RESUMO
The aim of this study was to investigate the frequency distribution of the cytochrome P450 (CYP450) enzymes, CYP2D6 and CYP2C19, and the form of tamoxifen metabolisation in premenopausal patients with breast cancer in the Han and Uygur ethnic groups of Xinjiang to guide rational clinical drug use. A total of 125 Han patients and 121 Uygur patients with premenopausal hormone-receptor-positive breast cancer treated at the Xinjiang Uygur Autonomous Region Cancer Hospital between 1 June 2011 and 1 December 2013 were selected. The common mutation sites in CYP450 were analysed using TaqMan® minor groove binder technology. Genetic testing was performed to determine other metabolic types of tamoxifen, and the genotypes and metabolic types were compared using a Chi-squared test. Between the Han and Uygur groups, there were significant differences in the frequencies of the CYP2D6 (*10/*10) and CYP2C19 (*1/*1) genotypes, with P-values of 0.002 and 0.015, respectively. Genotypes of CYP2D6 (*1/*1), CYP2D6 (*1/*5), CYP2D6 (*5/*5), CYP2D6 (*5/*10) and CYP2C19 (*3/*3) were expressed in the two patient groups, and the difference was not statistically significant (P > 0.05). In the Han patients, the proportions of extensive, intermediate and poor metabolisers of tamoxifen were 72, 24 and 4%, respectively, whereas those in the Uygur patients were 76.9, 17.4 and 5.7%, respectively, with no significant difference (P > 0.05). In conclusion, There were partial differences in the CYP2D6 and CYP2C19 gene polymorphisms of CYP450 between the Han and Uygur patients with premenopausal breast cancer, but there was no significant difference between the CYP2D6 and CYP2C19 phenotypes. Further research is needed to determine the relationship between the enzyme genetic differences of CYP450 and the pharmacokinetics and efficacy of tamoxifen. Although there were some differences in genotypes, these did not result in differences in the predicted tamoxifen metabolisation phenotype between the Han and Uygur patients with breast cancer. Therefore, the doses should be adjusted according to the individual genotype data.
RESUMO
INTRODUCTION: Epidemiological studies show that breast cancer is the most common cancer in women in the world. Breast cancer treatment can be very effective, especially when the disease is detected in the early stages. The goal can be achieved by using large-scale breast cancer data with the machine learning models METHODS: This paper proposes a new intelligent approach using an optimized ensemble classifier for breast cancer diagnosis. The classification is done by proposing a new intelligent Group Method of Data Handling (GMDH) neural network-based ensemble classifier. This method improves the performance of the machine learning technique by using a Teaching-Learning-Based Optimization (TLBO) algorithm to optimize the hyperparameters of the classifier. Meanwhile, we use TLBO as an evolutionary method to address the problem of appropriate feature selection in breast cancer data. RESULTS: The simulation results show that the proposed method has a better accuracy between 7 and 26% compared to the best results of the existing equivalent algorithms. CONCLUSION: According to the obtained results, we suggest the proposed algorithm as an intelligent medical assistant system for breast cancer diagnosis.