The feature selection process can be considered a problem of global combinatorial optimization in machine learning, which reduces the number of features, removes irrelevant, noisy and redundant data, and results in acceptable classification accuracy. In this study, we propose a combined filter method (ReliefF) and a wrapper method (memetic algorithm, MA) for classification. The goal of our method is to filter the irrelevant features and select the most important feature subsets. We used the ReliefF algorithm to calculate and update the scores of every feature for each data set, and then applied a MA for feature selection. The K-nearest neighbor (K-NN) method with leave-one-out cross-validation (LOOCV) serves as a classifier for evaluating classification accuracies. The experimental results show that the proposed method is superior to existing methods in terms of classification accuracy.

Objective: The aim of this study was to identify if breast reconstruction is a surgical risk factor for axillary web syndrome (AWS) in breast cancer (BC) patients. Methods: The data of 207 patients who have been diagnosed with unilateral BC and who had mastectomy and lymph node dissection were retrospectively reviewed. Information of their clinical and pathological data, whether they had immediate ­reconstruction and intraoperative radiotherapy, surgical methods, and postoperative complications during the 3 months after their surgery (AWS, lymphedema, seroma, and myofascial adhesion) were collected, and the incidence of AWS was compared between different surgical methods. ­Results: The overall incidence of AWS was 48.8% in 207 patients. Of the 22 patients who received reconstruction, 19 developed AWS, yielding an incidence of 86%. Multivariate logistic regression modeling showed that patients who underwent reconstruction had a significantly higher incidence of AWS (odds ratio, 4.74), as did patients with postoperative complication of myofascial adhesion (odds ratio, 7.07). Conclusions: BC survivors after breast reconstruction are susceptible to AWS, and there is a significant association between myofascial adhesion and AWS. Our results can stimulate further investigation and provide an evidence base for the development of educational guidance for patients who plan to undergo breast reconstruction.

Background: Suction-curettage by arthroscopic shaver is the most effective treatment for bromhidrosis; however, postoperative complications require wound management and exhibit a high risk of hypertrophic scarring. We investigated factors affecting postoperative complications. Methods: We retrospectively evaluated data for 215 patients (430 axillae) with bromhidrosis treated with suction-curettage by arthroscopic shaver between 2011 and 2019. Cases followed for less than 1 year were excluded. Complications of hematoma or seroma, epidermis decortication, skin necrosis, and infection were recorded. Multinomial logistic analysis was used to calculate odds ratios and corresponding 95% confidence intervals for the complication of the surgery, adjusting for relevant statistically significant variables. Results: Complications occurred in 52 axillae (12.1%). Epidermis decortication occurred in 24 axillae (5.6%), with a significant difference for age (P < 0.001). Hematoma occurred in 10 axillae (2.3%) with a significant difference in tumescent infiltration use (P = 0.039). Skin necrosis occurred in 16 axillae (3.7%) with a significant difference for age (P = 0.001). Infection occurred in 2 axillae (0.5%). Severe scarring occurred in 15 axillae (3.5%), with complications related to more severe skin scarring (P < 0.05). Conclusion: Older age was a risk factor for complications. Use of tumescent infiltration resulted in good postoperative pain control and less hematoma. Patients with complications presented with more severe skin scarring, but none experienced limited range of motion after massage.

BACKGROUND Breast cancer has a major disease burden in the female population, and it is a highly genome-associated human disease. However, in genetic studies of complex diseases, modern geneticists face challenges in detecting interactions among loci. OBJECTIVE This study aimed to investigate whether variations of single-nucleotide polymorphisms (SNPs) are associated with histopathological tumor characteristics in breast cancer patients. METHODS A hybrid Taguchi-genetic algorithm (HTGA) was proposed to identify the high-order SNP barcodes in a breast cancer case-control study. A Taguchi method was used to enhance a genetic algorithm (GA) for identifying high-order SNP barcodes. The Taguchi method was integrated into the GA after the crossover operations in order to optimize the generated offspring systematically for enhancing the GA search ability. RESULTS The proposed HTGA effectively converged to a promising region within the problem space and provided excellent SNP barcode identification. Regression analysis was used to validate the association between breast cancer and the identified high-order SNP barcodes. The maximum OR was less than 1 (range 0.870-0.755) for two- to seven-order SNP barcodes. CONCLUSIONS We systematically evaluated the interaction effects of 26 SNPs within growth factor–related genes for breast carcinogenesis pathways. The HTGA could successfully identify relevant high-order SNP barcodes by evaluating the differences between cases and controls. The validation results showed that the HTGA can provide better fitness values as compared with other methods for the identification of high-order SNP barcodes using breast cancer case-control data sets.