Cannonkline9132

9%), 1.8 OR (95% CI 1.1-2.7, p = 0.006)]. On multivariate logistic regression analysis, the lack of epidural analgesia and duration of second stage of labor were both independently positively associated with OASIS [adjusted OR 2.67 (95% CI 1.55-4.62), p less then 0.001, adjusted OR 1.23 (95% CI 1.11-1.43), p less then 0.001, respectively)]. CONCLUSION Sonographic head circumference and birth weight are not associated with OASIS occurrence among primiparous women delivering by an unassisted vaginal delivery. Prolonged second stage and the use of epidural analgesia are modifiable risk factors among these women.PURPOSE Biomedical data frequently contain imbalance characteristics which make achieving good predictive performance with data-driven machine learning approaches a challenging task. In this study, we investigated the impact of re-sampling techniques for imbalanced datasets in PET radiomics-based prognostication model in head and neck (HNC) cancer patients. METHODS Radiomics analysis was performed in two cohorts of patients, including 166 patients newly diagnosed with nasopharyngeal carcinoma (NPC) in our centre and 182 HNC patients from open database. Conventional PET parameters and robust radiomics features were extracted for correlation analysis of the overall survival (OS) and disease progression-free survival (DFS). We investigated a cross-combination of 10 re-sampling methods (oversampling, undersampling, and hybrid sampling) with 4 machine learning classifiers for survival prediction. Diagnostic performance was assessed in hold-out test sets. Statistical differences were analysed using Monte Carlo cross-validations by post hoc Nemenyi analysis. RESULTS Oversampling techniques like ADASYN and SMOTE could improve prediction performance in terms of G-mean and F-measures in minority class, without significant loss of F-measures in majority class. We identified optimal PET radiomics-based prediction model of OS (AUC of 0.82, G-mean of 0.77) for our NPC cohort. BMS935177 Similar findings that oversampling techniques improved the prediction performance were seen when this was tested on an external dataset indicating generalisability. CONCLUSION Our study showed a significant positive impact on the prediction performance in imbalanced datasets by applying re-sampling techniques. We have created an open-source solution for automated calculations and comparisons of multiple re-sampling techniques and machine learning classifiers for easy replication in future studies.PURPOSE To evaluate if there was a correlation between in vivo kinematics of a medial-stabilized (MS) total knee arthroplasty (TKA) and post-operative clinical scores. We hypothesized that (1) a MS-TKA would produce a medial pivot movement and that (2) this specific pattern would be correlated with higher clinical scores. METHODS 18 patients were evaluated through clinical and functional scores evaluation (Knee Society Score clinical and functional, Womac, Oxford), and kinematically through dynamic radiostereometric analysis (RSA) at 9 months after MS-TKA, during the execution of a sit-to-stand and a lunge motor task. The anteroposterior (AP) Low Point translation of medial and lateral femoral compartments was compared through Student's t test (p  less then  0.05). A correlation analysis between scores and kinematics was performed through the Pearson's correlation coefficient r. RESULTS A significantly greater (p  less then  0.0001) anterior translation of the lateral compartment with respect to the medial onf medial pivot and higher post-operative scores. LEVEL OF EVIDENCE IV.PURPOSE The purpose of this study was to clinically validate the Hill-Sachs interval to glenoid track width ratio (H/G ratio) compared with the instability severity index (ISI) score for predicting an increased risk of recurrent instability after arthroscopic Bankart repair. METHODS A retrospective evaluation was performed using data from patients with anteroinferior shoulder instability who underwent arthroscopic Bankart repair with a follow-up period of at least 24 months. A receiver operating characteristic (ROC) curve was used to determine the optimal cut-off values for the H/G ratio and the ISI score to predict an increased risk of recurrent instability. The area under the ROC curve (AUC) of the two methods and the sensitivity and specificity of their optimal cut-off values were compared. RESULTS A total of 222 patients were included, among whom 31 (14.0%) experienced recurrent instability during the follow-up period. The optimal cut-off values for predicting an increased risk of recurrent instability were an H/G ratio of ≥ 0.7 and ISI score of ≥ 4. There were no significant differences between the AUC of the two methods (H/G ratio AUC = 0.821, standard error = 0.035 and ISI score AUC = 0.792, standard error = 0.04; n.s.) nor between the sensitivity and specificity of the optimal cut-off values (n.s. and n.s., respectively). CONCLUSIONS The H/G ratio is comparable to the ISI score for predicting an increased risk of recurrent instability after arthroscopic Bankart repair. Surgeons are recommended to consider other strategies to treat anterior shoulder instability if H/G ratio is ≥ 0.7. LEVEL OF EVIDENCE III.PURPOSE The role of the anterior cruciate ligament (ACL) in knee biomechanics in vivo and under weight-bearing is still unclear. The purpose of this study was to compare the tibiofemoral kinematics of ACL-deficient knees to healthy contralateral ones during the execution of weight-bearing activities. METHODS Eight patients with isolated ACL injury and healthy contralateral knees were included in the study. Patients were asked to perform a single step forward and a single leg squat first with the injured knee and then with the contralateral one. Knee motion was determined using a validated model-based tracking process that matched subject-specific MRI bone models to dynamic biplane radiographic images, under the principles of Roentgen stereophotogrammetric analysis (RSA). Data processing was performed in a specific software developed in Matlab. RESULTS Statistically significant differences (p  less then  0.05) were found for single leg squat along the frontal plane ACL-deficient knees showed a more varus angle, especially at the highest knee flexion angles (40°-50° on average), compared to the contralateral knees.