Predicting treatment outcomes in patients with panic disorder: Cross-sectional and two-year longitudinal structural connectome analysis using machine learning methods.

This study examined the relationship between structural brain networks and long-term treatment outcomes in patients with panic disorder (PD) using machine learning methods. The study involved 80 participants (53 PD patients and 27 healthy controls) and included clinical assessments and MRI scans at baseline and after two years (160 MRIs). Patients were categorized based on their response to two-year pharmacotherapy. Brain networks were analyzed using white matter tractography and network-based statistics. Results showed structural network changes in PD patients, particularly in the extended fear network, including frontal regions, thalamus, and cingulate gyrus. Longitudinal analysis revealed that increased connections to the amygdala, hippocampus, and insula were associated with better treatment response. Conversely, overconnectivity in the amygdala and insula at baseline was associated with poor response, and similar patterns were found in the insula and parieto-occipital cortex related to non-remission. This study found that SVM and CPM could effectively predict treatment outcomes based on network pattern changes in PD. These findings suggest that monitoring structural connectome changes in limbic and paralimbic regions is critical for understanding PD and tailoring treatment. The study highlights the potential of using personalized biomarkers to develop individualized treatment strategies for PD.

Pae C ，Kim HJ ，Bang M ，Il Park C ，Lee SH ... -  《-》

Initial white matter connectivity differences between remitters and non-remitters of patients with panic disorder after 6 months of pharmacotherapy.

Panic disorder (PD) is a harmful mental condition that causes relapsed and persistent impairment. In the treatment of PD, the prognosis for PD should be considered. However, the relationship between pharmacotherapy and biomarkers, for predicting a better response through neuroimaging, is a little known. The purpose of the present study was to examine whether there would be the initial white matter (WM) regions associated with the remission in 6 months. A total of 104 patients with PD were investigated in the study. After six months, there were 17 remission patients with PD and 81 non-remission patients. The Panic Disorder Severity Scale, Albany Panic and Phobia Questionnaire, Anxiety Sensitivity Inventory-Revised, Beck Anxiety Inventory, and Beck Depression Inventory were assessed for all patients at baseline. We compared the diffusion indices between remission and non-remission group at 6 months using Tract-Based Spatial Statistics. The results showed that the fractional anisotropy (FA) values were significantly higher in the non-remitter group compared with those in the remitter group in the WM regions, such as the posterior corona radiata and superior longitudinal fasciculus, at the 6 month evaluation. The logistic regression analysis with clinical symptom severity and FA values of the WM regions as covariates showed that FA values in those regions and the Beck Depression Inventory-II predicted poor remission. This study suggests that posterior corona radiata and superior longitudinal fasciculus are related to potential predictive factors of 6-month remission in patients with PD. WM regions associated with the long-term remission should be verified with further investigations.

Song CR ，Kang NO ，Bang M ，Park CI ，Choi TK ，Lee SH ... -  《-》

Evaluation of machine learning algorithms for treatment outcome prediction in patients with epilepsy based on structural connectome data.

The objective of this study is to evaluate machine learning algorithms aimed at predicting surgical treatment outcomes in groups of patients with temporal lobe epilepsy (TLE) using only the structural brain connectome. Specifically, the brain connectome is reconstructed using white matter fiber tracts from presurgical diffusion tensor imaging. To achieve our objective, a two-stage connectome-based prediction framework is developed that gradually selects a small number of abnormal network connections that contribute to the surgical treatment outcome, and in each stage a linear kernel operation is used to further improve the accuracy of the learned classifier. Using a 10-fold cross validation strategy, the first stage in the connectome-based framework is able to separate patients with TLE from normal controls with 80% accuracy, and second stage in the connectome-based framework is able to correctly predict the surgical treatment outcome of patients with TLE with 70% accuracy. Compared to existing state-of-the-art methods that use VBM data, the proposed two-stage connectome-based prediction framework is a suitable alternative with comparable prediction performance. Our results additionally show that machine learning algorithms that exclusively use structural connectome data can predict treatment outcomes in epilepsy with similar accuracy compared with "expert-based" clinical decision. In summary, using the unprecedented information provided in the brain connectome, machine learning algorithms may uncover pathological changes in brain network organization and improve outcome forecasting in the context of epilepsy.

Munsell BC ，Wee CY ，Keller SS ，Weber B ，Elger C ，da Silva LA ，Nesland T ，Styner M ，Shen D ，Bonilha L ... -  《-》

White matter correlates of anxiety sensitivity in panic disorder.

Anxiety sensitivity (AS) refers to a fear of anxiety-related sensations and is a dispositional variable especially elevated in patients with panic disorder (PD). Although several functional imaging studies of AS in patients with PD have suggested the presence of altered neural activity in paralimbic areas such as the insula, no study has investigated white matter (WM) alterations in patients with PD in relation to AS. The objective of this study was to investigate the WM correlates of AS in patients with PD. One-hundred and twelve right-handed patients with PD and 48 healthy control (HC) subjects were enrolled in this study. The Anxiety Sensitivity Inventory-Revised (ASI-R), the Panic Disorder Severity Scale (PDSS), the Albany Panic and Phobia Questionnaire (APPQ), the Beck Anxiety Inventory (BAI), and the Beck Depression Inventory (BDI) were administered. Tract-based spatial statistics were used for diffusion tensor magnetic resonance imaging analysis. Among the patients with PD, the ASI-R total scores were significantly correlated with the fractional anisotropy values of the WM regions near the insula, the splenium of the corpus callosum, the tapetum, the fornix/stria terminalis, the posterior limb of the internal capsule, the retrolenticular part of the internal capsule, the posterior thalamic radiation, the sagittal striatum, and the posterior corona radiata located in temporo-parieto-limbic regions and are involved in interoceptive processing (p<0.01; threshold-free cluster enhancement [TFCE]-corrected). These WM regions were also significantly correlated with the APPQ interoceptive avoidance subscale and BDI scores in patients with PD (p<0.01, TFCE-corrected). Correlation analysis among the HC subjects revealed no significant findings. There has been no comparative study on the structural neural correlates of AS in PD. The current study suggests that the WM correlates of AS in patients with PD may be associated with the insula and the adjacent temporo-parieto-limbic WM regions, which may play important roles in interoceptive processing in the brain and in depression in PD.

Kim MK ，Kim B ，Kiu Choi T ，Lee SH ... -  《-》

Connectome analysis with diffusion MRI in idiopathic Parkinson's disease: Evaluation using multi-shell, multi-tissue, constrained spherical deconvolution.

Kamagata K ，Zalesky A ，Hatano T ，Di Biase MA ，El Samad O ，Saiki S ，Shimoji K ，Kumamaru KK ，Kamiya K ，Hori M ，Hattori N ，Aoki S ，Pantelis C ... -  《NeuroImage-Clinical》