Classification of schizophrenia spectrum disorder using machine learning and functional connectivity: reconsidering the clinical application

Abstract Background Early identification of Schizophrenia Spectrum Disorder (SSD) is crucial for effective intervention and prognosis improvement. Previous neuroimaging-based classifications have primarily focused on chronic, medicated SSD cohorts. However, the question remains whether brain metrics identified in these populations can serve as trait biomarkers for early-stage SSD. This study investigates whether brain metrics identified in chronic, medicated SSD can function as trait biomarkers for early-stage SSD.Methods Data were collected from 502 SSD patients and 575 healthy controls (HCs) across four medical institutions. Resting-state functional connectivity (FC) features were used to train a Support Vector Machine (SVM) classifier on individuals with medicated chronic SSD and HCs from three sites. The remaining site, comprising both chronic medicated and first-episode unmedicated SSD patients, was used for independent validation. A univariable analysis examined the association between medication dosage or illness duration and FC.Results The classifier achieved 69% accuracy (P = 2.86e-13), 63% sensitivity, and 75% specificity when tested on an independent dataset. Subgroup analysis showed 71% sensitivity (P = 4.63e-05) for chronic medicated SSD, but poor generalization to first-episode unmedicated SSD (sensitivity = 48%, P = 0.68). Univariable analysis revealed a significant association between FC and medication usage, but not disease duration.Conclusions Classifiers developed on chronic medicated SSD may predominantly capture state features of chronicity and medication, overshadowing potential SSD traits. This partially explains the current classifiers' non-generalizability across SSD patients with different clinical states, underscoring the need for models that can enhance the early detection of schizophrenia neural pathology.