〔Abstract〕 To explore the effect of tumor cell perineural invasion on the prognosis of cervical cancer and the early predictive factors of perineural invasion in patients with cervical cancer. Methods A retrospective analysis was conducted on the clinical, pathological, and survival data of 551 patients with cervical cancer. These patients were categorized into a survival group (n=477) and a death group (n=74). The baseline characteristics of the two groups were compared using independent samples t-tests, Wilcoxon rank-sum tests, and chi-square tests. Multivariate binary logistic stepwise regression analysis was employed to identify independent risk factors associated with mortality. In addition, univariate logistic regression analysis was performed to determine predictive factors for perineural invasion. A predictive model for perineural invasion in cervical cancer was subsequently developed based on the multivariate regression equation, and its predictive accuracy was assessed using the ROC curve. Results In the basic data of cervical cancer patients, the high level of perineural invasion, lymphatic metastasis and postoperative pathological stage in pathological data had an impact on the poor prognosis of patients (P<0.05), Lymphovascular space invasion, parametrial involvement, and tumor invasion depth ≥1/2 were identified as significant predictors of PNI. The predictive value was the best in the multivariate model (Area under the curve =0.80). Conclusion Perineural invasion is an independent risk factor for poor prognosis of cervical cancer patients, and the occurrence of perineural invasion can be effectively predicted by the constructed multivariate mode.