Oktar O, et al. J Gynecol Oncol. 2023 Dec;35:e39. https://doi.org/10.3802/jgo.2024.35.e39

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.

Background: It is crucial to predict the response to chemotherapy and identify prognostic markers for recurrence and survival in patients with epithelial ovarian cancer (EOC), in order to effectively manage patient care. The CA-125 elimination rate constant K (KELIM) has recently been developed as a means of assessing the chemotherapy response and has been tested mainly in patients enrolled in randomized controlled trials. The objective of this study was to investigate whether the KELIM score is a prognostic marker for progression-free survival (PFS) and overall survival (OS) in EOC, utilizing its role in predicting the chemotherapy response in real-life settings. Method: Demographic, surgical, and survival data of patients with EOC operated on in Antalya Training and Research Hospital between January 2015 and December 2021 were obtained from the electronic gynecological oncology clinic database system and analyzed retrospectively. Results: A total of 102 patients with EOC were included; 30 patients (29.4%) had a KELIM score ≥ 1 and 72 (70.6%) patients had a KELIM score < 1. In the group with a KELIM score < 1, recurrence and refractory disease occurred in 49 patients, while it was 11 patients in the group with a KELIM score ≥ 1 (p = 0.004). PFS was 12 months and 32 months in the groups with KELIM scores of <1 and ≥1, respectively (p = 0.012). There was no difference between groups regarding OS (p = 0.139). In the whole group, KELIM score (<1 vs. ≥1) and type of surgery (IDS vs. PDS) were found to be independent prognostic factors for PFS (RR = 0.44; 95%CI: 0.22–0.88; p = 0.021 and RR = 2.97; 95%CI: 1.76–5.01; p < 0.001, respectively). Conclusion: We found that a favorable KELIM score was associated with better PFS in all groups of patients undergoing surgery for EOC in a real-life setting. With the increasing number of studies, the KELIM score will play an important role in providing better guidance to clinicians at the initial presentation of patients and in subsequent treatment planning.

Background/Objectives: This study was designed to investigate the relationship between peripheral hematological inflammation markers, namely, neutrophil/lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), monocyte/lymphocyte ratio (MLR), systemic immune inflammation index (SII), and systemic inflammatory response index (SIRI) and high-grade cervical lesions (CIN2+). Methods: A retrospective cohort analysis was conducted on 358 patients who underwent cervical excision procedures. Patients were divided into two groups: <CIN2 and CIN2+. Preoperative complete blood count data were used to calculate the inflammation indices. HPV genotypes were also recorded. Logistic regression and ROC analyses were performed to evaluate the predictive performance. Results: CIN2+ lesions were detected in 69.6% of participants. In the univariate analysis, only age and HPV 16 positivity (p < 0.005) showed a significant association with the presence of CIN2+. NLR, PLR, MLR, SII, and SIRI values did not show significant differences between groups (all p > 0.05). In the multivariate analysis, increasing age was independently associated with a decrease in the risk of CIN2+ (OR = 0.96, 95% CI: 0.94–0.99), while HPV 16 positivity was associated with an increase in risk (OR = 2.44, 95% CI: 1.43–4.18). ROC analysis showed that combining age and HPV 16 status improved the specificity (85.1%) of predicting CIN2+ compared to using age alone (42.2%). Conclusions: Peripheral haematological inflammation markers (NLR, PLR, MLR, SII, and SIRI) did not show predictive value in predicting CIN2+ lesions. However, age and HPV 16 infection were found to be independent predictors. These findings suggest that haematological indices may reflect systemic inflammatory responses but are not sufficient on their own for the detection of CIN2+. HPV genotyping is of critical importance for the early detection of high-grade lesions.

Background: To identify prognostic factors related to survival in patients with early-stage cervical cancer treated with radical surgery in six high-volume gynecologic oncology centers in Turkey. Methods: This retrospective analysis examined a cohort of 612 patients diagnosed with cervical cancer who underwent type II/III radical hysterectomy and pelvic lymphadenectomy, with or without para-aortic lymphadenectomy at six gynecologic oncology centers. A total of 537 patients between 1993 and 2023 were included. According to the 2009 FIGO staging system, 411 patients (76.5%) were stage IB1, 76 (14.2%) were stage IB2, 40 (4.7%) were stage IIA1, and 10 (1.9%) were stage IIA2. Patients underwent either type II or type III radical hysterectomy with pelvic lymphadenectomy, with para-aortic lymphadenectomy performed in 93.1% of cases. Among the 537 patients, 258 (48%) underwent type II radical hysterectomy and 279 (52%) underwent type III. Univariate and multivariate analyses of 5-year overall survival (OS) and 5-year disease-free survival (DFS) were performed. Results: In the entire cohort, 258 (48%) patients underwent radical surgery alone, while 279 (52%) patients underwent radical surgery followed by adjuvant therapy. The 5-year DFS and 5-year OS rates were 85.3% and 98.4%, respectively. In the multivariate logistic analysis, lymph node metastasis was identified as an independent prognostic factor for DFS and OS. Conclusions: Lymph node metastasis was the most important prognostic factor for survival in this large multicenter Turkish cohort. These findings highlight the prognostic value of nodal status, stromal invasion, margin status, and LVSI, while underscoring the importance of tailored adjuvant treatment strategies.