A new multimodality fusion classification approach to explore the uniqueness of schizophrenia and autism spectrum disorder

Abstract

Schizophrenia (SZ) and autism spectrum disorder (ASD) sharing overlapping symptoms have a long history of diagnostic confusion. It is unclear what their differences at a brain level are. Here, we propose a multimodality fusion classification approach to investigate their divergence in brain function and structure. Using brain functional network connectivity (FNC) calculated from resting-state fMRI data and gray matter volume (GMV) estimated from sMRI data, we classify the two disorders using the main data (335 SZ and 380 ASD patients) via an unbiased 10-fold cross-validation pipeline, and also validate the classification generalization ability on an independent cohort (120 SZ and 349 ASD patients). The classification accuracy reached up to 83.08% for the testing data and 72.10% for the independent data, significantly better than the results from using the single-modality features. The discriminative FNCs that were automatically selected primarily involved the sub-cortical, default mode, and visual domains. Interestingly, all discriminative FNCs relating to the default mode network showed an intermediate strength in healthy controls (HCs) between SZ and ASD patients. Their GMV differences were mainly driven by the frontal gyrus, temporal gyrus, and insula.Regarding these regions, the mean GMV of HC fell intermediate between that of SZ and ASD, and ASD showed the highest GMV. The middle frontal gyrus was associated with both functional and structural differences. In summary, our work reveals the unique neuroimaging characteristics of SZ and ASD that can achieve high and generalizable classification accuracy, supporting their potential as disorder-specific neural substrates of the two entwined disorders.

Video-Audio Neural Network Ensemble For Comprehensive Screening Of Autism Spectrum Disorder in Young Children

“…Given the need for scalable tools that can be applied in less standardized contexts, the complementarity characteristic of multi-modal information could be an asset, especially in the contexts of lower validity 47,53 . In other domains, such as brain imaging, combining different modalities has shown to represent a promising manner to increase classification accuracy [54][55][56] . A recent study that used acoustic analyses combined with a computer vision approach applied in the context of the paradigm of response to name has achieved 92% consistency with clinical ground-truth ratings 57 .…”

Working memory and sensory memory in subclinical high schizotypy: An avenue for understanding schizophrenia?

“…WM impairments are broad and include verbal (reviewed in Seabury & Cannon, 2020), visuospatial and executive functioning aspects of WM (Barch & Ceaser, 2012; Forbes et al, 2009). It is worth noting that poor WM performance in people with schizophrenia is associated with a variety of neural differences including reduced grey matter volume (Du et al, 2022; Kochunov et al, 2022), abnormal (hypo‐ and hyper‐) connectivity patterns (Ding et al, 2019; Du et al, 2022; Fryer et al, 2015; Hashimoto et al, 2010; Schutte et al, 2021; Seabury & Cannon, 2020; Unschuld et al, 2014), hypoactive clusters (Seabury & Cannon, 2020) and abnormal oscillations (Reilly et al, 2018). At a lower level, one account of the WM deficit in schizophrenia suggests that prefrontal cortex (PFC) inhibition is disrupted, leading to impaired WM (Meiron et al, 2022).…”

Working Memory and Sensory Memory in Subclinical High Schizotypy: An Avenue for Understanding Schizophrenia?

“…WM impairments are broad and include verbal (reviewed in (Seabury & Cannon, 2020), visuospatial, and executive functioning aspects of WM (Barch & Ceaser, 2012;Forbes et al, 2009). It is worth noting that poor WM performance in people with schizophrenia is associated with a variety of neural differences including reduced gray matter volume (Du et al, 2022;Kochunov et al, 2022), abnormal (hypo-and hyper-) connectivity patterns (Ding et al, 2019;Du et al, 2022;Fryer et al, 2015;Hashimoto et al, 2010;Schutte et al, 2021;Seabury & Cannon, 2020;Unschuld et al, 2014), hypoactive clusters (Seabury & Cannon, 2020), and abnormal oscillations (Reilly et al, 2018). At a lower level, one account of the WM deficit in schizophrenia suggests that PFCinhibition is disrupted, leading to impaired WM (Meiron et al, 2022).…”