CN114913981A - Breast cancer prognosis prediction device, prediction model and establishment method thereof - Google Patents
Breast cancer prognosis prediction device, prediction model and establishment method thereof Download PDFInfo
- Publication number
- CN114913981A CN114913981A CN202210664996.0A CN202210664996A CN114913981A CN 114913981 A CN114913981 A CN 114913981A CN 202210664996 A CN202210664996 A CN 202210664996A CN 114913981 A CN114913981 A CN 114913981A
- Authority
- CN
- China
- Prior art keywords
- breast cancer
- information
- survival rate
- year
- unit
- 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.)
- Withdrawn
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
- 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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a breast cancer prognosis prediction device, which relates to the technical field of intelligent medical treatment and comprises the following components: the system comprises a data acquisition module, a prognosis prediction module and a result output module, wherein the data acquisition module is used for acquiring relevant information of a breast cancer patient; the invention also discloses a breast cancer prognosis prediction model and a breast cancer prognosis prediction model establishing method.
Description
Technical Field
The invention relates to the technical field of intelligent medical treatment, in particular to a breast cancer prognosis prediction device, a prediction model and an establishment method thereof.
Background
Young breast cancer patients refer to a population diagnosed with breast cancer under the age of 40 years, although accounting for 5.6-6.6% of breast cancer, young breast cancer has distinct biological behaviors and epidemiological characteristics, and is significantly worse in prognosis than other breast cancer populations, who also receive mastectomy and chemotherapy at a higher rate, and the molecular typing of young breast cancer includes four subtypes: type a of the luminal surface (estrogen receptor positive, i.e. ER +, progesterone receptor positive, i.e. PR +, human epidermal growth factor receptor 2 negative, i.e. HER2-, and low Ki67 index), type B of the luminal surface (ER +, PR-or high Ki67 index, HER2+ or HER2-), HER2 overexpression type (ER-, PR-and HER2+) and triple negative type (ER-, PR-and HER2-), with a triple negative proportion in young breast cancer patients of up to 26%, significantly higher than 12% in the whole breast cancer population. Among them, as a kind of breast cancer rich in heterogeneity, triple negative breast cancer is generally more aggressive, has early recurrence and metastasis time, has high local recurrence rate and has poorer prognosis, so the prognosis evaluation of young triple negative breast cancer patients is particularly important, and even if the young triple negative breast cancer is the same, the prognosis is very different due to different individual clinical pathological features, tumor burden and potential tumor biological characteristics, the young triple negative breast cancer has a limited number of cases, so that the prognosis of the young triple negative breast cancer patient is lack of a systematic analysis of prognosis factors by using a large number of cases, and a targeted prognosis model, and in addition, the prognosis of the young breast cancer patient is more influenced by other complex factors, such as marital status and economic factors, but at present, a comprehensive prognosis model including the factors is not available.
Therefore, it is an urgent need to solve the above problems by providing a new technical solution.
Disclosure of Invention
In view of the above, the present invention provides a device for predicting breast cancer prognosis, a prediction model and a method for establishing the prediction model, so as to solve the above technical problems.
In order to achieve the purpose, the invention provides the following technical scheme:
a breast cancer prognosis prediction apparatus comprising: the device comprises a data acquisition module, a prognosis prediction module and a result output module.
In the above scheme, the data acquisition module is used for acquiring relevant information of a breast cancer patient.
In the above scheme, the prognosis prediction module is configured to predict the overall survival rate of breast cancer and the specific survival rate of breast cancer of the patient according to the relevant information acquired by the data acquisition module.
In the above scheme, the result output module is configured to output the prediction result of the prognosis prediction module, receive operation information input by a user, and display a historical prediction record.
In the above scheme, the information related to the breast cancer patient includes medical insurance status information, marital status information, ethnic information, histological grading information, TNM stage information of the breast cancer, stage number information of the breast cancer, age information at the time of diagnosis, received surgery mode information, received chemotherapy information, and received radiotherapy information.
In the above scheme, the prognosis prediction module includes a three-year total survival rate calculation module, a five-year total survival rate calculation module, a three-year specific survival rate calculation module, and a five-year specific survival rate calculation module, where the three-year total survival rate calculation module is configured to analyze and process the relevant information acquired by the data acquisition module, and calculate three-year total survival rate data of the breast cancer patient; the five-year overall survival rate calculation module is used for analyzing and processing the relevant information acquired by the data acquisition module and calculating the five-year overall survival rate data of the breast cancer patient; the three-year specific survival rate calculating module is used for analyzing and processing the related information acquired by the data acquisition module and calculating the three-year specific survival rate data of the breast cancer patient; and the five-year specific survival rate calculating module is used for analyzing and processing the related information acquired by the data acquisition module and calculating the five-year specific survival rate data of the breast cancer patient.
In the above scheme, the result output module includes a data storage unit, an operation information obtaining unit, an information matching unit and a display unit, the data storage unit is configured to store the relevant information of the patient with breast cancer collected by the data collection module and the corresponding prediction information output by the prognosis prediction module, the operation information obtaining unit is configured to obtain the query information of the prediction record of the user, the information matching unit is configured to match the query information of the prediction record obtained by the operation information obtaining unit with the information stored in the data storage unit, and the display unit is configured to display the matching result obtained by the information matching unit.
The invention also provides a breast cancer prognosis prediction model which is applied to the breast cancer prognosis prediction device for carrying out breast cancer prognosis prediction and comprises a score distribution module, wherein the score distribution module comprises a first distribution unit, a second distribution unit, a third distribution unit and a fourth distribution unit, and the first distribution unit is used for distributing different scores to various information of a breast cancer patient according to the correlation between the relevant information of the breast cancer patient and the total three-year survival rate; the second allocating unit is used for allocating different scores to each item of information of the breast cancer patient according to the correlation between the relevant information of the breast cancer patient and the total five-year survival rate; the third distribution unit is used for distributing different scores to each item of information of the breast cancer patient according to the correlation between the relevant information of the breast cancer patient and the three-year specific survival rate of the breast cancer; the fourth distribution unit is used for distributing different scores to each item of information of the breast cancer patient according to the correlation between the information related to the breast cancer patient and the specific five-year survival rate of the breast cancer.
In the above scheme, the breast cancer prognosis prediction model further includes a total score calculation module, where the total score calculation module includes a first total score calculation unit, a second total score calculation unit, a third total score calculation unit, and a fourth total score calculation unit, and the first total score calculation unit is configured to perform summation operation on scores allocated by the first allocation unit to obtain a first total score; the second total score calculating unit is used for summing the scores distributed by the second distributing unit to obtain a second total score; the third total score calculating unit is used for performing summation operation on the scores distributed by the third distributing unit to obtain a third total score; and the fourth total score calculating unit is used for summing the scores distributed by the third distributing unit to obtain a fourth total score.
In the above scheme, the breast cancer prognosis prediction model further includes a survival rate matching module, where the survival rate matching module includes a three-year total survival rate matching unit, a five-year total survival rate matching unit, a three-year specific survival rate matching unit, and a five-year specific survival rate matching unit, and the three-year total survival rate matching unit is configured to match the first total score obtained by the first total score calculating unit with the corresponding three-year total survival rate, so as to obtain three-year total survival rate data of the breast cancer patient; the five-year overall survival rate matching unit is used for matching the second overall score obtained by the second overall score calculating unit with the corresponding five-year overall survival rate to obtain the five-year overall survival rate data of the breast cancer patient; the third total score calculating unit is used for calculating the third total score of the breast cancer patient according to the third total score of the breast cancer patient; and the five-year specific survival rate matching unit is used for matching the fourth total score obtained by the fourth total score calculating unit with the corresponding five-year specific survival rate to obtain the five-year specific survival rate data of the breast cancer patient.
The invention also provides a method for establishing the breast cancer prognosis prediction model, which is applied to the breast cancer prognosis prediction model for establishing the prediction model and comprises the following steps:
extracting medical insurance state information, marital state information, ethnic information, histology grading information, TNM stage information of breast cancer, stage number information of breast cancer, age information at the time of diagnosis, accepted operation mode information, accepted chemotherapy information and accepted radiotherapy information of the breast cancer patient from a database containing a plurality of breast cancer patient cases;
and (3) taking the breast cancer stage number data and the age data at the time of definite diagnosis of the breast cancer patient as screening conditions, and screening out cases meeting the requirements of the breast cancer stage number and the age at the time of definite diagnosis.
The screened cases are divided into a training set and a verification set according to a fixed proportion.
In the above scheme, the method for establishing the breast cancer prognosis prediction model further comprises:
medical insurance state information, marital state information, ethnic information, histology grading information, TNM staging information of breast cancer, number of stages of breast cancer, age information at the time of diagnosis, received operation mode information, received chemotherapy information and received radiotherapy information contained in the cases in the training set are input into a Cox proportional risk model for multi-factor analysis;
acquiring independent risk factors influencing the three-year overall survival rate, the five-year overall survival rate, the three-year specific survival rate of the breast cancer and the five-year specific survival rate of the breast cancer;
constructing a prognosis prediction model nomogram by R software according to independent risk factors influencing the three-year overall survival rate, the five-year overall survival rate, the three-year specific survival rate and the five-year specific survival rate;
calculating the values of the independent risk factors in the nomogram of the risk score prediction model, which are respectively related to the three-year total survival rate, the five-year total survival rate, the three-year specific survival rate of the breast cancer and the five-year specific survival rate of the breast cancer through a Cox proportional risk model;
and adding the scores to obtain a total score, and acquiring the total survival rate of three years, the total survival rate of five years, the specific survival rate of three years of breast cancer and the specific survival rate of five years of breast cancer predicted by the nomogram of the prediction model according to the data of the total score.
In the above scheme, the method for establishing the breast cancer prognosis prediction model further comprises:
inputting relevant data contained in the cases in the verification set into an established prognosis prediction model nomogram to obtain prediction data;
respectively calculating the C index input into the nomogram of the prognosis prediction model by the training set and the C index input into the nomogram of the prognosis prediction model by the verification set;
establishing an ROC curve corresponding to the training set and an ROC curve corresponding to the verification set, and respectively calculating the area under the ROC curve corresponding to the training set and the area under the ROC curve corresponding to the verification set;
establishing a correction curve corresponding to a training set and a correction curve corresponding to a verification set by a Bootstrap method, and comparing the correction curves with a reference line respectively;
and correcting a nomogram of the prognosis prediction model according to the obtained C index, the area under the ROC curve and the comparison result of the correction curve and the reference line until the comparison result of the C index, the area under the ROC curve and the correction curve and the reference line reaches a preset range.
In conclusion, the beneficial effects of the invention are as follows: the information including medical insurance state information, marital state information, ethnic information, histology grading information, TNM stage information of breast cancer, stage number information of breast cancer, age information of confirmed diagnosis, received operation mode information, received chemotherapy information and received radiotherapy information are brought into a breast cancer prognosis prediction model, individualized diagnosis and treatment are adopted for a patient, the survival rate of the patient is improved, and support is provided for breast cancer prognosis judgment.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the invention and not to limit the invention.
FIG. 1 is a schematic diagram illustrating the components of a device for predicting breast cancer prognosis according to the present invention.
FIG. 2 is a schematic diagram showing the components of the breast cancer prognosis prediction model of the present invention.
FIGS. 3, 4 and 5 are diagrams illustrating steps of a method for establishing a prognostic prediction model of breast cancer according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the following embodiments and accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
As shown in fig. 1, a breast cancer prognosis prediction apparatus of the present invention includes: the device comprises a data acquisition module, a prognosis prediction module and a result output module.
The data acquisition module is used for acquiring relevant information of a breast cancer patient; the prognosis prediction module is used for predicting the total survival rate and the specific survival rate of the breast cancer of the patient according to the relevant information acquired by the data acquisition module; the result output module is used for outputting the prediction result of the prognosis prediction module, receiving the operation information input by the user and displaying the historical prediction record.
Further, the information related to the breast cancer patient comprises medical insurance status information, marital status information, ethnic information, histology grading information, stage information of the TNM of the breast cancer, stage number information of the breast cancer, age information at the time of diagnosis, information of the accepted surgery mode, information of the accepted chemotherapy and information of the accepted radiotherapy.
In this embodiment, the data acquisition module is used for the user to enter and register medical insurance status information, marital status information, race information, histological grading information, TNM stage information of breast cancer, stage number information of breast cancer, age information at the time of diagnosis, information of accepted surgical mode, information of accepted chemotherapy and information of accepted radiotherapy, the medical insurance status information comprises medical insurance and no medical insurance, the marital status information comprises married living status and nonmarital living status, wherein the nonmarital living status comprises dissimilarity, residence, singleness and funeral, the race information comprises Huang, caucasian and Hei, the histological grading information comprises invasive ductal carcinoma, invasive lobular carcinoma, invasive ductal carcinoma combined invasive lobular carcinoma and all other rare pathological types except the types, the TNM stage information of the breast cancer comprises T stage information and N stage information, wherein the T stage information is T in TNM stages, represents a primary tumor, is divided into T1, T2, T3 and T4 according to the tumor invasion depth and the range of surrounding tissues, the N stage information is N in the TNM stages and represents local lymph node metastasis, generally N0 means that no lymph node metastasis exists, N1 and N2 represent that lymph node metastasis exists locally, the stage number information of the breast cancer includes stages I, II and III, the age information at the time of diagnosis includes 35 years to 40 years and below 35 years, the received operation mode information includes receiving breast preservation operation and receiving mastectomy, the received chemotherapy information includes receiving chemotherapy and not receiving chemotherapy, and the received radiotherapy information includes receiving radiotherapy and not receiving radiotherapy.
Furthermore, the prognosis prediction module comprises a three-year total survival rate calculation module, a five-year total survival rate calculation module, a three-year specific survival rate calculation module and a five-year specific survival rate calculation module, wherein the three-year total survival rate calculation module is used for analyzing and processing the relevant information acquired by the data acquisition module and calculating three-year total survival rate data of the breast cancer patient; the five-year overall survival rate calculation module is used for analyzing and processing the relevant information acquired by the data acquisition module and calculating the five-year overall survival rate data of the breast cancer patient; the three-year specific survival rate calculating module is used for analyzing and processing the related information acquired by the data acquisition module and calculating the three-year specific survival rate data of the breast cancer patient; and the five-year specific survival rate calculating module is used for analyzing and processing the related information acquired by the data acquisition module and calculating the five-year specific survival rate data of the breast cancer patient.
Further, the result output module comprises a data storage unit, an operation information acquisition unit, an information matching unit and a display unit, wherein the data storage unit is used for storing the relevant information of the patient with breast cancer, acquired by the data acquisition module, and the corresponding prediction information output by the prognosis prediction module, the operation information acquisition unit is used for acquiring the query information of the prediction record of the user, the information matching unit is used for matching the query information of the prediction record acquired by the operation information acquisition unit with the information stored in the data storage unit, and the display unit is used for displaying the matching result acquired by the information matching unit.
In this embodiment, the result output module employs a control display screen.
As shown in fig. 2, the present invention further provides a breast cancer prognosis prediction model applied to the above breast cancer prognosis prediction apparatus for performing breast cancer prognosis prediction, comprising a score assignment module, wherein the score assignment module comprises a first assignment unit, a second assignment unit, a third assignment unit and a fourth assignment unit, and the first assignment unit is configured to assign different scores to each item of information of a breast cancer patient according to the correlation magnitude between the information related to the breast cancer patient and the three-year overall survival rate; the second allocating unit is used for allocating different scores to each item of information of the breast cancer patient according to the correlation between the relevant information of the breast cancer patient and the total five-year survival rate; the third distribution unit is used for distributing different scores to each item of information of the breast cancer patient according to the correlation between the relevant information of the breast cancer patient and the three-year specific survival rate of the breast cancer; the fourth distribution unit is used for distributing different scores to each item of information of the breast cancer patient according to the correlation between the information related to the breast cancer patient and the specific five-year survival rate of the breast cancer.
Further, the breast cancer prognosis prediction model further comprises a total score calculation module, wherein the total score calculation module comprises a first total score calculation unit, a second total score calculation unit, a third total score calculation unit and a fourth total score calculation unit, and the first total score calculation unit is used for summing the scores distributed by the first distribution unit to obtain a first total score; the second total score calculating unit is used for summing the scores distributed by the second distributing unit to obtain a second total score; the third total score calculating unit is used for performing summation operation on the scores distributed by the third distributing unit to obtain a third total score; and the fourth total score calculating unit is used for performing summation operation on the scores distributed by the third distributing unit to obtain a fourth total score.
Furthermore, the breast cancer prognosis prediction model further comprises a survival rate matching module, wherein the survival rate matching module comprises a three-year total survival rate matching unit, a five-year total survival rate matching unit, a three-year specific survival rate matching unit and a five-year specific survival rate matching unit, and the three-year total survival rate matching unit is used for matching the first total score obtained by the first total score calculating unit with the corresponding three-year total survival rate to obtain three-year total survival rate data of the breast cancer patient; the five-year overall survival rate matching unit is used for matching the second overall score obtained by the second overall score calculating unit with the corresponding five-year overall survival rate to obtain the five-year overall survival rate data of the breast cancer patient; the third total score calculating unit is used for calculating the third total score of the breast cancer patient according to the third total score of the breast cancer patient; and the five-year specific survival rate matching unit is used for matching the fourth total score obtained by the fourth total score calculating unit with the corresponding five-year specific survival rate to obtain the five-year specific survival rate data of the breast cancer patient.
As shown in fig. 3 to 5, the present invention further provides a method for establishing a prognosis prediction model of breast cancer, which uses the above-mentioned prognosis prediction device for prediction model establishment, and comprises:
step S1: extracting medical insurance state information, marital state information, ethnic information, histology grading information, TNM stage information of breast cancer, stage number information of breast cancer, age information at the time of diagnosis, accepted operation mode information, accepted chemotherapy information and accepted radiotherapy information of the breast cancer patient from a database containing a plurality of breast cancer patient cases;
step S2: selecting cases which meet the requirements of the number of stages of the breast cancer and the age at the time of definite diagnosis by taking the data of the number of stages of the breast cancer patient and the age data at the time of definite diagnosis as screening conditions;
step S3: dividing the screened cases into a training set and a verification set according to a fixed proportion;
step S4: carrying out multi-factor analysis on medical insurance state information, marital state information, ethnic information, histological grading information, TNM staging information of breast cancer, number of stages of breast cancer, age information at the time of diagnosis, received operation mode information, received chemotherapy information and received radiotherapy information contained in the cases in the training set to a Cox proportional risk model;
step S5: acquiring independent risk factors influencing the three-year overall survival rate, the five-year overall survival rate, the three-year specific survival rate of the breast cancer and the five-year specific survival rate of the breast cancer;
step S6: constructing a prognosis prediction model nomogram by R software according to independent risk factors influencing the three-year overall survival rate, the five-year overall survival rate, the three-year specific survival rate and the five-year specific survival rate;
step S7: calculating the values of the independent risk factors in the nomogram of the risk score prediction model, which are respectively related to the three-year total survival rate, the five-year total survival rate, the three-year specific survival rate of the breast cancer and the five-year specific survival rate of the breast cancer through a Cox proportional risk model;
step S8: adding the scores to obtain a total score, and acquiring the total survival rate of three years, the total survival rate of five years, the specific survival rate of three years of breast cancer and the specific survival rate of five years of breast cancer predicted by a prediction model nomogram according to the data of the total score;
step S9: inputting relevant data contained in the cases in the verification set into an established prognosis prediction model nomogram to obtain prediction data;
step S10: respectively calculating the C index input into the nomogram of the prognosis prediction model by the training set and the C index input into the nomogram of the prognosis prediction model by the verification set;
step S11: establishing an ROC curve corresponding to the training set and an ROC curve corresponding to the verification set, and respectively calculating the area under the ROC curve corresponding to the training set and the area under the ROC curve corresponding to the verification set;
step S12: establishing a correction curve corresponding to a training set and a correction curve corresponding to a verification set by a Bootstrap method, and comparing the correction curves with a reference line respectively;
step S13: and correcting a nomogram of the prognosis prediction model according to the obtained C index, the area under the ROC curve and the comparison result of the correction curve and the reference line until the comparison result of the C index, the area under the ROC curve and the correction curve and the reference line reaches a preset range.
In this embodiment, the medical insurance status information, the marital status information, the ethnic information, the histological grading information, the TNM stage information of the breast cancer, the age information at the time of confirmed diagnosis, the received surgery information, the received chemotherapy information, and the received radiotherapy information, which are included in the cases in the training set, are input into a Cox proportional risk model for multi-factor analysis, so as to obtain independent risk factors, such as the medical insurance status information, the marital status information, the ethnic information, the histological grading information, the TNM stage information of the breast cancer, the age information at the time of confirmed diagnosis, the received surgery information, the received chemotherapy information, and the received radiotherapy information, which are all three-year overall survival rate and five-year overall survival rate, meanwhile, the risk factors are independent risk factors of the specific survival rate of three years and independent risk factors of the specific survival rate of five years.
In the embodiment, when the C index input by the training set to the alignment chart of the prognosis prediction model and the C index input by the validation set to the alignment chart of the prognosis prediction model are both greater than 0.78, the prognosis prediction model is shown to have good prediction effect; when the area under the curve of the ROC curve corresponding to the training set and the area under the curve of the ROC curve corresponding to the verification set are larger than 0.78, the prognosis prediction model has a good prediction effect; when the maximum vertical distance between the correction curve corresponding to the training set and the reference line is less than 0.22 and the maximum vertical distance between the correction curve corresponding to the verification set and the reference line is less than 0.22, the prognosis prediction model has a good prediction effect.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes may be made to the embodiment of the present invention by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A breast cancer prognosis prediction apparatus, comprising: the system comprises a data acquisition module, a prognosis prediction module and a result output module;
the data acquisition module is used for acquiring relevant information of a breast cancer patient;
the prognosis prediction module is used for predicting the total survival rate of the breast cancer and the specific survival rate of the breast cancer of the patient according to the relevant information acquired by the data acquisition module;
the result output module is used for outputting the prediction result of the prognosis prediction module, receiving the operation information input by the user and displaying the historical prediction record.
2. The breast cancer prognosis prediction device according to claim 1, wherein the information related to the breast cancer patient includes medical insurance status information, marital status information, ethnic information, histological grade information, TNM stage information of the breast cancer, number of stages of the breast cancer, age information at the time of diagnosis, accepted surgical procedure information, accepted chemotherapy information, and accepted radiotherapy information.
3. The breast cancer prognosis prediction device as claimed in claim 1, wherein the prognosis prediction module comprises a three-year overall survival rate calculation module, a five-year overall survival rate calculation module, a three-year specific survival rate calculation module and a five-year specific survival rate calculation module, the three-year overall survival rate calculation module is configured to analyze and process the relevant information acquired by the data acquisition module, and calculate three-year overall survival rate data of the breast cancer patient; the five-year overall survival rate calculation module is used for analyzing and processing the relevant information acquired by the data acquisition module and calculating the five-year overall survival rate data of the breast cancer patient; the three-year specific survival rate calculating module is used for analyzing and processing the related information acquired by the data acquisition module and calculating the three-year specific survival rate data of the breast cancer patient; and the five-year specific survival rate calculating module is used for analyzing and processing the related information acquired by the data acquisition module and calculating the five-year specific survival rate data of the breast cancer patient.
4. The breast cancer prognosis prediction device as claimed in claim 1, wherein the result output module comprises a data storage unit, an operation information obtaining unit, an information matching unit and a display unit, the data storage unit is used for storing the related information of the patient breast cancer patient collected by the data collection module and the corresponding prediction information output by the prognosis prediction module, the operation information obtaining unit is used for obtaining the prediction record inquiry information of the user, the information matching unit is used for matching the prediction record inquiry information obtained by the operation information obtaining unit with the information stored in the data storage unit, and the display unit is used for displaying the matching result obtained by the information matching unit.
5. A breast cancer prognosis prediction model applied to the breast cancer prognosis prediction device of any one of claims 1 to 4 for carrying out the breast cancer prognosis prediction, characterized by comprising a score assignment module, wherein the score assignment module comprises a first assignment unit, a second assignment unit, a third assignment unit and a fourth assignment unit, the first assignment unit is used for assigning different scores to the information of the breast cancer patient according to the correlation magnitude of the information related to the breast cancer patient and the three-year total survival rate; the second allocating unit is used for allocating different scores to each item of information of the breast cancer patient according to the correlation between the relevant information of the breast cancer patient and the total five-year survival rate; the third distributing unit is used for distributing different scores to each piece of information of the breast cancer patient according to the correlation between the related information of the breast cancer patient and the specific survival rate of the breast cancer in three years; the fourth distribution unit is used for distributing different scores to each item of information of the breast cancer patient according to the correlation between the information related to the breast cancer patient and the specific five-year survival rate of the breast cancer.
6. The breast cancer prognosis prediction model as claimed in claim 5, further comprising a total score calculation module, wherein the total score calculation module comprises a first total score calculation unit, a second total score calculation unit, a third total score calculation unit and a fourth total score calculation unit, and the first total score calculation unit is configured to perform a summation operation on the scores allocated by the first allocation unit to obtain a first total score; the second total score calculating unit is used for summing the scores distributed by the second distributing unit to obtain a second total score; the third total score calculating unit is used for performing summation operation on the scores distributed by the third distributing unit to obtain a third total score; and the fourth total score calculating unit is used for summing the scores distributed by the third distributing unit to obtain a fourth total score.
7. The breast cancer prognosis prediction model according to claim 6, further comprising a survival rate matching module, wherein the survival rate matching module comprises a three-year overall survival rate matching unit, a five-year overall survival rate matching unit, a three-year specific survival rate matching unit and a five-year specific survival rate matching unit, and the three-year overall survival rate matching unit is configured to match the first overall score obtained by the first overall score calculating unit with the corresponding three-year overall survival rate to obtain three-year overall survival rate data of the breast cancer patient; the five-year overall survival rate matching unit is used for matching the second overall score obtained by the second overall score calculating unit with the corresponding five-year overall survival rate to obtain the five-year overall survival rate data of the breast cancer patient; the third total score calculating unit is used for calculating the third total score of the breast cancer patient according to the third total score of the breast cancer patient; and the five-year specific survival rate matching unit is used for matching the fourth total score obtained by the fourth total score calculating unit with the corresponding five-year specific survival rate to obtain the five-year specific survival rate data of the breast cancer patient.
8. A method for establishing a prognosis prediction model of breast cancer, which is applied to the prognosis prediction model of breast cancer according to any one of claims 5 to 7 for prediction modeling, the method comprising:
extracting medical insurance state information, marital state information, ethnic information, histology grading information, TNM stage information of breast cancer, stage number information of breast cancer, age information at the time of diagnosis, accepted operation mode information, accepted chemotherapy information and accepted radiotherapy information of the breast cancer patient from a database containing a plurality of breast cancer patient cases;
selecting cases which meet the requirements of the number of stages of the breast cancer and the age at the time of definite diagnosis by taking the data of the number of stages of the breast cancer patient and the age data at the time of definite diagnosis as screening conditions;
the screened cases are divided into a training set and a verification set according to a fixed proportion.
9. The method for building a prognostic predictive model for breast cancer according to claim 8, further comprising:
medical insurance state information, marital state information, ethnic information, histology grading information, TNM staging information of breast cancer, number of stages of breast cancer, age information at the time of diagnosis, received operation mode information, received chemotherapy information and received radiotherapy information contained in the cases in the training set are input into a Cox proportional risk model for multi-factor analysis;
acquiring independent risk factors influencing the three-year overall survival rate, the five-year overall survival rate, the three-year specific survival rate of the breast cancer and the five-year specific survival rate of the breast cancer;
constructing a prognosis prediction model nomogram by R software according to independent risk factors influencing the three-year overall survival rate, the five-year overall survival rate, the three-year specific survival rate and the five-year specific survival rate;
calculating the values of the independent risk factors in the nomogram of the risk score prediction model, which are respectively related to the three-year total survival rate, the five-year total survival rate, the three-year specific survival rate of the breast cancer and the five-year specific survival rate of the breast cancer through a Cox proportional risk model;
and adding the scores to obtain a total score, and acquiring the total survival rate of three years, the total survival rate of five years, the specific survival rate of three years of breast cancer and the specific survival rate of five years of breast cancer predicted by the nomogram of the prediction model according to the data of the total score.
10. The method for building a prognostic predictive model for breast cancer according to claim 8, further comprising:
inputting relevant data contained in the cases in the verification set into an established prognosis prediction model nomogram to obtain prediction data;
respectively calculating the C index input into the nomogram of the prognosis prediction model by the training set and the C index input into the nomogram of the prognosis prediction model by the verification set;
establishing an ROC curve corresponding to the training set and an ROC curve corresponding to the verification set, and respectively calculating the area under the ROC curve corresponding to the training set and the area under the ROC curve corresponding to the verification set;
establishing a correction curve corresponding to a training set and a correction curve corresponding to a verification set by a Bootstrap method, and comparing the correction curves with a reference line respectively;
and correcting a nomogram of the prognosis prediction model according to the obtained C index, the area under the ROC curve and the comparison result of the correction curve and the reference line until the comparison result of the C index, the area under the ROC curve and the correction curve and the reference line reaches a preset range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210664996.0A CN114913981A (en) | 2022-06-13 | 2022-06-13 | Breast cancer prognosis prediction device, prediction model and establishment method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210664996.0A CN114913981A (en) | 2022-06-13 | 2022-06-13 | Breast cancer prognosis prediction device, prediction model and establishment method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114913981A true CN114913981A (en) | 2022-08-16 |
Family
ID=82770234
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210664996.0A Withdrawn CN114913981A (en) | 2022-06-13 | 2022-06-13 | Breast cancer prognosis prediction device, prediction model and establishment method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114913981A (en) |
-
2022
- 2022-06-13 CN CN202210664996.0A patent/CN114913981A/en not_active Withdrawn
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11636288B2 (en) | Platform, device and process for annotation and classification of tissue specimens using convolutional neural network | |
| Bristow et al. | Impact of National Cancer Institute Comprehensive Cancer Centers on ovarian cancer treatment and survival | |
| Kaufmann et al. | Use of standard markers and incorporation of molecular markers into breast cancer therapy: Consensus recommendations from an International Expert Panel | |
| US20160253473A1 (en) | Integrated virtual patient framework | |
| Sun et al. | A computational tumor-infiltrating lymphocyte assessment method comparable with visual reporting guidelines for triple-negative breast cancer | |
| Kensler et al. | PAM50 molecular intrinsic subtypes in the Nurses' health study cohorts | |
| Yamashiro et al. | Prevalence and risk factors of bone metastasis and skeletal related events in patients with primary breast cancer in Japan | |
| US20040236723A1 (en) | Method and system for data evaluation, corresponding computer program product, and corresponding computer-readable storage medium | |
| Xu et al. | Effect of an artificial intelligence clinical decision support system on treatment decisions for complex breast cancer | |
| CN105102637A (en) | Method for extracting biomarker for diagnosing pancreatic cancer, computing device therefor, biomarker for diagnosing pancreatic cancer and device for diagnosing pancreatic cancer including the same | |
| Bookman | Can we predict who lives long with ovarian cancer? | |
| Plichta et al. | A novel staging system for de novo metastatic breast cancer refines prognostic estimates | |
| Saxena et al. | Prognostic value of axillary lymph node status after neoadjuvant chemotherapy. Results from a multicentre study | |
| Kaye et al. | Association between early confirmatory testing and the adoption of active surveillance for men with favorable-risk prostate cancer | |
| Fasano et al. | Benefit of adjuvant chemotherapy in node-negative T1a versus T1b and T1c triple-negative breast cancer | |
| Lin et al. | Regional variability in percentage of breast cancers reported as positive for HER2 in California: implications of patient demographics on laboratory benchmarks | |
| Teerenhovi et al. | Real-world clinical outcomes in biological subgroups of breast cancer in the hospital district of southwest Finland | |
| CN113345592A (en) | Construction and diagnosis equipment for acute myeloid leukemia prognosis risk model | |
| Guzzi et al. | Automatic summarisation and annotation of microarray data | |
| CN114913981A (en) | Breast cancer prognosis prediction device, prediction model and establishment method thereof | |
| Kantor et al. | Comparative analysis of proposed strategies for incorporating biologic factors into breast cancer staging | |
| US12020823B2 (en) | Integrated virtual patient framework | |
| da Luz et al. | The current staging and classification systems of breast cancer and their pitfalls: Is it possible to integrate the complexity of this neoplasm into a unified staging system? | |
| Chiang et al. | Understanding cancer predisposition in Singapore: What’s next | |
| Westphal et al. | Transferring MINDACT to Daily Routine: Implementation of the 70-Gene Signature in Luminal Early Breast Cancer–Results from a Prospective Registry of the Austrian Group Medical Tumor Therapy (AGMT) |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220816 |
|
| WW01 | Invention patent application withdrawn after publication |