Brain imaging and behavior
-
Brain Imaging Behav · Aug 2019
Internet gaming disorder: deficits in functional and structural connectivity in the ventral tegmental area-Accumbens pathway.
Dopamine projections from the ventral tegmental area (VTA) to the nucleus accumbens (NAc) and from the substantia nigra (SN) to the dorsal striatum are involved in addiction. However, relatively little is known about the implication of these circuits in Internet gaming disorder (IGD). This study examined the alteration of resting-state functional connectivity (RSFC) and diffusion tensor imaging (DTI) -based structural connectivity of VTA/SN circuits in 61 young male participants (33 IGD and 28 healthy controls). ⋯ Since these pathways are important for dopamine reward signals and salience attribution, the findings suggest involvement of the brain DA reward system in the neurobiology of IGD. The association of functional but not structural connectivity of VTA circuits with IAT suggests that while lower structural connectivity might underlie vulnerability for IGD, lower functional connectivity may modulate severity. These results strengthen the evidence that IGD shares similar neuropathology with other addictions.
-
Brain Imaging Behav · Aug 2019
Evaluation of machine learning algorithms performance for the prediction of early multiple sclerosis from resting-state FMRI connectivity data.
Machine Learning application on clinical data in order to support diagnosis and prognostic evaluation arouses growing interest in scientific community. However, choice of right algorithm to use was fundamental to perform reliable and robust classification. Our study aimed to explore if different kinds of Machine Learning technique could be effective to support early diagnosis of Multiple Sclerosis and which of them presented best performance in distinguishing Multiple Sclerosis patients from control subjects. ⋯ We showed that best discriminant network between controls and early Multiple Sclerosis, was the sensori-motor I, according to early manifestation of motor/sensorial deficits in Multiple Sclerosis. Moreover, in classification performance, Random Forest and Support Vector Machine showed same 5-fold cross-validation accuracies (85.7%) using only this network, resulting to be best approaches. We believe that these findings could represent encouraging step toward the translation to clinical diagnosis and prognosis.