Constructing a prognostic model for colorectal cancer with synchronous liver metastases after preoperative chemotherapy: a study based on SEER and an external validation cohort

Abstract

Background: The combination of preoperative chemotherapy and surgical treatment has been shown to significantly enhance the prognosis of colorectal cancer with liver metastases (CRLM) patients. Nevertheless, as a result of variations in clinicopathological parameters, the prognosis of this particular group of patients differs considerably. This study aimed to develop and evaluate Cox proportional risk regression model and competing risk regression model using two patient cohorts. The goal was to provide a more precise and personalized prognostic evaluation system.

Methods: We collected information on individuals who had a pathological diagnosis of colorectal cancer between 2000 and 2019 from the Surveillance, Epidemiology, and End Results (SEER) Database. We obtained data from patients who underwent pathological diagnosis of colorectal cancer and got comprehensive therapy at the hospital between January 1, 2010, and June 1, 2022. The SEER data collected after screening according to the inclusion and exclusion criteria were separated into two cohorts: a training cohort (training cohort) and an internal validation cohort (internal validation cohort), using a random 1:1 split. Subgroup Kaplan-Meier (K-M) survival analyses were conducted on each of the three groups. The data that received following screening from the hospital were designated as the external validation cohort. The subsequent variables were chosen for additional examination: age, gender, marital status, race, tumor site, pretreatment carcinoembryonic antigen level, tumor size, T stage, N stage, pathological grade, number of tumor deposits, perineural invasion, number of regional lymph nodes examined, and number of positive regional lymph nodes. The primary endpoint was median overall survival (mOS). In the training cohort, we conducted univariate Cox regression analysis and utilized a stepwise regression approach, employing the Akaike information criterion (AIC) to select variables and create Cox proportional risk regression models. We evaluated the accuracy of the model using calibration curve, receiver operating characteristic curve (ROC), and area under curve (AUC). The effectiveness of the models was assessed using decision curve analysis (DCA). To evaluate the non-cancer-related outcomes, we analyzed variables that had significant impacts using subgroup cumulative incidence function (CIF) and Gray's test. These analyses were used to create competing risk regression models. Nomograms of the two models were constructed separately and prognostic predictions were made for the same patients in SEER database.

Results: This study comprised a total of 735 individuals. The mOS of the training cohort, internal validation cohort, and QDU cohort was 55.00 months (95%CI 46.97-63.03), 48.00 months (95%CI 40.65-55.35), and 68.00 months (95%CI 54.91-81.08), respectively. The multivariate Cox regression analysis revealed that age, N stage, presence of perineural infiltration, number of tumor deposits and number of positive regional lymph nodes were identified as independent prognostic risk variables (p < 0.05). In comparison to the conventional TNM staging model, the Cox proportional risk regression model exhibited a higher C-index. After controlling for competing risk events, age, N stage, presence of perineural infiltration, number of tumor deposits, number of regional lymph nodes examined, and number of positive regional lymph nodes were independent predictors of the risk of cancer-specific mortality (p < 0.05).

Conclusion: We have developed a prognostic model to predict the survival of patients with synchronous CRLM who undergo preoperative chemotherapy and surgery. This model has been tested internally and externally, confirming its accuracy and reliability.

Keywords: Preoperative chemotherapy; Prognosis; Risk model; Synchronous CRLM.

Fig. 1

Optimal grouping nodes for continuous variables identified by RCS. A The best grouping node for tumor size was 49.899497 mm; B the best grouping node for the number of positive regional lymph nodes was 0.9657; C the best grouping node for the number of regional lymph nodes examined was 16.824121; D the best grouping node for age was 57.03015 years; and E the best grouping node for tumor deposits was 0.000

Fig. 2

Kaplan–Meier survival analysis at SEER cohort and QDU external validation cohort. A The SEER cohort showed significant survival differences in age, number of tumor deposits, number of positive regional lymph nodes, perineural infiltration, T stage, N stage and tumor site subgroups (p < 0.05); B the QDU cohort showed significant survival differences (p < 0.05)

Fig. 2

Kaplan–Meier survival analysis at SEER cohort and QDU external validation cohort. A The SEER cohort showed significant survival differences in age, number of tumor deposits, number of positive regional lymph nodes, perineural infiltration, T stage, N stage and tumor site subgroups (p < 0.05); B the QDU cohort showed significant survival differences (p < 0.05)

Fig. 3

Cox proportional risk regression modeling and testing. A Age, N stage, number of tumor deposits, number of positive regional lymph nodes and perineural infiltration met the Cox regression proportional risk assumption test (p > 0.05); B calibration curves of the modeling set at 1 year, 3 years, and 5 years, respectively; C ROC curves of the modeling set at 1 year, 3 years, and 5 years, respectively, and the corresponding AUC values; D DCA curves of the modeling set at 1 year, 3 years, and 5 years, respectively, and compared with the TNM prediction model; E calibration curves for the internal validation set at 1 year, 3 years, and 5 years, respectively; F ROC curves and corresponding AUC values for the internal validation set at 1 year, 3 years, and 5 years, respectively; G DCA curves for the internal validation set at 1 year, 3 years, and 5 years, respectively; H calibration curves for the external validation set at 1 year, 3 years, and 5 years, respectively; I external ROC curves and corresponding AUC values for the validation set at 1 year, 3 years, and 5 years, respectively; J DCA curves for the external validation set at 1 year, 3 years, and 5 years, respectively. Model: the Cox proportional risk regression model, and TNM: the TNM prediction model

Fig. 3

Cox proportional risk regression modeling and testing. A Age, N stage, number of tumor deposits, number of positive regional lymph nodes and perineural infiltration met the Cox regression proportional risk assumption test (p > 0.05); B calibration curves of the modeling set at 1 year, 3 years, and 5 years, respectively; C ROC curves of the modeling set at 1 year, 3 years, and 5 years, respectively, and the corresponding AUC values; D DCA curves of the modeling set at 1 year, 3 years, and 5 years, respectively, and compared with the TNM prediction model; E calibration curves for the internal validation set at 1 year, 3 years, and 5 years, respectively; F ROC curves and corresponding AUC values for the internal validation set at 1 year, 3 years, and 5 years, respectively; G DCA curves for the internal validation set at 1 year, 3 years, and 5 years, respectively; H calibration curves for the external validation set at 1 year, 3 years, and 5 years, respectively; I external ROC curves and corresponding AUC values for the validation set at 1 year, 3 years, and 5 years, respectively; J DCA curves for the external validation set at 1 year, 3 years, and 5 years, respectively. Model: the Cox proportional risk regression model, and TNM: the TNM prediction model

Fig. 4

Cox proportional risk regression model nomogram

Fig. 5

Competition risk modeling and testing. A Nelson–Aalen curves for the variables age, pathological stage, tumor site, tumor size, tumor deposits, number of regional lymph nodes examined, N stage, number of positive regional lymph nodes, and perineural infiltration. B Competing risk model nomogram. id = 35,288,445 The patient’s total score is 193, and his cumulative probability of death at 1 year, 3 years, and 5 years is predicted to be: 0.0489, 0.357 and 0.663, respectively. C Calibration curves for the modeling set at 1 year, 3 years, and 5 years, respectively

Fig. 5

Competition risk modeling and testing. A Nelson–Aalen curves for the variables age, pathological stage, tumor site, tumor size, tumor deposits, number of regional lymph nodes examined, N stage, number of positive regional lymph nodes, and perineural infiltration. B Competing risk model nomogram. id = 35,288,445 The patient’s total score is 193, and his cumulative probability of death at 1 year, 3 years, and 5 years is predicted to be: 0.0489, 0.357 and 0.663, respectively. C Calibration curves for the modeling set at 1 year, 3 years, and 5 years, respectively