Various kinds of data mining algorithms are continuously raised with the development of related disciplines. The applicable scopes and their performances of these algorithms are different. Hence, finding a suitable algorithm for a dataset is becoming an important emphasis for biomedical researchers to solve practical problems promptly. In this paper, seven kinds of sophisticated active algorithms, namely, C4.5, support vector machine, AdaBoost, k-nearest neighbor, naïve Bayes, random forest, and logistic regression, were selected as the research objects. The seven algorithms were applied to the 12 top-click UCI public datasets with the task of classification, and their performances were compared through induction and analysis. The sample size, number of attributes, number of missing values, and the sample size of each class, correlation coefficients between variables, class entropy of task variable, and the ratio of the sample size of the largest class to the least class were calculated to character the 12 research datasets. The two ensemble algorithms reach high accuracy of classification on most datasets. Moreover, random forest performs better than AdaBoost on the unbalanced dataset of the multi-class task. Simple algorithms, such as the naïve Bayes and logistic regression model are suitable for a small dataset with high correlation between the task and other non-task attribute variables. K-nearest neighbor and C4.5 decision tree algorithms perform well on binary- and multi-class task datasets. Support vector machine is more adept on the balanced small dataset of the binary-class task. No algorithm can maintain the best performance in all datasets. The applicability of the seven data mining algorithms on the datasets with different characteristics was summarized to provide a reference for biomedical researchers or beginners in different fields.

Bazi Bushen capsule (BZBS), as a Chinese medicine used to relieve fatigue, has been proven effective for the treatment of atherogenesis through antilipid effects. To investigate the potential mechanism of BZBS in the anti-atherosclerotic effect, Ovx/ApoE^-/- mice were applied to investigate the anti-atherosclerotic efficiency and potential mechanism of BZBS. Therapeutic effect was evaluated based on the number of CD68⁺ and CD3⁺ cells, the level of intercellular adhesion molecule-1 (ICAM-1) and vascular cell adhesion molecule-1 (VCAM-1), and the ratio of cleaved caspase-3/caspase-3, as well as increasing ratio of Bcl2/Bax. Human umbilical vein endothelial cells (HUVECs) were chosen to evaluate the role of GPER1. Treatment with BZBS reduced lipid deposition by reducing the numbers of CD68⁺ and CD3⁺ cells, the level of ICAM-1 and VCAM-1, and the ratio of cleaved caspase-3/caspase-3, and increasing the ratio of Bcl2/Bax as compared with the control group. In si-GPER1-treated HUVECs, the anti-apoptotic effect of BZBS was decreased. This study revealed that BZBS exhibited a clear effect against atherogenesis via GPER1-dependent anti-inflammatory and anti-apoptotic mechanisms. We believe that this manuscript is informative and useful for researchers pursuing the related alleviation of post-menopausal AS via anti-inflammatory and anti-apoptotic mechanisms.

Purpose ¹⁸F-Alfatide II has been translated into clinical use and been proven to have good performance in identifying breast cancer. In this study, we investigated ¹⁸F-Alfatide II for evaluation of axillary lymph nodes (ALN) in breast cancer patients and compared the performance with ¹⁸F-FDG. Methods A total of 44 female patients with clinically suspected breast cancer were enrolled and underwent ¹⁸F-Alfatide II and ¹⁸F-FDG PET/CT within a week. Tracer uptakes in ALN were evaluated by visual analysis, semi-quantitative analysis with maximum standardized uptake value (SUV_max), mean standardized uptake value (SUV_mean), and SUV_max ratio of target/non-target (T/NT). Results Among 44 patients, 37 patients were pathologically diagnosed with breast cancer with metastatic (17 cases) or non-metastatic (20 cases) ALN. The sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) of visual analysis were 70.6%, 90%, 81.1%, 85.7%, and 78.3% for ¹⁸F-Alfatide II, 64.7%, 90%, 78.4%, 84.6%, and 75% for ¹⁸F-FDG, respectively. By combining ¹⁸F-Alfatide II and ¹⁸F-FDG, the sensitivity significantly increased to 82.4%, the specificity was 85%, the accuracy increased to 83.8%, the PPV was 82.4%, and the NPV significantly increased to 85.0%. Three cases of luminal B subtype were false negative for both ¹⁸F-Alfatide II and ¹⁸F-FDG. The other 2 false negative cases of ¹⁸F-Alfatide II were triple-negative subtype and 3 false negative cases of ¹⁸F-FDG were luminal B subtype too. The AUCs of three semi-quantitative parameters (SUV_max, SUV_mean, T/NT) for ¹⁸F-Alfatide II were between 0.8 and 0.9, whereas those for ¹⁸F-FDG were more than 0.9. ¹⁸F-Alfatide II T/NT had the highest Youden index (76.5%), specificity (100%), accuracy (89.2%), and PPV (100%) among these semi-quantitative parameters. ¹⁸F-Alfatide II uptake as well as ¹⁸F-FDG uptake in metastatic axillary lymph nodes (MALN) was significantly higher than that in benign axillary lymph nodes (BALN). Both ¹⁸F-Alfatide II and ¹⁸F-FDG did not show difference in primary tumor uptake irrespective of ALN status. Conclusion ¹⁸F-Alfatide II can be used in breast cancer patients to detect metastatic ALN, however, like ¹⁸F-FDG, with high specificity but relatively low sensitivity. The combination of ¹⁸F-Alfatide II and ¹⁸F-FDG can significantly improve sensitivity and NPV. ¹⁸F-Alfatide II T/NT may serve as the most important semi-quantitative parameter to evaluate ALN.

The incidence of prostate cancer increases annually. Prostate cancer is an underreported and emerging problem in China. We conducted a cross-sectional study of 392 eligible patients from 710 men with prostate cancer or benign prostatic hyperplasia between 2000 and 2003. For total prostate-specific antigen, age, three diameters of prostate, prostate volume and prostate-specific antigen density seven indices, analysis of variance and t test were used to analyze the difference between the groups. A decision tree with pruning was established using the prostate-specific antigen density, age and transversal diameter of the prostate to screen the patient with prostate cancer. According to the established decision tree model, prostate-specific antigen density was the most important factor affecting the occurrence of prostate cancer. In elderly people over the age of 83 years, the transverse diameter of prostate cancer was smaller than that of benign prostatic hyperplasia, with prostate-specific antigen density less than $0.49\text{ng/L}^2$ . No additional index was introduced, and the detection rate of prostate cancer was 86.6 %.The specificity was enhanced to 78.1%.

To investigate the effect of Fibrillin 2 (FBN2) expression on the invasion and migration of lung cancer cells, and the underlying mechanism. Protein and mRNA expressions of FBN2 were assayed. The relationship between FBN2 protein expression and clinical characteristics of lung cancer patients was analyzed. Correlation between FBN2 expression level and patient survival time was analyzed. Moreover, the mRNA and protein expression of FBN2 in lung cancer cells and human normal lung epithelial cells were assayed. After constructing low-expressing FBN2 cells, the cell proliferation, clone formation, migration and invasion capabilities were tested. Lung cancer cells proliferation with low FBN2 expression in nude mice was measured with a nude mouse tumorigenic experiment. The mRNA and protein expressions of FBN2 in lung cancer tissues were significantly higher than those in para-cancerous tissues (p<0.05). FBN2 protein expression was significantly correlated with TNM stage, lymph node metastasis and histological type (p<0.05). Survival time was markedly reduced in patients with high FBN2 expression (p<0.001). The expressions of FBN2 mRNA and protein were markedly higher in lung cancer cells than in human normal lung epithelial cells. The proliferation, migration and invasion of lung cancer cells were significantly inhibited by FBN2 knockdown. The FBN2 knockdown significantly inhibited the protein expressions of p-FAK, p-MEK and p-ERK. FBN2 is highly expressed in lung cancer tissues, and as an oncogene, it affects the pathogenesis of lung cancer. The knockdown of the expression of FBN2 significantly inhibits the proliferation, invasion and migration abilities of lung cancer cells.

Endoscopic grading of gastroesophageal flap valve (GEFV) is simple and reproducible and offers useful information for reflux activity. To investigate the potential correlation between GEFV grading and reflux finding score (RFS) in patients with laryngopharyngeal reflux disease (LPRD), 225 consecutive Patients with suspected LPRD who underwent both routine upper gastrointestinal endoscopy and laryngoscope were enrolled in our study. Patients with a RFS of more than 7 were diagnosed with LPRD. The GEFV was graded as I through IV according to Hill’s classification and was classified into two groups: normal GEFV group (grades I and II) and the abnormal GEFV group (grades III and IV). The percent of GEFV grades I to IV was 39.1%, 39.1%, 12.4%, and 9.3%, respectively. Age was significantly related to an abnormal GEFV (p = 0.002). Gender, BMI, smoke and alcohol were not related to GEFV grade. Fifty-one patients (22.67%) had positive RFS. Reflux finding scores were higher in GEFV grades III and IV than I and II (p < 0.05). Endoscopic grading of GEFV is well correlated with reflux finding score in patients with LPRD. This is a simple and useful technique that provides valuable diagnostic information of LPRD.