Improving the predictive potential of diffusion MRI in schizophrenia using normative models—Towards subject‐level classification

Abstract

Diffusion MRI studies consistently report group differences in white matter between individuals diagnosed with schizophrenia and healthy controls. Nevertheless, the abnormalities found at the group‐level are often not observed at the individual level. Among the different approaches aiming to study white matter abnormalities at the subject level, normative modeling analysis takes a step towards subject‐level predictions by identifying affected brain locations in individual subjects based on extreme deviations from a normative range. Here, we leveraged a large harmonized diffusion MRI dataset from 512 healthy controls and 601 individuals diagnosed with schizophrenia, to study whether normative modeling can improve subject‐level predictions from a binary classifier. To this aim, individual deviations from a normative model of standard (fractional anisotropy) and advanced (free‐water) dMRI measures, were calculated by means of age and sex‐adjusted z‐scores relative to control data, in 18 white matter regions. Even though larger effect sizes are found when testing for group differences in z‐scores than are found with raw values (p < .001), predictions based on summary z‐score measures achieved low predictive power (AUC < 0.63). Instead, we find that combining information from the different white matter tracts, while using multiple imaging measures simultaneously, improves prediction performance (the best predictor achieved AUC = 0.726). Our findings suggest that extreme deviations from a normative model are not optimal features for prediction. However, including the complete distribution of deviations across multiple imaging measures improves prediction, and could aid in subject‐level classification.

Application of a Machine Learning Algorithm for Structural Brain Images in Chronic Schizophrenia to Earlier Clinical Stages of Psychosis and Autism Spectrum Disorder: A Multiprotocol Imaging Dataset Study

“…As ASD is mostly classified as HC compared to other schizophrenia spectrum groups, the neuroanatomical changes used in the classifier during early clinical stages are specific to schizophrenia and weighed both differences in trait and progressions in brain pathology. Recent studies including whole brain (gray matter, white matter, and ventricular cerebrospinal fluid volumes) 33 or diffusion MRI as features reported a high performance rate 32 , 34 ; with more features, it is possible to achieve a higher accuracy with relatively smaller samples than this study.…”

Genetic polymorphism and neuroanatomical changes in schizophrenia

“…Differences in volume and structure were also found at the white matter, correlated with significant cortical deficits. Imaging research, based on the latest technologies, has revealed numerous white matter abnormalities [ 116 , 117 ]. One of the novel findings of this research was the increase in the volume of extracellular water.…”

Characterization of Extracellular Free Water Pathologies in Schizophrenia Using Multi-Site Diffusion MRI Harmonization

“…Each location collected site-specific schizophrenia participant populations and healthy controls with similar distributions of age and sex. Imaging and clinical data from this harmonized cohort has been previously published [5,[20][21][22]. A detailed description of the data collection and subsequent quality control procedures performed to attain to the final sample for the present study can be found in the Supplement (Section: Data Collection and Quality Control).…”

“…Therefore, we applied a dMRI data harmonization technique developed by our group to remove site-, sequence-, and scanner-specific effects from the dMRI data, while preserving inter-subject biological variability [19]. We have successfully validated and applied our harmonization framework in multiple studies [5,[20][21][22][23][24][25][26], including a recent study using FA, which revealed patterns of age-related white matter pathology in individuals with schizophrenia [5].…”