Immune assessment method for end-stage nephropathy dialysis patient

Abstract

The invention relates to the field of immune assessment, in particular to an end-stage nephropathy dialysis patient immune assessment method, which comprises the following steps: preparing a database for storing assessment scores of various parameters; preparing a convolutional neural network, and collecting immune intensity change data before and after dialysis of a patient population as a training library; immune intensity change data before and after dialysis under experimental conditions are obtained under laboratory conditions, the data under the experimental conditions are input into a convolutional neural network, and the convolutional neural network is used for training according to a preset mixing proportion rule and outputting a dialysis cause compensation function; data such as demographic characteristics, basic diseases, representative immune activation state data, representative immune senescence state data and dialysis frequency of a patient are collected, a total score is calculated based on a database and a dialysis cause compensation function, and the immunocompetence of the patient is evaluated. By adopting the method, the immunocompetence fluctuation caused by imperfect biocompatibility of the dialysis membrane can be compensated in immune assessment.

Description

Technical Field

[0001] The present invention relates to the field of immune assessment, and particularly to a method for immune assessment of end-stage renal disease dialysis patients. Background Art

[0002] Immunity is a physiological function of the human body. By relying on this function, the human body can identify "self" and "non-self" components, thereby destroying and rejecting antigenic substances entering the human body, or damaged cells and tumor cells produced by the human body itself, etc., to maintain the health of the human body. It is a state of resistance or prevention of infection by microorganisms or parasites or other unwanted biological invasions. Immunity involves specific and non-specific components. Non-specific components do not require prior exposure, can respond immediately, and can effectively prevent the invasion of various pathogens.

[0003] Dialysis is one of the renal replacement therapies for patients with acute and chronic renal failure. It involves draining the body fluid to the outside of the body, passing it through a dialyzer composed of countless hollow fibers. Inside and outside each hollow fiber, the body fluid and an electrolyte solution with a concentration similar to that of the body carry out mass exchange through the principles of diffusion, ultrafiltration, adsorption, and convection to remove metabolic wastes in the body, maintain electrolyte and acid-base balance; at the same time, remove excess water in the body, and the whole process of returning the purified body fluid is called dialysis.

[0004] When a nephropathy patient is in stage 5 of chronic kidney disease or has been on maintenance dialysis for more than 3 months, it indicates the end stage of the patient's kidney disease, and the renal function has basically been lost, and the probability of recovery is relatively small. Along with this come complications such as chronic inflammation, accumulation of uremic toxins, and malnutrition, which require long-term nursing treatment. In addition, patients in this state will be in a state of imbalance between immune senescence and immune activation, that is, a state where immune senescence (such as a decline in T cell function) and immune overactivation (such as monocyte activation) coexist.

[0005] In the prior art, for example, patent publication number CN118553310A discloses an immune repertoire for evaluating organ transplantation immune function and immune senescence assessment indicators, and evaluates patients through comprehensive immune senescence assessment indicators; CN117012391A discloses an artificial intelligence-based pre-renal transplantation risk assessment system, which judges the immune ability of patients by collecting patients' basic information, renal function information, and immune system status information. However, in addition to the patient's own reasons affecting immunity, the dialysis process will also change the patient's immune ability. The dialysis membrane is difficult to achieve perfect biocompatibility, which may activate the complement system and monocytes, trigger an inflammatory response, thereby exacerbating the imbalance of the patient's immune activation, resulting in changes in the patient's immunity over time between two dialysis sessions. Therefore, to accurately evaluate the patient's immune ability, it is necessary to compensate for the immune impact brought by dialysis itself. Summary of the Invention

[0006] To solve the above problems, the present invention provides an immune assessment method for end-stage renal disease dialysis patients, which is used to compensate for the immune capacity fluctuations caused by the imperfect biocompatibility of the dialysis membrane during immune assessment.

[0007] To achieve the above object, the technical solution of the present invention is as follows: An immune assessment method for end-stage renal disease dialysis patients, comprising:

[0008] Prepare a database, which is used to store scores reflecting the changes in immune strength for various demographic characteristics, various underlying diseases, various representative immune activation state data, and various representative immune senescence state data.

[0009] Prepare a convolutional neural network, and collect the data on the changes in immune strength before and after dialysis of the patient population as a training library.

[0010] Conduct an immune side effect experiment of dialysis under laboratory conditions to obtain the data on the changes in immune strength before and after dialysis under experimental conditions. Input the data on the changes in immune strength before and after dialysis under experimental conditions into the convolutional neural network. The convolutional neural network is used to mix the data on the changes in immune strength before and after dialysis under experimental conditions into the training library according to the preset mixing ratio rule, and then train based on the training library and output a dialysis cause compensation function.

[0011] The dialysis cause compensation function is used to output a score reflecting the changes in immune strength caused by dialysis according to the dialysis frequency, dialysis membrane parameters, dialysis parameters, dialysis age, and the time length from the end time point of the most recent dialysis to the assessment time point.

[0012] Collect the demographic characteristics, underlying diseases, representative immune activation state data, representative immune senescence state data, dialysis frequency, dialysis age, dialysis membrane parameters, dialysis parameters, and the end time point of the most recent dialysis of the patient; after calculating the time length from the end time point of the most recent dialysis to the assessment time point, calculate the total score based on the database and the dialysis cause compensation function respectively, and evaluate the patient's immune capacity according to the total score.

[0013] Adopting the above scheme has the following beneficial effects:

[0014] 1. In this scheme, the immune capacity of the patient is evaluated, which is convenient for formulating subsequent nursing and treatment guidelines. The evaluation is divided into multiple aspects, that is, the evaluation is based on the patient's own immune capacity and the change in immune capacity caused by dialysis causes. Among them, the patient's own immune capacity is based on three aspects, namely the demographic characteristics and underlying diseases representing the patient's physical constitution, the data representing the immune activation state, and the data representing the immune senescence state. The immune capacity of the patient is evaluated based on these three aspects, so as to evaluate the current immune capacity level of the patient.

[0015] 2. In this solution, the immune capacity level evaluated based on demographic characteristics, underlying diseases, data representing the immune activation state, and data representing the immune senescence state includes the fluctuations in immune capacity caused by dialysis, and these fluctuations will gradually disappear with metabolism. A convolutional neural network can learn based on a training library, that is, by using the data on the changes in immune strength before and after dialysis in a large number of patient populations, it can reflect the fluctuations in immune capacity caused by dialysis. Healthy people do not need dialysis, and dialysis can cause complications such as hypotension, dizziness, and dehydration in healthy people. Therefore, the data collected hardly contains data on the impact of dialysis on immune capacity in a healthy state. Based on the fluctuations in immune capacity in patients with existing diseases, there may be pathological amplification or reduction of the impact of dialysis. Therefore, under experimental conditions, the data on the changes in immune strength of healthy individuals are collected as a neutralization of the pathological impact, so as to more accurately obtain the dialysis cause compensation function.

[0016] 3. In this solution, the dialysis cause compensation function is used to eliminate the changes in immune capacity caused by dialysis, so as to more accurately evaluate the immune capacity level of patients.

[0017] Furthermore, the demographic characteristics and underlying diseases include age, gender, height, weight, history of diabetes, and history of cardiovascular and cerebrovascular diseases.

[0018] Beneficial effects: The immune capacities of different ages, genders, heights, and weights are different. The immune capacity of patients with a history of diabetes and a history of cardiovascular and cerebrovascular diseases declines faster. Therefore, the demographic characteristics and underlying diseases are used to evaluate the immune capacity of patients.

[0019] Furthermore, the data on the immune activation state includes the concentration of hsCRP, the monocyte count, the concentration of sIL2R, and the concentration of IL-6.

[0020] Beneficial effects: The concentration of hsCRP, the monocyte count, the concentration of sIL2R, and the concentration of IL-6 are all verified sensitive markers and data reflecting the inflammatory state and the degree of immune cell activation. Therefore, the data on the immune activation state can be objectively evaluated.

[0021] Furthermore, the data on the immune senescence state includes the lymphocyte count, CD8 + CD28 - T cell ratio, CD4 + CD73 + T cell ratio.

[0022] Beneficial effects: CD28 is a T cell co-stimulatory molecule and is crucial for T cell activation and function. CD73 is an ectonucleotidase that can convert AMP into adenosine, and adenosine is a potent immune senescence molecule. Through the CD8 + CD28 - T cell ratio, CD4+ CD73 + The proportion of T cells can objectively evaluate the immune senescence status of patients.

[0023] Furthermore, in the database, the score proportion is such that the sum of age, gender, height, and weight is 0 - 2, the history of diabetes and cardiovascular and cerebrovascular diseases are both 0 - 1, the hsCRP concentration, monocyte count, lymphocyte count, sIL2R concentration, IL-6 concentration, CD8 + CD28 - The proportion of T cells and CD4 + CD73 + The proportion of T cells are both 0 - 2.

[0024] Beneficial effect: Different evaluation parameters have different effects on immune ability, so there are differences in the evaluation scores of different parameters. Through an appropriate scoring proportion, the scores of different parameters can be reasonably integrated, so as to objectively evaluate the immune ability of patients.

[0025] Furthermore, when collecting data on the change in immune strength before and after dialysis in the patient population, patients with a dialysis interval of 3 - 4 days are selected, and data on the change in immune strength is collected at several time points after dialysis.

[0026] Beneficial effect: If patients undergo dialysis frequently, the immune impact of the previous dialysis may not have ended before the next dialysis is carried out, making it difficult to reflect the actual impact of a single dialysis. Therefore, patients with a dialysis interval of 3 - 4 days are selected to reduce the mutual influence between multiple dialysis sessions. In addition, collecting data on the change in immune strength at several time points after dialysis can enable the trained convolutional neural network to effectively reflect the impact of the time length from the most recent dialysis end time point to the evaluation time point on immune strength.

[0027] Furthermore, the mixing proportion rule is to divide the collected patient population into 4 - 9 gradients according to the severity of the disease symptoms, and the data on the change in immune strength before and after dialysis under experimental conditions is used as the data reference for 1 gradient and mixed into the training library.

[0028] Beneficial effect: In the collected patient data for training, there is almost an interaction between pathology and dialysis effects. And under experimental conditions, due to the data being in an overly ideal state, it is also difficult to reflect the actual impact generated. Therefore, the data on the change in immune strength before and after dialysis under experimental conditions is mixed in an appropriate proportion, and the training results after neutralization are used to evenly reflect the change in immune ability caused by dialysis causes.

[0029] Furthermore, when the total score of the immune activation state data is greater than 4, the patient is evaluated as having immune overactivation or having an active infection.

[0030] Beneficial effects: The total score of the immune activation status data can also reflect the immune status of the patient, so as to understand whether the patient is in an immune activation state or has an infection.

[0031] Furthermore, when the total score of the immune senescence status data is greater than 4, the patient is evaluated as being in an immune senescence and high-risk tumor infection state.

[0032] Beneficial effects: The score of the immune senescence status can reflect whether the patient is in a high-risk immune senescence infection state.

[0033] Furthermore, when the total evaluation score is greater than 6, the patient is evaluated as a high-risk individual for cardiovascular complications and high infection triggers within 1 year.

[0034] Beneficial effects: When the total evaluation score is greater than 6, it indicates that the overall immune ability of the patient is weak. According to experience, it can be judged that the probability of the patient having high cardiovascular complications and infections within 1 year is greater than 60%, and early intervention and enhanced treatment are required.

[0035] Additional aspects and advantages of the present invention will be given in part in the following description, will become apparent in part from the following description, or will be understood through the practice of the present invention. Brief Description of the Drawings

[0036] Figure 1 It is a schematic diagram of an embodiment of the immune evaluation method for end-stage renal disease dialysis patients of the present invention. Detailed Embodiments

[0037] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0038] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. In addition, the terms "first", "second", "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0039] In the description of the present invention, it should be noted that unless otherwise clearly specified and defined, the terms "installation", "connection", and "coupling" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0040] The following is a further detailed description through specific embodiments:

[0041] As shown in the attached Figure 1 figure: An immune assessment method for end-stage renal disease dialysis patients, including:

[0042] Prepare a database, which is used to store scores reflecting the changes in immune strength of various demographic characteristics, various underlying diseases, various representative immune activation state data, and various representative immune senescence state data.

[0043] The demographic characteristics and underlying diseases at least include age, gender, height, weight, diabetes history, and cardiovascular and cerebrovascular disease history.

[0044] The immune activation state data at least includes hsCRP concentration, monocyte count, sIL2R concentration, and IL-6 concentration.

[0045] The immune senescence state data includes lymphocyte count, CD8 + CD28 - T cell ratio, CD4 + CD73 + T cell ratio.

[0046] Prepare a convolutional neural network, collect data on the changes in immune strength before and after dialysis of the patient population as a training library, select patients with a dialysis interval of 3 - 4 days, and collect data on the changes in immune strength at several time points after dialysis. The total number of the patient population collected is greater than 800, and the number of patient populations for the training data of the characteristic parameters of dialysis frequency, dialysis membrane parameters, dialysis parameters, dialysis age, and the time length from the most recent dialysis end time point to the evaluation time point is greater than 100;

[0047] An immune side effect experiment is conducted under laboratory conditions. The experimental target individuals can be experimental animal individuals. Data on the changes in immune strength before and after dialysis under experimental conditions are obtained. The data on the changes in immune strength are all based on the immune assessment carried out only relying on the database. The data on the changes in immune strength before and after dialysis under experimental conditions are input into a convolutional neural network. The convolutional neural network is used to mix according to a preset mixing ratio rule. The mixing ratio rule is to divide the collected patient population into 4 - 9 gradients according to the severity of the disease symptoms, and the data on the changes in immune strength before and after dialysis under experimental conditions are separately used as the data reference of 1 gradient and mixed into the training library. Then, training is carried out based on the training library to generate at least a mapping that reflects the relationship between dialysis frequency, dialysis membrane parameters, dialysis parameters, dialysis age, the time length from the most recent dialysis end time point to the evaluation time point, and immune strength, and then a dialysis - cause compensation function is output.

[0048] The dialysis - cause compensation function is used to output a score reflecting the change in immune strength caused by dialysis according to dialysis frequency, dialysis membrane parameters, dialysis parameters, dialysis age, and the time length from the most recent dialysis end time point to the evaluation time point.

[0049] Collect the demographic characteristics, underlying diseases, data representing the immune activation state, data representing the immune senescence state, dialysis frequency, dialysis age, dialysis membrane parameters, dialysis parameters, and the most recent dialysis end time point of the patient; after calculating the time length from the most recent dialysis end time point to the evaluation time point, calculate the total score respectively based on the database and the dialysis - cause compensation function, and evaluate the patient's immune ability according to the total score.

[0050] The evaluation is for nephropathy patients in stage 5 of chronic kidney disease or who have been on maintenance dialysis for more than 3 months, so as to facilitate the formulation of subsequent nursing treatment guidelines. The evaluation is divided into multiple aspects, that is, based on the patient's own immune ability and the change in immune ability caused by dialysis. Among them, the patient's own immune ability is based on three aspects, namely the demographic characteristics and underlying diseases representing the patient's physical constitution, the data representing the immune activation state, and the data representing the immune senescence state. The patient's immune ability is evaluated based on these three aspects, so as to evaluate the current patient's immune ability level.

[0051] There are differences in immune ability among people of different ages, genders, heights, and weights. Patients with a history of diabetes and cardiovascular and cerebrovascular diseases have a faster decline in immune ability. Therefore, the demographic characteristics and underlying diseases are used to evaluate the patient's immune ability.

[0052] The concentrations of hsCRP, monocyte count, sIL2R concentration, and IL - 6 concentration are all verified sensitive markers and data reflecting the inflammatory state and the degree of immune cell activation. Therefore, they can objectively evaluate the data on the immune activation state.

[0053] CD28 is a T cell co-stimulatory molecule that is crucial for T cell activation and function. CD73 is an ectonucleotidase that can convert AMP to adenosine, and adenosine is a potent immune senescence molecule. Through CD8 + CD28 - T cell ratio, CD4 + CD73 + T cell ratio can objectively evaluate the immune senescence status of patients.

[0054] The immune capacity level evaluated based on demographic characteristics, underlying diseases, data representing immune activation status, and data representing immune senescence status includes the fluctuations in immune capacity caused by dialysis, and this part of the fluctuations will gradually disappear with metabolism. The convolutional neural network can learn based on the training library, that is, using the data of the changes in immune strength before and after dialysis in a large number of patient populations, it can reflect the fluctuations in immune capacity caused by dialysis. Healthy people do not need dialysis, and dialysis will cause complications such as hypotension, dizziness, and dehydration in healthy people. Therefore, there is almost no data on the impact of dialysis on immune capacity under healthy conditions in the collected data. Based on the fluctuations in immune capacity in patients with existing diseases, there may be pathological amplification or reduction of the impact of dialysis. Therefore, under experimental conditions, the data of the changes in immune strength of healthy individuals are collected, a gradient from health to critical illness is constructed, and the pathological effects at different levels are considered as a neutralization of the pathological effects, so as to more accurately compensate the dialysis causation function. By eliminating the changes in immune capacity caused by dialysis through the dialysis causation compensation function, the immune capacity level of patients can be more accurately evaluated.

[0055] If patients undergo dialysis frequently, it is possible that the immune impact of the previous dialysis has not ended before the next dialysis is continued, making it difficult to reflect the actual impact of a single dialysis. Therefore, patients with a dialysis interval of 3 - 4 days are selected to reduce the mutual influence between multiple dialysis sessions. In addition, collecting data on the changes in immune strength at several time points after dialysis can enable the trained convolutional neural network to effectively reflect the impact of the time length from the end time point of the most recent dialysis to the evaluation time point on immune strength.

[0056] In the database, the score ratio is such that the sum of age, gender, height, and weight is 0 - 2, the history of diabetes and cardiovascular and cerebrovascular diseases are both 0 - 1, and the concentrations of hsCRP, monocyte count, lymphocyte count, sIL2R concentration, IL-6 concentration, CD8 + CD28 - T cell ratio, and CD4 + CD73 + T cell ratio are all 0 - 2.

[0057] The effects of different evaluation parameters on immune capacity are different, so there are differences in the evaluation scores of different parameters. Through an appropriate scoring score ratio, the scores of different parameters can be reasonably integrated, so as to objectively evaluate the immune capacity of patients.

[0058] When the sum of the scores of the immune activation state data is greater than 4, the patient is evaluated as having over-activated immunity or current infection.

[0059] The sum of the scores of the immune activation state data can also reflect the immune state of the patient, so as to understand whether the patient is in an immune activation state or has an infection.

[0060] When the sum of the scores of the immune senescence state data is greater than 4, the patient is evaluated as having an immune senescence and high-risk tumor infection state.

[0061] The score of the immune senescence state can feedback whether the patient is in a high-risk infection state of immune senescence.

[0062] When the total evaluation score is greater than 6, the patient is evaluated as a high-risk individual for cardiovascular complications and infection trigger within 1 year.

[0063] When the total evaluation score is greater than 6, it indicates that the overall immune capacity of the patient is weak. According to experience, it can be judged that the probability of the patient having high cardiovascular complications and infection within 1 year is greater than 60%, and early intervention and strengthened treatment are required.

[0064] Obviously, the above embodiments are only examples clearly described and not limitations on the implementation manners. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation manners here. And the obvious changes or modifications derived therefrom are still within the protection scope of the present invention.

Claims

1. An immune assessment method for end-stage renal disease dialysis patients, characterized in that, Including preparing a database, which is used to store scores reflecting the change in immune strength of various demographic characteristics, various underlying diseases, various representative immune activation state data, and various representative immune senescence state data; Preparing a convolutional neural network, and collecting the data of the change in immune strength before and after dialysis of the patient population as a training library; Conducting an immune side effect experiment of dialysis under laboratory conditions to obtain the data of the change in immune strength before and after dialysis under experimental conditions, and inputting the data of the change in immune strength before and after dialysis under experimental conditions into the convolutional neural network. The convolutional neural network is used to mix the data of the change in immune strength before and after dialysis under experimental conditions into the training library according to a preset mixing ratio rule, and then training based on the training library and outputting a dialysis cause compensation function; The dialysis cause compensation function is used to output a score reflecting the change in immune strength caused by dialysis according to the dialysis frequency, dialysis membrane parameters, dialysis parameters, dialysis age, and the time length from the most recent dialysis end time point to the evaluation time point; Collecting the demographic characteristics, underlying diseases, representative immune activation state data, representative immune senescence state data, dialysis frequency, dialysis age, dialysis membrane parameters, dialysis parameters, and the most recent dialysis end time point of the patient; after calculating the time length from the most recent dialysis end time point to the evaluation time point, calculating the total score based on the database and the dialysis cause compensation function respectively, and evaluating the patient's immune ability according to the total score.

2. The immune assessment method for end-stage renal disease dialysis patients according to claim 1, wherein The demographic characteristics and underlying diseases include age, gender, height, weight, diabetes history, and cardiovascular and cerebrovascular disease history.

3. The immune assessment method for end-stage renal disease dialysis patients according to claim 2, characterized in that, The immune activation state data includes hsCRP concentration, monocyte count, sIL2R concentration, and IL-6 concentration.

4. The immune assessment method for end-stage renal disease dialysis patients according to claim 3, wherein Immune senescence state data includes lymphocyte count, CD4 + CD28 - T cell ratio, CD4 + CD73 + T cell ratio.

5. The immune assessment method for end-stage renal disease dialysis patients according to claim 4, wherein, In the database, the fractional ratio is such that the sum of age, gender, height, and weight is 0 - 2, the history of diabetes and the history of cardiovascular and cerebrovascular diseases are both 0 - 1, and the concentrations of hsCRP, monocyte count, lymphocyte count, sIL2R concentration, IL-6 concentration, CD4 + CD28 - T cell ratio and CD4 + CD73 + T cell ratios are all 0 - 2.

6. The immune assessment method for end-stage renal disease dialysis patients according to claim 5, wherein When collecting the data of the change in immune strength before and after dialysis of the patient population, patients with a dialysis interval of 3 - 4 days are selected, and the data of the change in immune strength is collected at several time nodes after dialysis.

7. The immune assessment method for end-stage renal disease dialysis patients according to claim 6, characterized in that The mixing ratio rule is to divide the collected patient population into 4 - 9 gradients according to the severity of the disease symptoms, and mix the data of the change in immune strength before and after dialysis under experimental conditions into the training library as the data reference of 1 gradient alone.

8. The immune assessment method for end-stage renal disease dialysis patients according to claim 7, wherein When the total score of the immune activation state data is greater than 4, the patient is evaluated as having overactive immunity or having an active infection.

9. The immune assessment method for end-stage renal disease dialysis patients according to claim 8, wherein, When the total score of the immune senescence state data is greater than 4, the patient is evaluated as being in a state of immune senescence and high risk of tumor.

10. The immune assessment method for end-stage renal disease dialysis patients according to claim 9, characterized in that, When the evaluated total score is greater than 6, the patient is evaluated as a high cardiovascular complication and high infection trigger individual within 1 year.

Images