Hybrid liver cancer prognosis model, prognosis system and medium

Abstract

A hybrid liver cancer prognosis model, prognosis system and medium, the model takes independent influence factors as input and outputs hybrid liver cancer postoperative risk scores, the hybrid liver cancer postoperative risk scores are used for dividing risk levels, and the risk levels are used for hybrid liver cancer prognosis evaluation. And / or is used for postoperative adjuvant chemotherapy decision-making of mixed liver cancer. The hybrid liver cancer prognosis model is jointly constructed by combining the traditional clinical pathological characteristics and immune microenvironment indexes, the key effect of the tumor immune microenvironment in CHC prognosis is indicated, and the constructed hybrid liver cancer prognosis model has good CHC prognosis prediction performance; in addition, decisions of postoperative adjuvant chemotherapy can be provided for patients with different risk levels, precise treatment of the CHC patients is achieved, and long-term survival prognosis of the CHC patients is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of postoperative cancer prognosis, and in particular to a mixed liver cancer prognosis model, a prognosis system and a medium. Background Art

[0002] Combined hepatocellular cholangiocarcinoma (CHC) is a rare primary liver malignancy with dual histological features of hepatocellular carcinoma (HCC) and cholangiocarcinoma (CCA). Despite its relatively low incidence, its complex biological behavior and significant molecular and histological heterogeneity make this tumor more aggressive, with a higher postoperative recurrence rate and significantly inferior long-term survival compared to single tumor types. Currently, surgical resection remains the only curative treatment for CHC patients, but the recurrence rate exceeding 50% and the lack of standardized adjuvant treatment strategies have become major obstacles to long-term survival.

[0003] In the era of precision medicine, providing scientific, personalized postoperative management strategies for CHC patients has become a critical clinical issue that needs to be addressed. As an intuitive prediction tool based on multivariate analysis, the nomogram effectively integrates a patient's clinicopathological features and molecular biological markers to provide personalized, quantitative survival predictions. It has been widely used in the prognostic assessment of various malignancies.

[0004] In recent years, more and more studies have been conducted on the prognostic nomogram model for mixed liver cancer. In the study "Study on the Prognostic Evaluation Value of PNI-CA19-9-Based Nomogram for Patients with Mixed Liver Cancer", a nomogram model was constructed based on virology, treatment methods, prognostic nutritional index and alkaline phosphatase as independent prognostic indicators for patients with mixed liver cancer. The nomogram model constructed in "Construction of Prognostic Risk Model for Patients with Mixed Liver Cancer Based on SEER Database" takes patient age, tumor differentiation, treatment methods, and TNM stage factors as independent clinical risk factors. In "Establishment and Validation of Prognostic Evaluation Model for Mixed Liver Cancer Based on SEER Database", fibrosis score and surgical status were further incorporated into the nomogram model for CHC prognosis.

[0005] However, existing nomogram models for CHC prognosis do not incorporate immune microenvironment-related indicators, ignoring the critical role of the tumor immune microenvironment in CHC prognosis. Furthermore, existing nomogram models can only provide CHC prognosis but cannot provide decision-making recommendations for adjuvant treatment of CHC patients, limiting their clinical applicability. Summary of the Invention

[0006] An object of the present application is to provide a mixed hepatocellular carcinoma prognosis model which combines traditional clinicopathological features and immune microenvironment indicators, not only has good CHC prognosis prediction performance, but also provides a basis for intervention strategy exploration around the immune microenvironment, and the model can also provide postoperative adjuvant chemotherapy decisions for patients at different risk levels, realize precise treatment of CHC patients, and improve the long-term survival prognosis of CHC patients.

[0007] The present application is realized by the following technical solutions:

[0008] A mixed hepatocellular carcinoma prognosis model, the model takes independent influencing factors as input, and outputs a mixed hepatocellular carcinoma postoperative risk score, the mixed hepatocellular carcinoma postoperative risk score is used to divide risk levels, the risk levels are used for mixed hepatocellular carcinoma prognosis evaluation, and / or for mixed hepatocellular carcinoma postoperative adjuvant chemotherapy decision-making;

[0009] The construction method of the mixed hepatocellular carcinoma prognosis model comprises the following steps:

[0010] Pathological data of mixed hepatocellular carcinoma patients are collected, a single factor Cox regression model is used to screen variables with p < 0.157 from the pathological data as potential variables affecting overall survival, the potential variables are included in a multi-factor Cox regression model to determine the independent influencing factors, and the mixed hepatocellular carcinoma prognosis model is constructed based on the independent influencing factors.

[0011] In the technical solution, the pathological data of patients diagnosed as CHC and receiving radical surgery are used to construct the mixed hepatocellular carcinoma prognosis model, including basic information, tumor characteristics, treatment-related data, immune microenvironment indicators, etc., and a single factor Cox regression model is used to preliminarily screen potential variables affecting the overall survival (OS) of patients. In the technical solution, the screening standard is set to p < 0.157 to avoid missing important potential variables. Next, the screened potential variables are further included in a multi-factor Cox regression model for analysis to determine independent prognostic factors affecting the overall survival of patients.

[0012] In the technical solution, based on the determined independent prognostic factors, a mixed hepatocellular carcinoma prognosis model, i.e. a nomogram prediction model, can be further constructed, so that after inputting the data of the independent prognostic factors of the patient, the mixed hepatocellular carcinoma postoperative risk score is output according to the data of the independent prognostic factors, and the risk level is divided according to the mixed hepatocellular carcinoma postoperative risk score. Different risk levels can not only reflect the prognosis evaluation of patients, but also provide accurate decisions for adjuvant chemotherapy of patients at different risk levels, and effectively improve the long-term survival prognosis of patients.

[0013] In this technical solution, the collected pathological data mainly include demographic data, liver function indicators, tumor characteristics, serum markers, treatment methods, follow-up data, and immune microenvironment indicators. By introducing immune microenvironment indicators into the collected pathological data, the role of the tumor immune microenvironment in CHC prognosis can be reflected, providing a basis for subsequent exploration of intervention strategies around the immune microenvironment. In one or more embodiments, demographic data mainly include gender, age, smoking history, drinking history, etc.; liver function indicators mainly include hepatitis B virus, cirrhosis, albumin (ALB), total bilirubin (TBIL), prothrombin time (PT), etc.; tumor characteristics mainly include maximum tumor diameter, microvascular invasion, macrovascular invasion, satellite nodules, lymph node metastasis, etc.; serum markers mainly include alpha-fetoprotein (AFP), etc.; treatment method is whether to receive adjuvant chemotherapy; follow-up data include overall survival, survival status, etc.; immune microenvironment indicators include CD8, CD20, FOXP3, PD-L1, etc.

[0014] In some preferred embodiments, the pathological data include gender, age, hepatitis B virus, cirrhosis, albumin, total bilirubin, prothrombin time, alpha-fetoprotein, satellite nodules, microvascular invasion, macrovascular invasion, lymph node metastasis, maximum tumor diameter, CD8, CD20, FOXP3, and PD-L1.

[0015] In some preferred embodiments, in order to reduce the interference of confounding factors and improve the scientific nature of the treatment effect evaluation, a propensity score matching method is used to construct a balanced propensity score matching (PSM) cohort.

[0016] In some preferred embodiments, the hybrid liver cancer prognostic model is used to predict 2-year and 3-year overall survival rates.

[0017] Furthermore, after incorporating immune microenvironment indicators into pathological data, five independent influencing factors were identified through univariate Cox regression model and multivariate Cox regression model analysis: maximum tumor diameter, large blood vessel invasion, lymph node metastasis, CD8, and FOXP3.

[0018] In this technical solution, of the five independent influencing factors, maximum tumor diameter, macrovascular invasion, and lymph node metastasis are tumor characteristics, while CD8 and FOXP3 are immune microenvironment indicators. This shows that after the inclusion of immune microenvironment indicators, the importance of patient age, treatment method, and alkaline phosphatase, which are used as independent influencing factors in the existing technology, for the prognosis assessment of CHC patients is reduced. In other words, tumor characteristics and immune microenvironment indicators have a stronger impact on the prognosis assessment of CHC than demographic data, liver function indicators, serum markers, and treatment methods.

[0019] Furthermore, the two immune microenvironment indicators, CD8 and FOXP3, can also reflect the responsiveness to adjuvant chemotherapy. For example, the greater the number of immune-activating cells, CD8, the better the response to treatment, and thus the better the prognosis. Another example is the greater the number of immunosuppressive cells, FOXP3, the worse the response to treatment, and thus the worse the prognosis. Therefore, by using the immune microenvironment indicators, CD8 and FOXP3, as independent influencing factors, targeted adjuvant therapy can be provided for patients at different risk levels as determined by the model, further improving prognosis.

[0020] In this technical solution, a mixed liver cancer prognostic model can be further constructed based on the variable lines of maximum tumor diameter, large blood vessel invasion, lymph node metastasis, CD8, and FOXP3.

[0021] Furthermore, the postoperative risk score for mixed liver cancer is calculated as follows:

[0022] The postoperative risk score for mixed-type HCC is (44.88 × maximum tumor diameter) + (59.65 × FOXP3) + (100 × CD8) + (65.2 × large vessel invasion) + (80.53 × lymph node metastasis).

[0023] Furthermore, the maximum tumor diameter greater than 5 cm was assigned a value of 1, and the maximum tumor diameter less than or equal to 5 cm was assigned a value of 0; FOXP3 positivity was assigned a value of 1, and FOXP3 negativity was assigned a value of 0; CD8 negativity was assigned a value of 1, and CD8 positivity was assigned a value of 0; the presence of macrovascular invasion was assigned a value of 1, and the absence of macrovascular invasion was assigned a value of 0; the presence of lymph node metastasis was assigned a value of 1, and the absence of lymph node metastasis was assigned a value of 0.

[0024] Furthermore, a higher postoperative risk score of mixed-type liver cancer indicates a worse prognosis, and conversely, a lower postoperative risk score of mixed-type liver cancer indicates a better prognosis.

[0025] Furthermore, patients with a postoperative risk score of mixed liver cancer greater than 130 points are divided into a high-risk group, and patients with a postoperative risk score of mixed liver cancer less than or equal to 130 points are divided into a low-risk group. For patients in the high-risk group, adjuvant chemotherapy is recommended, while for patients in the low-risk group, adjuvant chemotherapy is not recommended.

[0026] In this technical solution, the mixed liver cancer postoperative risk score of 130 points is used as the cutoff value to divide patients into high-risk and low-risk groups. The experiment found that the survival prognosis of patients in the high-risk group was significantly worse than that in the low-risk group, indicating that the mixed liver cancer prognostic model has a good stratification ability in postoperative survival prognosis. In addition, in the low-risk group, the adjuvant chemotherapy group did not show a better survival prognosis, but in the high-risk group, the survival rate of patients who received adjuvant chemotherapy was significantly better than that of patients who did not receive adjuvant chemotherapy. Based on this, according to the risk levels divided by the model, different adjuvant chemotherapy recommendations can be provided to patients with different risks to improve the patient's prognosis in a targeted manner.

[0027] Another object of the present invention is to provide a hybrid liver cancer prognosis system based on any of the aforementioned hybrid liver cancer prognosis models. After obtaining patient data such as treatment-related data and immune microenvironment indicators, the system outputs the patient's risk level based on the hybrid liver cancer prognosis model, and can further make auxiliary chemotherapy decisions based on the patient's risk level.

[0028] Specifically, a hybrid liver cancer prognosis system adopts any of the aforementioned hybrid liver cancer prognosis models, and the system includes:

[0029] A data input module, used to obtain patient data, including maximum tumor diameter, macrovascular invasion, lymph node metastasis, CD8, and FOXP3;

[0030] An analysis module for calculating a postoperative risk score for mixed liver cancer based on patient data and a mixed liver cancer prognostic model;

[0031] The output module is used to output the prognosis evaluation result of mixed liver cancer and / or the postoperative adjuvant chemotherapy decision of mixed liver cancer based on the postoperative risk score of mixed liver cancer.

[0032] Furthermore, it also includes an assignment module, which is used to obtain the assignment of each patient data according to the patient data. The analysis module calculates the postoperative risk score of mixed liver cancer based on the assignment of each patient data and the mixed liver cancer prognosis model.

[0033] Another object of the present invention is to provide a storage medium, specifically comprising a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to perform the following steps:

[0034] Acquiring patient data, including maximum tumor diameter, macrovascular invasion, lymph node metastasis, CD8, and FOXP3;

[0035] Calculating a mixed liver cancer postoperative risk score based on the patient data and any of the aforementioned mixed liver cancer prognostic models;

[0036] According to the mixed liver cancer postoperative risk score, a mixed liver cancer prognosis evaluation result and / or a postoperative adjuvant chemotherapy decision for mixed liver cancer are output.

[0037] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0038] 1. This study combines traditional clinical pathological features with immune microenvironment indicators to construct a hybrid liver cancer prognostic model, demonstrating the key role of the tumor immune microenvironment in CHC prognosis. This hybrid liver cancer prognostic model not only has good CHC prognostic prediction performance but also can provide decision-making for postoperative adjuvant chemotherapy for patients at different risk levels, enabling precise treatment of CHC patients and improving their long-term survival prognosis.

[0039] 2. In the mixed liver cancer prognostic model constructed by the present invention, the higher the CD8 expression, the better the treatment response and the corresponding prognosis evaluation, while the higher the FOXP3 expression, the worse the treatment response and the corresponding prognosis evaluation. By using the immune microenvironment indicators CD8 and FOXP3 as independent influencing factors, targeted adjuvant therapy can be provided for patients with different risk levels divided by the model;

[0040] 3. The hybrid liver cancer prognostic model of the present invention outputs a risk score based on the input independent risk factor assignments, and then divides CHC patients into different risk levels. It can provide an effective tool for individualized survival prediction and auxiliary treatment decision-making after surgery for patients, and has important clinical translational value. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0042] Figure 1 The figure shows the comparison of survival curves between the chemotherapy group and the non-chemotherapy group in the cohort after propensity score matching in a specific embodiment of the present invention;

[0043] Figure 2 The figure shows a mixed liver cancer prognostic nomogram model constructed in a specific embodiment of the present invention;

[0044] Figure 3 The figure shows the ROC curve of the 2-year survival prediction of the mixed liver cancer prognostic model in a specific embodiment of the present invention;

[0045] Figure 4 The figure shows the ROC curve of 3-year survival prediction of the mixed liver cancer prognostic model in a specific embodiment of the present invention;

[0046] Figure 5The calibration curve of the 2-year overall survival prediction of the mixed hepatocellular carcinoma prognosis model in the embodiment of the present application is shown.

[0047] Figure 6 The calibration curve of the 3-year overall survival prediction of the mixed hepatocellular carcinoma prognosis model in the embodiment of the present application is shown.

[0048] Figure 7 The decision curve analysis of the 2-year survival prediction of the mixed hepatocellular carcinoma prognosis model in the embodiment of the present application is shown.

[0049] Figure 8 The decision curve analysis of the 3-year survival prediction of the mixed hepatocellular carcinoma prognosis model in the embodiment of the present application is shown.

[0050] Figure 9 The survival curve after risk stratification using the mixed hepatocellular carcinoma prognosis model in the embodiment of the present application is shown.

[0051] Figure 10 The survival curve comparison between the chemotherapy group and the non-chemotherapy group in the low-risk group divided by the mixed hepatocellular carcinoma prognosis model in the embodiment of the present application is shown.

[0052] Figure 11 The survival curve comparison between the chemotherapy group and the non-chemotherapy group in the high-risk group divided by the mixed hepatocellular carcinoma prognosis model in the embodiment of the present application is shown. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical scheme and advantages of the present application clearer, further detailed description of the present application will be given below in combination with embodiments and drawings, and the schematic embodiments of the present application and their descriptions are only used to explain the present application, and do not limit the present application.

[0054] All raw materials of the present application are not particularly limited in source, and can be purchased on the market or prepared according to conventional methods well known to those skilled in the art. All raw materials of the present application are not particularly limited in purity, and the present application preferably uses analytical purity or conventional purity requirements in the field of tumor molecular markers. The grade and abbreviation of all raw materials of the present application belong to conventional grade and abbreviation in the art, and each grade and abbreviation is clear and explicit in its relevant field, and those skilled in the art can purchase or prepare by conventional methods according to the grade, abbreviation and corresponding use.

[0055] In this study, all statistical analyses were performed using R software (version 4.4.3) and SPSS software (version 29.0). The nomogram model was constructed and validated using the "rms," ​​"survival," and "timeROC" packages in R software. ROC curves and calibration curves were drawn using the bootstrap resampling method. Decision curve analysis was performed using the "ggDCA" package. All statistical tests were two-sided, and the significance level was set at P < 0.05.

[0056] [Example 1]

[0057] In this example, a nomogram model was constructed as a mixed liver cancer prognostic model based on the clinical and follow-up data of CHC patients who underwent radical surgery at the Tianjin Medical University Cancer Institute and Hospital between January 2009 and December 2019.

[0058] Specifically, all patients were pathologically confirmed to have no distant metastasis or macrovascular invasion, and had complete postoperative follow-up data. Inclusion criteria were as follows: (1) age ≥ 18 years; (2) pathologically confirmed diagnosis of mixed HCC; (3) undergoing radical surgical resection (R0 resection); (4) complete clinical and follow-up data; (5) no macrovascular invasion or distant metastasis. Exclusion criteria were as follows: (1) follow-up less than 1 month; (2) history of other malignant tumors; (3) failure to achieve R0 resection after surgery; (4) incomplete clinical data. Finally, a total of 75 CHC patients were included in the study.

[0059] Of the 75 enrolled patients, 19 (25.3%) received adjuvant chemotherapy, while 56 (74.7%) did not. Patient basic information, tumor characteristics, and follow-up data were fully recorded, and long-term follow-up was performed to analyze the impact of adjuvant chemotherapy on overall survival. To eliminate the influence of potential confounding factors on the efficacy of adjuvant chemotherapy, propensity score matching (PSM) was used. A total of 57 patients were included: 19 in the chemotherapy group received adjuvant chemotherapy, and 38 in the non-chemotherapy group did not. After PSM matching, as shown in Table 1, there were no statistically significant differences in the main clinicopathological characteristics between the two groups, and baseline balance was good.

[0060] Table 1:

[0061]

[0062] After PSM matching, Kaplan-Meier survival analysis was performed on a total of 57 patients in the chemotherapy group (Chemotherapy) and the non-chemotherapy group (non-Chemotherapy). The results are as follows Figure 1As shown in the results, the overall survival of patients who received adjuvant chemotherapy was significantly better than that of patients who did not receive chemotherapy (P = 0.0011), indicating the survival benefit of adjuvant chemotherapy.

[0063] Next, a univariate Cox regression model was used to screen variables with p < 0.157 from the pathological data as potential variables affecting overall survival. As shown in Table 2 , six potential variables were obtained: gender, macrovascular invasion, lymph node metastasis, maximum tumor diameter, CD8, and FOXP3. Subsequently, the six potential variables were included in the multivariate Cox regression model. As shown in Table 2, macrovascular invasion (HR = 1.964, 95% CI: 1.074–3.591, P = 0.028), lymph node metastasis (HR = 3.712, 95% CI: 1.424–9.674, P = 0.007), maximum tumor diameter > 5 cm (HR = 1.661, 95% CI: 1.001–2.768, P = 0.050), CD8+ positive expression (HR = 0.285, 95% CI: 0.113–0.718, P = 0.008), and FOXP3+ positive expression (HR = 3.350, 95% CI: 1.192–9.415, P = 0.022) were independent prognostic factors affecting the overall survival of CHC patients. Therefore, five independent influencing factors were ultimately identified: macrovascular invasion, lymph node metastasis, maximum tumor diameter, CD8, and FOXP3. Notably, the multivariate Cox regression analysis results for the two immune microenvironment indicators further emphasized the importance of CD8 expression as a favorable prognostic factor and FOXP3 expression as a poor prognostic factor in the model, demonstrating the role of the tumor immune microenvironment in CHC prognosis.

[0064] Table 2:

[0065]

[0066] Then, a mixed liver cancer prognostic model was constructed based on five independent influencing factors: large vessel invasion, lymph node metastasis, maximum tumor diameter, CD8, and FOXP3. Figure 2 As shown in the figure, the nomogram predicts patients' 2-year (2-year OS) and 3-year (3-year OS) survival probabilities by assigning specific scores to each variable and calculating the total score. In the model, lymph node metastasis, macrovascular invasion, maximum tumor diameter >5 cm, and FOXP3 positive expression all significantly contribute to poor prognosis, while CD8 positive expression significantly improves survival prognosis.

[0067] The constructed prognostic model for mixed-type HCC is as follows: Postoperative risk score for mixed-type HCC = (44.88 × maximum tumor diameter value) + (59.65 × FOXP3 value) + (100 × CD8 value) + (65.2 × macrovascular invasion value) + (80.53 × lymph node metastasis value). A maximum tumor diameter greater than 5 cm is assigned a value of 1, while a maximum tumor diameter less than or equal to 5 cm is assigned a value of 0; FOXP3 positivity is assigned a value of 1, while FOXP3 negativity is assigned a value of 0; CD8 negativity is assigned a value of 1, while CD8 positivity is assigned a value of 0; the presence of macrovascular invasion (presence) is assigned a value of 1, while the absence of macrovascular invasion (absence) is assigned a value of 0; and the presence of lymph node metastasis (positive) is assigned a value of 1, while the absence of lymph node metastasis (negative) is assigned a value of 0.

[0068] [Example 2]

[0069] In this example, the mixed liver cancer prognostic model obtained in Example 1 was verified by ROC curve, calibration curve and decision curve analysis.

[0070] The results are as follows Figure 3 and Figure 4 As shown in the figure, the ROC curve results showed that the AUC of the model for predicting 2-year and 3-year survival were 0.694 and 0.689, respectively, suggesting that the mixed liver cancer prognostic model has good predictive accuracy.

[0071] The calibration performance of the model was evaluated by drawing calibration curves for 2-year and 3-year survival prediction using the Bootstrap method (re-sampling 100 times), as shown in Figure 2. Figure 5 and Figure 6 As shown in the figure, the calibration curves of 2-year and 3-year survival are close to the ideal reference line, indicating that the survival probability predicted by the hybrid liver cancer prognostic model is highly consistent with the actual survival rate.

[0072] Furthermore, decision curve analysis (DCA) was used to evaluate the clinical practicality of the model. Figure 7 and Figure 8 The results showed that the hybrid liver cancer prognostic model showed higher net clinical benefit (NetBenefit) in both 2-year and 3-year survival predictions, which was better than the "Treat All" or "No Treatment" strategy.

[0073] [Example 3]

[0074] Based on the risk score calculated by the hybrid liver cancer prognostic model in Example 1, 75 patients were divided into a high-risk group (46 cases) and a low-risk group (29 cases) with a cutoff value of 130 points. The Kaplan-Meier survival analysis results showed that Figure 10 As shown in the data, the survival prognosis of patients in the high-risk group was significantly worse than that in the low-risk group (P = 0.00031), verifying the good stratification ability of the hybrid liver cancer prognostic model in postoperative survival prognosis.

[0075] Furthermore, Figure 1 The results showed that the overall survival of patients who received adjuvant chemotherapy was significantly better than that of patients who did not receive chemotherapy (P = 0.0011). Figure 10 As shown in the data, in the low-risk group, the chemotherapy group did not show a better survival prognosis (P = 0.084). However, in the high-risk group, the survival rate of patients in the chemotherapy group was significantly better than that of patients in the non-chemotherapy group (P = 0.013).

[0076] Therefore, after dividing the risk levels into strata using the mixed liver cancer prognostic model, the risk levels can be further used to make decisions on postoperative adjuvant chemotherapy for mixed liver cancer and guide accurate prognosis.

[0077] [Example 4]

[0078] Based on the above embodiments, this embodiment provides a hybrid liver cancer prognosis system. The system adopts any of the above hybrid liver cancer prognosis models. The system includes:

[0079] A data input module, used to obtain patient data, including maximum tumor diameter, macrovascular invasion, lymph node metastasis, CD8, and FOXP3;

[0080] An analysis module for calculating a postoperative risk score for mixed liver cancer based on patient data and a mixed liver cancer prognostic model;

[0081] The output module is used to output the prognosis evaluation result of mixed liver cancer and / or the postoperative adjuvant chemotherapy decision of mixed liver cancer based on the postoperative risk score of mixed liver cancer.

[0082] In some preferred embodiments, the system further includes an assignment module, which is used to obtain the assignment of each patient data according to the patient data, and the analysis module calculates the postoperative risk score of mixed liver cancer based on the assignment of each patient data and the mixed liver cancer prognosis model.

[0083] [Example 5]

[0084] Based on the above embodiment, this embodiment provides a storage medium including a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to perform the following steps:

[0085] Acquiring patient data, including maximum tumor diameter, macrovascular invasion, lymph node metastasis, CD8, and FOXP3;

[0086] Calculating a postoperative risk score for mixed liver cancer based on the patient data and a mixed liver cancer prognostic model according to any one of claims 1 to 7;

[0087] According to the mixed liver cancer postoperative risk score, a mixed liver cancer prognosis evaluation result and / or a postoperative adjuvant chemotherapy decision for mixed liver cancer are output.

[0088] In this embodiment, the above-mentioned storage medium is a computer-readable storage medium. If the above-mentioned risk assessment steps are implemented in the form of a software functional unit and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above-mentioned various method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0089] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A mixed liver cancer prognosis model, characterized in that: The model uses independent influencing factors as input and outputs a postoperative risk score for mixed liver cancer. The postoperative risk score for mixed liver cancer is used to divide risk strata, and the risk strata are used for prognosis assessment of mixed liver cancer and / or for decision-making on postoperative adjuvant chemotherapy for mixed liver cancer. The method for constructing the mixed liver cancer prognosis model comprises the following steps: Pathological data of patients with mixed liver cancer were collected, and variables with p < 0.157 were screened from the pathological data using a univariate Cox regression model as potential variables affecting overall survival. The potential variables were incorporated into a multivariate Cox regression model to determine the independent influencing factors, and the mixed liver cancer prognostic model was constructed based on the independent influencing factors.

2. A mixed liver cancer prognosis model according to claim 1, characterized in that: The pathological data included gender, age, hepatitis B virus, liver cirrhosis, albumin, total bilirubin, prothrombin time, alpha-fetoprotein, satellite nodules, microvascular invasion, macrovascular invasion, lymph node metastasis, maximum tumor diameter, CD8, CD20, FOXP3, and PD-L1.

3. A mixed liver cancer prognosis model according to claim 1 or 2, characterized in that: The independent influencing factors include maximum tumor diameter, large blood vessel invasion, lymph node metastasis, CD8, and FOXP3.

4. A mixed liver cancer prognosis model according to claim 3, characterized in that: The calculation method of the postoperative risk score for mixed liver cancer is: The postoperative risk score for mixed-type HCC is (44.88 × maximum tumor diameter) + (59.65 × FOXP3) + (100 × CD8) + (65.2 × large vessel invasion) + (80.53 × lymph node metastasis).

5. A mixed liver cancer prognosis model according to claim 4, characterized in that: The maximum tumor diameter was assigned a value of 1 if it was greater than 5 cm, and 0 if it was less than or equal to 5 cm; FOXP3 positivity was assigned a value of 1, and FOXP3 negativity was assigned a value of 0; CD8 negativity was assigned a value of 1, and CD8 positivity was assigned a value of 0; the presence of macrovascular invasion was assigned a value of 1, and the absence of macrovascular invasion was assigned a value of 0; the presence of lymph node metastasis was assigned a value of 1, and the absence of lymph node metastasis was assigned a value of 0.

6. A mixed liver cancer prognostic model according to claim 5, characterized in that: A higher postoperative risk score for mixed-type liver cancer indicates a worse prognosis.

7. A mixed liver cancer prognostic model according to claim 5, characterized in that: Patients with a postoperative risk score of mixed liver cancer greater than 130 points are classified as a high-risk group, and patients with a postoperative risk score of mixed liver cancer less than or equal to 130 points are classified as a low-risk group. For patients in the high-risk group, adjuvant chemotherapy is recommended, while for patients in the low-risk group, adjuvant chemotherapy is not recommended.

8. A hybrid liver cancer prognosis system, characterized in that: A hybrid liver cancer prognosis model according to any one of claims 1 to 7 is used, the system comprising: A data input module, used to obtain patient data, including maximum tumor diameter, macrovascular invasion, lymph node metastasis, CD8, and FOXP3; An analysis module for calculating a postoperative risk score for mixed liver cancer based on patient data and a mixed liver cancer prognostic model; The output module is used to output the prognosis evaluation result of mixed liver cancer and / or the postoperative adjuvant chemotherapy decision of mixed liver cancer based on the postoperative risk score of mixed liver cancer.

9. A hybrid liver cancer prognosis system according to claim 8, characterized in that: It also includes an assignment module, which is used to obtain the assignment of each patient data according to the patient data. The analysis module calculates the postoperative risk score of mixed liver cancer based on the assignment of each patient data and the mixed liver cancer prognosis model.

10. A storage medium, characterized in that: The computer program includes a storage medium, wherein when the computer program is executed, the device where the storage medium is located is controlled to perform the following steps: Acquiring patient data, including maximum tumor diameter, macrovascular invasion, lymph node metastasis, CD8, and FOXP3; Calculating a postoperative risk score for mixed liver cancer based on the patient data and a mixed liver cancer prognostic model according to any one of claims 1 to 7; According to the mixed liver cancer postoperative risk score, a mixed liver cancer prognosis evaluation result and / or a postoperative adjuvant chemotherapy decision for mixed liver cancer are output.

Images