Mustafa Gokkaya

Prediction of Clavien Dindo Classification ≥ Grade III Complications After Epithelial Ovarian Cancer Surgery Using Machine Learning Methods

Background and Objectives: Ovarian cancer surgery requires multiple radical resections with a high risk of complications. The aim of this single-centre, retrospective study was to determine the best method for predicting Clavien–Dindo grade ≥ III complications using machine learning techniques. Material and Methods: The study included 179 patients who underwent surgery at the gynaecological oncology department of Antalya Training and Research Hospital between January 2015 and December 2020. The data were randomly split into training set n = 134 (75%) and test set n = 45 (25%). We used 49 predictors to develop the best algorithm. Mean absolute error, root mean squared error, correlation coefficients, Mathew’s correlation coefficient, and F1 score were used to determine the best performing algorithm. Cohens’ kappa value was evaluated to analyse the consistency of the model with real data. The relationship between these predicted values and the actual values were then summarised using a confusion matrix. True positive (TP) rate, False positive (FP) rate, precision, recall, and Area under the curve (AUC) values were evaluated to demonstrate clinical usability and classification skills. Results: 139 patients (77.65%) had no morbidity or grade I-II CDC morbidity, while 40 patients (22.35%) had grade III or higher CDC morbidity. BayesNet was found to be the most effective prediction model. No dominant parameter was observed in the Bayesian net importance matrix plot. The true positive (TP) rate was 76%, false positive (FP) rate was 15.6%, recall rate (sensitivity) was 76.9%, and overall accuracy was 82.2% A receiver operating characteristic (ROC) analysis was performed to estimate CDC grade ≥ III. AUC was 0.863 with a statistical significance of p < 0.001, indicating a high degree of accuracy. Conclusions: The Bayesian network model achieved the highest accuracy compared to all other models in predicting CDC Grade ≥ III complications following epithelial ovarian cancer surgery.

Does HPV‐18 co‐infection increase the risk of cervical pathology in individuals with HPV‐16?

Abstract Objective We aimed to investigate differences between HPV‐16 mono‐ and HPV‐16/18 co‐infections in terms of cervical dysplasia and invasive cancer. Methods This multicentre, retrospective study spanned from December 2017 to December 2020, involving women who visited gynaecological oncology clinics for colposcopy with either HPV‐16 or HPV‐16/18 positivity. A total of 736 patients, 670 in Group 1 (HPV‐16 positivity) and 66 in Group 2 (HPV‐16/18 positivity), were compared for the presence of CIN2+ lesions detected by colposcopic biopsy or endocervical curettage (ECC). Exclusions included hysterectomized patients, those with prior gynaecological cancers, and patients with HPV positivity other than types 16 and 18. Results Among the included patients, 42.4% had a diagnosis of CIN2+ lesions. The cytology results demonstrated abnormal findings in 45.3% in Group 1 and 42.2% in Group 2, with no significant difference between the groups. ECC revealed CIN2+ lesion in 49 (8.7%) patients in group 1, while only 1 (1.7%) patient had CIN2+ lesion in group 2. There was no difference between 2 groups in terms of ECC result ( p  = 0.052). In group 1, 289 (43.1%) patients had CIN2+ lesion, while 23 (34.8%) patients had CIN2+ lesions in group 2. There was no difference between group 1 and 2 in terms of diagnosis of CIN2+ lesions ( p  = 0.19). Conclusion This multicentre retrospective study found no significant differences between HPV‐16 mono‐ and HPV‐16/18 co‐infections regarding cervical pathologies. Larger studies are needed to validate and further explore these findings.