ABSTRACT
Objective:To explore the value of machine learning models based on MRI predict the brain age of smokers and healthy controls, and further to explore the relationship between smoking and brain aging.Methods:This was a retrospective study. Dataset 1 consisted of 95 male smokers [20-50 (34±7) years old] and 49 healthy controls [20-50 (33±7) years old] recruited from August 2014 to October 2017 in First Affiliated Hospital of Zhengzhou University. Dataset 2 contained 114 healthy male volunteers [20-50 (34±11) years old] from the Southwestern University Adult Imaging Database from 2010 to 2015. All subjects underwent high-resolution 3D T 1WI scan. Gaussian process regression (GPR) model and support vector machine model were constructed to predict brain age based on structural MR images of healthy controls in dataset 1 and dataset 2. After the performance of the model was verified by the cross-validation method, the mean absolute error (MAE) between the predicted brain age and the actual age and the correlation ( r-value) between the actual age and the predicted brain age were calculated, and the best model was finally selected. The best models were applied to smokers and healthy controls to predict brain age. Finally, a general linear model was used to compare the differences in brain-predicted age difference (PAD) between smokers and healthy controls with age, taking years of education and total intracranial volume as covariates. Result:The performance of GPR model (MAE=5.334, r=0.747) in predicting brain age was better than support vector machine model (MAE=6.040, r=0.679). The GPR model predicted that PAD value of smokers in dataset 1 (2.19±6.64) was higher than that of healthy controls in dataset 1 (-0.80±8.94), and the difference was statistically significant ( F=8.52, P=0.004). Conclusion:GPR model based MRI has better performance in predicting brain age in smokers and healthy controls, and smokers show increased PAD values, further indicating that smoking accelerates brain aging.
ABSTRACT
Objective:To investigate the abnormalities of gray matter volume (GMV) and the synergistic changes in different cerebral regions in the first-episode and early-onset depression (EOD) patients.Methods:A total of 60 patients with untreated EOD (EOD group) and 64 healthy controls (control group) matched for age, gender, and education underwent high-resolution T 1WI MR scans. Voxel-based morphometry was used to calculate the cerebral GMV. The difference in GMV between the two groups was compared with the t-test. Different brain regions were selected as seeds for structural covariation network (SCN) analysis. Spearman correlation model was used to analyze the correlation between the GMV in different cerebral regions and illness duration as well as the scores of Hamilton rating scale for depression (HAMD) 17 items in EOD group. Results:Compared to control group, the EOD group had significantly increased GMV in the right orbitofrontal cortex, right dorsolateral prefrontal cortex, right inferior parietal lobule, right superior parietal lobule and bilateral precuneus ( P<0.05, corrected by FDR). Based on the right orbitofrontal cortex and dorsolateral prefrontal cortex as seed regions, structural covariance analysis revealed that abnormal cooperative brain regions in EOD group, mainly distributed in the bilateral frontal lobe, parietal lobe, occipital lobe, temporal lobe, paralimbic system and cerebellum ( P<0.05, corrected by FDR). In EOD group, significant negative correlations were observed between the GMV in the right orbitofrontal cortex ( r=-0.314, P=0.015), the left precuneus ( r=-0.283, P=0.029), and illness duration. Significant positive correlations were observed between the GMV in the right dorsolateral prefrontal cortex and the scores of anxiety/somatization factor of HAMD17 ( r=0.331, P=0.010), the left precuneus and weight factor of HAMD17 ( r=0.255, P=0.049), respectively. Conclusions:Abnormal GMV changes are observed in some regions of the prefrontal and parietal lobule in patients with untreated EOD, accompanied by extensive covariant brain regions and additional structural connectivity. In addition, the abnormal GMV changes in some regions are associated with clinical features. Part of the prefrontal and parietal lobule may be the biomarkers to objectively evaluate abnormal brain structure in depression patients in the early stage.