one-year model achieving an area under the curve (AUC) of 0.990 and the two-year model an AUC of 0.934. Our analysis identified eight gene expression markers (such AC026691.1, CA8, STXBP6 and TMEM89) and seven DNA methylation markers (such as cg14258341 and cg10663442) that were associated with a one-year conversion to psychosis. Additionally, two gene expression markers were found to predict a two-year conversion. Notably, long non-coding RNAs were validated as contributors to the predictive models. Our study also contributes to the advancement of CHR-P prediction by further distinguishing between patients who maintain symptoms and those who recover. These results affirm the potential of non-invasive blood biomarkers to stratify CHR-P individuals by their risk of conversion, address the broader spectrum of clinical outcomes, thus facilitating early and targeted intervention strategies in psychosis.