Sparse deep neural networks on imaging genetics for schizophrenia case–control classification. Issue 8 (16th March 2021)

• Record Type: Journal Article
• Authors: Chen, Jiayu; Li, Xiang; Calhoun, Vince D.; Turner, Jessica A.; van Erp, Theo G. M.; Wang, Lei; Andreassen, Ole A.; Agartz, Ingrid; Westlye, Lars T.; Jönsson, Erik; Ford, Judith M.; Mathalon, Daniel H.; Macciardi, Fabio; O'Leary, Daniel S.; Liu, Jingyu; Ji, Shihao
• Is Part Of: Human brain mapping. Volume 42:Issue 8(2021)
• Page Start: 2556
• Page End: 2568
• Publication Date: 2021-03-16
• Subjects: deep neural network -- gray matter volume -- schizophrenia -- single nucleotide polymorphism -- sparse; Brain mapping -- Periodicals; 611.81
• DOI: 10.1002/hbm.25387
• Languages: English
• ISSNs: 1065-9471

Abstract

Abstract: Deep learning methods hold strong promise for identifying biomarkers for clinical application. However, current approaches for psychiatric classification or prediction do not allow direct interpretation of original features. In the present study, we introduce a sparse deep neural network (DNN) approach to identify sparse and interpretable features for schizophrenia (SZ) case–control classification. An L 0 ‐norm regularization is implemented on the input layer of the network for sparse feature selection, which can later be interpreted based on importance weights. We applied the proposed approach on a large multi‐study cohort with gray matter volume (GMV) and single nucleotide polymorphism (SNP) data for SZ classification. A total of 634 individuals served as training samples, and the classification model was evaluated for generalizability on three independent datasets of different scanning protocols ( N = 394, 255, and 160, respectively). We examined the classification power of pure GMV features, as well as combined GMV and SNP features. Empirical experiments demonstrated that sparse DNN slightly outperformed independent component analysis + support vector machine (ICA + SVM) framework, and more effectively fused GMV and SNP features for SZ discrimination, with an average error rate of 28.98% on external data. The importance weights suggested that the DNN model prioritized to select frontal and superior temporal gyrus for SZ classification with high sparsity, with parietal regions further included with lower sparsity, echoing previous literature. The results validate the application of the proposed approach to SZ classification, and promise extended utility on other data modalities and traits which ultimately may result in clinically useful tools. Abstract : A sparse deep neural network (DNN) approach is proposed to identify sparse and interpretable biological features with potential for clinical application. Empirical experiments suggest that sparse DNN slightly outperformed ICA + SVM and more effectively fused neuroimaging and genetic features for schizophrenia case‐control classification. The sparse DNN model yielded reasonable interpretation for identified discriminating brain regions, which strongly echoed previous literature.