Prediction of lymphedema occurrence in patients with breast cancer using the optimized combination of ensemble learning algorithm and feature selection.

BACKGROUND: Breast cancer-related lymphedema is one of the most important complications that adversely affect patients' quality of life. Lymphedema can be managed if its risk factors are known and can be modified. This study aimed to select an appropriate model to predict the risk of lymphedema and determine the factors affecting lymphedema. METHOD: This study was conducted on data of 970 breast cancer patients with lymphedema referred to a lymphedema clinic. This study was designed in two phases: developing an appropriate model to predict the risk of lymphedema and identifying the risk factors. The first phase included data preprocessing, optimizing feature selection for each base learner by the Genetic algorithm, optimizing the combined ensemble learning method, and estimating fitness function for evaluating an appropriate model. In the second phase, the influential variables were assessed and introduced based on the average number of variables in the output of the proposed algorithm. RESULT: Once the sensitivity and accuracy of the algorithms were evaluated and compared, the Support Vector Machine algorithm showed the highest sensitivity and was found to be the superior model for predicting lymphedema. Meanwhile, the combined method had an accuracy coefficient of 91%. The extracted significant features in the proposed model were the number of lymph nodes to the number of removed lymph nodes ratio (68%), feeling of heaviness (67%), limited range of motion in the affected limb (65%), the number of the removed lymph nodes ( 64%), receiving radiotherapy (63%), misalignment of the dominant and the involved limb (62%), presence of fibrotic tissue (62%), type of surgery (62%), tingling sensation (62%), the number of the involved lymph nodes (61%), body mass index (61%), the number of chemotherapy sessions (60%), age (58%), limb injury (53%), chemotherapy regimen (53%), and occupation (50%). CONCLUSION: Applying a combination of ensemble learning approach with the selected classification algorithms, feature selection, and optimization by Genetic algorithm, Lymphedema can be predicted with appropriate accuracy. Developing applications by effective variables to determine the risk of lymphedema can help lymphedema clinics choose the proper preventive and therapeutic method.

Predicting Factors of Complete Pathological Response in Locally Advanced Rectal Cancer.

Background: Current treatment of choice for locally advanced rectal cancer is neoadjuvant chemoradiotherapy (neo-CRT) followed by surgical resection and adjuvant chemotherapy. Some patients may experience complete pathological response (cPR) after the neoadjuvant treatment. However, the predicting factors are still debated. Methods: In this registry-based retrospective cohort study, 258 patients with locally advanced rectal cancer were included. Patients were categorized into two groups with or without cPR. Logistic regression analysis was recruited to investigate the odds ratio for all independent variables, and those with significant results were included in multivariate regression analysis. Results: Achievement of cPR was 21.3%. The odds ratio of cPR was significantly lower when the tumor distance from the anal verge was>10 centimeters (OR=0.24, P=0.040). Also, the odds of cPR with N1 involvement in comparison with N0 involvement decreased for 0.41 (P=0.043). It was also true for patients with N2 involvement in comparison with N0 involvement (OR=0.31, P=0.031). Higher odds ratio of cPR was observed in patients who underwent surgery in>12 weeks after neo-CRT (OR=2.9, P=0.022). Furthermore, the odds of cPR decreased for 0.9 with increasing in carcinoembryonic antigen (CEA) level (P=0.044). Conclusion: Patients with rectal cancer in clinical stage II or lower, without the involvement of the lymphatic system at diagnosis, and with tumors located in the lower parts of the rectum, with lower levels of CEA, and longer duration between neo-CRT and surgery were more likely to achieve cPR after neo-CRT. With the current knowledge, the "wait and watch policy" is still debated and needs to be defined more precisely by upcoming studies.

Effectiveness of Local Botulinum Toxin Injection for Perianal Pain after Hemorrhoidectomy.

Background: Hemorrhoidectomy is commonly associated with post-operative perianal pain. Local botulinum toxin injection by relaxing the smooth muscles of the perianal sphincter and reducing anal pressure can be effective in decreasing post-operative pain. This study evaluates the effectiveness of local botulinum toxin injection in controlling pain after hemorrhoidectomy. Methods: This study was a double-blind, randomized clinical trial. A total of 40 patients undergoing hemorrhoidectomy who were referred to Shariati Hospital in 2019- 2020 were enrolled as participants and divided into two groups. In one group, injection of botulinum toxin was done in intersphincteric area, and in the other group, there was no intervention after hemorrhoidectomy. SPSS software version 24 was used to analyze the data. Results: Local botulinum toxin injection (MASPORT® 500) significantly reduced post-operative perianal pain on the first, third, fifth, and seventh days after the operation compared with the second group (P<0.05). The mean pain scores in the first, third, fifth, and seventh days in the first and second groups were 7.60 (±0.88) versus 8.25 (±1.16), 40.5 (±0.88) versus 6.05 (±0.99), 2.45 (±0.51) versus 3.05 (±0.68), and 2.05 (±0.39) versus 1.70 (±0.57), respectively. Furthermore, pain during defecation was significantly lower for the experimental group (P<0.05). Conclusion: Local botulinum toxin injection effectively improves post-operative pain after hemorrhoidectomy. Further studies are needed to prove the clinical value of local botulinum toxin injection.

Clinical outcome of thymectomy in myasthenia gravis patients: A report from Iran.

Background: Myasthenia gravis (MG) is an autoimmune disease affecting acetylcholine postsynaptic receptor of voluntary muscles. Thymectomy is done in these patients and is a mainstay in the treatment of MG; however, the long-term result of surgery is still controversial. This study dealt with the investigation of the results of thymectomy in treatment, recovery and control of the symptoms of these patients. Methods: This study was performed through a retrospective method in patients suffering from MG who underwent trans-sternal thymectomy between 2011 and 2016. We conducted thymectomy, excision of mediastinal mass and contents of tissues between the right and left phrenic nerves for all patients. Then, the effect of various variables including age, sex, time interval between onset of disease and surgery, thymus pathology and the dosage of drug on clinical response after surgery was determined using various statistical tests. Results: 47 patients including 26 men and 21 women with the mean age of 33.0 ± 4.6 years have been investigated. The mean age of patients was 36.2 and 29.7 in men and women respectively (P = 0.041). Spiral chest computed tomography (CT) scan was present in 47 patients demonstrating mediastinal mass in 40 (85.1%) patients. Also, our pathological results showed thymic cells in aortopulmonary window contents of 4 patients. According to the results, the younger age of patients at the time of surgery, shorter time between diagnosis and thymectomy, being a woman and non-thymoma pathology were along with better clinical outcomes after thymectomy. Conclusion: Our study shows better clinical results of thymectomy in patients with normal chest CT scan and normal or atrophic thymus in pathologic reports. Generally, it seems that performing thymectomy in a shorter time interval after diagnosis of MG is beneficial. Moreover, in MG patients who do not suffer from thymoma, it is along with positive results.

Measuring the rate of weight gain and the influential role of diet in patients undergoing elective laparoscopic cholecystectomy: a 6-month follow-up study.

Weight gain after cholecystectomy is one of the major surgical problems consistent with morbidities and long-term mortalities. Here, we aimed to study the impact of palliative cholecystectomy on weight gain and nutritional status of the patients before and in 1, 4 and 6 months after surgery. We performed a prospective survey on a cohort of 48 patients undergoing elective cholecystectomy. The nutritional status of the patients was collected by nutrition nurse and analysed by NutriBase software. There were 13 (16%) females and 35 (84%) males with the mean age of 51.8 ± 1.97. In 6 months after surgery, patients had higher values of BMI, daily energy expenditure, carbohydrate and lipid consumption and a decreased level of protein consumption. Weight gain after surgery was caused by an increase in fat consumption which resulted in the weight gain and worsening of lipid profile. Dietary consultation, shortly after surgery, would improve patient outcome after cholecystectomy.