Abstract
Interest in the application of machine learning (ML) techniques to multimodal magnetic resonance imaging (MRI) data for the diagnosis of schizophrenia (SZ) at the individual level is growing. However, a few studies have applied the features of structural and functional brain networks derived from multimodal MRI data to the discriminative analysis of SZ patients at different clinical stages. In this study, 205 normal controls (NCs), 61 first-episode drug-naive SZ (FESZ) patients, and 79 chronic SZ (CSZ) patients were recruited. We acquired their structural MRI, diffusion tensor imaging, and resting-state functional MRI data and constructed brain networks for each participant, including the gray matter network (GMN), white matter network (WMN), and functional brain network (FBN). We then calculated 3 nodal properties for each brain network, including degree centrality, nodal efficiency, and betweenness centrality. Two classifications (SZ vs. NC and FESZ vs. CSZ) were performed using five ML algorithms. We found that the SVM classifier with the input features of the combination of nodal properties of both the GMN and FBN achieved the best performance to discriminate SZ patients from NCs [accuracy, 81.2%; area under the receiver operating characteristic curve (AUC), 85.2%; p < 0.05]. Moreover, the SVM classifier with the input features of the combination of the nodal properties of both the GMN and WMN achieved the best performance to discriminate FESZ from CSZ patients (accuracy, 86.2%; AUC, 92.3%; p < 0.05). Furthermore, the brain areas in the subcortical/cerebellum network and the frontoparietal network showed significant importance in both classifications. Together, our findings provide new insights to understand the neuropathology of SZ and further highlight the potential advantages of multimodal network properties for identifying SZ patients at different clinical stages.
Highlights
Schizophrenia (SZ) is a chronic psychiatric disease with hallucinations, delusions, and cognitive dysfunction (Lu et al, 2016)
The results indicated that the support vector machine (SVM) achieved the best performance compared to the other four machine learning (ML) algorithms based on recursive feature elimination (RFE) in both classifications (Supplementary Tables 1, 2)
Results of Classification Between Schizophrenia Patients and Normal Controls When discriminating SZ patients from normal controls (NCs), the classifier of SVM with the input features of the properties of gray matter networks (GMNs) and functional brain networks (FBNs) achieved the highest performance with an accuracy of 81.2% and area under the ROC curve (AUC) of 85.2% (p < 0.05), as shown in Figure 3 and Supplementary Table 1
Summary
Schizophrenia (SZ) is a chronic psychiatric disease with hallucinations, delusions, and cognitive dysfunction (Lu et al, 2016). With the development of magnetic resonance imaging (MRI), the vast majority of studies have shown structural and functional brain abnormalities in SZ patients (Yamasue et al, 2004; Antonova et al, 2005; Kuroki, 2006; Pagsberg et al, 2007; Zhou et al, 2007). Previous studies have indicated that structural brain abnormalities are more widespread in chronic SZ (CSZ) patients than in first-episode drug-naive SZ (FESZ) patients, suggesting the potential impact of antipsychotic medication on structural brain abnormalities (Moncrieff and Leo, 2010; Torres et al, 2016). Numerous functional MRI studies indicated that CSZ patients showed significant reductions in functional characteristics in brain regions involved in auditory, visual processing, and sensorimotor functions compared with FESZ patients (Wu et al, 2018). It is critical to develop neuroimaging-based biomarkers for distinguishing the illness stages of SZ patients
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
