Metabolic score combined with pathological information and treatment means to predict prognosis of esophageal cancer

Abstract

The present application belongs to the technical field of prediction model, and particularly relates to a nomogram system for predicting prognosis of esophageal cancer by combining metabolic score, pathological information and treatment method. The present application provides a nomogram system for predicting prognosis of esophageal cancer by combining metabolic score, clinical information, pathological information and treatment method, and belongs to the technical field of prediction model. The system is simple to operate, has good discrimination, calibration ability and clinical net benefit, and can be used as an important tool for individualized prediction of prognosis of esophageal cancer patients. The nomogram system considers the nonlinear influence of metabolic syndrome components on esophageal cancer, uses RCS curve to calculate metabolic score of metabolic syndrome components affecting death risk of esophageal cancer patients, more clearly observes the estimated correlation between metabolic syndrome components and esophageal cancer mortality results, and determines any potential threshold effect. The nomogram system considers the esophageal cancer adjuvant treatment decision model of adjuvant radiotherapy and chemotherapy factors, so that the prediction performance of the system is better.

Description

Technical Field

[0001] This invention belongs to the field of predictive model technology, specifically relating to a nomogram system for predicting the prognosis of esophageal cancer by combining metabolic scores with pathological information and treatment methods. Background Technology

[0002] Esophageal cancer is the seventh most common cancer worldwide and the sixth leading cause of cancer death. In 2018, there were approximately 572,000 new cases and 509,000 deaths, affecting more than 450,000 people globally each year, and the incidence is rapidly increasing. The highest incidence rates of esophageal cancer are found in Asia and Africa, with squamous cell carcinoma being the most common subtype, while adenocarcinoma is more common in North America and Western Europe. The causes of esophageal cancer are diverse and vary considerably across regions. Risk factors for esophageal cancer include alcohol consumption, smoking, polycyclic aromatic hydrocarbons (PAHs) from various sources, hot foods, dietary habits, oral health, and gut microbiota composition. Current guidelines recommend the combined use of fluoropyrimidine and platinum-based chemotherapy as first-line treatment.

[0003] China's large population and high incidence rate mean that it accounts for approximately half of the world's esophageal squamous cell carcinoma cases. Treatment options are limited for patients with inoperable, locally advanced, or metastatic esophageal cancer. The prognosis for patients with metastatic esophageal cancer is generally poor, with a 5-year survival rate of less than 5%. Therefore, finding new ways to improve the prognosis and prolong survival of esophageal cancer patients is of great clinical significance. Due to the combined effects of multiple factors—rapid globalization, demographic trends, changes in the prevalence and distribution of key risk factors, innovations in cancer diagnosis and treatment, and improvements in healthcare infrastructure—the incidence and mortality rates of major gastrointestinal cancer types exhibit significant heterogeneity across regions and countries worldwide. Identifying readily available, prognostic clinical biomarkers can contribute to improving the prognosis and prolonging survival of esophageal cancer patients.

[0004] Currently, systems for predicting the prognosis of esophageal cancer mainly rely on pathological information and treatment methods. Pathological information includes the primary location of the tumor, TNM stage, number of lymph nodes dissected, and tumor size, while treatment methods include surgery and chemotherapy. However, the causes of esophageal cancer are diverse, and current systems for predicting esophageal cancer prognosis are still imperfect, requiring further improvement.

[0005] Clinical studies have reported a correlation between metabolic syndrome (MetS) and esophageal cancer incidence; patients with MetS have an increased risk of esophageal cancer. MetS comprises a range of metabolic disorders, including obesity, hyperglycemia, dyslipidemia, and hypertension. Currently, metabolic syndrome is recognized as a major cause of increased risk for cardiovascular disease and type 2 diabetes. With socioeconomic development and lifestyle changes, the global incidence of MetS has increased significantly. Chronic inflammation and oxidative stress are key pathological features involved in cancer development and are crucial for patients with MetS. Increasing evidence suggests that metabolic syndrome has systemic effects, increasing susceptibility to various cancers. Therefore, MetS is associated with esophageal cancer and is considered a risk factor for esophageal cancer.

[0006] Currently, research on the relationship between metabolic markers and the prognosis of gastrointestinal tumors is relatively limited, and there is no literature reporting a system for predicting esophageal cancer prognosis by combining metabolic markers with pathological information and treatment methods. Since Metabolic Invasive Syndrome (MetS) is reversible, lifestyle modifications or medical interventions for MetS patients may be preventative strategies for gastrointestinal cancers, potentially improving the accuracy and effectiveness of interventions for esophageal cancer. Incorporating MetS markers into a system for predicting esophageal cancer prognosis based on pathological information and treatment methods will improve the accuracy and specificity of predictions. Therefore, there is an urgent need to establish a system for predicting esophageal cancer prognosis by combining metabolic markers with pathological information and treatment methods. Summary of the Invention

[0007] In order to overcome the problems existing in the prior art, the purpose of this invention is to provide a nomogram system for predicting the prognosis of esophageal cancer based on metabolic score, clinical information, pathological information and treatment plan.

[0008] This invention provides a nomogram system for predicting the prognosis of esophageal cancer, comprising the following modules:

[0009] I. Data Input Module

[0010] The input is used to obtain the patient's characteristic data, which includes age, T, N, metastatic site, intraoperative chemotherapy, smoking, and metabolic score; the patient is an esophageal cancer patient.

[0011] II. Model Building Module

[0012] A nomogram predicting overall survival for esophageal cancer patients was constructed using feature data from the input module.

[0013] III. Prediction Module

[0014] Input the feature data of the patient to be predicted into the nomogram constructed in step two, and output the prediction results.

[0015] Furthermore, the esophageal cancer patients mentioned are those who underwent esophagectomy for stage I-IV esophageal cancer.

[0016] Furthermore, the metabolic integral was calculated as follows: The influence of metabolic syndrome components on the prognosis of esophageal cancer patients was analyzed using restricted cubic plots to identify nonlinear and linear influencing factors. The metabolic integral value was then calculated using the following R language formula: res.cox<-coxph(surv(time,status)TG+HDL+rcs(GLU,4)+rcs(BMI,4)+SBP

[0017] +DBP,data=aa);

[0018] The metabolic syndrome components include body mass index, fasting blood glucose, blood pressure, triglycerides, and high-density lipoprotein, and the blood pressure includes systolic and diastolic blood pressure;

[0019] In the R language calculation formula, BMI is body mass index, GLU is fasting blood glucose, SBP is systolic blood pressure, DBP is diastolic blood pressure, TG is triglycerides, and HDL is high-density lipoprotein.

[0020] Furthermore, among the components of metabolic syndrome, BMI is a non-linear influencing factor, while GLU, SBP, DBP, TG, and HDL are linear influencing factors.

[0021] Furthermore, the age is a continuous variable, and the value of the age variable is the patient's age in years;

[0022] The T-stage is a discrete variable, and the value of the T-stage variable represents the depth of tumor invasion in the patient. The T-stage variable is assigned the following values: 1 represents T1, 2 represents T2, 3 represents T3, and 4 represents T4.

[0023] The N stage is a discrete variable, and the value of the N stage variable represents the lymph node metastasis in the tumor area of ​​the patient. The T stage variable is assigned the following values: 0 represents N0, 1 represents N1, 2 represents N2, and 3 represents N3.

[0024] The metastatic site is a discrete variable, represented by the value of the metastatic site variable. The assignment method of the metastatic site variable is as follows: 0 represents no metastasis, 1 represents lung metastasis, 2 represents liver metastasis, 3 represents abdominal metastasis, 4 represents bone metastasis, 5 represents multiple metastases, and NA represents unknown metastatic site.

[0025] Intraoperative chemotherapy is a discrete variable. The value of the intraoperative chemotherapy variable indicates whether chemotherapy was performed during the operation. The intraoperative chemotherapy variable is assigned the value as follows: 0 indicates no and 1 indicates yes.

[0026] Smoking is a discrete variable, represented by the value of the smoking variable. The smoking variable is assigned the following values: 0 represents non-smoker, 1 represents smoker, 2 represents former smoker who is currently quitting, 3 represents non-smoker, and 4 represents unknown smoking status.

[0027] The metabolic integral is a continuous variable.

[0028] Furthermore, in the model construction module, the method of constructing a nomogram predicting the overall survival of esophageal cancer patients using the feature data of the input module is to construct and draw the nomogram by performing multivariate Cox regression analysis on the feature data of the input module.

[0029] Furthermore, the total lifespan is 1 year, 3 years, and 5 years.

[0030] The present invention also provides the use of the above-described nomogram system in the preparation of a device for predicting the prognosis of esophageal cancer.

[0031] The present invention also provides a computer-readable storage medium having a computer program stored thereon for implementing the nodal graph system as described above.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] 1) This invention establishes a nomogram system for predicting the survival prognosis of esophageal cancer patients based on metabolic scores, clinical information, pathological information, and patient treatment plans based on metabolic syndrome components. The system is simple to operate, has good discrimination and calibration capabilities, and has clinical net benefits. It can serve as an important tool for personalized prediction of the prognosis of esophageal cancer patients.

[0034] 2) The prognostic prediction nomogram system of this invention considers the nonlinear effect of metabolic syndrome components on esophageal cancer. It uses RCS curves to calculate the metabolic integral of metabolic syndrome components affecting the mortality risk of esophageal cancer patients, so as to more clearly observe the estimated association between metabolic syndrome components and esophageal cancer mortality results and identify any potential threshold effects.

[0035] 3) The prognostic prediction nomogram system of this invention takes into account the adjuvant treatment decision model for esophageal cancer with adjuvant radiotherapy and chemotherapy factors, which makes the system more effective in prediction.

[0036] 4) Compared with the stage system, the Base system, and the Base+MeTs system, the prognostic prediction nomogram system of this invention is significantly superior in predicting tumor prognosis and assessing adjuvant therapy selection. Its sensitivity is higher than that of the Base system and the Base+MeTs system, and its specificity is higher than that of the stage system (tumor prognosis and adjuvant therapy selection assessment). It significantly improves the prognostic prediction ability for esophageal cancer patients. Compared with the Base system, the Base+MeTs system, and the stage system, the prognostic prediction nomogram system of this invention is better in predicting the overall survival of esophageal cancer. The AUC over time shows that the prognostic prediction nomogram system of this invention outperforms the aforementioned control systems at every time point.

[0037] Obviously, based on the above description of the present invention, and according to common technical knowledge and conventional methods in the field, various other modifications, substitutions, or alterations can be made without departing from the basic technical concept of the present invention.

[0038] The following detailed embodiments further illustrate the above-described content of the present invention. However, this should not be construed as limiting the scope of the present invention to the following embodiments. All technologies implemented based on the above-described content of the present invention fall within the scope of the present invention. Attached Figure Description

[0039] Figure 1 RCS analysis of metabolic syndrome components and overall survival in esophageal cancer.

[0040] Figure 2 Lasso regression analysis was used to screen for prognostic risk factors for esophageal cancer.

[0041] Figure 3 Example 1: Nodal plot of the esophageal cancer overall survival prediction model.

[0042] Figure 4 The nomogram of the esophageal cancer overall survival prediction model constructed in Example 1 was used to validate the prediction performance in internal (A) and external (B) cohorts. Detailed Implementation

[0043] The raw materials and equipment used in this invention are all known products, obtained by purchasing commercially available products.

[0044] This invention included 5542 patients with stage I-IV esophageal cancer who underwent resection surgery. Postoperative survival was followed up, and overall survival (OS) information was collected. After establishing a prognostic prediction model, the 5542 patients were randomly sampled at a ratio of 7:3 for internal and external validation.

[0045] The following are the steps for screening independent factors that predict overall survival (OS) in patients with esophageal cancer:

[0046] 1. Calculate the metabolic score of MetS components affecting the risk of death in patients with gastrointestinal tumors. The specific steps are as follows:

[0047] The impact of metabolic syndrome components (body mass index, fasting blood glucose, blood pressure, triglycerides, and high-density lipoprotein) on the prognosis of esophageal cancer patients was analyzed using restricted cube plots (RCS). Figure 1 This study identifies nonlinear and linear influencing factors. The components of metabolic syndrome include: Body Mass Index (BMI); Fasting Blood Glucose (GLU); Blood Pressure (SBP and DBP); Triglycerides (TG); and High-Density Lipoprotein (HDL).

[0048] The results showed a potential non-linear association between BMI and overall survival (OS) in esophageal cancer (p<0.001), exhibiting a J-type association. The optimal predictive range for BMI was 18.5–33 kg / m². 2 Other components of MetS showed a linear association with overall survival (OS) in esophageal cancer patients.

[0049] The metabolic integral value is calculated using the following R language formula:

[0050] R language calculation formula: res.cox <- coxph(surv(time,status)TG+HDL+rcs(GLU,4)+rcs(BMI,4)+SBP+DBP,data=aa).

[0051] The meanings of the codes involved in the above R language calculation formulas are well known to those skilled in the art.

[0052] 2. Lasso regression analysis was performed using patient demographic indicators, clinical information, pathological characteristics, and tumor-related treatments received, along with metabolic scores, to preliminarily screen for risk factors for the prognosis of gastrointestinal tumors. Figure 2The specific procedure involves using Lasso regression analysis based on metabolic score, patient sociodemographic information (including age, sex, education, etc.), medical history, lifestyle exposures (including smoking habits, dietary intake, and alcohol consumption), anthropometric measurements (including weight, height, systolic blood pressure, and diastolic blood pressure), pathological characteristics (TNM stage (I, II, III, IV), tumor size, depth of invasion (T1, T2, T3, T4), regional lymph node metastasis (N0, N1, N2, N3), distant metastasis (M0, M1)), and whether the patient received tumor-related treatment (intraoperative chemotherapy, immunotherapy, chemotherapy, radiotherapy). This preliminary screening identifies factors that influence the prognosis of gastrointestinal tumors. The Lasso model is adjusted for factors such as age, sex, T, N, M, family history, tumor size, histological grade, metastatic site, race, marital status, occupation, alcohol consumption, smoking, metabolic score, intraoperative chemotherapy, immunotherapy, chemotherapy, and radiotherapy. Intraoperative chemotherapy refers to chemotherapy administered concurrently with surgery; chemotherapy refers to chemotherapy administered outside of surgery.

[0053] 3. Univariate and multivariate Cox proportional hazards regression analysis was used to further screen the risk factors identified by Lasso regression, selecting those closely related to the prognosis of esophageal cancer patients. Specifically, univariate and multivariate Cox proportional hazards regression analysis was used to further screen the risk factors initially screened by Lasso regression, identifying those closely related to the prognosis of esophageal cancer patients. The Cox proportional hazards regression model was used to analyze the impact of metabolic syndrome components (BMI, fasting blood glucose, blood pressure, triglycerides, and high-density lipoprotein) on the prognosis of gastrointestinal tumors; the multivariate Cox survival model was adjusted according to age, T stage, N stage, metastatic site, marital status, smoking, and metabolic score. Multivariate Cox regression analysis showed that age, T, N, metastatic site, intraoperative chemotherapy, smoking, and metabolic score were independent predictors of esophageal cancer overall survival (OS).

[0054] Among them, age is a continuous variable, and the value of the age variable is the patient's age (in years);

[0055] T-staging is a discrete variable. The value of the T-staging variable represents the depth of tumor invasion in the patient. The T-staging variable is assigned the following values: 1 represents T1, 2 represents T2, 3 represents T3, and 4 represents T4.

[0056] N stage is a discrete variable, and the value of the N stage variable represents the lymph node metastasis in the tumor area of ​​the patient. The T stage variable is assigned the value as follows: 0 represents N0, 1 represents N1, 2 represents N2, and 3 represents N3.

[0057] The metastatic site is a discrete variable, represented by the value of the metastatic site variable. The assignment method of the metastatic site variable is as follows: 0 represents no metastasis, 1 represents lung metastasis, 2 represents liver metastasis, 3 represents abdominal metastasis, 4 represents bone metastasis, 5 represents multiple metastases, and NA represents unknown metastatic site.

[0058] Intraoperative chemotherapy is a discrete variable. The value of the intraoperative chemotherapy variable indicates whether chemotherapy was performed during the operation. The intraoperative chemotherapy variable is assigned the value as follows: 0 indicates no and 1 indicates yes.

[0059] Smoking is a discrete variable, represented by the value of the smoking variable. The smoking variable is assigned the following values: 0 represents non-smoker, 1 represents smoker, 2 represents former smoker who is currently quitting, 3 represents non-smoker, and 4 represents unknown smoking status.

[0060] The metabolic score is a continuous variable, and its value is the patient's metabolic score calculated in step 1.

[0061] The following is an example of constructing a nomogram system to predict the overall survival of esophageal cancer patients using seven independent prognostic factors: age, T, N, metastatic site, intraoperative chemotherapy, smoking, and metabolic score. Example 1: Construction method of a nomogram system (referred to as the base+risk system) for predicting esophageal cancer prognosis based on a combination of metabolic score, clinical information, pathological information, and treatment regimen.

[0062] I. Input Module

[0063] Collect the patient's age, T, N, metastatic sites, intraoperative chemotherapy, smoking, and metabolic score, and enter these indicators into the input module.

[0064] II. Establishment of a prognostic prediction model for esophageal cancer

[0065] Multivariate Cox regression analysis was performed using seven indicators: patient age, T, N, metastatic site, intraoperative chemotherapy, smoking, and metabolic score. A nomogram was constructed and plotted to predict the 1-, 3-, and 5-year overall survival prognosis of esophageal cancer patients. Figure 3 ).

[0066] Kaplan-Meier (KM) analysis was performed to determine survival outcomes. KM curves were plotted using the median as the critical threshold, and the log-rank test was used to assess their statistical significance.

[0067] III. Predicting Patient Prognosis Using Esophageal Cancer Prognostic Models

[0068] We collected data on age, T, N, metastatic sites, intraoperative chemotherapy, smoking, and metabolic scores from patients in the internal and external validation cohorts. We then used the nomogram model constructed in step two to predict the 1-, 3-, and 5-year overall survival prognosis of these patients.

[0069] The following is the method for constructing the control model.

[0070] Compare with Example 1: Methods for building a base system

[0071] Referring to the method in Example 1, the only difference is that the input indicators are modified to include the patient's age, T, N, metastatic site, intraoperative chemotherapy, and smoking, to construct a base system for predicting the prognosis of esophageal cancer.

[0072] Compare with Example 2: Construction method of base+MeTs system

[0073] Referring to the method in Example 1, the only difference is that the input indicators are modified to include the patient's age, T, N, metastatic site, intraoperative chemotherapy, smoking, and whether there is metabolic syndrome, to construct a base+MeTs system for predicting the prognosis of esophageal cancer.

[0074] Compare with Example 3: The construction method of the stage system

[0075] Referring to the method in Example 1, the only difference is that the input indicators are modified to the patient's T stage, N stage, and metastatic site to construct a pathological staging system for predicting the prognosis of esophageal cancer, also known as the stage system.

[0076] The following experimental examples demonstrate the beneficial effects of the nomogram system of the present invention, which combines metabolic scores, clinical information, pathological information, and treatment plans to predict the prognosis of esophageal cancer.

[0077] Experiment Example 1: Model Validation

[0078] 1. To verify the accuracy of the nomogram system for predicting esophageal cancer prognosis based on metabolic integral, clinical information, pathological information, and treatment plan in Embodiment 1 of the present invention, the prediction performance was assessed using a bootstrap calibration curve and quantified as a C-index. The probabilities of outcomes for both the internal and external validation cohorts were predicted. The calibration curves show good consistency between the actual probabilities of 1-year, 3-year, and 5-year overall survival (OS) and the nomogram predicted probabilities in both the internal and external validation cohorts. Figure 4 ).

[0079] 2. Analysis of C-index, age, T, N, metastatic site, intraoperative chemotherapy, smoking, and IDI

[0080] The Harrells C-Index (C-index), also known as the consistency index, is mainly used to calculate the discriminant between the predicted values ​​of the Cox model and the actual values ​​in survival analysis. It is an indicator used in survival analysis to evaluate the accuracy of the prediction model.

[0081] Net Reclassification Index (NRI) analysis method: If NRI>0, it is a positive improvement, indicating that the new model has improved the predictive ability of the old model; if NRI<0, it is a negative improvement, indicating that the predictive ability of the new model has decreased; if NRI=0, it is considered that the new model has not improved.

[0082] Integrated discrimination improvement (IDI) analysis method: The larger the IDI, the better the new model predicts compared to the old model.

[0083] Table 1. Comparison of the predictive capabilities of different prediction systems

[0084]

[0085]

[0086] Comparative analysis of different models in the embodiments and control examples using Harrell's C-statistic, NRI, and IDI (Table 1) confirmed that, compared with the stage system, the Base system, and the Base+MeTs system, the system constructed in Embodiment 1 of this invention (base+risk system) is significantly superior in predicting tumor prognosis and assessing adjuvant therapy selection. The sensitivity of both results is higher than that of the Base system and the Base+MeTs system, and the specificity is higher than that of the stage system (tumor prognosis and adjuvant therapy selection assessment), significantly improving the prognostic predictive ability for esophageal cancer patients.

[0087] Experimental Example 2: Clinical Benefit Evaluation

[0088] The model was validated using Decision Curve Analysis (DCA) and Calibration Curve, and ROC curves and C-index were calculated for the prediction model.

[0089] DCA (Discretionary Clinical Assessment) is a method for evaluating the net clinical benefit of a predictive model. DCA reflects a positive net benefit with a broad range of clinically reasonable risk threshold probabilities. To evaluate the clinical application of the metabolic score, decision curve analysis was employed. Compared to the Base system, the Base+MeTs system, or the stage system, the system constructed in Example 1 of this invention showed consistently positive results and greater net benefits across a broad range of risk thresholds. Based on the DCA results, a clinical impact curve was further plotted to assess the model's clinical application value. The clinical impact curve represents the acceptable potential clinical effect of the predicted metabolic score.

[0090] ROC analysis showed that, compared with other systems (Base system, Base+MeTs system, or stage system), the system constructed in Example 1 of this invention was superior in predicting overall survival for esophageal cancer (Table 1). AUC over time showed that the system constructed in Example 1 of this invention outperformed the control system at every time point (Table 1).

Claims

1. A nomogram system for predicting the prognosis of esophageal cancer, characterized in that, The line graph system includes the following modules: I. Data Input Module The input is used to obtain the patient's characteristic data, which includes age, T stage, N stage, metastatic site, intraoperative chemotherapy, smoking, and metabolic score; the patient is an esophageal cancer patient. II. Model Building Module A nomogram predicting overall survival for esophageal cancer patients was constructed using feature data from the input module. III. Prediction Module Input the feature data of the patient to be predicted into the nomogram constructed in step two, and output the prediction results.

2. The nodal chart system according to claim 1, characterized in that, The esophageal cancer patients mentioned are those who underwent esophagectomy for stage I-IV esophageal cancer.

3. The nodal chart system according to claim 1, characterized in that, The metabolic integral was calculated as follows: Restricted cubic plot analysis was used to analyze the impact of metabolic syndrome components on the prognosis of esophageal cancer patients, identifying nonlinear and linear influencing factors. The metabolic integral value was then calculated using the following R language formula: res.cox <- coxph(surv(time,status) TG+HDL+rcs(GLU,4)+rcs(BMI,4)+SBP+DBP,data=aa); The metabolic syndrome components include body mass index, fasting blood glucose, blood pressure, triglycerides, and high-density lipoprotein, and the blood pressure includes systolic and diastolic blood pressure; In the R language calculation formula, BMI is body mass index, GLU is fasting blood glucose, SBP is systolic blood pressure, DBP is diastolic blood pressure, TG is triglycerides, and HDL is high-density lipoprotein.

4. The nodal chart system according to claim 3, characterized in that, Among the components of metabolic syndrome, BMI is a non-linear influencing factor, while GLU, SBP, DBP, TG, and HDL are linear influencing factors.

5. The nodal chart system according to claim 1, characterized in that, The age is a continuous variable, and the value of the age variable is the patient's age in years; The T-stage is a discrete variable, and the value of the T-stage variable represents the depth of tumor invasion in the patient. The T-stage variable is assigned the following values: 1 represents T1, 2 represents T2, 3 represents T3, and 4 represents T4. The N stage is a discrete variable, and the value of the N stage variable represents the lymph node metastasis in the tumor area of ​​the patient. The T stage variable is assigned the value as follows: 0 represents N0, 1 represents N1, 2 represents N2, and 3 represents N3. The metastatic site is a discrete variable, represented by the value of the metastatic site variable. The assignment method of the metastatic site variable is as follows: 0 represents no metastasis, 1 represents lung metastasis, 2 represents liver metastasis, 3 represents abdominal metastasis, 4 represents bone metastasis, 5 represents multiple metastases, and NA represents unknown metastatic site. Intraoperative chemotherapy is a discrete variable. The value of the intraoperative chemotherapy variable indicates whether chemotherapy was performed during the operation. The intraoperative chemotherapy variable is assigned the value as follows: 0 indicates no, and 1 indicates yes. Smoking is a discrete variable, represented by the value of the smoking variable. The smoking variable is assigned the following values: 0 represents non-smoker, 1 represents smoker, 2 represents former smoker who is currently quitting, 3 represents non-smoker, and 4 represents unknown smoking status. The metabolic integral is a continuous variable.

6. The nomogram system according to any one of claims 1-5, characterized in that, In the model construction module, the method of constructing a nomogram predicting the overall survival of esophageal cancer patients using the feature data of the input module is to perform multivariate Cox regression analysis on the feature data of the input module and then draw the nomogram.

7. The nodal chart system according to any one of claims 1-5, characterized in that, The total survival periods are 1 year, 3 years, and 5 years.

8. Use of the nomogram system according to any one of claims 1 to 7 in the preparation of a device for predicting the prognosis of esophageal cancer.

9. A computer-readable storage medium having stored thereon a computer program for implementing the nodal chart system as claimed in any one of claims 1 to 7.

Images