Development and validation of a new clinical staging system to predict survival for esophageal squamous cell carcinoma patients: Application of the nomogram

A nomogram for predicting overall survival in oral squamous cell carcinoma: a SEER database and external validation study

Purpose

Oral squamous cell carcinoma (OSCC) often presents with unsatisfactory survival outcomes, especially in advanced stages. This study aimed to develop and validate a nomogram incorporating demographic, clinicopathologic, and treatment-related factors to improve the prediction of overall survival (OS) in OSCC patients.

Methods

Data from 15,204 OSCC patients in a US database were retrospectively utilized to construct a prognostic model and generate a nomogram. External validation was performed using an independent cohort of 359 patients from a specialized cancer center in China. Prognostic factors were identified using Cox regression analysis and incorporated into the nomogram. Model performance was evaluated by concordance index (C-index), time-dependent area under the receiver operating characteristic curves (AUC), calibration plots, and decision curve analysis (DCA). A risk stratification system was developed to classify patients into high- and low-risk groups.

Results

Age, sex, primary tumor site, T and N staging, and treatment modalities (including surgery, chemotherapy, and radiotherapy) were found to be independent prognostic factors. The nomogram achieved a C-index of 0.727 in the training set and 0.6845 in the validation set, outperforming the conventional TNM staging system. The nomogram's superior predictive accuracy was confirmed by higher AUC values, better calibration, and improved clinical utility as demonstrated by DCA. Risk stratification, based on the nomogram, distinguished patients into distinct prognostic groups with significant OS differences.

Conclusions

This nomogram provides an effective, personalized tool for predicting OS in OSCC. It offers clinicians a valuable aid for treatment decision-making and improves patient management.

A nomogram for predicting cancer-specific survival in patients with locally advanced unresectable esophageal cancer: development and validation study

Background

Immunotherapy research for esophageal cancer is progressing rapidly, particularly for locally advanced unresectable cases. Despite these advances, the prognosis remains poor, and traditional staging systems like AJCC inadequately predict outcomes. This study aims to develop and validate a nomogram to predict cancer-specific survival (CSS) in these patients.

Methods

Clinicopathological and survival data for patients diagnosed between 2010 and 2021 were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. Patients were divided into a training cohort (70%) and a validation cohort (30%). Prognostic factors were identified using the Least Absolute Shrinkage and Selection Operator (LASSO) regression. A nomogram was constructed based on the training cohort and evaluated using the concordance index (C-index), net reclassification improvement (NRI), integrated discrimination improvement (IDI), calibration plots, and area under the receiver operating characteristic curve (AUC). Kaplan-Meier survival curves were used to validate the prognostic factors.

Results

The study included 4,258 patients, and LASSO-Cox regression identified 10 prognostic factors: age, marital status, tumor location, tumor size, pathological grade, T stage, American Joint Committee on Cancer (AJCC) stage, SEER stage, chemotherapy, and radiotherapy. The nomogram achieved a C-index of 0.660 (training set) and 0.653 (validation set), and 1-, 3-, and 5-year AUC values exceeded 0.65. Calibration curves showed a good fit, and decision curve analysis (DCA), IDI, and NRI indicated that the nomogram outperformed traditional AJCC staging in predicting prognosis.

Conclusions

We developed and validated an effective nomogram model for predicting CSS in patients with locally advanced unresectable esophageal cancer. This model demonstrated significantly superior predictive performance compared to the traditional AJCC staging system. Future research should focus on integrating emerging biomarkers, such as PD-L1 expression and tumor mutational burden (TMB), into prognostic models to enhance their predictive accuracy and adapt to the evolving landscape of immunotherapy in esophageal cancer management.

Development of a nomogram for overall survival in patients with esophageal carcinoma: A prospective cohort study in China

BACKGROUND

Esophageal carcinoma (EC) presents a significant public health issue in China, with its prognosis impacted by myriad factors. The creation of a reliable prognostic model for the overall survival (OS) of EC patients promises to greatly advance the customization of treatment approaches.

AIM

To create a more systematic and practical model that incorporates clinically significant indicators to support decision-making in clinical settings.

METHODS

This study utilized data from a prospective longitudinal cohort of 3127 EC patients treated at Chongqing University Cancer Hospital between January 1, 2018, and December 12, 2020. Utilizing the least absolute shrinkage and selection operator regression alongside multivariate Cox regression analyses helped pinpoint pertinent variables for constructing the model. Its efficacy was assessed by concordance index (C-index), area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis (DCA).

RESULTS

Nine variables were determined to be significant predictors of OS in EC patients: Body mass index (BMI), Karnofsky performance status, TNM stage, surgery, radiotherapy, chemotherapy, immunotherapy, platelet-to-lymphocyte ratio, and albumin-to-globulin ratio (ALB/GLB). The model demonstrated a C-index of 0.715 (95%CI: 0.701-0.729) in the training cohort and 0.711 (95%CI: 0.689-0.732) in the validation cohort. In the training cohort, AUCs for 1-year, 3-year, and 5-year OS predictions were 0.773, 0.787, and 0.750, respectively; in the validation cohort, they were 0.772, 0.768, and 0.723, respectively, illustrating the model's precision. Calibration curves and DCA verified the model's predictive accuracy and net benefit.

CONCLUSION

A novel prognostic model for determining the OS of EC patients was successfully developed and validated to help clinicians in devising individualized treatment schemes for EC patients.

Development of a prognostic nomogram and risk stratification system for elderly patients with esophageal squamous cell carcinoma undergoing definitive radiotherapy: a multicenter retrospective analysis (3JECROG R-03 A)

BACKGROUND

Our goal is to develop a nomogram model to predict overall survival (OS) for elderly esophageal squamous cell carcinoma (ESCC) patients receiving definitive radiotherapy (RT) or concurrent chemoradiotherapy (CRT), aiding clinicians in personalized treatment planning with a risk stratification system.

METHODS

A retrospective study was conducted on 718 elderly ESCC patients treated with RT or CRT at 10 medical centers (3JECROG) from January 2004 to November 2016. We identified independent prognostic factors using univariate and multifactorial Cox regression to construct a nomogram model. Its effectiveness was evaluated using concordance statistics (C-index), area under the curve (AUC), net reclassification index (NRI), and integrated discrimination improvement (IDI), and compared against the AJCC staging. Additionally, decision curve analysis (DCA) assessed the model's clinical benefit. Patients were stratified into low, intermediate, and high-risk groups using the nomogram, and their prognoses in various disease stages were analyzed.

RESULTS

Significant prognostic factors identified included diabetes, tumor volume (GTVp), tumor length, location, and clinical stages (T, N, M), and RT response. Multivariate analysis confirmed these as independent factors for OS. The nomogram outperformed AJCC staging in prediction accuracy and discrimination, evidenced by a higher C-index, better AUC, and significant NRI and IDI values. Patients categorized by the nomogram demonstrated distinct 5-year OS rates, with a higher C-index than AJCC staging (0.597 vs. 0.562) .

CONCLUSIONS

The study identified key prognostic factors for elderly ESCC patients receiving RT or CRT. The nomogram model, based on these factors, showed enhanced prediction performance, discrimination, and clinical utility compared to AJCC staging. This risk stratification provided more accurate survival predictions and aided in personalized risk management.

Consensus Clustering Analysis Based on Enhanced-CT Radiomic Features: Esophageal Squamous Cell Carcinoma patients' 3-Year Progression-Free Survival

RATIONALE AND OBJECTIVES

To assess the efficacy of consensus cluster analysis based on CT radiomics in stratifying risk and predicting postoperative progression-free survival (PFS) in patients diagnosed with esophageal squamous cell carcinoma (ESC).

MATERIALS AND METHODS

We conducted a retrospective study involving 546 patients diagnosed with ESC between January 2016 and March 2021. All patients underwent preoperative enhanced CT examinations. From the enhanced CT images, radiomics features were extracted, and a consensus clustering algorithm was applied to group the patients based on these features. Statistical analysis was performed to examine the relationship between the clustering results and gene protein expression, histopathological features, and patients' 3-year PFS. We applied the Kruskal-Wallis test for continuous data, chi-square or Fisher's exact tests for categorical data, and the log-rank test for PFS.

RESULTS

This study identified four groups: Cluster 1 (n = 100, 18.3%), Cluster 2 (n = 197, 36.1%), Cluster 3 (n = 205, 37.5%), and Cluster 4 (n = 44, 8.1%). The cancer gene Breast Cancer Susceptibility Gene 1 (BRCA1) was most highly expressed in Cluster 4 (75%), showing significant differences between the four subtypes with a P-value of 0.035. The expression of programmed death-1 (PD-1) was highest in Cluster 1 (51%), with a P-value of 0.022. Vascular invasion occurred most frequently in Cluster 2 (28.9%), with a P-value of 0.022. The majority of patients with stage T3-4 were in Cluster 2 (67%), with a P-value of 0.003. Kaplan-Meier survival analysis revealed significant differences in PFS between the four groups (P = 0.013). Among them, patients in Cluster 1 had the best prognosis, while those in Cluster 2 had the worst.

CONCLUSION

This study highlights the effectiveness of consensus clustering analysis based on enhanced CT radiomics features in identifying associations between radiomics features, histopathological characteristics, and prognosis in different clusters. These findings provide valuable insights for clinicians in accurately and effectively evaluating the prognosis of esophageal cancer.

Design Appropriate Incision Length for Uniportal Video-Assisted Thoracoscopic Lobectomy: Take into Account Safety and Minimal Invasiveness

BACKGROUND

 There is no criterion on the length of the uniportal video-assisted thoracoscopic surgery (UVATS) incision when performing lobectomy. We aimed to develop a nomogram to assist surgeons in designing incision length for different individuals.

METHODS

 A cohort consisting of 290 patients were enrolled for nomogram development. Univariate and multivariate logistic regression analyses were performed to identify candidate variables among perioperative characteristics. C-index and calibration curves were utilized for evaluating the performance of the nomogram. Short-term outcomes of nomogram-predicted high-risk patients were compared between long incision group and conventional incision group.

RESULTS

 Of 290 patients, 150 cases (51.7%) were performed incision extension during the surgery. Age, tumor size, and tumor location were identified as candidate variables related with intraoperative incision extension and were incorporated into the nomogram. C-index of the nomogram was 0.75 (95% confidence interval: 0.6961-0.8064), indicating the good predictive performance. Calibration curves presented good consistency between the nomogram prediction and actual observation. Of high-risk patients identified by the nomogram, the long incision group (n = 47) presented shorter duration of operation (p = 0.03), lower incidence of total complications (p = 0.01), and lower incidence of prolonged air leak (p = 0.03) compared with the conventional incision group (n = 55).

CONCLUSION

 We developed a novel nomogram for predicting the risk of intraoperative incision extension when performing uniportal video-assisted thoracoscopic lobectomy. This model has the potential to assist clinicians in designing the incision length preoperatively to ensure both safety and minimal invasiveness.

A novel staging system based on deep learning for overall survival in patients with esophageal squamous cell carcinoma

PURPOSE

We developed DeepSurv, a deep learning approach for predicting overall survival (OS) in patients with esophageal squamous cell carcinoma (ESCC). We validated and visualized the novel staging system based on DeepSurv using data from multiple cohorts.

METHODS

Totally 6020 ESCC patients diagnosed from January 2010 to December 2018 were included in the present study from the Surveillance, Epidemiology, and End Results database (SEER), randomly assigned to the training and test cohorts. We developed, validated and visualized a deep learning model that included 16 prognostic factors; then a novel staging system was further constructed based on the total risk score derived from the deep learning model. The classification performance at 3-year and 5-year OS was assessed by the receiver-operating characteristic (ROC) curve. Calibration curve and the Harrell's concordance index (C-index) were also used to comprehensively assess the predictive performance of the deep learning model. Decision curve analysis (DCA) was utilized to assess the clinical utility of the novel staging system.

RESULTS

A more applicable and accurate deep learning model was established, which outperformed the traditional nomogram in predicting OS in the test cohort (C-index: 0.732 [95% CI 0.714-0.750] versus 0.671 [95% CI 0.647-0.695]). The ROC curves at 3-year and 5-year OS for the model also showed good discrimination ability in the test cohort (Area Under the Curve [AUC] at 3-/5-year OS = 0.805/0.825). Moreover, using our novel staging system, we observed a clear survival difference among different risk groups (P < 0.001) and a significant positive net benefit in the DCA.

CONCLUSIONS

A novel deep learning-based staging system was constructed for patients with ESCC, which performed a significant discriminability for survival probability. Moreover, an easy-to-use web-based tool based on the deep learning model was also implemented, offering convenience for personalized survival prediction. We developed a deep learning-based system that stages patients with ESCC according to their survival probability. We also created a web-based tool that uses this system to predict individual survival outcomes.

Neoadjuvant versus definitive chemoradiation in locally advanced esophageal cancer for patients of advanced age or significant comorbidities

The addition of surgery to chemoradiation for esophageal cancer has not shown a survival benefit in randomized trials. Patients with more comorbidities or advanced age are more likely to be given definitive chemoradiation due to surgical risk. We aimed to identify subsets of patients in whom the addition of surgery to chemoradiation does not provide an overall survival (OS) benefit. The National Cancer Database was queried for patients with locally advanced esophageal cancer who received either definitive chemoradiation or neoadjuvant chemoradiation followed by surgery. Bivariate analysis was used to assess the association between patient characteristics and treatment groups. Log-rank tests and Cox proportional hazards models were performed to assess for differences in survival. A total of 15,090 with adenocarcinoma and 5,356 with squamous cell carcinoma met the inclusion criteria. Patients treated with neoadjuvant chemoradiation and surgery had significantly improved survival by Cox proportional hazards model regardless of histology if <50, 50-60, 61-70, or 71-80 years old. There was no significant benefit or detriment in patients 81-90 years old. Survival advantage was also significant with a Charlson/Deyo comorbidity condition score of 0, 1, 2, and ≥3 in adenocarcinoma squamous cell carcinoma with scores of 2 or ≥3 had no significant benefit or detriment. Patients 81-90 years old or with squamous cell carcinoma and a Charlson/Deyo comorbidity score ≥ 2 lacked an OS benefit from neoadjuvant chemoradiation followed by surgery compared with definitive chemoradiation. Careful consideration of esophagectomy-specific surgical risks should be used when recommending treatment for these patients.

A novel risk classification system based on the eighth edition of TNM frameworks for esophageal adenocarcinoma patients: A deep learning approach

Objective

To develop and validate a deep learning predictive model with better performance in survival estimation of esophageal adenocarcinoma (EAC).

Method

Cases diagnosed between January 2010 and December 2018 were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. A deep learning survival neural network was developed and validated based on 17 variables, including demographic information, clinicopathological characteristics, and treatment details. Based on the total risk score derived from this algorithm, a novel risk classification system was constructed and compared with the 8th edition of the tumor, node, and metastasis (TNM) staging system.

Results

Of 7,764 EAC patients eligible for the study, 6,818 (87.8%) were men and the median (interquartile range, IQR) age was 65 (58-72) years. The deep learning model generated significantly superior predictions to the 8th edition staging system on the test data set (C-index: 0.773 [95% CI, 0.757-0.789] vs. 0.683 [95% CI, 0.667-0.699]; P < 0.001). Calibration curves revealed that the deep learning model was well calibrated for 1- and 3-year OS, most points almost directly distributing on the 45° line. Decision curve analyses (DCAs) showed that the novel risk classification system exhibited a more significant positive net benefit than the TNM staging system. A user-friendly and precise web-based calculator with a portably executable file was implemented to visualize the deep learning predictive model.

Conclusion

A deep learning predictive model was developed and validated, which possesses more excellent calibration and discrimination abilities in survival prediction of EAC. The novel risk classification system based on the deep learning algorithm may serve as a useful tool in clinical decision making given its easy-to-use and better clinical applicability.

Nomogram for prognosis of patients with esophageal squamous cell cancer after minimally invasive esophagectomy established based on non-textbook outcome

BACKGROUND

Non-textbook outcome (non-TO) represents a new prognostic evaluation index for surgical oncology. The present study aimed to develop new nomograms based on non-TO to predict the mortality and recurrence rate in patients with esophageal squamous cell cancer (ESCC) after minimally invasive esophagectomy (MIE).

METHODS

The study involved a retrospective analysis of 613 ESCC patients, from the prospectively maintained database from January 2011 to December 2018. All the included ESCC patients underwent MIE, and they were randomly (1:1) assigned to the training cohort (307 patients) and the validation cohort (306 patients). Kaplan-Meier survival analysis was used to analyze the differences recorded between overall survival (OS) and disease-free survival (DFS). In the case of the training cohort, the nomograms based on non-TO were developed using Cox regression, and the performance of these nomograms was calibrated and evaluated in the validation cohort.

RESULTS

Significant differences were recorded for 5-year OS and DFS between non-TO and TO groups (p < 0.05). Multivariate cox analysis revealed that non-TO, intraoperative bleeding, T stage, and N stage acted as independent risk factors that affected OS and DFS (p < 0.05). The results for multivariate regression were used to build non-TO-based nomograms to predict OS and DFS of patients with ESCC, the t-AUC curve analysis showed that the nomograms predicting OS and DFS were more accurate as compared to TNM staging, during the follow-up period in the training cohort and validation cohort. Further, the nomogram score was used to divide ESCC patients into low-, middle-, and high-risk groups and significant differences were recorded for OS and DFS between these three groups (p < 0.001).

CONCLUSIONS

Non-TO was identified as an independent prognostic factor for ESCC patients. The nomograms based on non-TO could availably predict OS and DFS in ESCC patients after MIE.

Development and validation of a deep learning model to predict survival of patients with esophageal cancer

Objective

To compare the performance of a deep learning survival network with the tumor, node, and metastasis (TNM) staging system in survival prediction and test the reliability of individual treatment recommendations provided by the network.

Methods

In this population-based cohort study, we developed and validated a deep learning survival model using consecutive cases of newly diagnosed stage I to IV esophageal cancer between January 2004 and December 2015 in a Surveillance, Epidemiology, and End Results (SEER) database. The model was externally validated in an independent cohort from Fujian Provincial Hospital. The C statistic was used to compare the performance of the deep learning survival model and TNM staging system. Two other deep learning risk prediction models were trained for treatment recommendations. A Kaplan–Meier survival curve was used to compare survival between the population that followed the recommended therapy and those who did not.

Results

A total of 9069 patients were included in this study. The deep learning network showed more promising results in predicting esophageal cancer-specific survival than the TNM stage in the internal test dataset (C-index=0.753 vs. 0.638) and external validation dataset (C-index=0.687 vs. 0.643). The population who received the recommended treatments had superior survival compared to those who did not, based on the internal test dataset (hazard ratio, 0.753; 95% CI, 0.556-0.987; P=0.042) and the external validation dataset (hazard ratio, 0.633; 95% CI, 0.459-0.834; P=0.0003).

Conclusion

Deep learning neural networks have potential advantages over traditional linear models in prognostic assessment and treatment recommendations. This novel analytical approach may provide reliable information on individual survival and treatment recommendations for patients with esophageal cancer.

Increased prognostic value of clinical–reproductive model in Chinese female patients with esophageal squamous cell carcinoma

BACKGROUND

In China, it has been well recognized that some female patients with esophageal squamous cell carcinoma (ESCC) have different overall survival (OS) time, even with the same tumor-node-metastasis (TNM) stage, challenging the prognostic value of the TNM system alone. An effective predictive model is needed to accurately evaluate the prognosis of female ESCC patients.

AIM

To construct a novel prognostic model with clinical and reproductive data for Chinese female patients with ESCC, and to assess the incremental prognostic value of the full model compared with the clinical model and TNM stage.

METHODS

A new prognostic nomogram incorporating clinical and reproductive features was constructed based on univariatie and Cox proportional hazards survival analysis from a training cohort (n = 175). The results were recognized using the internal (n = 111) and independent external (n = 85) validation cohorts. The capability of the clinical–reproductive model was evaluated by Harrell’s concordance index (C-index), Kaplan–Meier curve, time-dependent receiver operating characteristic (ROC), calibration curve and decision curve analysis. The correlations between estrogen response and immune-related pathways and some gene markers of immune cells were analyzed using the TIMER 2.0 database.

RESULTS

A clinical–reproductive model including incidence area, age, tumor differentiation, lymph node metastasis (N) stage, estrogen receptor alpha (ESR1) and beta (ESR2) expression, menopausal age, and pregnancy number was constructed to predict OS in female ESCC patients. Compared to the clinical model and TNM stage, the time-dependent ROC and C-index of the clinical–reproductive model showed a good discriminative ability for predicting 1-, 3-, and 5-years OS in the primary training, internal and external validation sets. Based on the optimal cut-off value of total prognostic scores, patients were classified into high- and low-risk groups with significantly different OS. The estrogen response was significantly associated with p53 and apoptosis pathways in esophageal cancer.

CONCLUSION

The clinical–reproductive prognostic nomogram has an incremental prognostic value compared with the clinical model and TNM stage in predicting OS in Chinese female ESCC patients.

Development and Validation of a Clinical Prognostic Nomogram for Esophageal Adenocarcinoma Patients

Background

Clinical staging is essential for clinical decisions but remains imprecise. We purposed to construct a novel survival prediction model for improving clinical staging system (cTNM) for patients with esophageal adenocarcioma (EAC).

Methods

A total of 4180 patients diagnosed with EAC were extracted from the Surveillance, Epidemiology, and End Results (SEER) database and included as the training cohort. Significant prognostic variables were identified for nomogram model development using multivariable Cox regression. The model was validated internally by bootstrap resampling, and then subjected to external validation with a separate cohort of 886 patients from 2 institutions in China. The prognostic performance was measured by concordance index (C-index), Akaike information criterion (AIC) and calibration plots. Different risk groups were stratified by the nomogram scores.

Results

A total of six variables were determined related with survival and entered into the nomogram construction. The calibration curves showed satisfied agreement between nomogram-predicted survival and actual observed survival for 1-, 3-, and 5-year overall survival. By calculating the AIC and C-index values, our nomogram presented superior discriminative and risk-stratifying ability than current TNM staging system. Significant distinctions in survival curves were observed between different risk subgroups stratified by nomogram scores.

Conclusion

The established and validated nomogram presented better risk-stratifying ability than current clinical staging system, and could provide a convenient and reliable tool for individual survival prediction and treatment strategy making.