Objective To observe the feature of post-operative hyperglycemia after coronary artery bypass grafting(CABG) surgery in department of intensive care unit（ICU） patients.Methods Patients who had CABG surgery in Zhongshan Hospital from January 2005 to December 2005 were enrolled.Data were collected including the history of diabetes，pre-operative and post-operative blood glucose(BG) levels，and the time that post-operative hyperglycemia and peak BG occurred.The patients were divided into diabetic and non-diabetic groups according to the diabetic history.The data were compared and analyzed between the two groups.Results 200 patients were enrolled in this study.The incidence of post-operative hyperglycemia was 77%，and about 99.4% occurred in the first 24 hours admitted to ICU，which was independent on diabetic history (χ2=2.58，P=0.108)，but was related to the BG level above 6.1 mmol/L (χ2=12.31，P=0.000).In 80% of the patients，peak BG occurred in the first 24 hours admitted to ICU，which was significantly earlier in the non-diabetic group compared with the diabetic group (8.5 h vs 18.5 h，P=0.02 ).In the patients who had post-operative hyperglycemia，the median time of the BG peak is 10 hours，and 75.3% of the BG peak occurred in the first 24 hours admitted to ICU.Conclusion There is a high incidence of post-operative hyperglycemia in post-CABG patients which always occur within 24 hours after operation and relate to pre-operative high BG.
Attention deficit/hyperactivity disorder (ADHD) is a behavioral disorder syndrome found mainly in school-age population. At present, the diagnosis of ADHD mainly depends on the subjective methods, leading to the high rate of misdiagnosis and missed-diagnosis. To solve these problems, we proposed an algorithm for classifying ADHD objectively based on convolutional neural network. At first, preprocessing steps, including skull stripping, Gaussian kernel smoothing, et al., were applied to brain magnetic resonance imaging (MRI). Then, coarse segmentation was used for selecting the right caudate nucleus, left precuneus, and left superior frontal gyrus region. Finally, a 3 level convolutional neural network was used for classification. Experimental results showed that the proposed algorithm was capable of classifying ADHD and normal groups effectively, the classification accuracies obtained by the right caudate nucleus and the left precuneus brain regions were greater than the highest classification accuracy (62.52%) in the ADHD-200 competition, and among 3 brain regions in ADHD and the normal groups, the classification accuracy from the right caudate nucleus was the highest. It is well concluded that the method for classification of ADHD and normal groups proposed in this paper utilizing the coarse segmentation and deep learning is a useful method for the purpose. The classification accuracy of the proposed method is high, and the calculation is simple. And the method is able to extract the unobvious image features better, and can overcome the shortcomings of traditional methods of MRI brain area segmentation, which are time-consuming and highly complicate. The method provides an objective diagnosis approach for ADHD.