Method and device for constructing cancerization level evaluation model

Abstract

The invention provides a cancerization level evaluation model construction method and device, and relates to the technical field of biomedices.The cancerization level evaluation model construction method comprises the steps that serum marker data, gene mutation data, protein expression data, genetic data and immune data of an evaluation object are obtained; performing mathematical analysis on the serum marker data, the gene mutation data and the protein expression data to obtain a cancerization state coefficient, analyzing the genetic data to obtain a cancer inhibition blocking coefficient, and generating a cancerization degree coefficient according to the cancer inhibition blocking coefficient and the cancerization state coefficient; performing feature extraction on the immune data to obtain a cellular immune coefficient and an immune factor correction coefficient, generating an anti-cancer index according to the cellular immune coefficient and the immune factor correction coefficient, and generating a cancerization level evaluation coefficient through the anti-cancer index and the cancerization degree coefficient; and comparing the cancerization level evaluation coefficient with a preset threshold value, and dividing cancerization into slight cancerization, medium cancerization and serious cancerization according to a comparison result.

Description

Technical Field

[0001] The present invention relates to the field of biomedical technology, and in particular to a method and device for constructing a canceration level assessment model. Background Art

[0002] In recent years, cancer has become one of the major health threats worldwide, and early detection and timely intervention are widely considered to be the key to improving cancer cure rates. However, current cancer diagnosis methods mostly rely on traditional imaging examinations and single marker blood tests, which often have limitations in identifying early cancers and assessing the degree of cancerization. In most cases, traditional tumor markers such as carcinoembryonic antigen (CEA) and alpha-fetoprotein (AFP) can only rise significantly after tumor formation, and the occurrence of cancer is a complex multi-step process involving multiple biological mechanisms such as cellular gene mutations, changes in protein expression, and immune escape. Existing technologies have failed to effectively integrate this complex information, resulting in insufficient accuracy in early diagnosis and assessment of cancer levels.

[0003] In addition, with the in-depth study of cancer biology, more and more evidence shows that the immune response in the tumor microenvironment plays a vital role in the development and progression of cancer. However, traditional diagnostic methods usually fail to incorporate immune data into the evaluation system and fail to fully reflect the complex interaction between tumor and host. This makes it difficult to accurately assess the patient's level of cancerization and formulate personalized treatment plans. Therefore, there is an urgent need for a new comprehensive evaluation method that can not only consider multiple biomarkers and gene mutations at the same time, but also incorporate immune response into the evaluation system, so as to more comprehensively and accurately evaluate the level of cancerization and provide practical decision support for clinical practice.

[0004] In the prior art, publication number CN113943817B discloses a model and construction method for evaluating the level of cervical cancer cancerization, which screens existing cervical cancer genes and their methylation regions, designs probes, and extracts cervical cell DNA from cervical cancer tumor tissues; performs end repair and linker ligation on cervical cell DNA fragments to construct a cervical cell DNA methylation library, and performs targeted enrichment of the library; performs bioinformatics analysis on the processed cervical cell DNA methylation library, uses a logistic regression algorithm to construct an evaluation model, and uses clinical samples to verify the evaluation model; the evaluation model is used to evaluate cervical cancer cancerization with a compliance rate of 92.5%, a clinical sensitivity of 0.888889, a clinical specificity of 0.954545, and an AUC of 0.9271, which can effectively reduce overtreatment to reduce the incidence and mortality of cervical cancer. However, the prior art still has defects. The prior art only relies on single DNA data for the evaluation of the level of cancerization, but cancerization is a complex process that involves changes in multiple body data. This single-dimensional data analysis will lead to insufficient comprehensiveness and accuracy of the evaluation results. Moreover, carcinogenesis involves multiple dimensions of DNA data. The existing technology does not conduct data mining for methylation analysis deeply enough, and the evaluation results are not reliable enough.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a method and device for constructing a canceration level assessment model to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A method for constructing a canceration level assessment model, comprising the following specific steps:

[0009] Step 1: Conduct medical tests on the evaluation subject, process the test results, and obtain serum marker data, gene mutation data, protein expression data, genetic data, and immune data of the evaluation subject;

[0010] Step 2: Perform mathematical analysis on serum marker data, gene mutation data and protein expression data to obtain cancer state coefficients, perform mathematical analysis on genetic data to obtain tumor suppression resistance coefficients, perform mathematical analysis on tumor suppression resistance coefficients and cancer state coefficients to generate cancer degree coefficients;

[0011] Step 3: Extract features from immune data to obtain cellular immunity coefficients and immune factor correction coefficients, generate anti-cancer indexes based on the cellular immunity coefficients and immune factor correction coefficients, and generate canceration level assessment coefficients based on the anti-cancer indexes and canceration degree coefficients;

[0012] Step 4: Compare the preset thresholds of the canceration level assessment coefficients, and classify the canceration into mild canceration, moderate canceration, and severe canceration according to the comparison results.

[0013] Furthermore, the serum marker data include alpha embryonic protein content and carcinoembryonic antigen content; the gene mutation data include KRAS mutation score and TP53 mutation score; the protein expression data include IHC rating of HER2 protein and H-score of p53 protein, and the genetic data include methylation degree of related cancer suppressor genes; the tumor suppressor genes include: PTEN gene, RB1 gene, CDKN2A gene and NF1 gene; the immune data include immune cell quantity data and cytokine data, and the immune cell quantity data include CD8+T cell quantity, CD4+T cell quantity, B cell quantity, natural killer cell quantity and cancer cell quantity in the tumor microenvironment, and the cytokine data include IL-6 level, TNF-alpha level and IL-10 level; the specific logic for obtaining the IHC score of HER2 protein is: converting the IHC rating into IHC score, setting level 0 to 1 point; setting level 1+ to 2 points, setting level 2+ to 3 points, and setting level 3+ to 4 points.

[0014] Furthermore, the specific logic for obtaining the KRAS mutation score is as follows: setting the influencing factor of the KRAS key mutation position, setting the influencing factor of the mutation at the G12D position to 1, setting the influencing factor of the mutation at the G12V position to 2, and setting the influencing factor of the mutation at the G13D position to 3, collecting a group of samples from the evaluation object, and taking the ratio of the number of mutations at the G12D position, G12V position, and G13D position in the group of samples to the total number of mutations at the G12D position, G12V position, and G13D position as the mutation frequency at the G12D position, G12V position, and G13D position, and counting the frequency of gene mutations at the G12D position, G12V position, and G13D position in this group of samples, and performing the KRAS mutation score according to the statistical results. The specific formula for performing the KRAS mutation score is as follows:

[0015] S krsa =f G12D +2f G12v +3f G13D

[0016] Among them, S krsa To score KRAS mutations, f G12Dis the mutation frequency at position G12D, f G12v is the mutation frequency at position G12V, f G13D is the mutation frequency at position G13D.

[0017] Furthermore, the specific logic for obtaining the TP53 mutation score is as follows: setting the influencing factors of the key mutation positions of TP53, setting the influencing factors of the mutation at the R175H position to 1, setting the influencing factors of the mutation at the R248Q position to 2, and setting the influencing factors of the mutation at the R273H position to 3, collecting a group of samples from the evaluation object, and taking the ratios of the number of mutations at the R175H position, R248Q position, and R273H position in the group of samples to the total number of mutations at the R175H position, R248Q position, and R273H position as the mutation frequencies at the R175H position, R248Q position, and R273H position, and counting the gene mutation frequencies at the R175H position, R248Q position, and R273H position of the group of samples, and performing the TP53 mutation score according to the statistical results. The specific formula for performing the TP53 mutation score is as follows:

[0018] S TP53 =f R175H +2f R248Q +3f R273H

[0019] Among them, S TP53 Scoring TP53 mutations, f R175H is the mutation frequency of position R175H, f R248Q is the mutation frequency at position R248Q, f R273H is the mutation frequency of R273H position.

[0020] Furthermore, the specific logic for generating the cancer state coefficient is: performing mathematical analysis on serum marker data, gene mutation data and protein expression data to obtain the cancer state coefficient. The specific formula for generating the cancer state coefficient is:

[0021]

[0022] Among them, Az is the cancer state coefficient, C J is the alpha embryo protein content, C A is the carcinoembryonic antigen content, S krsa Score for KRAS mutation, S TP53 Scoring TP53 mutations, S HER2 S is the IHC score for HER2 protein. p53 H-score of p53 protein.

[0023] Furthermore, the specific logic for generating the cancer degree coefficient is as follows: statistically calculating the methylation degree of tumor suppressor genes, the tumor suppressor genes including: PTEN gene, RB1 gene, CDKN2A gene and NF1 gene; calculating the difference between the methylation degree of various tumor suppressor genes and the corresponding methylation threshold, and setting the difference less than zero to zero to process the difference, performing mathematical analysis on the processed difference to generate the cancer suppression obstruction coefficient, performing mathematical analysis on the cancer suppression obstruction coefficient and the cancer state coefficient to generate the cancer degree coefficient; the specific formula for generating the cancer suppression obstruction coefficient is:

[0024]

[0025] Among them, Ya is the cancer inhibition coefficient, Kj i is the difference after treatment corresponding to the i-th tumor suppressor gene, M is the total number of tumor suppressor genes, and i is the index of the tumor suppressor gene type;

[0026] The specific formula for generating the cancer degree coefficient is:

[0027] AC=Az*e Ya

[0028] Among them, AC is the cancer degree coefficient, Az is the cancer state coefficient, and Ya is the cancer suppression obstruction coefficient.

[0029] Furthermore, the specific logic for generating the canceration level assessment coefficient is as follows: extracting features from immune data to obtain the cellular immunity coefficient and the immune factor correction coefficient, generating an anti-cancer index based on the cellular immunity coefficient and the immune factor correction coefficient, and generating a canceration level assessment coefficient through the anti-cancer index and the canceration degree coefficient; the specific formula for obtaining the cellular immunity coefficient is as follows:

[0030]

[0031] Among them, Xm is the cell immunity coefficient, N CD8+ is the number of CD8+T cells, N NK is the number of natural killer cells, N B is the number of B cells, N CD4+ is the number of CD4+T cells, N a is the number of cancer cells;

[0032] The specific formula for generating the immunity factor correction coefficient is:

[0033]

[0034] Among them, Xy is the correction coefficient of the immune factor, C IL-6 is the IL-6 level, C TNF is the level of TNF-alpha, C IL-10is the IL-10 level;

[0035] The specific formula for generating the anti-cancer index is:

[0036]

[0037] where KA is the anti-cancer index,

[0038] The specific formula for generating the cancerization level evaluation coefficient is: generating the cancerization level evaluation coefficient through the anti-cancer index and the cancerization degree coefficient;

[0039]

[0040] where KH is the cancerization level evaluation coefficient and AC is the cancerization degree coefficient.

[0041] Furthermore, the specific logic for classifying and evaluating the cancerization level is:

[0042] Preset the cancerization level evaluation threshold KH0. If KH < 0.6KH0, the cancerization level is mild cancerization. If 0.6KH0 ≤ KH < KH0, the cancerization level is moderate cancerization. If KH ≥ KH0, the cancerization level is severe cancerization.

[0043] The present invention further provides a device for constructing a cancerization level evaluation model. The device is used to implement the method for constructing the cancerization level evaluation model, and specifically includes:

[0044] Data acquisition module: used to perform medical tests on the evaluation object, process the test results, and obtain the serum marker data, gene mutation data, protein expression data, genetic data, and immune data of the evaluation object;

[0045] Degree evaluation module: used to perform mathematical analysis on the serum marker data, gene mutation data, and protein expression data to obtain the cancerization status coefficient, perform mathematical analysis on the genetic data to obtain the anti-cancer inhibition coefficient, and perform mathematical analysis on the anti-cancer inhibition coefficient and the cancerization status coefficient to generate the cancerization degree coefficient;

[0046] Resistance evaluation module: used to extract features from the immune data to obtain the cellular immunity coefficient and the immune factor correction coefficient, generate the anti-cancer index according to the cellular immunity coefficient and the immune factor correction coefficient, and generate the cancerization level evaluation coefficient through the anti-cancer index and the cancerization degree coefficient;

[0047] Cancerization evaluation module: used to compare the cancerization level evaluation coefficient with the preset threshold, and classify the cancerization into mild cancerization, moderate cancerization, and severe cancerization according to the comparison result.

[0048] Compared with the prior art, the beneficial effects of the present invention are:

[0049] The present invention constructs a comprehensive evaluation model by integrating multiple biological data such as serum markers, gene mutations, protein expression, immune response and methylation. This multi-dimensional analysis framework can fully reflect the complexity of the cancerization process, thereby improving the comprehensiveness and accuracy of the evaluation results.

[0050] For the mining of gene data, the present invention not only focuses on methylation, but also comprehensively considers gene mutations and the expression effects of related protein genes. Such a comprehensive evaluation method makes the evaluation results more reliable, thus better guiding clinical decision-making and formulating personalized treatment plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a schematic diagram of the overall method flow of the present invention.

[0052] Figure 2 It is a schematic diagram of the overall structure of the device of the present invention. DETAILED DESCRIPTION

[0053] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0054] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0055] Example:

[0056] See also Figure 1 , the present invention provides a technical solution:

[0057] A method for constructing a canceration level assessment model, comprising the following specific steps:

[0058] Step 1: Conduct medical tests on the evaluation subject, process the test results, and obtain serum marker data, gene mutation data, protein expression data, genetic data, and immune data of the evaluation subject;

[0059] The serum marker data include alpha embryonic protein content and carcinoembryonic antigen content; the gene mutation data include KRAS mutation score and TP53 mutation score; the protein expression data include IHC rating of HER2 protein and H-score of p53 protein, and the genetic data include methylation degree of related cancer suppressor genes; the tumor suppressor genes include: PTEN gene, RB1 gene, CDKN2A gene and NF1 gene; the immune data include immune cell quantity data and cytokine data, and the immune cell quantity data include CD8+T cell quantity, CD4+T cell quantity, B cell quantity, natural killer cell quantity and cancer cell quantity in the tumor microenvironment, and the cytokine data include IL-6 level, TNF-alpha level and IL-10 level; the specific logic for obtaining the IHC score of HER2 protein is: converting the IHC rating into IHC score, setting level 0 to 1 point; setting level 1+ to 2 points, setting level 2+ to 3 points, and setting level 3+ to 4 points. AFP and CEA are two commonly used tumor markers. AFP and CEA in serum can directly provide important basis for evaluating the level of cancer.

[0060] The specific logic for obtaining the KRAS mutation score is as follows: set the influencing factor of the key mutation position of KRAS, set the influencing factor of the mutation at the G12D position to 1, set the influencing factor of the mutation at the G12V position to 2, and set the influencing factor of the mutation at the G13D position to 3; collect a group of samples from the evaluation object; use the ratio of the number of mutations at the G12D position, G12V position, and G13D position in the group of samples to the total number of mutations at the G12D position, G12V position, and G13D position as the mutation frequency at the G12D position, G12V position, and G13D position; count the frequency of gene mutations at the G12D position, G12V position, and G13D position in this group of samples; perform the KRAS mutation score based on the statistical results; and the specific formula for performing the KRAS mutation score is as follows:

[0061] S krsa =f G12D +2f G12v +3f G13D

[0062] Among them, S krsa To score KRAS mutations, f G12D is the mutation frequency at position G12D, f G12v is the mutation frequency at position G12V, f G13D is the mutation frequency at position G13D.

[0063] KRAS gene mutations are common in various cancers. krsaIt reflects the effect of KRAS gene mutation on the degree of canceration. The larger the value, the greater the effect of KRAS gene mutation on the degree of canceration.

[0064] The specific logic for obtaining the TP53 mutation score is as follows: set the influencing factors of the key mutation positions of TP53, set the influencing factors of the mutation at the R175H position to 1, set the influencing factors of the mutation at the R248Q position to 2, and set the influencing factors of the mutation at the R273H position to 3, collect a group of samples from the evaluation object, and use the ratios of the number of mutations at the R175H position, R248Q position, and R273H position in the group of samples to the total number of mutations at the R175H position, R248Q position, and R273H position as the mutation frequencies at the R175H position, R248Q position, and R273H position, and count the gene mutation frequencies at the R175H position, R248Q position, and R273H position of this group of samples, and perform the TP53 mutation score based on the statistical results. The specific formula for performing the TP53 mutation score is as follows:

[0065] S TP53 =f R175H +2f R248Q +3f R273H

[0066] Among them, S TP53 Scoring TP53 mutations, f R175H is the mutation frequency of position R175H, f R248Q is the mutation frequency of position R248Q, f R273H is the mutation frequency of R273H position. TP53 mutation score S TP53 It reflects the effect of TP53 gene mutation on the degree of canceration. The larger the value, the greater the effect of TP53 gene mutation on the degree of canceration.

[0067] HER2 is a transmembrane receptor tyrosine kinase that plays an important role in cell proliferation and differentiation. The expression of HER2 protein can be divided into 4 levels through IHC rating, namely 0, 1+, 2+ and 3+. In order to facilitate the assessment of the degree of canceration, the IHC rating is changed to IHC score, with 0 set as 1 point; 1+ set as 2 points, 2+ set as 3 points, and 3+ set as 4 points; the higher the score, the more conducive to cell proliferation and differentiation. Rapid cell proliferation and differentiation are the prominent characteristics of cancer cells. The higher the IHC score of HER2 protein, the higher the degree of canceration.

[0068] p53 is a tumor suppressor protein that plays a key role in cell cycle regulation, DNA repair, and apoptosis. A high H-score of p53 protein may mean abnormal accumulation of p53 protein, which is often caused by TP53 gene mutations. These mutated p53 proteins cannot normally perform their tumor suppressor function and may promote the occurrence and development of tumors.

[0069] DNA methylation refers to the addition of methyl groups to DNA molecules, and this modification usually occurs at CpG dinucleotide sites. The DNA methylation state of the gene promoter region is an important epigenetic regulatory mechanism, which is usually associated with the inhibition of gene expression. High methylation of tumor suppressor genes can lead to inactivation of tumor suppressor genes, thereby promoting tumor occurrence and development. The specific formula for quantifying the degree of methylation in this embodiment is:

[0070]

[0071] Where Kj is the degree of methylation, M is the intensity of the methylated probe, and U is the intensity of the unmethylated probe;

[0072] The PTEN gene controls the synthesis of PTEN lipid phosphatase in cells. PTEN lipid phosphatase is involved in regulating cell growth and survival. If the methylation level of this gene is high, the synthesis of PTEN lipid phosphatase in the body will be reduced, which is conducive to cell canceration.

[0073] The RB1 gene encodes retinoblastoma protein, which mainly regulates the G1 / S transition of the cell cycle. High methylation of the RB1 gene will lead to blocked RB1 gene expression, which is associated with a variety of cancers. The higher the methylation of the RB1 gene, the greater the chance of developing cancer.

[0074] The CDKN2A gene encodes p16 (INK4a) and p14 (ARF), and is involved in regulating the cell cycle and apoptosis. High methylation of the CDKN2A gene will lead to a decrease in p16 (INK4a) and p14 (ARF), a higher probability of abnormal cell apoptosis, and a higher probability of cell canceration;

[0075] The NF1 gene encodes neurofibromatosis inhibitory protein, which is involved in cell signal transduction. High methylation of the NF1 gene will lead to obstruction of cell information transmission and increase the degree of cell canceration;

[0076] CD8+T cells are cytotoxic T cells that can directly kill tumor cells. CD4+T cells can assist and regulate immune responses; CD4+T cells are usually active in assisting and regulating immune responses. Therefore, the more CD4+T cells there are, the less favorable it is for cells to become cancerous. B cells produce antibodies and participate in humoral immunity, which has a positive effect on fighting cancer. Natural killer cells can directly kill tumors and virus-infected cells, and can prevent the process of cancer.

[0077] IL-6 is a proinflammatory cytokine that participates in immune response, inflammation and acute phase response. High levels of IL-6 are often associated with tumor aggressiveness. It can promote tumor cell proliferation, survival and metastasis. TNF-alpha is a potent proinflammatory cytokine that participates in inflammatory response, immune regulation and apoptosis. High levels of TNF-alpha can directly kill tumor cells and inhibit tumor growth. IL-10 is an anti-inflammatory cytokine that mainly exerts its effects by inhibiting inflammatory response and regulating immune response. High levels of IL-10 are often associated with immunosuppression and tumor escape, reducing anti-tumor immune response, thereby promoting tumor growth and metastasis.

[0078] Step 2: Perform mathematical analysis on serum marker data, gene mutation data and protein expression data to obtain cancer state coefficients, perform mathematical analysis on genetic data to obtain tumor suppression resistance coefficients, perform mathematical analysis on tumor suppression resistance coefficients and cancer state coefficients to generate cancer degree coefficients;

[0079] The specific logic for generating the cancer state coefficient is: the cancer state coefficient is obtained by mathematically analyzing the serum marker data, gene mutation data and protein expression data. The specific formula for generating the cancer state coefficient is:

[0080]

[0081] Among them, Az is the cancer state coefficient, C J is the alpha embryo protein content, C A is the carcinoembryonic antigen content, S krsa Score for KRAS mutation, S TP53 Scoring TP53 mutations, S HER2 S is the IHC score for HER2 protein. p53 is the H-score of p53 protein. The canceration state coefficient Az reflects the canceration state of the evaluated object. The higher the value, the higher the canceration state of the evaluated object.

[0082] The specific logic for generating the cancer degree coefficient is as follows: statistically calculating the methylation degree of tumor suppressor genes, the tumor suppressor genes include: PTEN gene, RB1 gene, CDKN2A gene and NF1 gene; calculating the difference between the methylation degree of various tumor suppressor genes and the corresponding methylation threshold, and setting the difference less than zero to zero to process the difference, performing mathematical analysis on the processed difference to generate the cancer suppression obstruction coefficient, performing mathematical analysis on the cancer suppression obstruction coefficient and the cancer state coefficient to generate the cancer degree coefficient; the specific formula for generating the cancer suppression obstruction coefficient is as follows:

[0083]

[0084] Among them, Ya is the cancer inhibition coefficient, Kj i is the difference after treatment corresponding to the i-th tumor suppressor gene, M is the total number of tumor suppressor genes, and i is the index of the tumor suppressor gene type;

[0085] The cancer suppression resistance coefficient Ya reflects the ability of the evaluated object to resist canceration. The larger the value is, the weaker the ability of the evaluated object to resist canceration is.

[0086] The specific formula for generating the cancer degree coefficient is:

[0087] AC=Az*e Ya

[0088] Among them, AC is the cancer degree coefficient, Az is the cancer state coefficient, and Ya is the cancer suppression obstruction coefficient. The cancer degree coefficient AC reflects the cancer degree of the evaluated object. The larger its value, the higher the cancer degree of the evaluated object.

[0089] Step 3: Extract features from immune data to obtain cellular immunity coefficients and immune factor correction coefficients, generate anti-cancer indexes based on the cellular immunity coefficients and immune factor correction coefficients, and generate canceration level assessment coefficients based on the anti-cancer indexes and canceration degree coefficients;

[0090] The specific logic for generating the canceration level assessment coefficient is as follows: extract the characteristics of the immune data to obtain the cellular immunity coefficient and the immune factor correction coefficient, generate the anti-cancer index based on the cellular immunity coefficient and the immune factor correction coefficient, and generate the canceration level assessment coefficient through the anti-cancer index and the canceration degree coefficient; the specific formula for obtaining the cellular immunity coefficient is as follows:

[0091]

[0092] Among them, Xm is the cell immunity coefficient, N CD8+ is the number of CD8+T cells, N NK is the number of natural killer cells, N B is the number of B cells, N CD4+ is the number of CD4+T cells, Na is the number of cancer cells; the cell immunity coefficient Xm reflects the confrontation between the immune cells and cancer cells of the evaluated object. The larger the value, the greater the advantage of the immune cells in the confrontation.

[0093] The specific formula for generating the immunity factor correction coefficient is:

[0094]

[0095] Among them, Xy is the correction coefficient of the immune factor, C IL-6 is the IL-6 level, C TNF is the level of TNF-alpha, C IL-10 is the IL-10 level; the immune factor correction coefficient Xy reflects the ability of cancer cells to proliferate, differentiate and metastasize. The larger its value is, the stronger the ability of cancer cells to proliferate, differentiate and metastasize is.

[0096] The specific formula for generating the anti-cancer index is:

[0097]

[0098] Among them, KA is the anti-cancer index, which reflects the ability of the immune system of the evaluated object to fight cancer. The larger the value, the stronger the ability of the immune system of the evaluated object to fight cancer.

[0099] The specific formula for generating the canceration level assessment coefficient is as follows: generating the canceration level assessment coefficient through the anti-cancer index and the canceration degree coefficient;

[0100]

[0101] Among them, KH is the canceration level assessment coefficient, and AC is the canceration degree coefficient. The canceration level assessment coefficient KH reflects the canceration level of the assessment object. The larger its value, the higher the canceration level of the assessment object.

[0102] Step 4: Compare the preset thresholds of the canceration level assessment coefficients, and classify the canceration into mild canceration, moderate canceration, and severe canceration according to the comparison results.

[0103] The specific logic for classifying and evaluating the cancerization level is as follows: A cancerization level evaluation threshold KH0 is preset. If KH < 0.6KH0, the cancerization level is mild cancerization. If 0.6KH0 ≤ KH < KH0, the cancerization level is moderate cancerization. If KH ≥ KH0, the cancerization level is severe cancerization. When the evaluation object is in a state of mild cancerization, the body's immune system has an advantage in combating cancerization and can be treated by means such as radiotherapy and chemotherapy. When the evaluation object is in a state of moderate cancerization, the body's immune system is in a stalemate in the process of combating cancerization, and surgical treatment should be carried out as soon as possible. When the evaluation object is in a state of severe cancerization, the body's immune system is no longer able to fight against cancerization, and round-the-clock medical care and treatment are required. The cancerization level evaluation threshold KH0 is determined by experts according to the specific physical conditions of the evaluation object. For example, the cancerization level evaluation coefficient of cancer patients can be obtained through the above method, and then cancer experts are invited to demonstrate the cancerization situation and the cancerization level evaluation coefficient of cancer patients to determine the cancerization level evaluation threshold. This is prior art and will not be elaborated here.

[0104] Please refer to Figure 2 , the present invention further provides a device for constructing a cancerization level evaluation model. The device is used to implement the method for constructing a cancerization level evaluation model, and specifically includes:

[0105] Data acquisition module: It is used to perform medical tests on the evaluation object, process the test results, and obtain the serum marker data, gene mutation data, protein expression data, genetic data, and immune data of the evaluation object;

[0106] Degree evaluation module: It is used to perform mathematical analysis on the serum marker data, gene mutation data, and protein expression data to obtain a cancerization state coefficient, perform mathematical analysis on the genetic data to obtain a tumor suppression obstruction coefficient, and perform mathematical analysis on the tumor suppression obstruction coefficient and the cancerization state coefficient to generate a cancerization degree coefficient;

[0107] Resistance evaluation module: It is used to extract features from the immune data to obtain a cellular immunity coefficient and an immune factor correction coefficient, generate an anti-cancer index based on the cellular immunity coefficient and the immune factor correction coefficient, and generate a cancerization level evaluation coefficient through the anti-cancer index and the cancerization degree coefficient;

[0108] Cancerization evaluation module: It is used to compare the cancerization level evaluation coefficient with a preset threshold, and classify the cancerization into mild cancerization, moderate cancerization, and severe cancerization according to the comparison result.

[0109] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain a formula that is closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0110] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0111] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0112] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for constructing a canceration level assessment model, characterized in that: The specific steps include: Step 1: Conduct medical tests on the evaluation subject, process the test results, and obtain serum marker data, gene mutation data, protein expression data, genetic data, and immune data of the evaluation subject; Step 2: Perform mathematical analysis on serum marker data, gene mutation data and protein expression data to obtain cancer state coefficients, perform mathematical analysis on genetic data to obtain tumor suppression resistance coefficients, perform mathematical analysis on tumor suppression resistance coefficients and cancer state coefficients to generate cancer degree coefficients; Step 3: Extract features from immune data to obtain cellular immunity coefficients and immune factor correction coefficients, generate anti-cancer indexes based on the cellular immunity coefficients and immune factor correction coefficients, and generate canceration level assessment coefficients based on the anti-cancer indexes and canceration degree coefficients; Step 4: Compare the preset thresholds of the canceration level assessment coefficients, and classify the canceration into mild canceration, moderate canceration, and severe canceration according to the comparison results.

2. The method for constructing a canceration level assessment model according to claim 1, characterized in that: The serum marker data include alpha embryonic protein content and carcinoembryonic antigen content; the gene mutation data include KRAS mutation score and TP53 mutation score; the protein expression data include IHC score of HER2 protein and H-score score of p53 protein, and the genetic data include methylation degree of related cancer suppressor genes; the tumor suppressor genes include: PTEN gene, RB1 gene, CDKN2A gene and NF1 gene; the immune data include immune cell quantity data and cytokine data, and the immune cell quantity data include CD8+T cell quantity, CD4+T cell quantity, B cell quantity, natural killer cell quantity and cancer cell quantity in the tumor microenvironment, and the cytokine data include IL-6 level, TNF-alpha level and IL-10 level; the specific logic for obtaining the IHC score of HER2 protein is: converting IHC rating into IHC score, setting level 0 to 1 point; setting level 1+ to 2 points, setting level 2+ to 3 points, and setting level 3+ to 4 points.

3. The method for constructing a canceration level assessment model according to claim 2, characterized in that: The specific logic for obtaining the KRAS mutation score is as follows: set the influencing factor of the key mutation position of KRAS, set the influencing factor of the mutation at the G12D position to 1, set the influencing factor of the mutation at the G12V position to 2, and set the influencing factor of the mutation at the G13D position to 3; collect a group of samples from the evaluation object; use the ratio of the number of mutations at the G12D position, G12V position, and G13D position in the group of samples to the total number of mutations at the G12D position, G12V position, and G13D position as the mutation frequency at the G12D position, G12V position, and G13D position; count the frequency of gene mutations at the G12D position, G12V position, and G13D position in this group of samples; perform the KRAS mutation score based on the statistical results; and the specific formula for performing the KRAS mutation score is as follows: S krsa =f G12D +2f G12v +3f G13D Among them, S krsa To score KRAS mutations, f G12D is the mutation frequency at position G12D, f G12v is the mutation frequency at position G12V, f G13D is the mutation frequency at position G13D.

4. The method for constructing a canceration level assessment model according to claim 2, characterized in that: The specific logic for obtaining the TP53 mutation score is as follows: Set the impact factors for key TP53 mutation positions. Set the impact factor for the mutation at position R175H to 1, the impact factor for the mutation at position R248Q to 2, and the impact factor for the mutation at position R273H to 3. Collect a set of samples from the evaluation object, and use the ratios of the number of mutations at positions R175H, R248Q, and R273H in this set of samples to the total number of positions R175H, R248Q, and R273H as the mutation frequencies at positions R175H, R248Q, and R273H respectively. Statistically analyze the gene mutation frequencies at positions R175H, R248Q, and R273H in this set of samples, and perform TP53 mutation scoring based on the statistical results. The specific formula for performing TP53 mutation scoring is: S TP53 =f R175H +2f R248Q +3f R273H Among them, S TP53 Scoring TP53 mutations, f R175H is the mutation frequency of position R175H, f R248Q is the mutation frequency at position R248Q, f R273H is the mutation frequency of R273H position.

5. The method for constructing a canceration level assessment model according to claim 1, characterized in that: The specific logic for generating the carcinogenic state coefficient is as follows: Perform mathematical analysis on serum marker data, gene mutation data, and protein expression data to obtain the carcinogenic state coefficient. The specific formula for generating the carcinogenic state coefficient is: Among them, Az is the cancer state coefficient, C J is the alpha embryo protein content, C A is the carcinoembryonic antigen content, S krsa Score for KRAS mutation, S TP53 Scoring TP53 mutations, S HER2 S is the IHC score for HER2 protein. p53 H-score of p53 protein.

6. The method for constructing a canceration level assessment model according to claim 1, characterized in that: The specific logic for generating the carcinogenic degree coefficient is as follows: Statistically analyze the methylation degree of tumor suppressor genes, where the tumor suppressor genes include: PTEN gene, RB1 gene, CDKN2A gene, and NF1 gene; calculate the difference between the methylation degree of each tumor suppressor gene and the corresponding methylation threshold, and set the difference less than zero to zero to process the difference. Perform mathematical analysis on the processed difference to generate the tumor suppressor inhibition coefficient. Perform mathematical analysis on the tumor suppressor inhibition coefficient and the carcinogenic state coefficient to generate the carcinogenic degree coefficient; The specific formula for generating the tumor suppressor inhibition coefficient is: Among them, Ya is the cancer inhibition coefficient, Kj i is the difference after treatment corresponding to the i-th tumor suppressor gene, M is the total number of tumor suppressor genes, and i is the index of the tumor suppressor gene type; The specific formula for generating the carcinogenic degree coefficient is: AC=Az*e Ya Where AC is the carcinogenic degree coefficient, Az is the carcinogenic state coefficient, and Ya is the tumor suppressor inhibition coefficient.

7. The method for constructing a canceration level assessment model according to claim 1, characterized in that: The specific logic for generating the carcinogenic level evaluation coefficient is as follows: Extract features from immune data to obtain the cellular immunity coefficient and the immune factor correction coefficient. Generate the anti-cancer index based on the cellular immunity coefficient and the immune factor correction coefficient. Generate the carcinogenic level evaluation coefficient through the anti-cancer index and the carcinogenic degree coefficient; The specific formula for obtaining the cellular immunity coefficient is: Among them, Xm is the cell immunity coefficient, N CD8+ is the number of CD8+T cells, N NK is the number of natural killer cells, N B is the number of B cells, N CD4+ is the number of CD4+T cells, N a is the number of cancer cells; The specific formula for generating the immune factor correction coefficient is: Among them, Xy is the correction coefficient of the immune factor, C IL-6 is the IL-6 level, C THF is the level of TNF-alpha, C IL-10 is the IL-10 level; The specific formula for generating the anti-cancer index is: Where KA is the anti-cancer index; The specific formula for generating the carcinogenic level evaluation coefficient is: Generate the carcinogenic level evaluation coefficient through the anti-cancer index and the carcinogenic degree coefficient; Where KH is the carcinogenic level evaluation coefficient and AC is the carcinogenic degree coefficient.

8. The method for constructing a canceration level assessment model according to claim 1, characterized in that: The specific logic for classifying and evaluating the carcinogenic level is: Preset the carcinogenic level evaluation threshold KH0. If KH < 0.6KH0, the carcinogenic level is slightly carcinogenic. If 0.6KH0 ≤ KH < KH0, the carcinogenic level is moderately carcinogenic. If KH ≥ KH0, the carcinogenic level is severely carcinogenic.

9. A device for constructing a canceration level assessment model, characterized in that: The device is used to implement the carcinogenic level evaluation model construction method according to any one of claims 1-8, and specifically includes: Data collection module: used to conduct medical tests on the evaluation subjects, process the test results, and obtain the serum marker data, gene mutation data, protein expression data, genetic data, and immune data of the evaluation subjects; Degree evaluation module: used to perform mathematical analysis on serum marker data, gene mutation data and protein expression data to obtain canceration state coefficients, perform mathematical analysis on genetic data to obtain cancer suppression resistance coefficients, perform mathematical analysis on cancer suppression resistance coefficients and canceration state coefficients, and generate canceration degree coefficients; Resistance evaluation module: used to extract features from immune data to obtain cellular immunity coefficients and immune factor correction coefficients, generate anti-cancer indexes based on the cellular immunity coefficients and immune factor correction coefficients, and generate canceration level evaluation coefficients based on the anti-cancer index and canceration degree coefficients; Canceration assessment module: used to compare the preset thresholds of the canceration level assessment coefficients, and classify canceration into mild canceration, moderate canceration and severe canceration according to the comparison results.

Images