Machine Learning of Schizophrenia Detection with Structural and Functional Neuroimaging

Abstract

Schizophrenia (SZ) is a severe psychiatric illness, and it affects around 1% of the general population; however, its reliable diagnosis is challenging. Functional MRI (fMRI) and structural MRI (sMRI) are useful techniques for investigating the functional and structural abnormalities of the human brain, and a growing number of studies have reported that multimodal brain data can improve diagnostic accuracy. Machine learning (ML) is widely used in the diagnosis of neuroscience and neuropsychiatry diseases, and it can obtain high accuracy. However, the conventional ML which concatenated the features into a longer feature vector could not be sufficiently effective to combine different features from different modalities. There are considerable controversies over the use of global signal regression (GSR), and few studies have explored the role of GSR in ML in diagnosing neurological diseases. The current study utilized fMRI and sMRI data to implement a new method named multimodal imaging and multilevel characterization with multiclassifier (M3) to classify SZs and healthy controls (HCs) and investigate the influence of GSR in SZ classification. We found that when we used Brainnetome 246 atlas and without performed GSR, our method obtained a classification accuracy of 83.49%, with a sensitivity of 68.69%, a specificity of 93.75%, and an AUC of 0.8491, respectively. We also got great classification performances with different processing methods (with/without GSR and different brain parcellation schemes). We found that the accuracy and specificity of the models without GSR were higher than that of the models with GSR. Our findings indicate that the M3 method is an effective tool to distinguish SZs from HCs, and it can identify discriminative regions to detect SZ to explore the neural mechanisms underlying SZ. The global signal may contain important neuronal information; it can improve the accuracy and specificity of SZ detection.

Discriminative Analysis of Schizophrenia Patients Using Topological Properties of Structural and Functional Brain Networks: A Multimodal Magnetic Resonance Imaging Study

“…A recent study revealed that the use of combined structural and functional measures allows the highest accuracy of classification to detect SZ ( Lei D. et al, 2020 ). However, the input features of previous SZ classification studies were derived from structural and functional neuroimaging features ( de Filippis et al, 2019 ; Shi et al, 2021 ). Our results based on brain network properties further highlight the potential advantages of multimodal features for distinguishing SZ patients from NCs.…”

Evidence for Embracing Normative Modeling

“…In the raw data models, which were residualized of covariates including site, sex, and linear plus quadratic effects of age and head motion (only included for functional models), we observe no group differences after multiple comparison correction. The lack of any group differences in the raw data was initially a puzzling finding due to reported group differences in the literature Arbabshirani et al (2013 ); Cetin et al (2015 , 2016); Dansereau et al (2017 ); Howes et al (2022 ); Lei et al (2020b ,a); Meng et al (2017 ); Rahim et al (2017 ); Rosa et al (2015 ); Salvador et al (2017 ); Shi et al (2021 ); van Erp et al (2018 ); Venkataraman et al (2012 ); Wannan et al (2019 ); Yu et al (2012 ), however, upon investigation of the uncorrected statistical maps, we observe that the raw data follows a similar pattern to the deviation group difference map, but these results do not withstand multiple comparison correction.…”

Machine Learning for Detecting Parkinson’s Disease by Resting-State Functional Magnetic Resonance Imaging: A Multicenter Radiomics Analysis

“…Both the two datasets had good classification performance, which further indicated the good classification performance and generalization of our model. Third, it has been reported that combining multimodal data and clinical data can improve the performance of the machine learning model (Shi et al, 2021a;Talai et al, 2021), but the primary set in this study only contained ALFF data. A subsequent study should incorporate other modal MRI data, metrics, and clinical data to construct and evaluate the model.…”

“…Resting-state functional magnetic resonance imaging (rs-fMRI), as one of the most commonly used non-invasive techniques in neuroimaging, has been widely used in the diagnosis ( Heim et al, 2017 ; Rubbert et al, 2019 ; Pang et al, 2021 ; Shi et al, 2021a ), monitoring of treatment effects ( Morgan et al, 2017 ; Ge et al, 2020 ), clinical score prediction ( Hou et al, 2016 ), and conversion prediction ( Hojjati et al, 2018 ) in neuropsychiatric diseases. The amplitude of low-frequency fluctuations (ALFF) is one of the most commonly used measurements of rs-fMRI.…”