Influencing factors and risk prediction model for cervical cancer recurrence

Abstract

Objectives: Cervical cancer is the most common malignant tumor in the female reproductive system worldwide. The recurrence rate for the treated cervical cancer patients is high, which seriously threatens women's lives and health. At present, the risk prediction study of cervical cancer has not been reported. Based on the influencing factors of cervical cancer recurrence, we aim to establish a risk prediction model of cervical cancer recurrence to provide a scientific basis for the prevention and treatment of cervical cancer recurrence.

Methods: A total of 4 358 cervical cancer patients admitted to the Hunan Cancer Hospital from January 1992 to December 2005 were selected as research subjects, and the recurrence of cervical cancer patients after treatment was followed up. Univariate analysis was used to analyze the possible influencing factors. Variables that were significant in univariate analysis or those that were not significant in univariate analysis but may be considered significant were included in multivariate Cox regression analysis to establish a cervical cancer recurrence risk prediction model. Line graphs was used to show the model and it was evaluated by using receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis.

Results: Univariate analysis showed that the recurrence rates of cervical cancer patients with different age, age of menarche, parity, miscarriage, clinical stage, and treatment method were significantly different (all P<0.05). Multivariate Cox regression analysis showed that RR=-0.489×(age≥55 years old)+0.481×(age at menarche >15 years old)+0.459×(number of miscarriages≥3)+0.416×(clinical stage II)+0.613×(clinical stage III/IV)+0.366×(the treatment method was surgery + chemotherapy) + 0.015×(the treatment method was chemotherapy alone). The area under the ROC curve (AUC) of the Cox risk prediction model for cervical cancer recurrence constructed was 0.736 (95% CI 0.684 to 0.789), the best prediction threshold was 0.857, the sensitivity was 0.576, and the specificity was 0.810. The accuracy of the Cox risk model constructed by this model was good. From the clinical decision curve, the net benefit value was high and the validity was good.

Conclusions: Patient age, age at menarche, miscarriages, clinical stages, and treatment methods are independent factors affecting cervical cancer recurrence. The Cox proportional hazards prediction model for cervical cancer recurrence constructed in this study can be better used for predicting the risk of cervical cancer recurrence.

Keywords: Cox regression; c ervical cancer recurrence; influencing factors; risk prediction model.

图1

宫颈癌复发的Cox风险预测模型列线图 Figure 1 Nomogram of Cox risk prediction model for cervical cancer recurrence

图2

宫颈癌复发的Cox风险模型ROC曲线 Figure 2 ROC curve of Cox risk model for cervical cancer recurrence

图3

宫颈癌复发的Cox风险模型的时间依赖性AUC联合曲线 Figure 3 Time-dependent AUC combined curve of Cox risk model for cervical cancer recurrence AUC: Area under ROC curve. Solid line is AUC with different follow-up time, and dashed line on both sides is 95% CI of AUC for different follow-up time.

图4

宫颈癌患者复发的Cox风险模型校准曲线 Figure 4 Calibration curve of Cox risk model for recurrence of cervical cancer patients The diagonal line in the figure is the reference line, and the predicted value is the actual value; the black dot line is the fitting curve, namely the event incidence. The blue line is a 95% CI.

图5

宫颈癌复发的Cox风险模型的临床决策曲线 Figure 5 Clinical decision curve of Cox risk model for cervical cancer recurrence The black dashed line indicates the net gain of the prediction model using the nomogram.