Artificial intelligence for prediction of endometrial intraepithelial neoplasia and endometrial cancer risks in pre- and postmenopausal women.

BACKGROUND: The current approach to endometrial cancer screening requires that all patients be able to recognize symptoms, report them, and carry out appropriate interventions. The current approach to endometrial cancer screening could become a problem in the future, especially for Black women and women from minority groups, and could lead to disparities in receiving proper care. Moreover, there is a lack of literature on artificial intelligence in the prediction and diagnosis of endometrial intraepithelial neoplasia and endometrial cancer. OBJECTIVE: This study analyzed different artificial intelligence methods to help in clinical decision-making and the prediction of endometrial intraepithelial neoplasia and endometrial cancer risks in pre- and postmenopausal women. This study aimed to investigate whether artificial intelligence may help to overcome the challenges that statistical and diagnostic tests could not. STUDY DESIGN: This study included 564 patients. The features that were collected included age, menopause status, premenopausal abnormal bleeding and postmenopausal bleeding, obesity, hypertension, diabetes mellitus, smoking, endometrial thickness, and history of breast cancer. Endometrial sampling was performed on all women with postmenopausal bleeding and asymptomatic postmenopausal women with an endometrial thickness of at least 3 mm. Endometrial biopsy was performed on premenopausal women with abnormal uterine bleeding and asymptomatic premenopausal women with suspected endometrial lesions. Python was used to model machine learning algorithms. Random forest, logistic regression, multilayer perceptron, Catboost, Xgboost, and Naive Bayes methods were used for classification. The synthetic minority oversampling technique was used to correct the class imbalance in the training sets. In addition, tuning and boosting were used to increase the performance of the models with a 5-fold cross-validation approach using a training set. Accuracy, sensitivity, specificity, positive predictive value, and F1 score were calculated. RESULTS: The prevalence of endometrial or preuterine cancer was 7.9%. Data from 451 patients were randomly assigned to the training group, and data from another 113 patients were used for internal validation. Of note, 3 of 9 features were selected by the Boruta algorithm for use in the final modeling. Age, body mass index, and endometrial thickness were all associated with a high risk of developing precancerous and cancerous diseases, after fine-tuning for the multilayer computer to have the highest area below the receiver operating characteristic curve (area under the curve, 0.938) to predict a precancerous disease. The accuracy was 0.94 for predicting a precancerous disease. Precision, recall, and F1 scores for the test group were 0.71, 0.50, and 0.59, respectively. CONCLUSION: Our study found that artificial intelligence can be used to identify women at risk of endometrial intraepithelial neoplasia and endometrial cancer. The model is not contingent on menopausal status or symptoms. This may be an advantage over the traditional methodology because many women, especially Black women and women from minority groups, could not recognize them. We have proposed to include patients to provide age and body mass index, and measurement of endometrial thickness by either sonography or artificial intelligence may help improve healthcare for women in rural or minority communities.

Vaginally Assisted Laparoscopic Urethrolysis and Mesh Excision after Tension-free Vaginal Tape.

STUDY OBJECTIVE: To present technique of vaginally assisted laparoscopic urethrolysis and mesh excision after tension-free vaginal tape. DESIGN: Demonstration video. SETTING: Despite the Food and Drug Administration's warning to limit the use of mesh, midurethral sling surgery (MUS) has not significantly decreased, but operations for complications have increased 3 times [1]. Urethral obstruction after MUS has an incidence of 2.7% to 11% [2] that requires resurgery, which ranges from pull-down, mesh excision to urethrolysis and is chosen by the surgeon's experience. Retropubic urethrolysis and mesh excision are reported to be more successful [3]. Urethrolysis can be performed by a retropubic, transvaginal, or suprameatal approach. Transvaginal mesh excision and urethrolysis are not satisfactory in all cases, and it might be difficult to identify the mesh if it is dislocated proximally or buried in dense fibrosis, which may increase urethral/bladder injuries. Although vaginal urethrolysis and mesh removal are usually preferred as the primary approach, there is no randomized controlled trial comparing retropubic and vaginal urethrolysis with/without mesh removal. Gynecologists should master each technique to provide individualized treatment. Laparoscopic urethrolysis has the advantage of the identification of neighboring structures and provides a safer operation (Fig. 1). Combined vaginal and laparoscopic approaches can be used to totally remove the mesh and for difficult surgeries at the junction of the retropubic urethra and the midurethra (Fig. 2). INTERVENTIONS: (1) Timing of urethrolysis is controversial. Although urethral loosening or pulling down in the first few days and mesh excision in the first 15 days can be useful, urethrolysis can be chosen for delayed cases with marked fibrosis. Preoperative diagnostic cystoscopy to exclude urethral mesh erosion is essential. Intermittent catheterization until surgery should be done. (2) The technique is described in 5 steps. The arcus tendineus is an important landmark [4] (Fig. 3). CONCLUSION: Laparoscopic urethrolysis for urinary obstruction after MUS can be a safe and successful procedure after failed vaginal approach or can be considered as a primary approach in select cases.

Assessment of the coronary venous system by using cardiac CT.

PURPOSE: We aimed to investigate the coronary venous system and its variations by using dual source computed tomography (CT). MATERIALS AND METHODS: Retrospective assessment was carried out on 339 patients who underwent coronary CT angiography using 128-slice dual source CT for suspected coronary artery disease. The examinations were performed according to routine imaging protocols used to evaluate coronary arteries. The coronary venous system was evaluated in each case using maximum intensity projection and volume rendering technique multiplanar reformation reconstructions. In each patient, the presence and calibration of normal anatomy, as well as the variations of the coronary sinus, middle cardiac vein, small cardiac vein, posterior cardiac vein, great cardiac vein, anterior interventricular vein, posterolateral vein, left marginal vein, and anterolateral vein were recorded. RESULTS: The coronary sinus, middle cardiac vein, great cardiac vein, and anterior interventricular vein were visualized in all of the patients. In all cases, one of the lateral or posterolateral veins of appropriate localization and diameter for cardiac resynchronization therapy was detected. The posterior cardiac vein was visualized in 87% of the cases, the left marginal vein in 87.9%, and the small cardiac vein in 20%. There was no significant difference in the diameters or visibilities of the coronary veins in terms of age. CONCLUSION: The coronary venous system and its tributaries may be examined in detail using CT angiography examination performed according to the routine coronary CT angiography protocol used for dual source CT. Dual source CT may be a valuable tool for evaluation of the coronary veins prior to invasive procedures that are directed at the coronary venous system.

Stent entrapment and guide wire fracture during percutaneous coronary intervention in the same patient.

In the performance of increasingly complex PCI there remains an ever-present risk of stent entrapment and guide wire or other device fracture. We report the first case with stent dislodgement and guide wire fracture to occur simultaneously in the same patient.

Cardioversion under the guidance of transesophageal echochardiograhy in persistent atrial fibrillation: results with low molecular weight heparin.

BACKGROUND: Transesophageal echocardiography (TEE) guided cardioversion to restoration of sinus rhythm is a therapeutic option in patients with atrial fibrillation (AF). Anticoagulation at the time of and after cardioversion is necessary to prevent formation of new thrombus during atrial stunning period. We aimed to evaluate the efficacy and safety to TEE guided cardioversion with low molecular weight heparin (LMWH) in patients with atrial fibrillation. METHODS: We followed up 208 patients with persistent AF (mean age: 65.5+/-10.2 years) who were attempted TEE guided cardioversion. LMWH were used as an anticoagulant and warfarin therapy was continued. RESULTS: Cardioversion were performed in 183 patients. Sinus rhythm restored in 144 patients (78.7%). Mean follow up duration was 155 days. No cardiac death occurred. In the early follow up period (within 30 day) one thromboembolic event (0.54%) occurred in a patient who was cardioverted. Two patients who had not been cardioverted because of left atrial thrombus presented embolic stroke, one in early and another in late follow up period. All embolic complications occurred in patients who had been taking warfarin and whose INR level was subtherapeutic at the time of stroke. Sinus rhythm was maintained in 64% and total hemorrhagic complications occurred in 4.8% of the patients in long-term follow-up. CONCLUSION: TEE guided cardioversion with a short-term anticoagulation protocol using low molecular weight heparin is a safe and effective method in restoring and maintaining sinus rhythm and enables us to make earlier cardioversion in atrial fibrillation.