ABSTRACT
Purpose@#The purpose of this study was to use data mining methods to establish a simple and reliable predictive model based on the risk factors related to gallbladder stones (GS) to assist in their diagnosis and reduce medical costs. @*Materials and Methods@#This was a retrospective cross-sectional study. A total of 4215 participants underwent annual health examinations between January 2019 and December 2019 at the Physical Examination Center of Shengjing Hospital Affiliated to China Medical University. After rigorous data screening, the records of 2105 medical examiners were included for the construction of J48, multilayer perceptron (MLP), Bayes Net, and Naïve Bayes algorithms. A ten-fold cross-validation method was used to verify the recognition model and determine the best classification algorithm for GS. @*Results@#The performance of these models was evaluated using metrics of accuracy, precision, recall, F-measure, and area under the receiver operating characteristic curve. Comparison of the F-measure for each algorithm revealed that the F-measure values for MLP and J48 (0.867 and 0.858, respectively) were not statistically significantly different (p>0.05), although they were significantly higher than the F-measure values for Bayes Net and Naïve Bayes (0.824 and 0.831, respectively; p<0.05). @*Conclusion@#The results of this study showed that MLP and J48 algorithms are effective at screening individuals for the risk of GS.The key attributes of data mining can further promote the prevention of GS through targeted community intervention, improve the outcome of GS, and reduce the burden on the medical system.
ABSTRACT
Objective To investigate the clinical significance of red blood cell distribution width-to-platelet ratio (RPR index) in evaluating the severity of metabolic-associated fatty liver disease and predicting fatty liver-associated cirrhosis. Methods A total of 192 patients with metabolic-associated fatty liver disease and 210 patients with fatty liver-associated cirrhosis who were admitted to Shengjing Hospital of China Medical University from January 2019 to June 2020 were enrolled as group A and group B, respectively, and 206 individuals who underwent physical examination in our hospital during the same period of time were enrolled as control group (group C). All subjects underwent general measurement, blood cell analysis, blood biochemical test, and abdominal CT examination, and related formulas were used to calculate RPR, aspartate aminotransferase-to-platelet ratio index (APRI), and fibrosis-4 (FIB-4) index. A one-way analysis of variance was used for comparison of continuous data with homogeneity of variance between groups, and the SNK method was used for comparison between two groups; the Kruskal-Wallis H test was used for comparison of continuous data with heterogeneity of variance between groups, and the Mann-Whitney U test was used for comparison between two groups; the chi-square test was used for comparison of categorical data between groups; the receiver operating characteristic (ROC) curve was used to analyze the accuracy of the prediction of liver cirrhosis. Results There were significant differences in red blood cell distribution width-standard deviation, albumin, creatinine, body mass index, RPR, and APRI between any two groups (all P < 0.001), and there were significant differences in white blood cell count, platelet count, alanine aminotransferase, aspartate aminotransferase, direct bilirubin, blood urea nitrogen, and FIB-4 between group A and group B (all P < 0.05). There were significant differences in waist circumference and fasting blood glucose between groups A and B and between groups A and C (all P < 0.001). There was a significant difference in RPR between any two groups of the mild, moderate, and severe metabolic-associated fatty liver disease groups (all P < 0.05). In terms of diagnostic efficiency, the three noninvasive models RPR, APRI, and FIB-4 had an area under the ROC curve of 0.932, 0.815, and 0.877, respectively, in predicting fatty liver-associated cirrhosis. Conclusion There is a difference in RPR index between different stages of liver disease, and RPR index gradually increases with the aggravation of metabolic-associated fatty liver disease. RPR index has a higher value than APRI and FIB-4 in the warning of fatty liver-associated cirrhosis.
ABSTRACT
Objective To analyze the prevalence and risk factors of hyperuricemia (HUA) in Shenyang City, and to provide evidence for the prevention and treatment of HUA in this region. Methods From January 2013 to December 2020, 98,327 subjects who underwent physical examination in Shengjing Hospital of China Medical University in Shenyang were selected. The detection rate of HUA was calculated, and the risk factors of HUA were analyzed by multivariate logistic regression analysis. Results From 2013 to 2020, the overall prevalence of HUA was 22.48%, 30.75% in males and 9.13% in females. The prevalence rate in the male was significantly higher than that in the female (P<0.05). Except for a slight decrease in 2015 and 2020, the total prevalence rate showed an increasing trend year by year. With the increase of age, the prevalence of HUA in males decreased, while in females, it decreased slightly from 40 to 59 years old and increased significantly after 60 years old. With the increase of BMI (Body Mass Index), the prevalence of HUA also increased, and the difference was statistically significant (P<0.05). Logistic regression analysis showed that male, body mass index, physical examination year, hypertension, hyperlipidemia, hyperglycemia, triglyceride, LDL-C, abnormal liver and renal function were positively correlated with HUA, while age and HDL-C were negatively correlated with HUA. Conclusion HUA occurs mainly in male people among physical examination population in Shenyang. With the increase of BMI, HUA increases.
ABSTRACT
Objective:To understand the status of overweight and obesity in healthy people in Shenyang area, and to explore the related factors of overweight and obesity and the influence of overweight and obesity on biochemical indicators such as blood lipid and blood glucose level.Methods:A total of 6 065 healthy subjects in our physical examination center of Shengjing Hospital Affiliated to China Medical University from January 2019 to October 2019 were collected and divided into normal group, overweight group and obesity group according to different BMI.The distribution characteristics of overweight and obesity in different gender, age were analyzed, as well as the influence of overweight and obesity on blood glucose, blood lipid and other indicators.Logistic regression was served to analyze the influence factors of overweight and obesity.Results:Among the 6 065 subjects, the prevalence of normal, overweight and obesity was 39.50%, 41.85% and 18.65%, respectively.The prevalence of overweight and obesity tended to rise with the increase of age(χ 2=118.958, P<0.001). The overweight and obesity rates of men(47.45%, 24.64%) were higher than those of women(33.08%, 9.26%), and the difference was statistically significant (χ 2=577.176, P=0.000). The levels of blood glucose, total cholesterol, triglyceride, low-density lipoprotein cholesterol, apolipoprotein B, creatinine, uricacid, cystatin C, glutamic-oxalacetic transaminase, glutamic-pyruvic transaminase, gamma-glutamyltransferase, alkaline phosphatase, prealbumin, systolic blood pressure and diastolic blood pressure in the overweight/obesity group were higher than those in the normal group, and the levels of high-density lipoprotein cholesterol and apolipoprotein A1 were lower than those in the normal group, the differences were statistically significant( t=13.904, 7.668, 0.057, 9.710, 19.723, 12.840, 27.840, 15.880, 8.368, 22.986, 18.382, 10.924, 17.283, 23.378, 8.033, 29.782 and 18.937, all P<0.001). Logistic regression analysis showed that the risk factors of overweight/obesity were age, gender, systolic blood pressure, triglyceride, blood glucose, apolipoprotein B, uricacid, cystatin C, glutamic-pyruvic transaminase, gamma-glutamyltransferase.High-density lipoprotein cholesterol, apolipoprotein A1, creatinine, glutamic-oxalacetic transaminase were the protective factors of overweight/obesity(Wald=37.863, 6.871, 40.632, 13.472, 16.800, 28.165, 94.152, 9.533, 126.332, 8.017, 16.427, 34.338, 13.948, 49.814, all P<0.01). Conclusion:The prevalence of overweight/obesity of the healthy people in Shenyang is high.We should take intervention measures as early as possible to improve the quality of life.
ABSTRACT
Objective:To investigate the effect of probucol + aspirin + atorvastatin (PAS) therapy on the serum levels of homocysteine (Hcy) and retinol binding protein 4 (RBP4) in patients with diabetes mellitus complicated with cerebral infarction.Methods:126 cases of cerebral infarction patients complicated with diabetes mellitus in our hospital were recruited during January 2014 to May 2017, and then all of them were randomly divided into control group and observation group, 63 cases in each group. The control group was treated with atorvastatin combined with aspirin on the basis of routine treatment (AS therapy), and the observation group received the probucol on that basis of control group (PAS therapy). The clinical efficacy, neurological function, complications, changes of serum inflammatory factors, Hcy and RBP4 were evaluated in both groups before and after treatment.Results:After treatment, the National Institute of Health Stroke Scale (NIHSS) score of both groups were decreased and the NIHSS score of the observation group was lower than that in the control group ( P<0.05). After treatment, the effective rate of clinical treatment in observation group and control group were respectively 87.3%, 68.3%, the effective rate of observation group was significantly higher than control group ( P<0.05). After treatment, the serum levels of tumor necrosis factors-α (TNF-α), high-sensitivity C-reactive protein (hs-CRP), Hcy and RBP4 in both groups were decreased significantly ( P<0.05); the serum levels of TNF-α, hs-CRP, Hcy and RBP4 in observation group were significantly lower than those in control group ( P<0.05). There was no significant difference in the incidence of adverse reactions between the two groups ( P>0.05). Conclusions:PAS therapy is safe and effective in the treatment of type 2 diabetes mellitus complicated with cerebral infarction, which can effectively reduce serum levels of Hcy and RBP4, relieve inflammatory injury and improve neurological function.