The associations between hyperhomocysteinaemia (HHcy), methylenetetrahydrofolate reductase (MTHFR) C677T polymorphism, and abdominal aortic aneurysm (AAA) remain controversial, with only few studies focused on these associations within the Chinese population. We performed subgroup and interaction analyses in a Chinese Han population to investigate these associations. In all, 155 AAA patients and 310 control subjects were evaluated for serum total homocysteine levels and MTHFR C677T polymorphisms. Multiple logistic regression models were used to evaluate the aforementioned associations. Interaction and stratified analyses were conducted according to age, sex, smoking status, drinking status, and chronic disease histories. The multiple logistic analyses showed a significant association between HHcy and AAA but no significant association between MTHFR C677T polymorphism and AAA. The interaction analysis showed that age and peripheral arterial disease played an interactive role in the association between HHcy and AAA, while drinking status played an interactive role in the association between MTHFR C677T polymorphism and AAA. In conclusion, HHcy is an independent risk factor of AAA in a Chinese Han population, especially in the elderly and peripheral arterial disease subgroups. Longitudinal studies and clinical trials aimed to reduce homocysteine levels are warranted to assess the causal nature of these relationships

In lung cancer computer-aided detection/diagnosis (CAD) systems, classification of regions of interest (ROI) is often used to detect/diagnose lung nodule accurately. However, problems of unbalanced datasets often have detrimental effects on the performance of classification. In this paper, both minority and majority classes are resampled to increase the generalization ability. We propose a novel SVM classifier combined with random undersampling (RU) and SMOTE for lung nodule recognition. The combinations of the two resampling methods not only achieve a balanced training samples but also remove noise and duplicate information in the training sample and retain useful information to improve the effective data utilization, hence improving performance of SVM algorithm for pulmonary nodules classification under the unbalanced data. Eight features including 2D and 3D features are extracted for training and classification. Experimental results show that for different sizes of training datasets our RU-SMOTE-SVM classifier gets the highest classification accuracy among the four kinds of classifiers, and the average classification accuracy is more than 92.94%.

No abstract

No abstract