BackgroundEffective and accurate diagnosis of attention-deficit/hyperactivity disorder (ADHD) is currently of significant interest. ADHD has been associated with multiple cortical features from structural MRI data. However, most existing learning algorithms for ADHD identification contain obvious defects, such as time-consuming training, parameters selection, etc. The aims of this study were as follows: (1) Propose an ADHD classification model using the extreme learning machine (ELM) algorithm for automatic, efficient and objective clinical ADHD diagnosis. (2) Assess the computational efficiency and the effect of sample size on both ELM and support vector machine (SVM) methods and analyze which brain segments are involved in ADHD.MethodsHigh-resolution three-dimensional MR images were acquired from 55 ADHD subjects and 55 healthy controls. Multiple brain measures (cortical thickness, etc.) were calculated using a fully automated procedure in the FreeSurfer software package. In total, 340 cortical features were automatically extracted from 68 brain segments with 5 basic cortical features. F-score and SFS methods were adopted to select the optimal features for ADHD classification. Both ELM and SVM were evaluated for classification accuracy using leave-one-out cross-validation.ResultsWe achieved ADHD prediction accuracies of 90.18% for ELM using eleven combined features, 84.73% for SVM-Linear and 86.55% for SVM-RBF. Our results show that ELM has better computational efficiency and is more robust as sample size changes than is SVM for ADHD classification. The most pronounced differences between ADHD and healthy subjects were observed in the frontal lobe, temporal lobe, occipital lobe and insular.ConclusionOur ELM-based algorithm for ADHD diagnosis performs considerably better than the traditional SVM algorithm. This result suggests that ELM may be used for the clinical diagnosis of ADHD and the investigation of different brain diseases.
BACKGROUND After the initial surge in COVID-19 cases, large numbers of patients were discharged from a hospital without assessment of recovery. Now, an increasing number of patients report postacute neurological sequelae, known as “long COVID” — even those without specific neurological manifestations in the acute phase. METHODS Dynamic brain changes are crucial for a better understanding and early prevention of “long COVID.” Here, we explored the cross-sectional and longitudinal consequences of COVID-19 on the brain in 34 discharged patients without neurological manifestations. Gray matter morphology, cerebral blood flow (CBF), and volumes of white matter tracts were investigated using advanced magnetic resonance imaging techniques to explore dynamic brain changes from 3 to 10 months after discharge. RESULTS Overall, the differences of cortical thickness were dynamic and finally returned to the baseline. For cortical CBF, hypoperfusion in severe cases observed at 3 months tended to recover at 10 months. Subcortical nuclei and white matter differences between groups and within subjects showed various trends, including recoverable and long-term unrecovered differences. After a 10-month recovery period, a reduced volume of nuclei in severe cases was still more extensive and profound than that in mild cases. CONCLUSION Our study provides objective neuroimaging evidence for the coexistence of recoverable and long-term unrecovered changes in 10-month effects of COVID-19 on the brain. The remaining potential abnormalities still deserve public attention, which is critically important for a better understanding of “long COVID” and early clinical guidance toward complete recovery. FUNDING National Natural Science Foundation of China.
Objective:To elucidate the timeframe and spatial patterns of cortical reorganization after different stroke-induced basal ganglia lesions, we measured cortical thickness at five timepoints over a six-month period. We hypothesized that cortical reorganization would occur very early and that, along with motor recovery, it would vary based on the stroke lesion site.Methods:Thirty-three patients with unilateral basal ganglia stroke and 23 healthy control participants underwent MRI scanning and behavioral testing. To further decrease heterogeneity, we split patients into two groups according to whether or not the lesions mainly affect the striatal motor network as defined by resting-state functional connectivity. A priori measures included cortical thickness and motor outcome, as assessed with the Fugl-Meyer scale.Results:Within 14 days post-stroke, cortical thickness already increased in widespread brain areas (p=0.001), mostly in the frontal and temporal cortices rather than in the motor cortex. Critically, the two groups differed in the severity of motor symptoms (p=0.03) as well as in the cerebral reorganization they exhibited over a period of six months (Dice overlap index=0.16). Specifically, the frontal and temporal regions demonstrating cortical thickening showed minimal overlap between these two groups, indicating different patterns of reorganization.Conclusions:Our findings underline the importance of assessing patients early on and of considering individual differences, as patterns of cortical reorganization differ substantially depending on the precise location of damage and occur very soon after stroke. A better understanding of the macrostructural brain changes following stroke and their relationship with recovery may inform individualized treatment strategies.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.