The diagnosis based on clinical assessment of pediatric bipolar disorder (PBD) may sometimes lead to misdiagnosis in clinical practice. For the past several years, machine learning (ML) methods were introduced for the classification of bipolar disorder (BD), which were helpful in the diagnosis of BD. In this study, brain cortical thickness and subcortical volume of 33 PBD-I patients and 19 age-sex matched healthy controls (HCs) were extracted from the magnetic resonance imaging (MRI) data and set as features for classification. The dimensionality reduced feature subset, which was filtered by Lasso or f_classif, was sent to the six classifiers (logistic regression (LR), support vector machine (SVM), random forest classifier, naïve Bayes, k-nearest neighbor, and AdaBoost algorithm), and the classifiers were trained and tested. Among all the classifiers, the top two classifiers with the highest accuracy were LR (84.19%) and SVM (82.80%). Feature selection was performed in the six algorithms to obtain the most important variables including the right middle temporal gyrus and bilateral pallidum, which is consistent with structural and functional anomalous changes in these brain regions in PBD patients. These findings take the computer-aided diagnosis of BD a step forward.

No abstract

No abstract

Sex differences in episodic memory (EM), remembering past events based on when and where they occurred, have been reported, but the neural mechanisms are unclear. T1-weighted images of 111 females and 61 males were acquired from the Dallas Lifespan Brain Study. Using surface-based morphometry and structural covariance (SC) analysis, we constructed structural covariance networks (SCN) based on cortical volume, and the global efficiency (Eglob) was computed to characterize network integration. The relationship between SCN and EM was examined by SC analysis among the top-n brain regions that were most relevant to EM performance. The number of SC connections (females: 3306; males: 437, P = 0.0212) and Eglob (females: 0.1845; males: 0.0417, P = 0.0408) of SCN in females were higher than those in males. The top-n brain regions with the strongest SC in females were located in auditory network, cingulo-opercular network (CON), and default mode network (DMN), and in males, they were located in frontoparietal network, CON, and DMN. These results confirmed that the Eglob of SCN in females was higher than males, sex differences in EM performance might be related to the differences in network-level integration. Our study highlights the importance of sex as a research variable in brain science.