Search

Patients with spontaneous intracerebral hemorrhage (ICH) have poor functional outcomes. This study investigated the status of hospitalized patients with ICH based on multicenter inpatient information. We analyzed data from the hospital information systems (HISs) of 14 tertiary hospitals, including 6 Chinese medicine hospitals and 8 western hospitals from 7 provinces and 2 municipalities. The inclusion criteria were age ≥25 years and radiologically confirmed spontaneous ICH within two weeks of symptom onset. Age groups were as follows: 25–44, 45–59, 60–74, 75–89, 90 and over 90 years old. Data are presented as the proportion (%), median (interquartile range) or mean (standard deviation). Descriptive statistical analyses were conducted to analyze demographic features, lengths of hospital stay, hospitalization expenses, hematoma locations, mortality and major comorbid conditions or complications. Patients were recruited from October 2003 to September 2011. A total of 9475 inpatients were recruited from 14 Class III Grade A hospitals. Baseline characteristics included a mean age of 58 (20) years old and 37.2% female (3303). The largest number of ICH patients were in the 44–59-year-old group. The ratio of males to females in the 25–44-year-old age group was 2.36:1, which was the highest of all groups; the lowest male to female ratio was 1.56:1 in the 45–59-year-old age group. The ratios of males to females in the 60–74, 75–89 and ≥90-year-old age groups were 1.60:1, 1.62:1 and 1.64:1, respectively. The proportion of males in all age groups was higher than that of females, significantly greater in the 25–44-year-old age group (P < 0.001). The lengths of hospital stay ranged from 15 to 28 days. The hospitalization expenses of the 25–44-year-old patients were 50,000–100,000 RMB, and the costs of the remaining age groups were 10,000–20,000 RMB. Basal ganglia/thalamic hemorrhage was the most common site of ICH in different age groups. Lobar and multiple locations were higher in those aged >75 years. Hypertension was the primary comorbid condition in all age groups, and it showed a rising trend with increasing age. The second most common comorbidity in the 25–44-year-old age group was vascular abnormality, while in the other age groups, comorbidities included cerebral infarction, dyslipidemia, coronary heart disease, diabetes mellitus and arrhythmia. Mortality increased with age; mortality for those under the age of 74 years fluctuated between 4.09% and 5.93%, whereas in those in the 75–89 and ≥90-year-old age groups, mortality was 13.34% and 34.09%, respectively. As age increased, the length of hospital stay, financial burden and mortality due to ICH increased. Different age groups had different distributions of neuroimaging features, major comorbid conditions or complications. [ABSTRACT FROM AUTHOR]

In this paper, we propose an adaptive stochastic gradient boosting tree for classification studies with imbalanced data. The adjustment of cost-sensitivity and the predictive threshold are integrated together with a composite criterion into the original stochastic gradient boosting tree to deal with the issues of the imbalanced data structure. Numerical study shows that the proposed method can significantly enhance the classification accuracy for the minority class with only a small loss in the true negative rate for the majority class. We discuss the relation of the cost-sensitivity to the threshold manipulation using simulations. An illustrative example of the analysis of suboptimal health-state data in traditional Chinese medicine is discussed. [ABSTRACT FROM AUTHOR]

Clustering algorithms are important methods widely used in mining data streams because of their abilities to deal with infinite data flows. Although these algorithms perform well to mining latent relationship in data streams, most of them suffer from loss of cluster purity and become unstable when the inputting data streams have too many noisy variables. In this article, we propose a clustering algorithm to cluster data streams with noisy variables. The result from simulation shows that our proposal method is better than previous studies by adding a process of variable selection as a component in clustering algorithms. The results of two experiments indicate that clustering data streams with the process of variable selection are more stable and have better purity than those without such process. Another experiment testing KDD-CUP99 dataset also shows that our algorithm can generate more stable result. [ABSTRACT FROM AUTHOR]

It is well known that statistical classifiers trained from imbalanced data lead to low true positive rates and select inconsistent significant variables. In this article, an improved method is proposed to enhance the classification accuracy for the minority class by differentiating misclassification cost for each group. The overall error rate is replaced by an alternative composite criterion. Furthermore, we propose an approach to estimate the tuning parameter, the composite criterion, and the cut-point simultaneously. Simulations show that the proposed method achieves a high true positive rate on prediction and a good performance on variable selection for both continuous and categorical predictors, even with highly imbalanced data. An illustrative example of the analysis of the suboptimal health state data in traditional Chinese medicine is discussed to show the reasonable application of the proposed method. [ABSTRACT FROM AUTHOR]