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.
BackgroundBy calculating cortical thickness (CT) and cortical structural covariance (SC), we aimed to investigate cortical morphology and cortical inter-regional correlation alterations in adolescent bipolar disorder type I (BD-I) and type II (BD-II) patients.MethodsT1-weighted images from 36 BD-I and 22 BD-II patients and 19 healthy controls (HCs) were processed to estimate CT. CT values of the whole brain were compared among three groups. Cortical regions showing CT differences in groups were regarded as seeds for analyzing cortical SC differences between groups. The relationship between CT and clinical indices was further assessed.ResultsBoth BD groups showed cortical thinning in several frontal and temporal areas vs. HCs, and CT showed no significant difference between two BD subtypes. Compared to HCs, both BD groups exhibited reduced SC connections between left superior frontal gyrus (SFG) and right postcentral gyrus (PCG), left superior temporal gyrus (STG) and right pars opercularis, and left STG and right PCG. Compared with HCs, decreased SC connections between left STG and right inferior parietal gyrus (IPG) and right pars opercularis and right STG were only observed in the BD-I group, and left PCG and left SFG only in the BD-II group. CT of right middle temporal gyrus was negatively correlated with number of episodes in BD-II patients.ConclusionsAdolescent BD-I and BD-II showed commonly decreased CT while presenting commonly and distinctly declined SC connections. This study provides a better understanding of cortical morphology and cortical inter-regional correlation alterations in BD and crucial insights into neuroanatomical mechanisms and pathophysiology of different BD subtypes.
Introduction: It remains unknown whether volumetric alterations of ventricles are similar or not in pediatric bipolar disorder (PBD) among different mood states. The present study aims to estimate ventricular volumetric alteration of PBD patients in manic and euthymic status, as well as the relationship between this alteration and cognitive changes.Methods: T1 magnetic resonance images were obtained from 20 manic PBD patients, 21 euthymic PBD patients, and 19 healthy controls (HCs). Ventricular volumes were automatically obtained via FreeSurfer 6.0 software. Ventricular volumes and cognitive indices were compared among the three groups, and the relationship between ventricular volumes and cognitive/clinical indices was analyzed.Results: In contrast to HCs, manic and euthymic PBD patients exhibited decreased cognitive scores of the Stroop color-word test and the digit span subtest. Manic PBD subjects presented enlarged volumes in the bilateral ventricles, third ventricle, and whole ventricles, and euthymic PBD participants displayed increased volumes in the third ventricle, fourth ventricle, and whole ventricles. No significant differences in cognitive performance and ventricular volumes were found between PBD groups. No significant correlation was discovered between ventricular volumes and cognitive/clinical indices in both manic and euthymic PBD patients.Conclusions: No significant differences in cognitive performance and ventricle volume were observed between euthymic and manic PBD groups, which may imply that the alterations are not specific to mood state. It may indicate structural and functional damage of corresponding brain circuits in euthymic PBD patients similar with that of manic PBD, which may provide clues to the diagnosis and treatment of euthymic PBD.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.