Recurrence pattern and prognostic factors for survival in cervical cancer with lymph node metastasis

Preoperative scoring system for the prediction of risk of lymph node metastasis in cervical cancer

The study aimed to develop and validate a preoperative scoring system to predict the risk of lymph node metastasis (LNM) in cervical cancer (CC). A total of 426 stage IB1-IIA1 CC patients were randomly divided into two sets. A logistic regression model was used to determine independent factors that contribute to LNM. A preoperative scoring system was developed based on beta (β) coefficients. An area under the receiver operating curve (AUC) was used to test for model discrimination. Five-year overall survival (OS) rate was 91.7%. Multivariable logistic regression analysis showed that FIGO stage, tumor size, depth of invasion on MRI, and squamous cell carcinoma antigen levels were independent risk factors in the development set (all P < 0.05). The AUCs of the scoring system for the development and validation sets were 0.833 (95% CI = 0.757-0.909) and 0.767 (95% CI = 0.634-0.891), respectively. Patients who scored 0-2, 3-5, and 6-8 were classified into low-risk, medium-risk, and high-risk groups. Predicted rates were in accord with observed rates in both sets. The 5-year OS rates of the new groups were also significantly different for the entire group, development set, and validation set (all P < 0.05). LNM affects the prognosis of CC patients. The scoring system can be used to assist in evaluating the risk of LNM in CC patients preoperatively. It is easy to obtain and can provide reference for clinical treatment decision-making.

Hematological indicator-based machine learning models for preoperative prediction of lymph node metastasis in cervical cancer

Background

Lymph node metastasis (LNM) is an important prognostic factor for cervical cancer (CC) and determines the treatment strategy. Hematological indicators have been reported as being useful biomarkers for the prognosis of a variety of cancers. This study aimed to evaluate the feasibility of machine learning models characterized by preoperative hematological indicators to predict the LNM status of CC patients before surgery.

Methods

The clinical data of 236 patients with pathologically confirmed CC were retrospectively analyzed at the Gynecology Oncology Department of the First Affiliated Hospital of Bengbu Medical University from November 2020 to August 2022. The least absolute shrinkage and selection operator (LASSO) was used to select 21 features from 35 hematological indicators and for the construction of 6 machine learning predictive models, including Adaptive Boosting (AdaBoost), Gaussian Naive Bayes (GNB), and Logistic Regression (LR), as well as Random Forest (RF), Support Vector Machines (SVM), and Extreme Gradient Boosting (XGBoost). Evaluation metrics of predictive models included the area under the receiver operating characteristic curve (AUC), accuracy, specificity, sensitivity, and F1-score.

Results

RF has the best overall predictive performance for ten-fold cross-validation in the training set. The specific performance indicators of RF were AUC (0.910, 95% confidence interval [CI]: 0.820-1.000), accuracy (0.831, 95% CI: 0.702-0.960), specificity (0.835, 95% CI: 0.708-0.962), sensitivity (0.831, 95% CI: 0.702-0.960), and F1-score (0.829, 95% CI: 0.696-0.962). RF had the highest AUC in the testing set (AUC = 0.854).

Conclusion

RF based on preoperative hematological indicators that are easily available in clinical practice showed superior performance in the preoperative prediction of CC LNM. However, investigations on larger external cohorts of patients are required for further validation of our findings.

Radiotherapy for postoperative vaginal recurrences of cervical squamous cell carcinoma: analysis of dosing and prognosis

Squamous cell carcinoma (SCC) is the most common type of vaginal recurrence in cervical cancer patients, and the role of salvage radiotherapy on these patients remains unclear. This study aimed to investigate the efficacy of salvage radiotherapy for vaginal recurrence of SCC in patients who previously underwent surgery and to explore prognostic factors associated with survival. Ninety-seven patients with histologically proven SCC who were treated for vaginal recurrence at Peking Union Medical College Hospital were identified. All patients had previously undergone surgery and received salvage radiotherapy. Factors predictive of overall survival (OS), progression-free survival (PFS), and local control (LC) were investigated. The median follow-up time was 42.5 months. The estimated 5-year OS, PFS, and LC rates were 84%, 79%, and 91%. On multivariate analysis, inguinal lymph node metastasis was significantly associated with poor OS; a tumour size ≤4 cm was associated with longer PFS (p < 0.05); the recurrence pattern was an independent predictor of LC (p < 0.05). In the 45 patients with recurrences that were paravaginal or invasive of surrounding organs, biologically equivalent doses in 2 Gy fractions of ≥72.6 Gy were independently predictive of longer LC (p < 0.05). RT is an effective treatment for postoperative vaginal recurrence in patients with cervical SCC. For patients with extravaginal recurrence, a salvage dose of ≥72.6 Gy appears to be optimal.Impact statementWhat is already known on this subject? Radiotherapy plays a critical role in treating recurrent cervical cancer, but the effectiveness of RT for vaginal recurrence in patients who previously underwent surgery remains limited. Few studies have focussed on the effect of RT dose on patient survival.What do the results of this study add? This study investigated the efficacy of RT in patients with cervical squamous cell carcinoma who experienced postoperative recurrence. Lymph node metastasis, tumour size and recurrence pattern were significantly associated with survival. Moreover, an EQD2 ≥ 72.6 Gy was independently predictive of longer LC.What are the implications of these findings for clinical practice and/or further research? RT is an effective treatment for postoperative vaginal recurrence in patients with cervical squamous cell carcinoma. For patients with extravaginal recurrence, a salvage dose of ≥72.6 Gy appears to be optimal.

Development of novel tracers for sentinel node identification in cervical cancer

Indocyanine green (ICG) with near-infrared (NIR) fluorescence imaging is used for lymphatic mapping. However, binding of ICG to blood proteins like serum albumin can shorten its retention time in sentinel lymph nodes (SLNs). Here, we investigated the efficacy and safety of a new fluorescence tracer comprising phytate and liposome (LP)-encapsulated ICG. Coadministration of phytate with LP containing phosphatidic acid promotes chelation mediated by Ca2+ in bodily fluids to enhance SLN retention. Uniformly sized LPs (100 nm) encapsulating ICG under conditions that minimized fluorescence self-quenching during storage were produced. We analyzed the behavior of the new tracer (ICG-phytate-LP) and control tracers (ICG and ICG-LP) in the lymphatic flow of mice in terms of lymph node retention time. We also tested lymphatic flow and safety in pigs that have a more human-like lymphatic system. LPs encapsulating stabilized ICG were successfully prepared. Mixing LP with phytate in the presence of Ca2+ increased both the particle size and negative surface charge. In mice, ICG-phytate-LP had the best lymph node retention, with a fluorescence intensity ratio that increased over 6 h and then decreased slowly over the next 24 h. In pigs, administration of ICG and ICG-phytate-LP resulted in no death or weight loss. There were no obvious differences between blood test results for the ICG and ICG-phytate-LP groups, and the overall safety was good. ICG-phytate-LP may be a useful new tracer for gynecological cancers that require time for lymph node identification due to a retroperitoneal approach.

Survival after sentinel node biopsy alone in early-stage cervical cancer: a systematic review

OBJECTIVE

To assess the oncologic outcomes of sentinel lymph node biopsy alone as part of surgical management in patients with early-stage cervical cancer.

METHODS

A systematic search of the literature was performed following the PRISMA checklist. MEDLINE (through PubMed), EMBASE, and Scopus databases were searched from June 1991 to May 2023. Studies of women with early-stage cervical cancer International Federation of Gynecology and Obstetrics (FIGO) 2009 stage IA-IIA, of any age or histology, and articles only in English language were included. After the removal of duplicates, only articles including sentinel node mapping alone compared with full pelvic lymphadenectomy were retained.

RESULTS

Four studies with a total of 2226 patients were included. Among these, 354 (15.9%) underwent sentinel lymph node biopsy alone. A total of 2210 (99.2%) patients had FIGO 2009 stage I disease and 1514 (68%) patients had squamous cell carcinoma. Median body mass index was 25.5 kg/m2 (range 23.5-27). Lymph vascular space invasion was present in 633 patients (34%) who underwent full lymphadenectomy and in 78 patients (22%) who underwent sentinel node biopsy alone. The results of the survival analysis showed that there was no significant difference in the 3-year progression-free survival rates of patients who underwent either sentinel biopsy alone or lymphadenectomy. Three-year recurrence-free survival was 93.1% (95% CI 28.3% to 64.7%) for patients who underwent sentinel node biopsy alone and 92.5% (95% CI 39.0% to 53.4%) for patients who underwent sentinel node biopsy and lymphadenectomy (p=0.773).

CONCLUSIONS

In patients with early-stage cervical cancer, performing sentinel lymph node biopsy alone compared with pelvic lymphadenectomy does not appear to independently confer a higher risk or recurrence.

Identification of lymph node metastasis in pre-operation cervical cancer patients by weakly supervised deep learning from histopathological whole-slide biopsy images

BACKGROUND

Lymph node metastasis (LNM) significantly impacts the prognosis of individuals diagnosed with cervical cancer, as it is closely linked to disease recurrence and mortality, thereby impacting therapeutic schedule choices for patients. However, accurately predicting LNM prior to treatment remains challenging. Consequently, this study seeks to utilize digital pathological features extracted from histopathological slides of primary cervical cancer patients to preoperatively predict the presence of LNM.

METHODS

A deep learning (DL) model was trained using the Vision transformer (ViT) and recurrent neural network (RNN) frameworks to predict LNM. This prediction was based on the analysis of 554 histopathological whole-slide images (WSIs) obtained from Qilu Hospital of Shandong University. To validate the model's performance, an external test was conducted using 336 WSIs from four other hospitals. Additionally, the efficiency of the DL model was evaluated using 190 cervical biopsies WSIs in a prospective set.

RESULTS

In the internal test set, our DL model achieved an area under the curve (AUC) of 0.919, with sensitivity and specificity values of 0.923 and 0.905, respectively, and an accuracy (ACC) of 0.909. The performance of the DL model remained strong in the external test set. In the prospective cohort, the AUC was 0.91, and the ACC was 0.895. Additionally, the DL model exhibited higher accuracy compared to imaging examination in the evaluation of LNM. By utilizing the transformer visualization method, we generated a heatmap that illustrates the local pathological features in primary lesions relevant to LNM.

CONCLUSION

DL-based image analysis has demonstrated efficiency in predicting LNM in early operable cervical cancer through the utilization of biopsies WSI. This approach has the potential to enhance therapeutic decision-making for patients diagnosed with cervical cancer.

CircRNA hsa_circ_0001627 aggravates cervical cancer progression through upregulation of FNDC3B and activating PI3K/mTOR signaling pathway

Circular RNAs (CircRNAs) are key regulators in the development and progression of human cancers. However, the biological roles and mechanisms of circRNAs in gastric cancer (GC) remain largely unknown. Analyzing circRNA microarray dataset (GSE102686) and clinical specimens, a novel circRNA termed hsa_circ_0001627, was identified and it was highly expressed in CC cancerous tissues and cells, and was associated with poor clinical outcomes. Functionally, hsa_circ_0001627 silencing impaired the malignant progression of CC cells and the growth of CC xenografts in nude mice. Mechanistically, hsa_circ_0001627 acted as a miR-1225-5p sponge, thus indirectly regulating FNDC3B and leading to the activation of PI3K/mTOR signaling pathway. Collectively, the present study indicates that hsa_circ_0001627 regulates miR-1225-5p/FNDC3B/PI3K/mTOR axis and functions as an oncogene in CC progression, suggesting the potential therapeutic use of hsa_circ_0001627 in CC treatment.

Machine learning applied to MRI evaluation for the detection of lymph node metastasis in patients with locally advanced cervical cancer treated with neoadjuvant chemotherapy

PURPOSE

Concurrent cisplatin-based chemotherapy and radiotherapy (CCRT) plus brachytherapy is the standard treatment for locally advanced cervical cancer (LACC). Platinum-based neoadjuvant chemotherapy (NACT) followed by radical hysterectomy is an alternative for patients with stage IB2-IIB disease. Therefore, the correct pre-treatment staging is essential to the proper management of this disease. Pelvic magnetic resonance imaging (MRI) is the gold standard examination but studies about MRI accuracy in the detection of lymph node metastasis (LNM) in LACC patients show conflicting data. Machine learning (ML) is emerging as a promising tool for unraveling complex non-linear relationships between patient attributes that cannot be solved by traditional statistical methods. Here we investigated whether ML might improve the accuracy of MRI in the detection of LNM in LACC patients.

METHODS

We analyzed retrospectively LACC patients who underwent NACT and radical hysterectomy from 2015 to 2020. Demographic, clinical and MRI characteristics before and after NACT were collected, as well as information about post-surgery histopathology. Random features elimination wrapper was used to determine an attribute core set. A ML algorithm, namely Extreme Gradient Boosting (XGBoost) was trained and validated with tenfold cross-validation. The performances of the algorithm were assessed.

RESULTS

Our analysis included n.92 patients. FIGO stage was IB2 in n.4/92 (4.3%), IB3 in n.42/92 (45%), IIA1 in n.1/92 (1.1%), IIA2 in n.16/92 (17.4%) and IIB in n.29/92 (31.5%). Despite detected neither at pre-treatment and post-treatment MRI in any patients, LNM occurred in n.16/92 (17%) patients. The attribute core set used to train ML algorithms included grading, histotypes, age, parity, largest diameter of lesion at either pre- and post-treatment MRI, presence/absence of fornix infiltration at pre-treatment MRI and FIGO stage. XGBoost showed a good performance (accuracy 89%, precision 83%, recall 78%, AUROC 0.79).

CONCLUSIONS

We developed an accurate model to predict LNM in LACC patients in NACT, based on a ML algorithm requiring few easy-to-collect attributes.

Whether individualized dose escalation should be recommended for lymph nodes with different sizes in the definitive radiotherapy of cervical cancer?

Background and purpose

Dose escalation for positive node maybe improve the regional control of patients with node-positive cervical cancer, but the optimal dose for nodes of different sizes remains controversial. The purpose of this study was to explore the individualized dose escalation for lymph nodes (LNs) with different sizes in the definitive radiotherapy of cervical cancer.

Methods

A total of 1002 cervical cancer patients with the International Federation of Gynecology and Obstetrics (FIGO 2009) stage IB1–IVA, who were treated by definitively radiotherapy between September 2013 and December 2016 were enrolled. All LNs identified by computed tomography/magnetic resonance imaging (CT/MRI) were assigned into three groups according to the short diameters of < 1 cm, 1–2 cm or ≥ 2 cm at pretreatment.

Results

In total, 580 patients with 1310 LNs were detected. The nodal control rate in groups of LNs < 1 cm, 1–2 cm and ≥ 2 cm was 99.4%, 96%, and 75.9%, respectively (P = 0.000). Among LNs < 1 cm, the control, overall survival (OS) and progression-free survival (PFS) rates did not significantly differ among three dose-based groups (≤ 50.4 Gy, 50.4–60 Gy, > 60 Gy) (control rate, 99.4% vs. 99.3% vs. 100%, P = 0.647) (5-year OS, 76.2% vs. 79% vs. 81.6%, P = 0.682) (5-year PFS, 74.1% vs. 73.9% vs. 78.9% P = 0.713). Among LNs of 1–2 cm, the control and PFS rates were significantly higher in the group of dose ≥ 55 Gy than the group of dose < 55 Gy (control rate, 98% vs. 93.6%, P = 0.028) (5-year PFS, 69.6% vs. 56.7%, P = 0.025). However, this did not cause a significant difference for 5-year OS rate (72.6% vs. 68.3%, P = 0.5). Among LNs ≥ 2 cm, the control, OS, and PFS rates were higher in the group of dose ≥ 55 Gy than the group of dose < 55 Gy, while no significant difference was found (control rate, 82.1% vs. 63.2%, P = 0.107) (5-year OS, 60.6% vs. 37.5%, P = 0.141) (5-year PFS, 51.5% vs.37.5%, P = 0.232).

Conclusions

Radiation dose escalation is not necessary for LNs < 1 cm, and dose escalation of 55 Gy is enough for LNs of 1–2 cm.

Analysis of Treatment Outcomes and Prognosis After Concurrent Chemoradiotherapy for Locally Advanced Cervical Cancer

The aims of this study were to investigate the short-term and long-term efficacies and chronic radiotoxicity of concurrent chemoradiotherapy (CCRT) combined with image-guided adaptive brachytherapy (IGABT) in patients with locally advanced cervical cancer (LACC) and identify prognostic factors in this patient population. The clinical data of 204 patients with cervical cancer who completed CCRT and subsequent brachytherapy in our hospital between February 2015 and March 2017 were retrospectively analyzed. Short-term and long-term outcomes, chronic radiotoxicity, and prognostic factors were assessed. The median follow-up was 61.1 months. The short-term objective response (OR) rate was 85%. Lymph node metastasis before treatment was an independent predictor of OR (HR = 6.290, 95% CI: 2.211-17.897, p = 0.001). Fifty-two patients developed recurrence, with a median recurrence-free survival of 9.9 months (range, 2.4-52.2 months) and a post-recurrence survival of 12.1 months (range, 2.9-58.1 months). At 3 years, the cumulative incidence of overall recurrence was 26% (95% CI: 17-36). Multivariate analysis showed that Stage IIIB (HR = 2.332, 95% CI: 1.195-4.551, p = 0.013; reference, Stage IIB) and lymph node metastasis (HR = 4.462, 95% CI: 2.365-8.419, p < 0.001) were significant independent predictors of recurrence. Fifty-three patients developed chronic radiation proctitis (CRP). The incidence of severe CRP was approximately 5%, and the average rectal D2cm3 accumulation in patients with severe CRP was 73.4 Gy which is 3.9 Gy higher than that in patients without CRP (p = 0.013). At 4 years, the overall survival (OS) and disease-free survival rates were 65% and 62%, respectively, and lymph node metastasis before treatment was an independent prognostic risk factor for OS. The short-term and long-term efficacies of CCRT combined with IGABT for the treatment of LACC patients were relatively satisfactory. However, the short-term and long-term efficacies of patients with lymph node metastasis before treatment were poor. For patients with lymph node metastasis before treatment, more active individualized treatment strategies should be adopted. When designing a radiotherapy plan, it is necessary to strictly limit the rectal D2cm3 accumulation to prevent serious CRP.

Pretreatment Radiologically Enlarged Lymph Nodes as a Significant Prognostic Factor in Clinical Stage IIB Cervical Cancer: Evidence from a Taiwanese Tertiary Care Center in Reaching Consensus

The incidence of lymph node (LN) involvement and its prognostic value based on radiological imaging in stage IIB cervical cancer (CC) remains unclear, and evidence regarding oncological outcomes of patients with stage IIB CC with LN metastases is limited. In this study we retrospectively reviewed the incidence and prognostic significance of pretreatment radiologic LN status in 72 patients with clinical stage IIB CC (FIGO 2009), with or without radiologic evidence of LN enlargement. An enlarged LN was defined as a diameter > 10 mm on CT/MRI. Progression-free survival (PFS) and overall survival (OS) were assessed. Radiologic LN enlargement of >10 mm was observed in 45.8% of patients with stage IIB CC. PFS (p = 0.0088) and OS rates (p = 0.0032) were significantly poorer in the LN group (n = 33) than in the non-LN group (n = 39). Univariate Cox analysis revealed that LN > 10 mm contributed to a higher rate of recurrence and mortality. In conclusion, nearly half of the patients with clinical stage IIB CC had enlarged LNs (>10 mm) identified during pretreatment radiologic evaluation, which negatively impacted prognosis. Our findings highlight the need to incorporate CT- or MRI-based LN assessment before treatment for stage IIB CC.

Development of a Machine Learning-Based Predictive Model for Lung Metastasis in Patients With Ewing Sarcoma

BACKGROUND

This study aimed to develop and validate machine learning (ML)-based prediction models for lung metastasis (LM) in patients with Ewing sarcoma (ES), and to deploy the best model as an open access web tool.

METHODS

We retrospectively analyzed data from the Surveillance Epidemiology and End Results (SEER) Database from 2010 to 2016 and from four medical institutions to develop and validate predictive models for LM in patients with ES. Patient data from the SEER database was used as the training group (n = 929). Using demographic and clinicopathologic variables six ML-based models for predicting LM were developed, and internally validated using 10-fold cross validation. All ML-based models were subsequently externally validated using multiple data from four medical institutions (the validation group, n = 51). The predictive power of the models was evaluated by the area under receiver operating characteristic curve (AUC). The best-performing model was used to produce an online tool for use by clinicians to identify ES patients at risk from lung metastasis, to improve decision making and optimize individual treatment.

RESULTS

The study cohort consisted of 929 patients from the SEER database and 51 patients from multiple medical centers, a total of 980 ES patients. Of these, 175 (18.8%) had lung metastasis. Multivariate logistic regression analysis was performed with survival time, T-stage, N-stage, surgery, and bone metastasis providing the independent predictive factors of LM. The AUC value of six predictive models ranged from 0.585 to 0.705. The Random Forest (RF) model (AUC = 0.705) using 4 variables was identified as the best predictive model of LM in ES patients and was employed to construct an online tool to assist clinicians in optimizing patient treatment. (https://share.streamlit.io/liuwencai123/es_lm/main/es_lm.py).

CONCLUSIONS

Machine learning were found to have utility for predicting LM in patients with Ewing sarcoma, and the RF model gave the best performance. The accessibility of the predictive model as a web-based tool offers clear opportunities for improving the personalized treatment of patients with ES.

Development and Validation of Novel Nomograms to Predict the Overall Survival and Cancer-Specific Survival of Cervical Cancer Patients With Lymph Node Metastasis

Objective

The objective of this study was to establish and validate novel individualized nomograms for predicting the overall survival (OS) and cancer-specific survival (CSS) in cervical cancer patients with lymph node metastasis.

Methods

A total of 2,956 cervical cancer patients diagnosed with lymph node metastasis (American Joint Committee on Cancer, AJCC N stage=N1) between 2000 and 2018 were included in this study. Univariate and multivariate Cox regression models were applied to identify independent prognostic predictors, and the nomograms were established to predict the OS and CSS. The concordance index (C-index), calibration curves, and receiver operating characteristic (ROC) curves were applied to estimate the precision and discriminability of the nomograms. Decision-curve analysis (DCA) was used to assess the clinical utility of the nomograms.

Results

Tumor size, log odds of positive lymph nodes (LODDS), radiotherapy, surgery, T stage, histology, and grade resulted as significant independent predictors both for OS and CSS. The C-index value of the prognostic nomogram for predicting OS was 0.788 (95% CI, 0.762–0.814) and 0.777 (95% CI, 0.758–0.796) in the training and validation cohorts, respectively. Meanwhile, the C-index value of the prognostic nomogram for predicting CSS was 0.792 (95% CI, 0.767–0.817) and 0.781 (95% CI, 0.764–0.798) in the training and validation cohorts, respectively. The calibration curves for the nomograms revealed gratifying consistency between predictions and actual observations for both 3- and 5-year OS and CSS. The 3- and 5-year area under the curves (AUCs) for the nomogram of OS and CSS ranged from 0.781 to 0.828. Finally, the DCA curves emerged as robust positive net benefits across a wide scale of threshold probabilities.

Conclusion

We have successfully constructed nomograms that could predict 3- and 5-year OS and CSS of cervical cancer patients with lymph node metastasis and may assist clinicians in decision-making and personalized treatment planning.

Nomogram Predicting Overall Survival in Patients with FIGO II to III Squamous Cell Cervical Carcinoma Under Radical Radiotherapy: A Retrospective Analysis Based on 2018 FIGO Staging

Purpose

To present a nomogram to predict overall survival in patients with FIGO-2018 II to III squamous cell cervical carcinoma undergoing radical radiotherapy.

Patients and Methods

Patients diagnosed with FIGO-2018 II to III squamous cell cervical cancer between December 2013 and December 2014 were analyzed retrospectively. The optimal cutoff point for tumor length and width were determined by R package. We identified prognostic factors by univariate and multivariate Cox proportional-hazard regression, then built a nomogram to visualize the prediction model. Our model was compared to the 2018 FIGO staging prediction model. Harrell’s concordance index, receiver operating characteristic curve, calibration plot were used to evaluate the discriminability and accuracy of the predictive models, and decision curve analysis (DCA) was used to show the net benefits.

Results

Data from 469 patients were included in the final analyses. The cutoff values of tumor length and width were 5.10 cm and 4.13 cm, respectively. Four independent prognostic variables—tumor length, tumor width, lower one-third vaginal involvement, and lymph node metastases—were used to establish the nomogram. The C-index of the nomogram was 0.71 (95%, CI = 0.66–0.77), which was better than that of the 2018 FIGO stage prediction model (C-index: 0.62, 95% CI = 0.58–0.66, p = 0.009). The calibration plot of the nomogram was a good fit for both 3-year and 5-year overall survival predictions. And DCA curves showed that net benefits for our model were higher than FIGO-2018 staging system.

Conclusion

A clinically useful nomogram for calculating overall survival probability in FIGO-2018 II to III squamous cell cervical cancer patients who had received radical radiotherapy was developed. Tumor length, tumor width, lower one-third vaginal involvement, and lymph node metastases were found to be independent prognostic factors. Our model performed better than the 2018 FIGO staging model. The findings could help clinicians in China to predict the survival of these patients in clinical care and research.