Multimodal neuroimaging features might enable accurate classification and provide personalized treatment options in psychiatric domain. We conducted a retrospective study to investigate whether structural and functional features for predicting response to overall treatment of schizophrenia at the end of the first or a single hospitalization and in addition cross validate the results. This structural and functional magnetic resonance imaging (MRI) study included 85 and 63 patients with schizophrenia at baseline in dataset 1 and 2, respectively. After treatment, patients were classified as responders and non-responders. Features of gray matter and functional connectivity were extracted. Radiomics analysis was used to explore the predictive performance. Prediction models were based on structural features, functional features, and combined features. We found that the prediction accuracy was 80.38% (sensitivity: 87.28%; specificity 82.47%) for the model using functional features, and 69.68% (sensitivity: 83.96%; specificity: 72.41%) for the model using structural features. Our model combined both structural and functional features accurately predicted 92.04% responder and 80.23% non-responders to overall treatment, with an accuracy of 85.03%. These results highlight the power of structural and functional MRI-derived radiomics features to predict early response to treatment in schizophrenia. Prediction models of the very early treatment response in schizophrenia could augment effective therapeutic strategies.
Baseline structural and functional magnetic resonance imaging predicts early treatment response in schizophrenia with radiomics strategy
