Consistent frontal-limbic-occipital connections in distinguishing treatment-resistant and non-treatment-resistant schizophrenia

作者：Yijie Zhang, Shuzhan Gao, Chuang Liang, Juan Bustillo, Peter Kochunov, Jessica A. Turner, Vince D. Calhoun, Lei Wu, Zening Fu, Rongtao Jiang, Daoqiang Zhang, Jing Jiang, Fan Wu, Ting Peng, Xijia Xu, Shile Qi · 发表于：NeuroImage Clinical · 年份：2024 · DOI：10.1016/j.nicl.2024.103726 · 被引用次数：4 · 研究领域：Functional Brain Connectivity Studies、Schizophrenia research and treatment、Neural dynamics and brain function

• The whole brain FCs, except the temporal-occipital FC, were consistent in distinguishing SZ and HC across 3 atlases, 2 feature selections and 4 classifiers. • Abnormal frontal-limbic, frontal-parietal and occipital-temporal FCs were consistent in distinguishing TR-SZ and NTR-SZ, that correlated with disease progression, symptoms and medication dosage. • The frontal-limbic and frontal-parietal FCs were consistent for the diagnosis of SZ (TR-SZ vs. HC, NTR-SZ vs. HC and TR-SZ vs. NTR-SZ). • BNA atlas achieved the highest classification accuracy (>90 %) comparing with AAL and YEO. Treatment-resistant schizophrenia (TR-SZ) and non-treatment-resistant schizophrenia (NTR-SZ) lack specific biomarkers to distinguish from each other. This investigation aims to identify consistent dysfunctional brain connections with different atlases, multiple feature selection strategies, and several classifiers in distinguishing TR-SZ and NTR-SZ. 55 TR-SZs, 239 NTR-SZs, and 87 healthy controls (HCs) were recruited from the Affiliated Brain Hospital of Nanjing Medical University. Resting-state functional connection (FC) matrices were constructed from automated anatomical labeling (AAL), Yeo-Networks (YEO) and Brainnetome (BNA) atlases. Two feature selection methods (Select From Model and Recursive Feature Elimination) and four classifiers (Adaptive Boost, Bernoulli Naïve Bayes, Gradient Boosting and Random Forest) were combined to identify the consistent FCs in distinguishing TR-SZ and HC, NTR-SZ a...