CN113571189A - Establishment method of prediction model for survival benefit of gallbladder cancer patient after radiotherapy and chemotherapy - Google Patents
Establishment method of prediction model for survival benefit of gallbladder cancer patient after radiotherapy and chemotherapy Download PDFInfo
- Publication number
- CN113571189A CN113571189A CN202110966188.5A CN202110966188A CN113571189A CN 113571189 A CN113571189 A CN 113571189A CN 202110966188 A CN202110966188 A CN 202110966188A CN 113571189 A CN113571189 A CN 113571189A
- Authority
- CN
- China
- Prior art keywords
- patients
- data
- benefit
- model
- group
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention relates to a method for establishing a prediction model for survival benefit of a gallbladder cancer patient after radiotherapy and chemotherapy, which comprises the steps of obtaining clinical and pathological data of the gallbladder cancer patient; dividing the acquired data into a plurality of groups of data according to the TNM stages, and respectively judging whether the patients in each stage benefit from the auxiliary treatment; dividing data corresponding to the TNM stages into a building module and an internal verification group; analyzing the prediction capability of clinical and pathological variables of the modeling group data on the total survival time OS through a single-factor COX risk proportion model, and screening out risk factors which obviously influence the total survival time OS of patients in the modeling group; bringing the screened risk factors into multi-factor COX risk proportion model analysis, and screening influence variables which obviously influence the total survival time OS of the patient; drawing a nomogram for predicting the total survival time OS according to the obtained influence variables to obtain a prediction model; and verifying the model. Compared with the prior art, the method has the advantages of providing credible prediction and analysis results for GBC patients, being simple and convenient to operate and the like.
Description
Technical Field
The invention relates to the technical field of prognosis evaluation, in particular to a prediction model establishment method for survival benefit of a gallbladder cancer patient after radiotherapy and chemotherapy.
Background
Gallbladder cancer (GBC) is the fifth most prevalent of gastrointestinal tumors, with an annual incidence of 2 to 27 per 10 million people. Although relatively rare, GBC is the most aggressive malignancy of the biliary tract, with a 5-year survival rate of about 5%. Surgical resection is the only method of treating GBC. However, the recurrence rate after complete resection is high, often leading to poor prognosis. Therefore, adjuvant treatments such as postoperative chemotherapy, chemotherapy in combination with radiotherapy are applied to GBC patients to improve patient prognosis.
However, because of the low incidence rate of GBC, the difference of the GBC auxiliary treatment indication and the curative effect of the combination of postoperative chemotherapy and chemotherapy radiotherapy is controversial. At present, the difference of the curative effects of postoperative chemotherapy and chemotherapy combined radiotherapy in the prior art is lack of deep research, and no better method for predicting the prognosis of GBC patients receiving chemotherapy or chemotherapy combined radiotherapy exists at present, so that the prognosis cannot be reliably analyzed.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide a prediction model establishing method which can provide credible prediction and analysis results for GBC patients and is simple and convenient to operate and can help gallbladder cancer patients to survive and benefit after radiotherapy and chemotherapy.
The purpose of the invention can be realized by the following technical scheme:
a method for establishing a prediction model for survival benefit of a gallbladder cancer patient after radiotherapy and chemotherapy, the method for establishing the prediction model comprises the following steps:
step 1: acquiring clinical and pathological data of a gallbladder cancer patient;
step 2: dividing the data acquired in the step 1 into a plurality of groups of data according to TNM stages, comparing survival differences of TNM analysis patients corresponding to the plurality of groups of data after receiving different auxiliary treatments, respectively judging whether the patients in each stage benefit from the auxiliary treatments, if the corresponding TNM stage patients can benefit from the auxiliary treatments, executing the step 3, otherwise, directly outputting that the patients in the stage can not benefit from the auxiliary treatments;
and step 3: according to the result obtained in the step 2, dividing the data corresponding to the TNM staging in the step 1 into a building module group and an internal verification group;
and 4, step 4: analyzing the prediction capability of clinical and pathological variables of the modeling group data on the total survival time OS through a single-factor COX risk proportion model, and screening out risk factors which obviously influence the total survival time OS of patients in the modeling group;
and 5: bringing the risk factors screened out in the step 4 into multi-factor COX risk proportion model analysis, and screening out influence variables which obviously influence the total survival time OS of the patient;
step 6: drawing a nomogram for predicting the total survival time OS according to the influence variables obtained in the step 5 to obtain a prediction model;
and 7: and verifying the model.
Preferably, the clinical and pathological data of the gallbladder cancer patient in step 1 include: sex, age, degree of tumor differentiation, TNM staging, mode of operation, number of lymph nodes cleared, mode of adjuvant treatment after operation, and overall survival time OS of the patient; the operation mode comprises non-adjuvant therapy NCRT and chemotherapy CT qualified chemotherapy combined radiotherapy CRT.
More preferably, the step 2 specifically includes:
step 2-1: dividing the data in the step 1 into a plurality of groups of data according to the TNM stages;
step 2-2: calculating a tendency score PS by adopting a generalized enhanced model GBM;
step 2-3: carrying out inverse probability weighting IPTW on each group of data by adopting a tendency score PS;
step 2-4: comparing the difference of each group of variables before and after IPTW weighting;
step 2-5: and (3) carrying out survival analysis on the samples before and after IPTW weighting by a Kaplan-Meier method, judging whether the patients in each stage benefit from the auxiliary treatment, if the corresponding TNM staged patients can benefit from the auxiliary treatment, executing the step 3, and otherwise, directly outputting that the patients in the stage cannot benefit from the auxiliary treatment.
More preferably, the weight of the sample when inverse probability weighting IPTW is performed in the step 2-3 is the reciprocal of the trend score, namely:
where w is the sample weight and PS is the trend score of the sample.
More preferably, in the step 2-4, the difference of each group of variables before and after IPTW weighting is compared by using absolute standard difference; the calculation method of the absolute standard difference comprises the following steps:
wherein, PtreatCorresponding parameter values for the processing set; pcontrolCorresponding parameter values for the control group.
More preferably, the steps 2 to 5 further include: the difference in survival curves was compared using the log-rank test.
Preferably, the step 4 specifically includes:
the prediction capability of clinical and pathological variables of the modeling group data on the total survival time OS is analyzed through a single-factor COX risk proportion model, and the factors with the p less than 0.05 in the analysis result are screened out to be used as risk factors which obviously influence the total survival time OS of patients in the modeling group.
Preferably, the step 5 specifically comprises:
and (4) bringing the risk factors screened out in the step (4) into multi-factor COX risk proportion model analysis, and screening out variables with p less than 0.05 in the analysis result as influence variables which obviously influence the total survival time OS of the patient.
Preferably, the step 3 further comprises: and (3) acquiring an external verification group while dividing the data corresponding to the TNM stage in the step (1) into a building group and an internal verification group.
More preferably, the step 7 specifically includes:
and verifying the prediction model by using the internal verification group data and the external verification group data, wherein the verification of the model is completed by C-index and consistency curve analysis.
Compared with the prior art, the invention has the following beneficial effects:
firstly, providing credible prediction and analysis results for GBC patients: the method for establishing the prediction model for survival benefit of the gallbladder cancer patient after radiotherapy and chemotherapy extracts the characteristic modeling nomogram prediction model by collecting the conventional clinical pathological indexes of the patient, has objective and accurate results, respectively performs prediction analysis on specific individuals, and provides credible prediction and analysis results.
Secondly, the operation is simple and convenient: the establishing method of the survival benefit prediction model of the gallbladder cancer patient after radiotherapy and chemotherapy has simple, visual and easily repeated operation process, and can be completed by the hospitalized doctors.
Drawings
FIG. 1 is a schematic flow chart of a method for establishing a prediction model of survival benefit of a gallbladder cancer patient after radiotherapy and chemotherapy according to the present invention;
FIG. 2(a) is a graph showing the difference between baseline indicators before and after NCRT \ CT matching and weighting for GBC patients in stage II according to an embodiment of the present invention;
FIG. 2(b) is a graph showing the difference between the baseline indicators before and after NCRT \ CRT matching and weighting for the GBC patient in stage II in the example of the present invention;
FIG. 2(c) is a graph of baseline index variation before and after CT \ CRT matching and weighting for GBC patients in stage II in accordance with an embodiment of the present invention;
FIG. 3(a) is a graph of K-M survival before matching for stage II GBC patients in an example of the invention;
FIG. 3(b) is a K-M survival graph after matching of stage II GBC patients in an example of the invention;
FIG. 4(a) is a graph of the change in baseline index difference before and after NCRT \ CT matching and weighting for patients with stage III-IV GBC in accordance with an embodiment of the present invention;
FIG. 4(b) is a graph of the change in baseline index difference before and after NCRT \ CRT matching and weighting for patients with stage III-IV GBC in accordance with an embodiment of the present invention;
FIG. 4(c) is a graph of baseline index variation before and after CT \ CRT matching and weighting for patients with stage III-IV GBC in accordance with an embodiment of the present invention;
FIG. 5(a) is a graph of K-M survival before matching for patients with stage III-IV GBC in an example of the invention;
FIG. 5(b) is a graph of K-M survival following matching of patients with stage III-IV GBC in an example of the invention;
FIG. 6 is a nomogram of prognosis for patients with GBC stages III-IV in an example of the present invention;
FIG. 7(a) is a graph of the consistency of predicted survival rates at 12, 24, 36 months obtained from modeling group data in an example of the invention;
FIG. 7(b) is a graph of the consistency of predicted survival rates at 12, 24, 36 months obtained for internal validation cohort data in an example of the present invention;
fig. 7(c) is a graph of consistency of predicted survival rates for 12, 24, 36 months obtained from external validation cohort data in an example of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of protection of the present invention.
The embodiment relates to a method for establishing a prediction model of survival benefit of a gallbladder cancer patient after radiotherapy and chemotherapy, the flow of which is shown in fig. 1 and comprises the following steps:
step 1: obtaining clinical and pathological data of a gallbladder cancer patient, comprising: sex, age, tumor differentiation degree, TNM staging, operation mode, number of lymph nodes cleaned, postoperative adjuvant therapy mode and total survival time OS of the patient, wherein the operation mode comprises non-adjuvant therapy NCRT, chemotherapy CT qualified chemotherapy and radiotherapy CRT;
step 2: dividing the data acquired in the step 1 into a plurality of groups of data according to TNM stages, comparing survival differences of TNM analysis patients corresponding to the plurality of groups of data after receiving different auxiliary treatments, respectively judging whether the patients in each stage benefit from the auxiliary treatments, if the corresponding TNM stage patients can benefit from the auxiliary treatments, executing the step 3, otherwise, directly outputting that the patients in the stage can not benefit from the auxiliary treatments;
the step 2 specifically comprises the following steps:
step 2-1: dividing the data in the step 1 into a plurality of groups of data according to the TNM stages;
step 2-2: calculating a tendency score PS by adopting a generalized enhanced model GBM;
step 2-3: carrying out inverse probability weighting IPTW on each group of data by adopting a tendency score PS;
the weight of the sample when inverse probability weighting IPTW is performed is the inverse of the trend score, i.e.:
wherein w is the sample weight, and PS is the tendency score of the sample;
step 2-4: comparing the difference of each group of variables before and after IPTW weighting;
comparing the difference of each group of variables before and after IPTW weighting by adopting absolute standard difference, wherein the calculation method of the absolute standard difference comprises the following steps:
wherein, PtreatCorresponding parameter values for the processing set; pcontrolThe corresponding parameter value of the comparison group;
step 2-5: carrying out survival analysis on the samples before and after IPTW weighting by a Kaplan-Meier method, meanwhile, comparing the difference of survival curves by adopting log-rank test, judging whether the patients in each stage benefit from the auxiliary treatment, if the corresponding TNM staged patients can benefit from the auxiliary treatment, executing the step 3, otherwise, directly outputting that the patients in the stage can not benefit from the auxiliary treatment;
and step 3: according to the result obtained in the step 2, dividing the data corresponding to the TNM stage in the step 1 into a building module group and an internal verification group, and simultaneously obtaining an external verification group;
and 4, step 4: analyzing the prediction capability of clinical and pathological variables of the modeling group data on the total survival time OS through a single-factor COX risk proportion model, and screening out factors with p less than 0.05 in an analysis result as risk factors which obviously influence the total survival time OS of patients in the modeling group;
and 5: bringing the risk factors screened out in the step 4 into multi-factor COX risk proportion model analysis, and screening out variables with p less than 0.05 in the analysis result as influence variables which obviously influence the total survival time OS of the patient;
step 6: drawing a nomogram for predicting the total survival time OS according to the influence variables obtained in the step 5 to obtain a prediction model;
and 7: and verifying the prediction model by using the internal verification group data and the external verification group data, wherein the verification of the model is completed by C-index and consistency curve analysis.
The following provides a specific application case:
(1) collecting data
2689 GBC patients who underwent surgery in the SEER database in 2004-.
Clinical and pathological data were collected as follows: gender, age, degree of tumor differentiation, TNM staging, mode of surgery, number of lymph nodes cleared, mode of adjuvant treatment after surgery, total survival time (OS).
(2) Determining whether benefit can be gained from adjuvant therapy
2689 patients with GBC from SEER database were staged by TNM into stages II and III-IV. Calculating a trend score (PS) by adopting a Generalized enhanced model (GBM), balancing the variables of patients without adjuvant therapy, chemotherapy and chemotherapy combined radiotherapy, such as sex, age, tumor differentiation degree, operation mode, number of cleaned lymph nodes and the like in each group by adopting inverse probability weighting (IPTW), drawing a Kaplan-Meier survival curve, and comparing the survival difference after different adjuvant therapies are received in the II stage and the III-IV stage. Patients with GBC stage III-IV were found to benefit from adjuvant therapy.
(2.1) calculating the Trend score PS of a sample Using the GBM model
Classical PS estimates are mostly derived by using parametric linear logistic regression models or variable selection techniques to screen out interactive terms or non-linear terms, which may miss important confounding variables or misassigning functional relationships between covariates and process choices in the model. The invention is based on a GBM model, which is a model that combines multiple regression trees to obtain an iterative process of complex nonlinear relationships between intervention allocation and preprocessing covariates without overfitting data. The total model is formed by accumulating a plurality of submodels according to corresponding weights, the assumed space of the submodels is not particularly limited and can be any discrete or continuous function. The GBM, by means of an iterative algorithm, outputs probability values, i.e. groups of PS, in accordance with the categories.
For GBC patients in stage II, their age, sex, differentiation grade, mode of operation, number of lymph node cleanings, etc. were taken into account and their PS calculated. And (4) calculating PS (prostate specific antigen) for the GBC patients in stages III-IV by taking the GBC patients in stages III-IV into the age, sex, differentiation grade, T stage, N stage, operation mode, lymph node clearing number and other variables. This is achieved by the Tweng package of the R software (V4.0.2).
(2.2) inverse probability weighting IPTW on samples Using trend Scoring PS
Assuming no unidentified confounders exist, the weighting adjustment adjusts the data based on two probabilities of counterfactual events under certain conditions: namely, the two cases of processing factors and not processing are assumed to be received by each observation object. The estimated weight of the tendency score is used for weighting each observation unit to generate a virtual standard population (the generation of the virtual population refers to the number of persons who copy the weight), and in the virtual population, two groups of mixed factors tend to be consistent and are similar to a certain pre-selected standard population distribution. The tendency score weighting method is based on calculating the tendency score, and based on the principle of a standardized method, each research object is given a corresponding weight for weighting through the tendency score value, so that the tendency scores in each group are distributed consistently, and the purpose of eliminating the influence of confounding factors is achieved. Thus the weighted method of predisposition score is a standardized method based on individuals. IPTW is a weighting method that adjusts for all observed objects as a "standard population". The sample weight w is the inverse of the trend score PS, i.e., w is 1/PS.
(2.3) comparison of the differences between the variables of the respective groups before and after IPTW Using Absolute Standard Difference (Absolute Standard differentiated reference)
The absolute standard deviation calculation method comprises the following steps:
it is generally accepted that the balance between groups is better when the absolute standard deviation is less than 10%. It can be seen from fig. 2(a), 2(b) and 2(c) that the phase II GBC patient variables receiving different adjunctive therapies after IPTW weighting tend to balance. It can be seen from figures 4(a), 4(b) and 4(c) that the GBC stage III-IV patient variables receiving different adjunctive therapies after IPTW weighting tend to balance.
(2.4) survival assay
And (3) carrying out survival analysis on the samples before and after IPTW weighting by a Kaplan-Meier method, comparing the difference of survival curves by adopting log-rank test, and testing the standard alpha to be 0.05. FIG. 3(a) and FIG. 3(b) show the survival of GBC patients in stage II before and after IPTW weighting, respectively, with no significant difference in prognosis among NCRT, CT and CRT patients. FIGS. 5(a) and 5(b) show the survival of GBC stage III-IV patients before and after IPTW weighting, respectively, with superior CT treatment prognosis for GBC stage III-IV patients receiving CRT treatment and superior CT treatment prognosis for GBC stage III-IV patients receiving CT treatment than NCRT. Therefore, stage III-IV GBC patients may benefit from CT and CRT adjunctive therapy.
(3) The method divides the GBC patients who receive the operations in stages III-IV in the SEER database 1496 into a building group (2004 + 2012 confirmed) and an internal verification group (2013 + 2015 confirmed), and 88 GBC patients who receive the operations in a certain hospital in 2016 + 2018 are used as external verification groups.
(4) Using SPSS software (V19.0 statistical software), the predictive power of variables such as sex, age, differentiation grade, T stage, N stage, surgical mode, number of lymph node cleanings, adjuvant therapy mode, etc. in the modeling group on OS was first analyzed by a one-way COX risk ratio model, and variables with statistical significance p < 0.05 in the analysis results were considered to be significantly related to OS and included in the multi-factor analysis.
In this example, variables such as sex, age, differentiation grade, T stage, N stage lymph node clearing number, adjuvant therapy mode, etc. were screened to be significantly related to patient OS in a single-factor COX risk ratio model.
(5) Inputting all factors related to the OS obtained by analyzing in the step 4, carrying out multi-factor COX risk proportion model analysis, and bringing variables with p less than 0.05 in the analysis result into a final nomogram model.
In this example, age, differentiation grade, T stage, N stage, lymph node clearing number, and adjuvant therapy mode were screened to be significantly related to OS in the multifactorial COX risk ratio model.
(6) The variables obtained from step 5 were analyzed and nomograms for predicting OS were plotted using survivval and rms packages of R software (V4.0.2).
In the alignment chart shown in fig. 6, the first line is a point scale (Points), and Points range from 0 to 10. Age of second act (Age), differentiation Grade (differentiation Grade) in third act, T Stage (TStage) in fourth act, N Stage (N Stage) in fifth act, lymph node clearing number (Lymphadenectomy) in sixth act, and Adjuvant Therapy approach in seventh act (Adjuvant Therapy). The eighth action is Total Points (Total Points), with a score range of 0-35 Points. A ninth behavior of 1-year survival rate, a tenth behavior of 2-year survival rate, an eleventh behavior of 3-year survival rate, and a twelfth behavior of Median survival Time (media survival Time).
(7) After the nomogram model is established, the model is verified using the internal verification group and the external verification group data. The model was verified by C-index and consistency curve analysis. The C-index indexes of the modeling group, the internal verification group and the external verification group are respectively 0.673 (95% CI:0.654-0.692), 0.707 (95% CI: 0.677-0. 739) and 0.729 (95% CI: 0.688-0. 775). The corresponding consistency curves are shown in fig. 7(a), fig. 7(b) and fig. 7 (c).
For any GBC patient undergoing surgical resection, the actual condition of each clinical pathological variable in the second to seventh lines of the nomogram is scored, and the specific score scale of each variable is the score of the position corresponding to the first line. The scores of the 6 variables are summed to determine the total score for the patient, and the corresponding score position is found in the eighth row, and then the predicted probability of survival of the patient in 12 th, 24 th, 36 th months and the median OS time can be derived from the corresponding positions of the total score in the tenth, eleventh, and twelfth rows.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method for establishing a prediction model for survival benefit of a gallbladder cancer patient after radiotherapy and chemotherapy is characterized by comprising the following steps:
step 1: acquiring clinical and pathological data of a gallbladder cancer patient;
step 2: dividing the data acquired in the step 1 into a plurality of groups of data according to TNM stages, comparing survival differences of TNM analysis patients corresponding to the plurality of groups of data after receiving different auxiliary treatments, respectively judging whether the patients in each stage benefit from the auxiliary treatments, if the corresponding TNM stage patients can benefit from the auxiliary treatments, executing the step 3, otherwise, directly outputting that the patients in the stage can not benefit from the auxiliary treatments;
and step 3: according to the result obtained in the step 2, dividing the data corresponding to the TNM staging in the step 1 into a building module group and an internal verification group;
and 4, step 4: analyzing the prediction capability of clinical and pathological variables of the modeling group data on the total survival time OS through a single-factor COX risk proportion model, and screening out risk factors which obviously influence the total survival time OS of patients in the modeling group;
and 5: bringing the risk factors screened out in the step 4 into multi-factor COX risk proportion model analysis, and screening out influence variables which obviously influence the total survival time OS of the patient;
step 6: drawing a nomogram for predicting the total survival time OS according to the influence variables obtained in the step 5 to obtain a prediction model;
and 7: and verifying the model.
2. The method of claim 1, wherein the clinical and pathological data of the gallbladder cancer patient in step 1 comprises: sex, age, degree of tumor differentiation, TNM staging, mode of operation, number of lymph nodes cleared, mode of adjuvant treatment after operation, and overall survival time OS of the patient; the operation mode comprises non-adjuvant therapy NCRT and chemotherapy CT qualified chemotherapy combined radiotherapy CRT.
3. The method for establishing a predictive model of survival benefit of a gallbladder cancer patient after radiotherapy and chemotherapy according to claim 2, wherein the step 2 specifically comprises:
step 2-1: dividing the data in the step 1 into a plurality of groups of data according to the TNM stages;
step 2-2: calculating a tendency score PS by adopting a generalized enhanced model GBM;
step 2-3: carrying out inverse probability weighting IPTW on each group of data by adopting a tendency score PS;
step 2-4: comparing the difference of each group of variables before and after IPTW weighting;
step 2-5: and (3) carrying out survival analysis on the samples before and after IPTW weighting by a Kaplan-Meier method, judging whether the patients in each stage benefit from the auxiliary treatment, if the corresponding TNM staged patients can benefit from the auxiliary treatment, executing the step 3, and otherwise, directly outputting that the patients in the stage cannot benefit from the auxiliary treatment.
4. The method for modeling survival benefit of gallbladder cancer patients after radiotherapy and chemotherapy according to claim 3, wherein the sample weight in the step 2-3 is inverse of the trend score when inverse probability weighting IPTW is performed, that is:
where w is the sample weight and PS is the trend score of the sample.
5. The method for establishing a predictive model of survival benefit of patients with gallbladder cancer after radiotherapy and chemotherapy according to claim 3, wherein the differences of the variables before and after IPTW weighting are compared by absolute standard difference in steps 2-4; the calculation method of the absolute standard difference comprises the following steps:
wherein, PtreatCorresponding parameter values for the processing set; pcontrolCorresponding parameter values for the control group.
6. The method according to claim 3, wherein the steps 2-5 further comprise: the difference in survival curves was compared using the log-rank test.
7. The method for establishing a predictive model of survival benefit of a gallbladder cancer patient after radiotherapy and chemotherapy according to claim 1, wherein the step 4 specifically comprises:
the prediction capability of clinical and pathological variables of the modeling group data on the total survival time OS is analyzed through a single-factor COX risk proportion model, and the factors with the p less than 0.05 in the analysis result are screened out to be used as risk factors which obviously influence the total survival time OS of patients in the modeling group.
8. The method for establishing a predictive model of survival benefit of a gallbladder cancer patient after radiotherapy and chemotherapy according to claim 1, wherein the step 5 specifically comprises:
and (4) bringing the risk factors screened out in the step (4) into multi-factor COX risk proportion model analysis, and screening out variables with p less than 0.05 in the analysis result as influence variables which obviously influence the total survival time OS of the patient.
9. The method of claim 1, wherein the step 3 further comprises: and (3) acquiring an external verification group while dividing the data corresponding to the TNM stage in the step (1) into a building group and an internal verification group.
10. The method for establishing a predictive model of survival benefit of a gallbladder cancer patient after radiotherapy and chemotherapy according to claim 9, wherein the step 7 comprises:
and verifying the prediction model by using the internal verification group data and the external verification group data, wherein the verification of the model is completed by C-index and consistency curve analysis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110966188.5A CN113571189A (en) | 2021-08-23 | 2021-08-23 | Establishment method of prediction model for survival benefit of gallbladder cancer patient after radiotherapy and chemotherapy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110966188.5A CN113571189A (en) | 2021-08-23 | 2021-08-23 | Establishment method of prediction model for survival benefit of gallbladder cancer patient after radiotherapy and chemotherapy |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113571189A true CN113571189A (en) | 2021-10-29 |
Family
ID=78172306
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110966188.5A Pending CN113571189A (en) | 2021-08-23 | 2021-08-23 | Establishment method of prediction model for survival benefit of gallbladder cancer patient after radiotherapy and chemotherapy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113571189A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113555123A (en) * | 2021-08-27 | 2021-10-26 | 复旦大学附属中山医院 | Method for establishing prediction model of survival benefit of gallbladder cancer patient after radiotherapy and chemotherapy |
| CN116092664A (en) * | 2022-11-25 | 2023-05-09 | 中山大学孙逸仙纪念医院 | Pancreatic cancer prognosis prediction model establishment method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150024409A1 (en) * | 2012-02-22 | 2015-01-22 | Nahid Razi | Methods and systems for predicting drug-response |
| WO2015114146A1 (en) * | 2014-02-03 | 2015-08-06 | Sividon Diagnostics Gmbh | Method for predicting the response to an anti-her2 containing therapy and/or chemotherapy in patients with breast cancer |
| CN112542247A (en) * | 2020-08-17 | 2021-03-23 | 中山大学孙逸仙纪念医院 | Method and system for predicting probability of complete remission of pathology after breast cancer neoadjuvant chemotherapy |
| CN112802605A (en) * | 2021-01-13 | 2021-05-14 | 四川大学华西医院 | Prediction model for survival benefit of metastatic renal cancer patient after receiving system treatment and establishment method and application thereof |
-
2021
- 2021-08-23 CN CN202110966188.5A patent/CN113571189A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150024409A1 (en) * | 2012-02-22 | 2015-01-22 | Nahid Razi | Methods and systems for predicting drug-response |
| WO2015114146A1 (en) * | 2014-02-03 | 2015-08-06 | Sividon Diagnostics Gmbh | Method for predicting the response to an anti-her2 containing therapy and/or chemotherapy in patients with breast cancer |
| CN112542247A (en) * | 2020-08-17 | 2021-03-23 | 中山大学孙逸仙纪念医院 | Method and system for predicting probability of complete remission of pathology after breast cancer neoadjuvant chemotherapy |
| CN112802605A (en) * | 2021-01-13 | 2021-05-14 | 四川大学华西医院 | Prediction model for survival benefit of metastatic renal cancer patient after receiving system treatment and establishment method and application thereof |
Non-Patent Citations (5)
| Title |
|---|
| 于建发;仲崇立;郎琦;田雨;: "基于SEER数据库分析胆囊癌肝转移患者预后因素并构建竞争风险列线图", 现代肿瘤医学, no. 21 * |
| 王思斯;陈明;孙哲;林洁涛;曹洋;: "非小细胞肺癌生存预测列线图的构建与验证", 实用肿瘤杂志, no. 04 * |
| 秦琼 等: ""Ⅱ期结肠癌根治术后奥沙利铂联合氟尿嘧啶类药物辅助化疗疗效和获益人群分析"", 《中国肿瘤临床》, vol. 40, no. 5 * |
| 秦琼;杨林;王金万;周爱萍;孙永琨;宋岩;: "Ⅱ期结肠癌根治术后奥沙利铂联合氟尿嘧啶类药物辅助化疗疗效和获益人群分析", 中国肿瘤临床, no. 05 * |
| 许小珊 等: ""基于 GBM 倾向评分逆概率加权法的非小细胞肺癌患者疗效评价"", 《中国卫生统计》, vol. 37, no. 1 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113555123A (en) * | 2021-08-27 | 2021-10-26 | 复旦大学附属中山医院 | Method for establishing prediction model of survival benefit of gallbladder cancer patient after radiotherapy and chemotherapy |
| CN116092664A (en) * | 2022-11-25 | 2023-05-09 | 中山大学孙逸仙纪念医院 | Pancreatic cancer prognosis prediction model establishment method |
| CN116092664B (en) * | 2022-11-25 | 2023-08-25 | 中山大学孙逸仙纪念医院 | Pancreatic cancer prognosis prediction model establishment method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Nguyen et al. | Ability of a genomic classifier to predict metastasis and prostate cancer-specific mortality after radiation or surgery based on needle biopsy specimens | |
| Mazumdar et al. | Categorizing a prognostic variable: review of methods, code for easy implementation and applications to decision‐making about cancer treatments | |
| Karim et al. | Generalisability of common oncology clinical trial eligibility criteria in the real world | |
| CN113571189A (en) | Establishment method of prediction model for survival benefit of gallbladder cancer patient after radiotherapy and chemotherapy | |
| Steuer et al. | Predictors and outcomes of venous thromboembolism in hospitalized lung cancer patients: A Nationwide Inpatient Sample database analysis | |
| Hoffman et al. | Self-reported health status predicts other-cause mortality in men with localized prostate cancer: results from the prostate cancer outcomes study | |
| CN112466464B (en) | Prognosis prediction model for primary metastatic prostate cancer patient, and establishment method and application method thereof | |
| Starr et al. | Socioeconomic position and surgery for early-stage non-small-cell lung cancer: a population-based study in Denmark | |
| Yang et al. | Identifying cancer patients at risk for heart failure using machine learning methods | |
| Richard et al. | The uptake of active surveillance for the management of prostate cancer: A population-based analysis | |
| CN112626218A (en) | Gene expression classifier and in-vitro diagnosis kit for predicting pancreatic cancer metastasis risk | |
| Kankesan et al. | Factors associated with referral to medical oncology and subsequent use of adjuvant chemotherapy for non-small-cell lung cancer: a population-based study | |
| Bagaria et al. | Validation of a soft tissue sarcoma nomogram using a national cancer registry | |
| Li et al. | Prognostic nomogram for overall survival in extranodal natural killer/T-cell lymphoma patients | |
| Dodson et al. | Chronic thromboembolic pulmonary hypertension cases cluster in families | |
| Wang et al. | Comparison and screening of different risk assessment models for deep vein thrombosis in patients with solid tumors | |
| Cheng et al. | Oncotype DX breast recurrence score distribution and chemotherapy benefit among women of different age groups with HR-positive, HER2-negative, node-negative breast cancer in the SEER database | |
| CN113345592B (en) | Construction and diagnosis equipment for acute myeloid leukemia prognosis risk model | |
| Coughlin et al. | Economic evaluation of new therapies in critical illness | |
| Thuluvath et al. | Acute liver failure in Budd–Chiari syndrome and a model to predict mortality | |
| Pintilie et al. | The analysis of case cohort design in the presence of competing risks with application to estimate the risk of delayed cardiac toxicity among Hodgkin lymphoma survivors | |
| Vander Poorten et al. | Prognostic scoring for malignant salivary gland neoplasms | |
| Kobylińska et al. | Explainable machine learning for modeling of early postoperative mortality in lung cancer | |
| CN113555123A (en) | Method for establishing prediction model of survival benefit of gallbladder cancer patient after radiotherapy and chemotherapy | |
| Pepe et al. | Methods for evaluating prediction performance of biomarkers and tests |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |