CN111370117A - Prognosis prediction system for colorectal cancer treatment population - Google Patents
Prognosis prediction system for colorectal cancer treatment population Download PDFInfo
- Publication number
- CN111370117A CN111370117A CN202010395087.2A CN202010395087A CN111370117A CN 111370117 A CN111370117 A CN 111370117A CN 202010395087 A CN202010395087 A CN 202010395087A CN 111370117 A CN111370117 A CN 111370117A
- Authority
- CN
- China
- Prior art keywords
- patient
- colorectal cancer
- population
- module
- assignment
- 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- Withdrawn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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- 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)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a prognosis prediction system for colorectal cancer treatment population, which comprises a colorectal cancer patient medical record data input module, a data acquisition and conversion module, a discrimination analysis module, an auxiliary decision module and a final display module, wherein the original data information meeting preset conditions is input, the original data information is subjected to assignment processing and converted into independent variable parameters for the discrimination analysis module, an auxiliary decision model is generated after a sample is trained, the prognosis of the patient is subjected to prediction analysis, the medical record data of a target patient is used as input, the discrimination analysis module compares a probability value output by the trained auxiliary decision model with a preset threshold value to discriminate that the target patient belongs to treatment dominant population, disadvantaged population and general population, the system is suitable for discriminating colorectal cancer and assisting treatment in the prognosis analysis of the colorectal cancer patient, improving the treatment pertinence and providing a basis for postoperative radiotherapy and chemotherapy.
Description
The technical field is as follows:
the invention relates to the technical field of medical treatment, in particular to a prognosis prediction system for colorectal cancer treatment population.
Background art:
colorectal cancer (CRC) is a common malignant tumor, and is one of the malignant tumors with high incidence worldwide. Controlling morbidity and reducing mortality has been the focus of colorectal cancer prevention and treatment. In order to enable more colon cancer patients to be treated more scientifically and reasonably, indexes with high sensitivity and specificity are continuously searched for judging the prognosis and the chemotherapy curative effect of the patients and guiding the individualized treatment of the patients.
At present, surgery is still the most important part in the treatment of colorectal cancer, and the selection of the postoperative adjuvant chemotherapy scheme for colorectal cancer is an important decision in the treatment process of colorectal cancer, but now generally depends on the selection of the chemotherapy scheme by doctors based on self diagnosis and treatment experience and clinical guidance. Many researches show that the judgment analysis can assist clinical diagnosis, improve the standardization, objectivity and accuracy of clinical diagnosis and is beneficial to predicting the development condition after operation, and the like, so that a prognosis prediction system for colorectal cancer treatment population is established, multi-factor analysis is carried out on the prognosis of a colorectal cancer patient to assist treatment, the pertinence of treatment can be improved, and a basis is provided for postoperative chemoradiotherapy.
The invention content is as follows:
the invention provides a prognosis prediction system for colorectal cancer treatment population, which is used for judging advantages and disadvantages of the colorectal cancer treatment population and classifying general population, is simple to use, has high prediction accuracy, and is beneficial to carrying out standardized management and individual treatment scheme implementation on colorectal cancer patients.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a prognosis prediction system for colorectal cancer treatment population comprises a colorectal cancer patient medical record data input module, a data acquisition and conversion module, a discriminant analysis module, an auxiliary decision module and a final display module, wherein,
the colorectal cancer patient medical record data input module is used for inputting basic information of a patient and state information of colorectal cancer which meet preset conditions, and uploading the basic information and the state information of the patient as original data information to the data acquisition and conversion module;
the data acquisition and conversion module is used for acquiring original data information in the medical record data input module of the colorectal cancer patient, performing assignment processing on the acquired original data information, converting the original data information into independent variable parameters for the discriminant analysis module, and uploading the independent variable parameters to the discriminant analysis module;
the discriminant analysis module receives the independent variable parameters as training samples and generates an auxiliary decision model after training the samples;
the auxiliary decision-making module carries out prediction analysis on the prognosis of the patient based on an auxiliary decision-making model generated by the discriminant analysis module, medical record data of the target colorectal cancer patient is used as input, when the discriminant analysis module compares the probability value output by the trained auxiliary decision-making model with a preset threshold value, the target colorectal cancer patient is judged to belong to treatment dominant population, treatment disadvantaged population and general population, and the discrimination result is sent to the final display module for terminal display.
The patient basic information of the patient medical record data comprises one or more of the age, sex, disease history of the patient, and the condition information of the colorectal cancer comprises the TNM stage of the disease and the risk factors influencing the colorectal cancer.
The risk factors affecting colorectal cancer include primary tumor site, metastatic site, chromosome instability, CpG island methylation phenotype, microsatellite instability.
In the data acquisition and transformation module, the data information uploaded by the patient medical record data input module is assigned, and for different tumor disease parts, the assignment is 1 or 0, the assignment of the left half colon is 1, and the assignment of the right half colon is 0; for different metastatic sites, liver metastasis was assigned a value of 1, no liver metastasis was assigned a value of 0, lung metastasis was assigned a value of 1, and no lung metastasis was assigned a value of 0; for chromosome instability, there was an 18qLOH assignment of 1, no 18qLOH assignment of 0, there was a 20q13 amplification assignment of 1, and no 20q13 amplification assignment of 0; for the CpG island methylation phenotype, the p16CpG island methylation assignment is 1 and the p16CpG island non-methylation assignment is 0; for microsatellite instability, MMR protein deficiency is one of the hallmarks of microsatellite instability, with an MMR absence assignment of 1 and an MMR presence assignment of 0.
The discriminant analysis module takes the patient data assigned by the data acquisition and conversion module as a training sample, namely an independent variable, and adopts a cross validation method to generate a discriminant function and establish an auxiliary decision model; in the discriminant analysis module, a linear discriminant model is used to train the patient data.
The linear discriminant model is trained according to the following contents, and the discriminant analysis module uploads probability distribution formulas of dominant population, disadvantaged population and general population obtained after training as an auxiliary decision-making model to the auxiliary decision-making module:
(i) sample data, i.e. argument parameters, are compressed into two dimensions, each in the form of a linear combination of arguments, according to the following equation:
V1＝μ11x1+μ12x2+μ13x3+...+μ1ixi；
V2＝μ21x1+μ22x2+μ23x3+...+μ2ixi；
wherein the independent variables share i dimensions; v1、V2Respectively representing sample characteristic values in two dimensions; x is the number of1、x2、x3…xiRespectively representing independent variable parameters representing different patient data after being assigned; mu.s11、μ12、μ13…μ1iRepresenting the coefficients, mu, corresponding to the respective variables in a first dimension21、μ22、μ23…μ2iRepresenting coefficients corresponding to respective variables in a second dimension;
(ii) the corresponding coefficient values in two dimensions are solved by adopting a method for maximizing the following index sigma:
where tr is the matrix trace operator and w is the operation of μ11、μ12、μ13…μ1iAnd mu21、μ22、μ23…μ2iI rows and 2 columns of a matrix, wTIs a transposed matrix of w, SbMeasure the between-class variance, SwMeasuring the intra-class variance;
(iii) setting the sample data of each category to conform to Gaussian distribution according to independent variable x1、x2、x3…xiAnd coefficient values mu corresponding in two dimensions determined11～μ1i，μ21～μ2iCalculating a sample eigenvalue V in two dimensions1、V2；
(iv) Then calculating the mean value and the variance of projection data of each category, wherein the categories comprise disadvantaged people, dominant people and general people; setting probability density function of each crowd to accord with two-dimensional Gaussian distribution to obtain probability distribution formula f of disadvantaged crowd1(V1，V2) Probability distribution formula f of dominant population2(V1，V2) And the probability distribution formula f of the general population3(V1，V2)。
For a target patient, the data of the patient is input through a medical record data input module of the colorectal cancer patient, and in the assistant decision-making module, the probability P that the target patient belongs to various crowds is calculated based on an assistant decision-making model obtained through training, namely a probability distribution formula of three crowds1，P2，P3；
Wherein, P1，P2，P3Respectively representing the probabilities of the population with poor prognosis, the population with superior prognosis and the population with general prognosis; when P is present1>When 0.5, judging that the patient belongs to the population with poor prognosis; when P is present2<When 0.5 hour, the patient is judged to belong to the population with the prognosis advantage; otherwise, the patient is judged to belong to the general population with prognosis.
By the prognosis prediction system for the colorectal cancer treatment population, the dominant population, the disadvantaged population and the general population in patients are accurately judged, multi-factor analysis is carried out on the prognosis of the colorectal cancer patients to assist in treatment, the pertinence of the treatment can be improved, and a basis is provided for postoperative chemoradiotherapy.
Description of the drawings:
FIG. 1 is a system block diagram of an embodiment of the invention.
The specific implementation mode is as follows:
in order to clearly explain the technical features of the present invention, the following detailed description of the present invention is provided with reference to the accompanying drawings.
As shown in fig. 1, the prognosis prediction system for people with colorectal cancer therapy includes a colorectal cancer patient medical record data input module, a data acquisition and transformation module, a discriminant analysis module, an assistant decision module and a final display module, wherein,
the colorectal cancer patient medical record data input module is used for inputting basic information of a patient and state information of colorectal cancer which meet preset conditions, and uploading the basic information and the state information of the patient as original data information to the data acquisition and conversion module; the predetermined conditions include whether the diagnosis is colorectal cancer, whether a colorectal cancer operation has been performed, and whether chemotherapy is performed within a predetermined time after the operation.
The data acquisition and conversion module is used for acquiring original data information in the medical record data input module of the colorectal cancer patient, performing assignment processing on the acquired original data information, converting the original data information into independent variable parameters for the discriminant analysis module, and uploading the independent variable parameters to the discriminant analysis module; the discrimination analysis module receives the independent variable parameters as training samples and generates an auxiliary decision model after training the samples; the auxiliary decision-making module carries out prediction analysis on the prognosis of the patient based on an auxiliary decision-making model generated by the discriminant analysis module, medical record data of the target colorectal cancer patient is used as input, when the discriminant analysis module compares the probability value output by the trained auxiliary decision-making model with a preset threshold value, the target colorectal cancer patient is judged to belong to treatment dominant population, treatment disadvantaged population and general population, and the discrimination result is sent to a final display module for terminal display.
Patient basic information of the patient medical record data includes one or more of patient age, sex, disease history, and condition information of colorectal cancer includes TNM stage of disease and risk factors affecting colorectal cancer. Specifically, risk factors affecting colorectal cancer include tumor primary site, metastatic site, chromosome instability, CpG island methylation phenotype, microsatellite instability. In the data acquisition and transformation module, assigning values to data information uploaded by the patient medical record data input module, wherein for different tumor disease parts, the values are 1 or 0, the value of the left half colon is 1, and the value of the right half colon is 0; for different metastatic sites, liver metastasis was assigned a value of 1, no liver metastasis was assigned a value of 0, lung metastasis was assigned a value of 1, and no lung metastasis was assigned a value of 0; for chromosome instability, there was an 18qLOH assignment of 1, no 18qLOH assignment of 0, there was a 20q13 amplification assignment of 1, and no 20q13 amplification assignment of 0; for the CpG island methylation phenotype, the p16CpG island methylation assignment is 1 and the p16CpG island non-methylation assignment is 0; for microsatellite instability, MMR protein deficiency is one of the hallmarks of microsatellite instability, with an MMR absence assignment of 1 and an MMR presence assignment of 0.
The discriminant analysis module takes the patient data assigned by the data acquisition and conversion module as a training sample, namely an independent variable, and adopts a cross validation method to generate a discriminant function and establish an auxiliary decision model; in the discriminant analysis module, a linear discriminant model is used to train the patient data.
The linear discriminant model is trained according to the following contents, and the discriminant analysis module uploads probability distribution formulas of dominant population, disadvantaged population and general population obtained after training as an auxiliary decision-making model to the auxiliary decision-making module:
(i) sample data, i.e. argument parameters, are compressed into two dimensions, each in the form of a linear combination of arguments, according to the following equation:
V1＝μ11x1+μ12x2+μ13x3+...+μ1ixi；
V2＝μ21x1+μ22x2+μ23x3+...+μ2ixi；
wherein the independent variables share i dimensions; v1、V2Respectively representing sample characteristic values in two dimensions; x is the number of1、x2、x3…xiRespectively representing independent variable parameters representing different patient data after being assigned; mu.s11、μ12、μ13…μ1iRepresenting the coefficients, mu, corresponding to the respective variables in a first dimension21、μ22、μ23…μ2iRepresenting coefficients corresponding to respective variables in a second dimension;
(ii) the corresponding coefficient values in two dimensions are solved by adopting a method for maximizing the following index sigma:
where tr is the matrix trace operator and w is the operation of μ11、μ12、μ13…μ1iAnd mu21、μ22、μ23…μ2iI rows and 2 columns of a matrix, wTIs a transposed matrix of w, SbMeasure the between-class variance, SwMeasuring the intra-class variance;
Sb＝St-Sw。
(iii) setting the sample data of each category to conform to Gaussian distribution according to independent variable x1、x2、x3…xiAnd coefficient values mu corresponding in two dimensions determined11～μ1i，μ21～μ2iCalculating in two dimensionsSample eigenvalue V1、V2；
(iv) Then calculating the mean value and the variance of projection data of each category, wherein the categories comprise disadvantaged people, dominant people and general people; setting probability density function of each crowd to accord with two-dimensional Gaussian distribution to obtain probability distribution formula f of disadvantaged crowd1(V1，V2) Probability distribution formula f of dominant population2(V1，V2) And the probability distribution formula f of the general population3(V1，V2)。
Probability distribution formula f of dominant population2(V1，V2) For the purpose of example only,
for the dominant population, σ1Is V1Standard deviation, σ2Is V2Standard deviation, ω1Is V1Mean value, ω2Is V2The mean, ρ, is the correlation coefficient. In the same way, f can be obtained1(V1，V2)、f3(V1，V2)。
For a target patient, the data of the patient is input through a medical record data input module of the colorectal cancer patient, and in the assistant decision-making module, the probability P that the target patient belongs to various crowds is calculated based on an assistant decision-making model obtained through training, namely a probability distribution formula of three crowds1，P2，P3；
Wherein, P1，P2，P3Respectively representing the probabilities of the population with poor prognosis, the population with superior prognosis and the population with general prognosis; when P is present1>When 0.5, judging that the patient belongs to the population with poor prognosis; when P is present2<When 0.5 hour, the patient is judged to belong to the population with the prognosis advantage; otherwise, judging that the patient belongs to the general person with prognosisAnd (4) clustering.
The above-described embodiments should not be construed as limiting the scope of the invention, and any alternative modifications or alterations to the embodiments of the present invention will be apparent to those skilled in the art. The present invention is not described in detail, but is known to those skilled in the art.
Claims (7)
1. A prognostic prediction system for a population treated for colorectal cancer, comprising: comprises a colorectal cancer patient medical record data input module, a data acquisition and conversion module, a discriminant analysis module, an auxiliary decision module and a final display module, wherein,
the colorectal cancer patient medical record data input module is used for inputting basic information of a patient and state information of colorectal cancer which meet preset conditions, and uploading the basic information and the state information of the patient as original data information to the data acquisition and conversion module;
the data acquisition and conversion module is used for acquiring original data information in the medical record data input module of the colorectal cancer patient, performing assignment processing on the acquired original data information, converting the original data information into independent variable parameters for the discriminant analysis module, and uploading the independent variable parameters to the discriminant analysis module;
the discriminant analysis module receives the independent variable parameters as training samples and generates an auxiliary decision model after training the samples;
the auxiliary decision-making module carries out prediction analysis on the prognosis of the patient based on an auxiliary decision-making model generated by the discriminant analysis module, medical record data of the target colorectal cancer patient is used as input, when the discriminant analysis module compares the probability value output by the trained auxiliary decision-making model with a preset threshold value, the target colorectal cancer patient is judged to belong to treatment dominant population, treatment disadvantaged population and general population, and the discrimination result is sent to the final display module for terminal display.
2. The prognostic prediction system for populations treated with colorectal cancer according to claim 1, characterized in that: the patient basic information of the patient medical record data comprises one or more of the age, sex, disease history of the patient, and the condition information of the colorectal cancer comprises the TNM stage of the disease and the risk factors influencing the colorectal cancer.
3. The prognostic prediction system for populations treated with colorectal cancer according to claim 2, characterized in that: the risk factors affecting colorectal cancer include primary tumor site, metastatic site, chromosome instability, CpG island methylation phenotype, microsatellite instability.
4. The prognostic prediction system for populations treated with colorectal cancer according to claim 3, characterized in that: in the data acquisition and transformation module, the data information uploaded by the patient medical record data input module is assigned, and for different tumor disease parts, the assignment is 1 or 0, the assignment of the left half colon is 1, and the assignment of the right half colon is 0; for different metastatic sites, liver metastasis was assigned a value of 1, no liver metastasis was assigned a value of 0, lung metastasis was assigned a value of 1, and no lung metastasis was assigned a value of 0; for chromosome instability, there was an 18qLOH assignment of 1, no 18qLOH assignment of 0, there was a 20q13 amplification assignment of 1, and no 20q13 amplification assignment of 0; for the CpG island methylation phenotype, the p16CpG island methylation assignment is 1 and the p16CpG island non-methylation assignment is 0; for microsatellite instability, MMR protein deficiency is one of the hallmarks of microsatellite instability, with an MMR absence assignment of 1 and an MMR presence assignment of 0.
5. The prognostic prediction system for populations treated with colorectal cancer according to claim 4, characterized in that: the discriminant analysis module takes the patient data assigned by the data acquisition and conversion module as a training sample, namely an independent variable, and adopts a cross validation method to generate a discriminant function and establish an auxiliary decision model; in the discriminant analysis module, a linear discriminant model is used to train the patient data.
6. The prognostic prediction system for populations treated with colorectal cancer according to claim 5, characterized in that: the linear discriminant model is trained according to the following contents, and the discriminant analysis module uploads probability distribution formulas of dominant population, disadvantaged population and general population obtained after training as an auxiliary decision-making model to the auxiliary decision-making module:
(i) sample data, i.e. argument parameters, are compressed into two dimensions, each in the form of a linear combination of arguments, according to the following equation:
V1＝μ11x1+μ12x2+μ13x3+...+μ1ixi；
V2＝μ21x1+μ22x2+μ23x3+...+μ2ixi；
wherein the independent variables share i dimensions; v1、V2Respectively representing sample characteristic values in two dimensions; x is the number of1、x2、x3…xiRespectively representing independent variable parameters representing different patient data after being assigned; mu.s11、μ12、μ13…μ1iRepresenting the coefficients, mu, corresponding to the respective variables in a first dimension21、μ22、μ23…μ2iRepresenting coefficients corresponding to respective variables in a second dimension;
(ii) the corresponding coefficient values in two dimensions are solved by adopting a method for maximizing the following index sigma:
where tr is the matrix trace operator and w is the operation of μ11、μ12、μ13…μ1iAnd mu21、μ22、μ23…μ2iI rows and 2 columns of a matrix, wTIs a transposed matrix of w, SbMeasure the between-class variance, SwMeasuring the intra-class variance;
(iii) setting the sample data of each category to conform to Gaussian distribution according to independent variable x1、x2、x3…xiAnd coefficient values mu corresponding in two dimensions determined11～μ1i，μ21～μ2iCalculating a sample eigenvalue V in two dimensions1、V2；
(iv) Then calculating the mean value and the variance of projection data of each category, wherein the categories comprise disadvantaged people, dominant people and general people; setting probability density function of each crowd to accord with two-dimensional Gaussian distribution to obtain probability distribution formula f of disadvantaged crowd1(V1，V2) Probability distribution formula f of dominant population2(V1，V2) And the probability distribution formula f of the general population3(V1，V2)。
7. The prognostic prediction system for populations treated with colorectal cancer according to claim 6, characterized in that: for a target patient, the data of the patient is input through a medical record data input module of the colorectal cancer patient, and in the assistant decision-making module, the probability P that the target patient belongs to various crowds is calculated based on an assistant decision-making model obtained through training, namely a probability distribution formula of three crowds1，P2，P3；
Wherein, P1，P2，P3Respectively representing the probabilities of the population with poor prognosis, the population with superior prognosis and the population with general prognosis; when P is present1>When 0.5, judging that the patient belongs to the population with poor prognosis; when P is present2<When 0.5 hour, the patient is judged to belong to the population with the prognosis advantage; otherwise, the patient is judged to belong to the general population with prognosis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010395087.2A CN111370117A (en) | 2020-05-12 | 2020-05-12 | Prognosis prediction system for colorectal cancer treatment population |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010395087.2A CN111370117A (en) | 2020-05-12 | 2020-05-12 | Prognosis prediction system for colorectal cancer treatment population |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111370117A true CN111370117A (en) | 2020-07-03 |
Family
ID=71212257
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010395087.2A Withdrawn CN111370117A (en) | 2020-05-12 | 2020-05-12 | Prognosis prediction system for colorectal cancer treatment population |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111370117A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112365988A (en) * | 2020-11-10 | 2021-02-12 | 杭州市肿瘤医院 | Prognosis prediction system |
| CN115132354A (en) * | 2022-07-06 | 2022-09-30 | 哈尔滨医科大学 | Patient type identification method and device, electronic equipment and storage medium |
-
2020
- 2020-05-12 CN CN202010395087.2A patent/CN111370117A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112365988A (en) * | 2020-11-10 | 2021-02-12 | 杭州市肿瘤医院 | Prognosis prediction system |
| CN112365988B (en) * | 2020-11-10 | 2023-08-04 | 杭州市肿瘤医院 | Prognosis prediction system |
| CN115132354A (en) * | 2022-07-06 | 2022-09-30 | 哈尔滨医科大学 | Patient type identification method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sun et al. | Identification of 12 cancer types through genome deep learning | |
| Williams et al. | Quantification of subclonal selection in cancer from bulk sequencing data | |
| KR102233740B1 (en) | Method for predicting cancer type based on DNA copy number variation | |
| CN110957033A (en) | Disease prediction system | |
| CN109872776B (en) | Screening method for potential biomarkers of gastric cancer based on weighted gene co-expression network analysis and application thereof | |
| US20210020269A1 (en) | Multi-level architecture of pattern recognition in biological data | |
| CN111370117A (en) | Prognosis prediction system for colorectal cancer treatment population | |
| JP2023526241A (en) | Clinical predictor based on multiple machine learning models | |
| US20040236723A1 (en) | Method and system for data evaluation, corresponding computer program product, and corresponding computer-readable storage medium | |
| Siqueira et al. | SVM for FT‐MIR prostate cancer classification: An alternative to the traditional methods | |
| Gangurde et al. | Developing an efficient cancer detection and prediction tool using convolution neural network integrated with neural pattern recognition | |
| Wang et al. | Value of radiomics model based on multi-parametric magnetic resonance imaging in predicting epidermal growth factor receptor mutation status in patients with lung adenocarcinoma | |
| Altuhaifa et al. | Predicting lung cancer survival based on clinical data using machine learning: A review | |
| Huang et al. | Promoting similarity of model sparsity structures in integrative analysis of cancer genetic data | |
| US20190189248A1 (en) | Methods, systems and apparatus for subpopulation detection from biological data based on an inconsistency measure | |
| EP3891761A1 (en) | Integrated system and method for personalized stratification and prediction of neurodegenerative disease | |
| US9734122B2 (en) | System, method and computer-accessible medium for evaluating a malignancy status in at-risk populations and during patient treatment management | |
| CN115206530A (en) | Method and system for improving prediction precision of postoperative complications of esophageal cancer | |
| CN115100155A (en) | Method and system for establishing radiation pneumonitis prediction model | |
| Ghanem et al. | Deep Learning Approaches for Glioblastoma Prognosis in Resource-Limited Settings: A Study Using Basic Patient Demographic, Clinical, and Surgical Inputs | |
| KR102492977B1 (en) | Providing method for health information based on microbiome and analysis apparatus | |
| CN110246591B (en) | Prognosis prediction system for traditional Chinese medicine treatment population | |
| Raets et al. | Radiomics for the prediction of the regression grade of colorectal cancer: a challenging classification problem | |
| CN113393931A (en) | Breast cancer diagnosis and treatment method based on system dynamics | |
| Khaliq et al. | LCCNet: A Deep Learning based Method for the Identification of Lungs Cancer using CT Scans |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200703 |
|
| WW01 | Invention patent application withdrawn after publication |