Prognostic Variables of Younger-Aged Cervical Carcinoma Patients: A Retrospective Study

Abstract

Purpose. The prevalence of carcinoma of the cervix is increasing in younger women. This study aimed to evaluate the sociodemographic, pathological, and clinical features, prognosis, and treatment of women aged ≤35 years with carcinoma of the cervix (CC). Methods and Materials. We retrospectively analysed the clinical information of 352 younger women with carcinoma of the cervix aged ≤35 years at the Gynaecological Oncology Department of Zhengzhou University People’s Hospital from April 2000 to January 2018. The overall survival was evaluated with the Kaplan–Meier model, and the log-ranked analysis was compared with the univariate analysis to determine prognostic survival-related risk factors. Cox Proportional Hazards analysis was further used in analysing parameters correlated with survival after univariate analysis. A p value <0.05 was considered statistically significant. SPSS version 23.0 was used for the data analysis. Results. The most frequent histopathological type observed in the selected 352 younger women was squamous cell carcinoma (SCC) (n = 221, 62.9%), adenocarcinoma (n = 125, 35.5%), and adenosquamous carcinoma (n = 6, 1.7%). The 5-year overall survival time was 80.5%. The prognostic risk factors discovered through univariate analysis were tumour stage (IA1-IIB vs. IIIA-IVA) (89.2% vs. 35.1%: p value = 0.002), histological type (SCC vs. non-SCC) (95.7% vs. 56.2%: p value = 0.001), surgical margin (negative vs. positive) (90.9% vs. 41.2%: p value = 0.001), and pelvic lymph node metastasis (no vs. yes) (93.4% vs. 39.2%: p value = .001). The Cox proportional hazards test demonstrated that lymph node metastases ([HR] = 2.924, 95% CI: 1.432–7.426; p = 0.014 ), tumour stage IIIA-IVA ([HR] = 3.765, 95% CI: 1.398–9.765; p = 0.016 ), and surgical margin ([HR] = 2.167, 95% CI: 1.987–9.554; p = 0.019 ) were independent prognostic risk factors for overall survival in younger women with cervical carcinoma. Conclusion. In conclusion, the status of lymph node metastases, tumour stage, and surgical margin and the type of histopathology substantially influence the rate of survival.

Development and validation of a deep learning survival model for cervical adenocarcinoma patients

“…Most prognostication studies for cervical AC were developed with multivariate analysis, Cox proportional hazards (CPH) regression analysis, and the Kaplan-Meier (K-M) survival curve model [8][9][10]. However, these traditional methods have been proven to be less accurate in the survival prediction of some cancers than those new models like the linear multi-task (LMT) model, random survival forest (RSF) model, support vector machine (SVM) model and deep learning (DL) model [11,12].…”