Malignant tumor metastasis risk prediction system based on neutrophil polarization state

Abstract

The invention provides a malignant tumor metastasis risk prediction system based on a neutrophil polarization state, and relates to the technical field of biology, and the system comprises a neutrophil detection module which is used for detecting neutrophil polarization state information in a tumor microenvironment; the patient information acquisition module is used for acquiring patient information; the tumor information acquisition module is used for acquiring tumor information; the malignancy degree scoring module is used for determining a tumor malignancy degree score according to the tumor information; the risk prediction scoring module is used for determining a malignant tumor metastasis risk prediction score according to the neutrophil polarization state information, the tumor malignancy degree score and the patient information; and the risk prediction report module is used for generating a risk prediction report according to the malignant tumor metastasis risk prediction score. According to the invention, the accuracy of malignant tumor metastasis risk prediction can be improved.

Description

Technical Field

[0001] The present invention relates to the field of biotechnology, and in particular to a malignant tumor metastasis risk prediction system based on the polarization state of neutrophils. Background Art

[0002] In the related art, CN117316426A discloses a tumor bone metastasis prediction system and method based on bone metastasis-specific bone markers, which relates to the field of machine learning technology, including: an index acquisition module for acquiring a plurality of bone marker indexes related to bone metastasis in the patient serum obtained by serum detection of the patient; a bone metastasis prediction module connected to the index acquisition module for inputting each bone marker index into a pre-trained tumor bone metastasis prediction model to predict the early bone metastasis incidence rate of the patient for doctors to refer to for clinical diagnosis. The beneficial effect is that by quantitatively detecting the contents of bone markers such as calcium and phosphorus metabolism regulation indexes, bone formation and bone resorption markers, bone metabolism-related hormones and cytokines, and electrolytes in serum, and early predicting the bone metastasis incidence rate through machine learning, it can be used for the early auxiliary diagnosis of tumor bone metastasis, the auxiliary evaluation of curative effect during the treatment process, and the monitoring of metastasis recurrence after the treatment, and the detection result can be earlier than the clinical symptoms.

[0003] CN115620903A discloses a method and system for predicting the incidence risk of bone metastasis in pan-cancer malignant tumors. The method includes: classifying cancer types with bone metastasis risk according to the bone metastasis prevalence rate; constructing a prediction model with the cancer type classification result as one of the risk factors; obtaining the clinical characteristics of the predicted sample corresponding to the risk factors, and using the prediction model to predict the bone metastasis risk. This solution intends to first construct a cancer classification system based on the bone metastasis prevalence rate, and provide a prediction model for the incidence risk of bone metastasis in pan-cancer based on the cancer type, age, gender, insurance status, histological stage of the tumor, TNM stage, and liver, lung, and brain metastasis conditions of cancer patients, determine the current bone metastasis probability of tumor patients, and accurately predict the bone metastasis incidence probability of pan-cancer malignant tumor patients, which is easy to use and has high prediction accuracy.

[0004] Based on the above related technologies, the bone metastasis incidence probability of malignant tumor patients can be accurately predicted. However, the related technologies do not consider the influence of the polarization state of neutrophils on the malignant tumor metastasis risk, that is, the malignant tumor metastasis risk cannot be predicted based on the polarization state of neutrophils. Summary of the Invention

[0005] The present invention provides a malignant tumor metastasis risk prediction system based on the polarization state of neutrophils, which can solve the technical problem that the related technologies cannot predict the malignant tumor metastasis risk based on the polarization state of neutrophils.

[0006] According to a first aspect of the present invention, there is provided a malignant tumor metastasis risk prediction system based on the polarization state of neutrophils, comprising:

[0007] A neutrophil detection module for detecting the neutrophil polarization state information in the tumor microenvironment, wherein the neutrophil polarization state information includes: the proportion of N1-type neutrophils and the proportion of N2-type neutrophils;

[0008] A patient information acquisition module for acquiring patient information, wherein the patient information includes: patient age and immune system parameters;

[0009] A tumor information acquisition module for acquiring tumor information, wherein the tumor information includes: tumor location, cell differentiation degree, nuclear division frequency, and tumor infiltration range;

[0010] A malignancy scoring module for determining a tumor malignancy score based on the tumor information;

[0011] A risk prediction scoring module for determining a malignant tumor metastasis risk prediction score based on the neutrophil polarization state information, the tumor malignancy score, and the patient information,

[0012] A risk prediction report module for generating a risk prediction report based on the malignant tumor metastasis risk prediction score.

[0013] According to a second aspect of the present invention, there is provided a method for predicting the risk of malignant tumor metastasis based on the polarization state of neutrophils, comprising:

[0014] Detecting the neutrophil polarization state information in the tumor microenvironment, wherein the neutrophil polarization state information includes: the proportion of N1-type neutrophils and the proportion of N2-type neutrophils;

[0015] Acquiring patient information, wherein the patient information includes: patient age and immune system parameters;

[0016] Acquiring tumor information, wherein the tumor information includes: tumor location, cell differentiation degree, nuclear division frequency, and tumor infiltration range;

[0017] Determining a tumor malignancy score based on the tumor information;

[0018] Determining a malignant tumor metastasis risk prediction score based on the neutrophil polarization state information, the tumor malignancy score, and the patient information;

[0019] Generating a risk prediction report based on the malignant tumor metastasis risk prediction score.

[0020] Technical effects: According to the present invention, the polarization state information of neutrophils in the tumor microenvironment can be accurately detected, and the malignancy degree of the patient's tumor can be accurately analyzed. Further, based on the neutrophil polarization state information, tumor malignancy degree, and patient information, the risk of malignant tumor metastasis can be predicted, improving the accuracy of predicting the risk of malignant tumor metastasis. When determining the tumor malignancy degree score, the tumor malignancy degree score can be determined according to the tumor location recognition result, cell differentiation degree, nucleus division frequency, and tumor infiltration range. During the calculation process, the malignancy degree of the tumor can be evaluated from four aspects: the location status, cell differentiation status, nucleus division status, and infiltration range status of the tumor, improving the comprehensiveness and accuracy of the tumor malignancy degree score. When determining the first relationship function, the first relationship function can be determined according to the historical proportion of N1-type neutrophils, historical proportion of N2-type neutrophils, historical tumor malignancy degree score, historical adaptive immune cell count, historical immunoglobulin level, and historical innate immune cell count, accurately describing the relationship between the patient's immune system status, tumor malignancy degree, and the tumor malignancy degree in the next cycle, improving the accuracy and objectivity of the first relationship function. When determining the predicted tumor malignancy degree score, the predicted tumor malignancy degree score in the next time cycle can be determined based on the tumor malignancy degree score in the current time cycle, the first relationship function, adaptive immune cell count, immunoglobulin level, innate immune cell count, and neutrophil polarization state information, improving the accuracy of the predicted tumor malignancy degree score and providing a data basis for calculating the malignant tumor metastasis risk prediction score. Description of the Drawings

[0021] Figure 1 Exemplarily shown is a block diagram of a malignant tumor metastasis risk prediction system based on neutrophil polarization state according to an embodiment of the present invention;

[0022] Figure 2 Exemplarily shown is a flowchart of a method for predicting the risk of malignant tumor metastasis based on neutrophil polarization state according to an embodiment of the present invention. Detailed Embodiments

[0023] Hereinafter, the technical solutions of the present invention will be described in detail with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0024] Figure 1 Exemplarily shown is a block diagram of a malignant tumor metastasis risk prediction system based on neutrophil polarization state according to an embodiment of the present invention, and the system includes:

[0025] A neutrophil detection module for detecting information on the polarization status of neutrophils in the tumor microenvironment, where the information on the polarization status of neutrophils includes: the proportion of N1-type neutrophils and the proportion of N2-type neutrophils;

[0026] A patient information acquisition module for acquiring patient information, where the patient information includes: patient age and immune system parameters;

[0027] A tumor information acquisition module for acquiring tumor information, where the tumor information includes: tumor location, degree of cell differentiation, frequency of nuclear division, and tumor infiltration range;

[0028] A malignancy scoring module for determining a tumor malignancy score based on the tumor information;

[0029] A risk prediction scoring module for determining a malignant tumor metastasis risk prediction score based on the information on the polarization status of neutrophils, the tumor malignancy score, and the patient information,

[0030] A risk prediction report module for generating a risk prediction report based on the malignant tumor metastasis risk prediction score.

[0031] The malignant tumor metastasis risk prediction system based on the polarization status of neutrophils according to an embodiment of the present invention can accurately detect the information on the polarization status of neutrophils in the tumor microenvironment, and accurately analyze the malignancy of the patient's tumor. Further, based on the information on the polarization status of neutrophils, the tumor malignancy, and the patient information, the risk of malignant tumor metastasis is predicted, improving the accuracy of the prediction of the risk of malignant tumor metastasis.

[0032] According to an embodiment of the present invention, in the neutrophil detection module, it is used to detect the information on the polarization status of neutrophils in the tumor microenvironment, where the information on the polarization status of neutrophils includes: the proportion of N1-type neutrophils and the proportion of N2-type neutrophils.

[0033] For example, specific antibodies are used to label different markers on the surface of neutrophils, such as CD11b, CD15, CD66b, and specific markers related to polarization (for example, N1-type may highly express certain pro-inflammatory cytokine receptors, while N2-type may express other anti-inflammatory related molecules), and the fluorescence intensity of cells is analyzed by flow cytometry to distinguish neutrophils in different polarization states,

[0034] According to an embodiment of the present invention, in the patient information acquisition module, it is used to acquire patient information, where the patient information includes: patient age and immune system parameters.

[0035] For example, obtain the age of the patient, check the status of the patient's immune system, and obtain immune system parameters.

[0036] According to an embodiment of the present invention, in the tumor information acquisition module, it is used to acquire tumor information, where the tumor information includes: tumor location, degree of cell differentiation, frequency of nuclear division, and tumor infiltration range.

[0037] For example, by slicing the tumor tissue and observing its cell morphology, tissue structure, nucleus size, number of nucleoli and other characteristics to judge the degree of tumor differentiation. The degree of cell differentiation is generally divided into high differentiation, medium differentiation and low differentiation. Set the value corresponding to high differentiation to 100, the value corresponding to medium differentiation to 10, and the value corresponding to low differentiation to 1; use a microscope to observe the mitotic figures of tumor cells, calculate the number of nuclear divisions per unit area or unit volume to obtain the frequency of nuclear division, and use B-ultrasound, CT and magnetic resonance imaging examination methods to observe the size, shape, edge, internal structure of the tumor and the changes in the surrounding tissues to determine the tumor infiltration range.

[0038] According to an embodiment of the present invention, in the malignancy score module, it is used to determine the malignancy score of the tumor according to the tumor information.

[0039] According to an embodiment of the present invention, determining the malignancy score of the tumor according to the tumor information includes:

[0040] Determine the tumor location recognition result according to the tumor location;

[0041] Determine the malignancy score of the tumor according to the tumor location recognition result, the degree of cell differentiation, the frequency of nuclear division and the tumor infiltration range.

[0042] For example, if the tumor is located in a position prone to metastasis, such as organs like the brain, lungs, liver and bone marrow, then the tumor cells are more likely to metastasize, and the value of the tumor location recognition result is 1. Conversely, the value of the tumor location recognition result is 0; evaluate the malignancy of the tumor according to the tumor location recognition result, degree of cell differentiation, frequency of nuclear division and tumor infiltration range, and determine the malignancy score of the tumor.

[0043] According to an embodiment of the present invention, determining the malignancy score of the tumor according to the tumor location recognition result, the degree of cell differentiation, the frequency of nuclear division and the tumor infiltration range includes: determining the malignancy score Mdot of the i-th patient in the current time period according to formula (1) i ,

[0044]

[0045] Among them, α1, α2, α3, α4 are preset weights, and Tp i is the tumor location recognition result of the i-th patient, Cdd i is the degree of cell differentiation of the tumor cells of the i-th patient, Cdd T is the preset cell differentiation degree threshold, Ndf i is the nuclear division frequency of the tumor cells of the i-th patient, Ndf T is the preset nuclear division frequency threshold, Tir i is the tumor invasion range of the i-th patient, Tir T is the preset tumor invasion range threshold.

[0046] According to an embodiment of the present invention, Tp i is the tumor location recognition result of the i-th patient. If the tumor location of the i-th patient is in a metastasizable location, such as the brain, lungs, liver, bone marrow, etc., these locations have rich blood supply and lymphatic system, providing convenient conditions for the metastasis of tumor cells, indicating that the tumor is prone to metastasis and has a high degree of malignancy. Tp i has a value of 1. Conversely, Tp i has a value of 0.

[0047] According to an embodiment of the present invention, well-differentiated tumors indicate that the cells still retain many normal tissue structure characteristics and have a low degree of malignancy. Poorly-differentiated tumors are very different from normal cell morphology and have a significantly increased degree of malignancy. is the relative difference between the degree of cell differentiation of the tumor cells of the i-th patient and the preset cell differentiation degree threshold. The larger this ratio is, the lower the relative degree of cell differentiation of the tumor cells of the i-th patient is, and the higher the degree of malignancy of the tumor is. The preset cell differentiation degree threshold can be set to the value corresponding to the well-differentiated degree of cells, that is, 100. In malignant tumors, the number of nuclear mitotic figures increases and is active, indicating rapid proliferation of tumor cells and great malignant potential. is the relative difference between the nuclear division frequency of the tumor cells of the i-th patient and the preset nuclear division frequency threshold. The larger this ratio is, the higher the relative nuclear division frequency of the tumor cells of the i-th patient is, and the higher the degree of malignancy of the tumor is. The preset nuclear division frequency threshold is a threshold set according to the tumor type. For example, when the tumor type is colorectal adenocarcinoma, the preset nuclear division frequency threshold can be set to 6 / 10HPF. The larger the invasion range of the tumor is, the more invasive the tumor is, the easier the tumor is to metastasize, and the higher the degree of malignancy is. is the relative difference between the tumor infiltration range of the i-th patient and the preset tumor infiltration range threshold. The larger this ratio, the relatively larger the tumor infiltration range of the i-th patient, and the greater the malignancy of the tumor. The preset tumor infiltration range threshold is a threshold set according to the tumor type. For example, when the tumor type is breast cancer, the preset tumor infiltration range threshold can be set to 5 mm.

[0048] is to determine the tumor malignancy score of the i-th patient in the current time period based on four aspects: the location status, cell differentiation status, mitosis status, and infiltration range status of the tumor of the i-th patient.

[0049] In this way, the tumor malignancy score can be determined based on the tumor location recognition result, cell differentiation degree, nucleus mitosis frequency, and tumor infiltration range. During the calculation process, the malignancy of the tumor can be evaluated respectively according to the four aspects of the location status, cell differentiation status, mitosis status, and infiltration range status of the tumor, improving the comprehensiveness and accuracy of the tumor malignancy score.

[0050] According to an embodiment of the present invention, the risk prediction scoring module is used to determine the malignant tumor metastasis risk prediction score according to the neutrophil polarization state information, the tumor malignancy score, and the patient information.

[0051] For example, according to the neutrophil polarization state information, the tumor malignancy score, and the patient information, the metastasis risk of the malignant tumor is evaluated to determine the malignant tumor metastasis risk prediction score.

[0052] According to an embodiment of the present invention, determining the malignant tumor metastasis risk prediction score according to the neutrophil polarization state information, the tumor malignancy score, and the patient information includes:

[0053] Determine the adaptive immune cell count, immunoglobulin level, and innate immune cell count according to the immune system parameters;

[0054] Obtain the historical tumor information of multiple historical patients;

[0055] Determine the historical tumor malignancy score according to the historical tumor information;

[0056] Determine the similar historical patients according to the patient age, the tumor malignancy score, and the historical tumor malignancy score;

[0057] Obtain the historical tumor malignancy score, historical immune system parameters, and historical neutrophil polarization state information of the similar historical patients;

[0058] Determine the historical adaptive immune cell count, historical immunoglobulin level, and historical innate immune cell count according to the historical immune system parameters;

[0059] Determine the historical N1 neutrophil ratio and historical N2 neutrophil ratio according to the historical neutrophil polarization state information;

[0060] Determine a first relationship function according to the historical N1 neutrophil ratio, the historical N2 neutrophil ratio, the historical tumor malignancy score, the historical adaptive immune cell count, the historical immunoglobulin level, and the historical innate immune cell count;

[0061] Determine a malignant tumor metastasis risk prediction score according to the first relationship function, the tumor malignancy score, the adaptive immune cell count, the immunoglobulin level, and the innate immune cell count.

[0062] For example, obtain the adaptive immune cell count, immunoglobulin level, and innate immune cell count of a patient; obtain the tumor location, cell differentiation degree, nuclear division frequency, and tumor infiltration range of multiple historical patients; determine the historical tumor malignancy score of the historical patients according to the tumor location, cell differentiation degree, nuclear division frequency, and tumor infiltration range of the historical patients. The calculation method of the historical tumor malignancy score is similar to formula (1) and will not be elaborated here; determine the patients with the same age and tumor malignancy score as the current patient among the historical patients as similar historical patients; obtain the historical tumor malignancy score, historical immune system parameters, and historical neutrophil polarization state information of the similar historical patients in the historical database; determine the historical adaptive immune cell count, historical immunoglobulin level, and historical innate immune cell count of the similar historical patients according to the historical immune system parameters; determine the historical N1 neutrophil ratio and historical N2 neutrophil ratio of the similar historical patients according to the historical neutrophil polarization state information; the historical tumor malignancy score is related to the historical N1 neutrophil ratio, historical N2 neutrophil ratio, historical tumor malignancy score, historical adaptive immune cell count, historical immunoglobulin level, and historical innate immune cell count to a certain extent. For example, when the patient's immunity is stronger, the patient's treatment effect is relatively better, and the tumor malignancy score of the patient in the next cycle is also lower. Based on the correlation of the above data, determine the first relationship function; evaluate the metastasis risk of the malignant tumor according to the first relationship function, the tumor malignancy score, the adaptive immune cell count, the immunoglobulin level, and the innate immune cell count, and determine the malignant tumor metastasis risk prediction score.

[0063] According to an embodiment of the present invention, determining a first relationship function based on the historical proportion of N1 neutrophils, the historical proportion of N2 neutrophils, the historical tumor malignancy score, the historical adaptive immune cell count, the historical immunoglobulin level, and the historical innate immune cell count includes: determining a first undetermined coefficient equation of the first relationship function according to formula (2).

[0064]

[0065] where Mdot h，k，j is the historical tumor malignancy score of the k-th similar historical patient in the j-th historical period, Mdot h，k，j+1 is the historical tumor malignancy score of the k-th similar historical patient in the (j + 1)-th historical period, Aicc h，k，j is the historical adaptive immune cell count of the k-th similar historical patient in the j-th historical period, Hil h,k,j is the historical immunoglobulin level of the k-th similar historical patient in the j-th historical period, Wbcc h,k,j is the historical innate immune cell count of the k-th similar historical patient in the j-th historical period, N1 h,k,j is the historical proportion of N1 neutrophils of the k-th similar historical patient in the j-th historical period, N2 h,k,j is the historical proportion of N2 neutrophils of the k-th similar historical patient in the j-th historical period, and β1, β2, β3, β4, β5, β6, β7, β8, β9, β 10 β 11 and β 12 are the first undetermined coefficients of the first undetermined coefficient equation.

[0066] Solving the first undetermined coefficients based on the historical tumor malignancy score, the historical adaptive immune cell count, the historical immunoglobulin level, and the historical innate immune cell count to obtain the solution values of the first undetermined coefficients.

[0067] Determining the first relationship function based on the solution values of the first undetermined coefficients and the first undetermined coefficient equation.

[0068] According to an embodiment of the present invention, It indicates a positive correlation between the historical tumor malignancy score of the k-th similar historical patient in the (j + 1)-th historical cycle and the historical adaptive immune cell count of the k-th similar historical patient in the j-th historical cycle. For example, adaptive immune cells recognize tumor cell surface antigens (presented by MHC), release perforin and granzyme to induce apoptosis, and reduce the malignancy of the tumor. The more the historical adaptive immune cell count of the patient in the j-th historical cycle, the relatively smaller the historical tumor malignancy score of the patient in the (j + 1)-th historical cycle. It indicates a negative correlation between the historical tumor malignancy score of the k-th similar historical patient in the (j + 1)-th historical cycle and the historical immunoglobulin level of the k-th similar historical patient in the j-th historical cycle. For example, it recognizes tumor antigens through antibody-dependent cell-mediated cytotoxicity (ADCC), marks malignant cells for clearance by NK cells and macrophages, and reduces the malignancy of the tumor. The higher the historical immunoglobulin level of the patient in the j-th historical cycle, the relatively smaller the historical tumor malignancy score of the patient in the (j + 1)-th historical cycle. It indicates a negative correlation between the historical tumor malignancy score of the k-th similar historical patient in the (j + 1)-th historical cycle and the historical innate immune cell count of the k-th similar historical patient in the j-th historical cycle. For example, innate immune cells recognize abnormal phenotypes of tumor cells through surface receptors (such as NKG2D, NKp30), release perforin and granzyme, and reduce the malignancy of the tumor. The more the historical innate immune cell count of the patient in the j-th historical cycle, the relatively smaller the historical tumor malignancy score of the patient in the (j + 1)-th historical cycle. It indicates a negative correlation between the historical tumor malignancy score of the k-th similar historical patient in the (j + 1)-th historical cycle and the proportion of N1 neutrophils of the k-th similar historical patient in the j-th historical cycle. For example, N1 neutrophils show enhanced antibacterial ability, increased ROS production, and release cytotoxic granules, playing an anti-tumor role. The higher the proportion of N1 neutrophils of the patient in the j-th historical cycle, the relatively smaller the historical tumor malignancy score of the patient in the (j + 1)-th historical cycle. (β9Mdot h，k，j +β 10 ) It indicates a positive correlation between the historical tumor malignancy score of the k-th similar historical patient in the (j + 1)-th historical cycle and the historical tumor malignancy score of the k-th similar historical patient in the j-th historical cycle. For example, when the historical tumor malignancy score of the k-th similar historical patient in the j-th historical cycle is relatively large, the malignancy of the patient's tumor is relatively large, the treatment effect of the patient is relatively poor, and the historical tumor malignancy score of the patient in the (j + 1)-th historical cycle is relatively large. (β 11 N2 h，k，j +β 12)It indicates that there is a positive correlation between the historical tumor malignancy score of the k-th similar historical patient in the (j + 1)-th historical cycle and the historical N2 neutrophil ratio of the k-th similar historical patient in the j-th historical cycle. For example, N2 neutrophils promote tissue repair and angiogenesis, but may inhibit the immune response and even be exploited by tumors to support their growth. The higher the historical N2 neutrophil ratio of the patient in the j-th historical cycle, the relatively greater the historical tumor malignancy score of the patient in the (j + 1)-th historical cycle. Based on the above relationship, the first undetermined coefficient equation of the first relationship function can be obtained.

[0069] According to an embodiment of the present invention, fitting can be performed based on multiple parameters involved in the above first undetermined coefficients, that is, fitting is performed based on the historical tumor malignancy score, historical adaptive immune cell count, historical immunoglobulin level, and historical innate immune cell count, and the above multiple first undetermined coefficients are solved. There are 12 first undetermined coefficients, namely, β1, β2, β3, β4, β5, β6, β7, β8, β9, β 10 , β 11 and β 12 . The above 12 first undetermined coefficients are solved according to the historical tumor malignancy score, historical adaptive immune cell count, historical immunoglobulin level, and historical innate immune cell count of at least 12 similar historical patients, and the solution values of the above 12 first undetermined coefficients are obtained. Then, the solution values of the above 12 first undetermined coefficients are substituted into the first undetermined coefficient equation to determine the first relationship function.

[0070] In this way, based on the historical N1 neutrophil ratio, historical N2 neutrophil ratio, historical tumor malignancy score, historical adaptive immune cell count, historical immunoglobulin level, and historical innate immune cell count, the first relationship function can be determined, which accurately describes the relationship between the patient's immune system status, tumor malignancy, and the tumor malignancy in the next cycle, improving the accuracy and objectivity of the first relationship function.

[0071] According to an embodiment of the present invention, determining the malignant tumor metastasis risk prediction score according to the neutrophil polarization state information, the tumor malignancy score, and the patient information includes:

[0072] Determining the predicted tumor malignancy score in the next time cycle according to the tumor malignancy score in the current time cycle, the first relationship function, the adaptive immune cell count, the immunoglobulin level, the innate immune cell count, and the neutrophil polarization state information;

[0073] Determining the first difference according to the tumor malignancy score in the current time cycle and the predicted tumor malignancy score;

[0074] Determine the predicted risk score of malignant tumor metastasis for the patient in the current time period based on the first difference and the tumor malignancy score of the current time period.

[0075] For example, substitute the tumor malignancy score of the patient in the current time period, the count of adaptive immune cells, the immunoglobulin level, and the count of innate immune cells of the patient into the first relationship function to determine the predicted tumor malignancy score of the patient in the next time period; if the predicted tumor malignancy score is less than or equal to the tumor malignancy score, it indicates that the patient's condition will improve in the next time period and the risk of malignant tumor metastasis is low, and the first difference is determined to be 0; if the predicted tumor malignancy score is greater than the tumor malignancy score, it indicates that the patient's condition will worsen in the next time period and the risk of malignant tumor metastasis is high. Determine the first difference according to the predicted tumor malignancy score minus the tumor malignancy score of the current time period; determine the predicted risk score of malignant tumor metastasis for the patient in the current time period based on the ratio of the first difference to the tumor malignancy score of the current time period. The greater the predicted risk score of malignant tumor metastasis, the greater the risk of malignant tumor metastasis.

[0076] According to an embodiment of the present invention, determine the predicted tumor malignancy score of the next time period based on the tumor malignancy score of the current time period, the first relationship function, the count of adaptive immune cells, the immunoglobulin level, the count of innate immune cells, and the neutrophil polarization state information, including: determining the predicted tumor malignancy score PMdot of the i-th patient in the next time period according to formula (3) i ,

[0077]

[0078] where Modt i is the tumor malignancy score of the i-th patient in the current time period, Aicc i is the count of adaptive immune cells of the i-th patient in the current time period, Hil i is the historical immunoglobulin level of the i-th patient in the current time period, Wbcc i is the historical count of innate immune cells of the i-th patient in the current time period, N1 i is the proportion of N1-type neutrophils of the i-th patient in the current time period, N2 i is the proportion of N2-type neutrophils of the i-th patient in the current time period, β 1，F is the solution value of β1, β 2，F is the solution value of β2, β 3，F is the solution value of β3, β4,F is the solved value of β4, β 5,F is the solved value of β5, β 6,F is the solved value of β6, β 7，F is the solved value of β7, β 8，F is the solved value of β8, β 9,F is the solved value of β9, β 10，F is β 10 's solved value, β 11，F is β 11 's solved value, β 12，F is β 12 's solved value.

[0079] According to an embodiment of the present invention, the tumor malignancy score, the count of adaptive immune cells, the immunoglobulin level, the count of innate immune cells, and the neutrophil polarization state information of the current time period, as well as the solved value of the first undetermined coefficient, are substituted into the first relationship function to obtain formula (4), thereby obtaining the predicted tumor malignancy score of the i-th patient in the next time period.

[0080] In this way, based on the tumor malignancy score, the first relationship function, the count of adaptive immune cells, the immunoglobulin level, the count of innate immune cells, and the neutrophil polarization state information of the current time period, the predicted tumor malignancy score of the next time period can be determined, which can improve the accuracy of the predicted tumor malignancy score and provide a data basis for calculating the predicted score of the risk of malignant tumor metastasis.

[0081] According to an embodiment of the present invention, in the risk prediction report module, it is used to generate a risk prediction report based on the predicted score of the risk of malignant tumor metastasis.

[0082] For example, when the predicted score of the risk of malignant tumor metastasis is 0, there is no risk of malignant tumor metastasis; when the predicted score of the risk of malignant tumor metastasis is greater than 0.1, there may be a risk of malignant tumor metastasis.

[0083] The malignant tumor metastasis risk prediction system based on the neutrophil polarization state according to an embodiment of the present invention can accurately detect the neutrophil polarization state information in the tumor microenvironment, and accurately analyze the malignancy degree of the patient's tumor. Further, according to the neutrophil polarization state information, the malignancy degree of the tumor, and the patient information, the malignant tumor metastasis risk is predicted, improving the accuracy of the malignant tumor metastasis risk prediction. When determining the malignancy degree score of the tumor, the malignancy degree score of the tumor can be determined according to the tumor location recognition result, the degree of cell differentiation, the frequency of nuclear division, and the tumor infiltration range. During the calculation process, the malignancy degree of the tumor can be evaluated respectively from four aspects: the location status of the tumor, the cell differentiation status, the nuclear division status, and the infiltration range status, improving the comprehensiveness and accuracy of the malignancy degree score of the tumor. When determining the first relationship function, the first relationship function can be determined according to the historical proportion of N1 neutrophils, the historical proportion of N2 neutrophils, the historical malignancy degree score of the tumor, the historical count of adaptive immune cells, the historical immunoglobulin level, and the historical count of innate immune cells, accurately describing the relationship between the patient's immune system status, the malignancy degree of the tumor, and the malignancy degree of the tumor in the next cycle, improving the accuracy and objectivity of the first relationship function. When determining the predicted malignancy degree score of the tumor, the predicted malignancy degree score of the next time cycle can be determined according to the malignancy degree score of the tumor in the current time cycle, the first relationship function, the count of adaptive immune cells, the immunoglobulin level, the count of innate immune cells, and the neutrophil polarization state information, improving the accuracy of the predicted malignancy degree score of the tumor and providing a data basis for calculating the malignant tumor metastasis risk prediction score.

[0084] Figure 2 Exemplarily shown is a schematic flowchart of a method for predicting the risk of malignant tumor metastasis based on the neutrophil polarization state according to an embodiment of the present invention. The method includes:

[0085] Step S101, detecting the neutrophil polarization state information in the tumor microenvironment, where the neutrophil polarization state information includes: the proportion of N1 neutrophils and the proportion of N2 neutrophils;

[0086] Step S102, obtaining patient information, where the patient information includes: patient age and immune system parameters;

[0087] Step S103, obtaining tumor information, where the tumor information includes: tumor location, degree of cell differentiation, frequency of nuclear division, and tumor infiltration range;

[0088] Step S104, determining the malignancy degree score of the tumor according to the tumor information;

[0089] Step S105: Determine a predicted score for the risk of malignant tumor metastasis based on the neutrophil polarization state information, the malignant degree score of the tumor, and the patient information;

[0090] Step S106: Generate a risk prediction report based on the predicted score for the risk of malignant tumor metastasis.

[0091] The present invention can be a method, an apparatus, a system, and / or a computer program product. The computer program product may include a computer-readable storage medium having thereon computer-readable program instructions for performing various aspects of the present invention.

[0092] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functions and structural principles of the present invention have been demonstrated and explained in the embodiments, and the embodiments of the present invention may have any variations or modifications without departing from the principles.

Claims

1. A malignant tumor metastasis risk prediction system based on neutrophil polarization state, characterized in that: include: A neutrophil detection module, used to detect neutrophil polarization state information in the tumor microenvironment, wherein the neutrophil polarization state information includes: a proportion of N1 neutrophils and a proportion of N2 neutrophils; A patient information acquisition module, used to acquire patient information, wherein the patient information includes: patient age and immune system parameters; A tumor information acquisition module, used to acquire tumor information, wherein the tumor information includes: tumor location, cell differentiation degree, cell nuclear division frequency and tumor infiltration range; A malignancy scoring module, used to determine a tumor malignancy score according to the tumor information; A risk prediction scoring module, used to determine a risk prediction score for malignant tumor metastasis based on the neutrophil polarization state information, the tumor malignancy score and the patient information; The risk prediction report module is used to generate a risk prediction report based on the malignant tumor metastasis risk prediction score.

2. The malignant tumor metastasis risk prediction system based on neutrophil polarization state according to claim 1, characterized in that: Determine the tumor malignancy score based on the tumor information, including: Determining a tumor position identification result according to the tumor position; The tumor malignancy score is determined based on the tumor location identification result, the cell differentiation degree, the cell nuclear division frequency and the tumor infiltration range.

3. The malignant tumor metastasis risk prediction system based on neutrophil polarization state according to claim 2, characterized in that: Determining a tumor malignancy score according to the tumor location identification result, the cell differentiation degree, the cell nuclear division frequency and the tumor infiltration range includes: According to the formula Determine the tumor malignancy score Mdot of the i-th patient in the current time period i , where α1, α2, α3, α4 and are preset weights, Tp i is the tumor location identification result of the i-th patient, Cd i is the cell differentiation degree of tumor cells of the i-th patient, Cdd T Ndf is the preset cell differentiation threshold. i is the nuclear division frequency of tumor cells of the i-th patient, Ndf T To preset the cell nuclear division frequency threshold, Tir i is the tumor infiltration range of the i-th patient, Tir T The preset tumor infiltration range threshold.

4. The malignant tumor metastasis risk prediction system based on neutrophil polarization state according to claim 1, characterized in that: Determining a malignant tumor metastasis risk prediction score according to the neutrophil polarization state information, the tumor malignancy score and the patient information, including: determining adaptive immune cell counts, immunoglobulin levels, and innate immune cell counts based on the immune system parameters; Obtain historical tumor information of multiple historical patients; Determining a historical tumor malignancy score according to the historical tumor information; Determining a patient with similar history according to the patient's age, the tumor malignancy score and the historical tumor malignancy score; Obtain historical tumor malignancy scores, historical immune system parameters, and historical neutrophil polarization status information of patients with similar histories; determining, based on the historical immune system parameters, historical adaptive immune cell counts, historical immunoglobulin levels, and historical innate immune cell counts; Determining a historical N1 type neutrophil ratio and a historical N2 type neutrophil ratio according to the historical neutrophil polarization state information; Determining a first relationship function according to the historical N1 neutrophil ratio, the historical N2 neutrophil ratio, the historical tumor malignancy score, the historical adaptive immune cell count, the historical immunoglobulin level, and the historical innate immune cell count; A malignant tumor metastasis risk prediction score is determined based on the first relationship function, the tumor malignancy score, the adaptive immune cell count, the immunoglobulin level and the innate immune cell count.

5. The malignant tumor metastasis risk prediction system based on neutrophil polarization state according to claim 4, characterized in that: Determining a first relationship function according to the historical N1 neutrophil ratio, the historical N2 neutrophil ratio, the historical tumor malignancy score, the historical adaptive immune cell count, the historical immunoglobulin level, and the historical innate immune cell count includes: According to the formula Determine the first undetermined coefficient equation of the first relationship function, where Mdot h，k，j Score the malignancy of the historical tumor of the kth patient with similar history in the jth historical period, Mdot h，k，j+1 Aicc is the historical tumor malignancy score of the kth similar historical patient in the j+1th historical period. h，k，j is the historical adaptive immune cell count of the kth similar historical patient in the jth historical period, Hil h，k，j is the historical immunoglobulin level of the kth patient with similar history in the jth historical period, Wbcc h，k，j N1 is the historical innate immune cell count of the kth similar historical patient in the jth historical cycle. h，k，j is the historical N1 neutrophil ratio of the kth patient with similar history in the jth historical period, N2 h，k，j is the historical N2 neutrophil ratio of the kth patient with similar history in the jth historical period, β1, β2, β3, β4, β5, β6, β7, β8, β9, β 10 , β 11 and β 12 is the first undetermined coefficient of the first undetermined coefficient equation; Solving the first undetermined coefficient according to the historical tumor malignancy score, the historical adaptive immune cell count, the historical immunoglobulin level, and the historical innate immune cell count to obtain a solution value of the first undetermined coefficient; A first relationship function is determined according to the solution value of the first undetermined coefficient and the first undetermined coefficient equation.

6. The malignant tumor metastasis risk prediction system based on neutrophil polarization state according to claim 4, characterized in that: Determining a malignant tumor metastasis risk prediction score according to the neutrophil polarization state information, the tumor malignancy score and the patient information, including: Determining a predicted tumor malignancy score for the next time period according to the tumor malignancy score for the current time period, the first relationship function, the adaptive immune cell count, the immunoglobulin level, the innate immune cell count, and the neutrophil polarization state information; Determining a first difference value according to the tumor malignancy score of the current time period and the predicted tumor malignancy score; A malignant tumor metastasis risk prediction score of the patient in the current time period is determined based on the first difference and the tumor malignancy score in the current time period.

7. The malignant tumor metastasis risk prediction system based on neutrophil polarization state according to claim 5, characterized in that: Determining a predicted tumor malignancy score for the next time period according to the tumor malignancy score for the current time period, the first relationship function, the adaptive immune cell count, the immunoglobulin level, the innate immune cell count, and the neutrophil polarization state information, comprising: According to the formula Determine the predicted tumor malignancy score PMdot of the i-th patient in the next time period i , among which, Mdot i Aicc is the tumor malignancy score of the i-th patient in the current time period, i is the adaptive immune cell count of the ith patient in the current time period, Hil i is the historical immunoglobulin level of the ith patient in the current time period, Wbcc i is the historical innate immune cell count of the ith patient in the current time period, N1 i is the proportion of N1 neutrophils in the i-th patient in the current time period, N2 i is the proportion of N2 neutrophils in the i-th patient in the current time period, β 1，F is the solution value of β1, β 2，F is the solution value of β2, β 3，F is the solution value of β3, β 4，F is the solution value of β4, β 5，F is the solution value of β5, β 6，F is the solution value of β6, β 7，F is the solution value of β7, β 8，F is the solution value of β8, β 9，F is the solution value of β9, β 10，F β 10 The solution value, β 11，F β 11 The solution value, β 12，F β 12 The solution value of .

Images