PurposeThis study aimed to develop machine learning models for the diagnosis of Parkinson’s disease (PD) using multiple structural magnetic resonance imaging (MRI) features and validate their performance.MethodsBrain structural MRI scans of 60 patients with PD and 56 normal controls (NCs) were enrolled as development dataset and 69 patients with PD and 71 NCs from Parkinson’s Progression Markers Initiative (PPMI) dataset as independent test dataset. First, multiple structural MRI features were extracted from cerebellar, subcortical, and cortical regions of the brain. Then, the Pearson’s correlation test and least absolute shrinkage and selection operator (LASSO) regression were used to select the most discriminating features. Finally, using logistic regression (LR) classifier with the 5-fold cross-validation scheme in the development dataset, the cerebellar, subcortical, cortical, and a combined model based on all features were constructed separately. The diagnostic performance and clinical net benefit of each model were evaluated with the receiver operating characteristic (ROC) analysis and the decision curve analysis (DCA) in both datasets.ResultsAfter feature selection, 5 cerebellar (absolute value of left lobule crus II cortical thickness (CT) and right lobule IV volume, relative value of right lobule VIIIA CT and lobule VI/VIIIA gray matter volume), 3 subcortical (asymmetry index of caudate volume, relative value of left caudate volume, and absolute value of right lateral ventricle), and 4 cortical features (local gyrification index of right anterior circular insular sulcus and anterior agranular insula complex, local fractal dimension of right middle insular area, and CT of left supplementary and cingulate eye field) were selected as the most distinguishing features. The area under the curve (AUC) values of the cerebellar, subcortical, cortical, and combined models were 0.679, 0.555, 0.767, and 0.781, respectively, for the development dataset and 0.646, 0.632, 0.690, and 0.756, respectively, for the independent test dataset, respectively. The combined model showed higher performance than the other models (Delong’s test, all p-values < 0.05). All models showed good calibration, and the DCA demonstrated that the combined model has a higher net benefit than other models.ConclusionThe combined model showed favorable diagnostic performance and clinical net benefit and had the potential to be used as a non-invasive method for the diagnosis of PD.
BACKGROUND AND PURPOSEObstructive sleep apnoea is associated with excessive daytime sleepiness due to sleep fragmentation and hypoxemia, both of which can lead to abnormal brain morphology. However, the pattern of brain structural changes associated with excessive daytime sleepiness is still unclear. This study aims to investigate the effects of excessive daytime sleepiness on cortical thickness in patients with obstructive sleep apnoea.MATERIALS AND METHODS:61 male patients with newly diagnosed obstructive sleep apnoea were included in the present study. Polysomnography and structural MRI were performed for each participant. Subjective daytime sleepiness was assessed using the Epworth Sleepiness Scale score. Surface-based morphometric analysis was performed using Statistical Parametric Mapping 12 and Computational Anatomy 12 toolboxes to extract cortical thickness. RESULTS:Using the median Epworth Sleepiness Scale score, patients were divided into the non-sleepiness group and the sleepiness group. The cortical thickness was markedly thinner in the sleepiness group in the left temporal, frontal, and parietal lobe and bilateral pre- and postcentral gyri (pFWE<0.05). There was a significant negative correlation between the cortical thickness and the Epworth Sleepiness Scale score. After adjusting for age, body mass index, and obstructive sleep apnoea severity, the Epworth Sleepiness Scale score remained an independent factor affecting the cortical thickness of the left middle temporal lobe, transverse temporal and temporal pole.CONCLUSION:Subjective daytime sleepiness is associated with decreased cortical thickness, and the Epworth Sleepiness Scale score may be of utility as a clinical marker of brain injury in patients with obstructive sleep apnoea.
Background and purposeObstructive sleep apnoea is associated with excessive daytime sleepiness due to sleep fragmentation and hypoxemia, both of which can lead to abnormal brain morphology. However, the pattern of brain structural changes associated with excessive daytime sleepiness is still unclear. This study aims to investigate the effects of excessive daytime sleepiness on cortical thickness in patients with obstructive sleep apnoea.Materials and methods61 male patients with newly diagnosed obstructive sleep apnoea were included in the present study. Polysomnography and structural MRI were performed for each participant. Subjective daytime sleepiness was assessed using the Epworth Sleepiness Scale score. Surface-based morphometric analysis was performed using Statistical Parametric Mapping 12 and Computational Anatomy 12 toolboxes to extract cortical thickness.ResultsUsing the median Epworth Sleepiness Scale score, patients were divided into the non-sleepiness group and the sleepiness group. The cortical thickness was markedly thinner in the sleepiness group in the left temporal, frontal, and parietal lobe and bilateral pre- and postcentral gyri (pFWE < 0.05). There was a significant negative correlation between the cortical thickness and the Epworth Sleepiness Scale score. After adjusting for age, body mass index, and obstructive sleep apnoea severity, the Epworth Sleepiness Scale score remained an independent factor affecting the cortical thickness of the left middle temporal lobe, transverse temporal and temporal pole.ConclusionSubjective daytime sleepiness is associated with decreased cortical thickness, and the Epworth Sleepiness Scale score may be of utility as a clinical marker of brain injury in patients with obstructive sleep apnoea.
BackgroundObstructive Sleep Apnea (OSA) characteristically leads to nocturnal hypoxia and sleep disturbance. Despite clear evidence of OSA-induced cognitive impairments, the literature offers no consensus on the relationship between these pathophysiological processes and brain structure alterations in patients.ObjectiveThis study leverages the robust technique of structural equation modeling to investigate how hypoxia and sleep disturbance exert differential effects on gray matter structures.MethodsSeventy-four Male participants were recruited to undergo overnight polysomnography and T1-weighted Magnetic Resonance Imaging. Four structural outcome parameters were extracted, namely, gray matter volume, cortical thickness, sulcal depth, and fractal dimension. Structural equation models were constructed with two latent variables (hypoxia, and sleep disturbance) and three covariates (age, body mass index, and education) to examine the association between gray matter structural changes in OSA and the two latent variables, hypoxia and sleep disturbance.ResultsThe structural equation models revealed hypoxia-associated changes in diverse regions, most significantly in increased gray matter volume, cortical thickness and sulcal depth. In contrast, sleep disturbance. Was shown to be largely associated with reduce gray matter volume and sulcal depth.ConclusionThis study provides new evidence showing significant effects of OSA-induced hypoxia and sleep disturbance on gray matter volume and morphology in male patients with obstructive sleep apnea. It also demonstrates the utility of robust structural equation models in examining obstructive sleep apnea pathophysiology.
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.