Transcriptomic and Neuroimaging Data Integration Enhances Machine Learning Classification of Schizophrenia

Abstract

Schizophrenia is a polygenetic disorder associated with changes in brain structure and function. Integrating macroscale brain features and microscale genetic data may provide a more complete overview of the disease etiology and may serve as potential diagnostic markers for schizophrenia. We aim to systematically evaluate the impact of multi-scale neuroimaging and transcriptomic data fusion in schizophrenia classification models. we collected brain imaging data and blood RNA-seq data from 43 schizophrenia patients and 60 age-, gender-matched healthy controls, and we extracted multi-omics features of macroscale brain morphology, brain structural connectivity and functional connectivity, and gene transcription of schizophrenia risk genes. Multi-scale data fusion was performed using a machine learning integration framework, together with several conventional machine learning methods and neural networks for patient classification. We found that multi-omics data fusion in conventional machine learning models achieved the highest accuracy in contrast to the single-modality models, with AUC improvements of 8.88% to 22.64%. Similar findings were observed for the neural network, showing an increase of 16.57% for the multimodal classification accuracy compared to the single-modal average. In addition, we identified several brain regions in the left posterior cingulate and right frontal pole that contribute to disease classification. We provide empirical evidence for the increased accuracy achieved by imaging genetic data integration in schizophrenia classification. Multi-scale data fusion holds promise for enhancing diagnostic precision, facilitating early detection and personalizing treatment regimens in schizophrenia.