Role of Bariatric Surgery in Patients With Endometrial Cancer: A Case Report and Review of Literature.

Objective: The standard surgery for endometrial cancer can be deferred in some situations, including morbid obesity, comorbidities, and the patient's desire for fertility. One of the options to improve patients' circumstances is bariatric surgery. Case report: This study presented two patients with stage IA, grade I endometrioid endometrial adenocarcinoma. Both patients had morbid obesity and had comorbidities. In case 1, because of fertility preservation, and in case 2, because of severe comorbidities, hormone therapy was started, followed by bariatric surgery after counseling patients. Both patients had acceptable changes in body mass index during follow-up, so cancer surgery through laparoscopy was done. Both patients did not need adjuvant therapy; months after cancer surgery, there is no recurrence, and their body mass index is also decreasing. Conclusion: Bariatric surgery can improve outcomes in patients with morbid obesity who suffer endometrial cancer.

Endometrial cancer in women with abnormal uterine bleeding: Data mining classification methods.

Background: Over the last decade, artificial intelligence in medicine has been growing. Since endometrial cancer can be treated with early diagnosis, finding a non-invasive method for screening patients, especially high-risk ones, could have a particular value. Regarding the importance of this issue, we aimed to investigate the risk factors related to endometrial cancer and find a tool to predict it using machine learning. Methods: In this cross-sectional study, 972 patients with abnormal uterine bleeding from January 2016 to January 2021 were studied, and the essential characteristics of each patient, along with the findings of curettage pathology, were analyzed using statistical methods and machine learning algorithms, including artificial neural networks, classification and regression trees, support vector machine, and logistic regression. Results: Out of 972 patients with a mean age of 45.77 ± 10.70 years, 920 patients had benign pathology, and 52 patients had endometrial cancer. In terms of endometrial cancer prediction, the logistic regression model had the best performance (sensitivity of 100% and 98%, specificity of 98.83% and 98.7%, for trained and test data sets respectively,) followed by the classification and regression trees model. Conclusion: Based on the results, artificial intelligence-based algorithms can be applied as a non-invasive screening method for predicting endometrial cancer.