A platelet trajectory calculator and its use in constructing a risk assessment model for acute graft-versus-host disease

Abstract

The present invention discloses the use of a platelet trajectory calculator or a platelet trajectory model in constructing a risk assessment model for acute graft-versus-host disease (aGVHD). By using the two-stage GBTM model, the present invention discovers that there are three different change trajectories in the platelet pattern after transplantation, and finds that the platelet trajectory is an independent risk factor for predicting the occurrence of aGVHD, especially severe aGVHD. Patients in the low platelet trajectory group have a higher cumulative incidence of severe aGVHD, providing an earlier time window and a more convenient clinical index for clinically predicting the occurrence of aGVHD, and providing new ideas for predicting diseases such as aGVHD. At the same time, based on the research results of the present invention, a platelet trajectory calculator is developed, and a unique aGVHD risk assessment model is constructed, making the technical solution of the present invention more valuable for clinical practical applications.

Description

Technical Field

[0001] The present disclosure relates to the field of medical informatics. In particular, the present disclosure relates to a platelet trajectory calculator / platelet trajectory model and its use in constructing a risk assessment model for acute graft-versus-host disease (aGVHD). Background Art

[0002] Hematopoietic stem cell transplantation (HSCT) is an important means of curing blood diseases such as acute myeloid leukemia (AML), especially for those high-risk (chemotherapy-resistant) or relapsed patients. HSCT provides the only possible cure.

[0003] Acute graft-versus-host disease (aGVHD) is the most common short-term complication after transplantation, and its severity is closely related to the transplantation outcome. The 1-year survival rate of patients with severe aGVHD is less than 50%, and the 1-year non-relapse mortality (NRM) of aGVHD patients with treatment failure can even reach 60%. Early prediction of the occurrence of aGVHD and drug prophylaxis can reduce the incidence of aGVHD, thereby improving the long-term survival of patients. Currently, many research results on predicting the occurrence of aGVHD have been published internationally, and most of its predictors are biomarkers including some cytokines. In addition, machine prediction models established based on large-scale clinical data have been reported more and more, but the existing prediction models have not reached an ideal state. How to identify high-risk aGVHD patients earlier and more accurately after transplantation is still a challenge. There is an urgent need to explore risk factors that can predict aGVHD earlier after transplantation, and this factor should have clinical applicability. Summary of the Invention

[0004] Technical Problem to be Solved

[0005] One aspect of the present disclosure is to provide a platelet trajectory calculator / platelet trajectory model and its use in constructing a risk assessment model for acute graft-versus-host disease (aGVHD) in view of the lack of new prediction means and models for acute graft-versus-host disease in the prior art.

[0006] Specifically, the inventors of the present disclosure creatively found that the platelet count trajectory can be used as an independent risk factor for predicting / evaluating the risk of acute graft-versus-host disease in patients after allogeneic hematopoietic stem cell transplantation. Applying the calculator / platelet trajectory model for the platelet count trajectory to the construction of an aGVHD risk assessment model can provide an earlier time window and a more convenient clinical index for clinically predicting the occurrence of aGVHD, and provide new ideas for the prediction of diseases such as aGVHD, thereby solving the above technical problems.

[0007] Technical Solutions Provided by the Present Disclosure

[0008] Use of a platelet trajectory calculator or a platelet trajectory model in constructing a risk assessment model for acute graft-versus-host disease (aGVHD).

[0009] In some embodiments of the present disclosure, the inventors further studied the platelet trajectories of patients in the early stage after allogeneic hematopoietic stem cell transplantation and found that patients with an early need for platelet transfusion were more likely to develop aGVHD. Therefore, in some embodiments of the present disclosure, the above-mentioned platelet trajectories are the platelet trajectories of patients from day 0 after allogeneic hematopoietic stem cell transplantation until before the occurrence of acute graft-versus-host disease. Further, in some other embodiments of the present disclosure, the above-mentioned platelet trajectories are the platelet trajectories of patients within the first 0 to 10 days after allogeneic hematopoietic stem cell transplantation.

[0010] In the present disclosure, the acute graft-versus-host disease (aGVHD) is a common complication after allogeneic hematopoietic stem cell transplantation and is also one of the important complications leading to early death after transplantation. Diseases that can receive allogeneic hematopoietic stem cell transplantation include, for example, leukemia (such as acute myeloid leukemia, acute lymphoblastic leukemia, chronic myeloid leukemia, chronic lymphocytic leukemia), lymphoma, multiple myeloma, severe aplastic anemia, immunodeficiency diseases, paroxysmal nocturnal hemoglobinuria, autoimmune diseases (such as lupus erythematosus), malignant non-hematological tumors, etc. The above-mentioned diseases are all likely to develop acute graft-versus-host disease (aGVHD) complications after haploidentical hematopoietic stem cell transplantation (HID-HSCT) treatment. In one embodiment of the present disclosure, the above-mentioned acute graft-versus-host disease is developed by acute myeloid leukemia patients after treatment.

[0011] In some embodiments of the present disclosure, the above-mentioned acute graft-versus-host disease is severe acute graft-versus-host disease, and the severe acute graft-versus-host disease is grades 3 to 4 classified according to the Glucksberg criteria.

[0012] In the present disclosure, the inventors performed GBTM modeling on the platelet counts of 165 AML-CR patients after HID-HSCT from day 0 to 10 and determined 3 types of platelet trajectories: low platelet count trajectory, medium platelet count trajectory, and high platelet count trajectory, and found that the low platelet count trajectory group had a higher proportion of severe aGVHD than the high platelet count trajectory group (28.6% vs 4.9%, P<0.001). Therefore, in some embodiments of the present disclosure, the above-mentioned platelet trajectories are the low platelet count trajectories.

[0013] In some embodiments of the present disclosure, the construction method of the above platelet trajectory calculator includes the following steps:

[0014] S1: Using the GBTM model (Group - Based Trajectory Modeling), divide the platelet trajectories into three groups, namely the low platelet count trajectory group, the medium platelet count trajectory group, and the high platelet count trajectory group, and construct the posterior probability of calculating that y belongs to class as follows:

[0015] ,

[0016] where, = 3,

[0017] y = (y0, y1, y2,..., yT ) represents the trajectory observed over time from 0 to T,

[0018] m k is a quadratic function of time t, and different groups have different coefficient sets: ,

[0019] are all the parameters owned;

[0020] S2: Use the two - stage decision tree method to reconstruct the model obtained in S1:

[0021] First, in the initial stage, set = 2 and use formula (2) in S1 to classify the observed trajectories into one of the following two groups: non - group 3 ( = 1) or group 3 ( = 2),

[0022] Then, in the second stage, for the trajectories assigned to the non - group 3 class in the initial stage, use formula (2) in S1 to further divide them into two subgroups: group 1 ( = 1) or group 2 ( = 2);

[0023] S3: The calculation method of the probability of the observed trajectories of these three groups is as follows:

[0024] .

[0025] Furthermore, in an embodiment of the present disclosure, the model parameters in the initial stage in S2 are:

[0026] ;

[0027] The model parameters in the second stage of the above S2 are:

[0028] .

[0029] Using the research ideas and results in the present disclosure, another aspect of the present disclosure is to provide a method for constructing a risk assessment model for acute graft-versus-host disease (aGVHD), including:

[0030] Step 1) Collect clinical data of patients;

[0031] Step 2) Determine the prediction variables of the risk assessment model, and the prediction variables include platelet trajectory;

[0032] Step 3) Establish an aGVHD prediction risk nomogram using the prediction variables in Step 2);

[0033] Step 4) Construct the risk assessment model for acute graft-versus-host disease using the aGVHD prediction risk nomogram obtained in Step 3).

[0034] Further, in some embodiments of the present disclosure, the above platelet trajectory is an independent risk factor in the prediction risk nomogram.

[0035] In order to achieve better effects, in some embodiments of the present disclosure, the prediction variables in the above Step 2) further include known aGVHD risk factors, and the known aGVHD risk factors include one or more selected from the patient's age, transplantation type, donor-recipient sex pair, aGVHD prevention regimen already administered to the patient, total mononuclear cell count, or CD34 + cell count.

[0036] Further, in some embodiments of the present disclosure, the above acute graft-versus-host disease is generated after allogeneic hematopoietic stem cell transplantation in patients with acute myeloid leukemia.

[0037] Using the research ideas and results in the present disclosure, another aspect of the present disclosure is to provide the use of a platelet trajectory calculator or a platelet trajectory model in the preparation of a product for evaluating the prognosis of acute myeloid leukemia treatment.

[0038] Using the research ideas and results in the present disclosure, another aspect of the present disclosure is to provide a device for evaluating the occurrence risk of acute graft-versus-host disease, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor;

[0039] When the computer program is executed by the processor, it runs the acute graft-versus-host disease (aGVHD) risk assessment model constructed by the above construction method.

[0040] Using the research ideas and results in the present disclosure, another aspect of the present disclosure is to provide a computer-readable storage medium, on which is stored the acute graft-versus-host disease (aGVHD) risk assessment model program constructed by the above construction method, and when the program is executed by a processor, it realizes the functions of the above device.

[0041] Beneficial effects

[0042] The present invention uses the GBTM model to find that there are three different change trajectories in the platelet pattern after transplantation, and finds that the platelet trajectory is an independent risk factor for predicting the occurrence of aGVHD, especially severe aGVHD. Patients in the low platelet trajectory group have a higher cumulative incidence of severe aGVHD, providing an earlier time window and a more convenient clinical index for clinically predicting the occurrence of aGVHD. At the same time, a risk prediction model is constructed by combining other clinical factors, providing a new idea for predicting diseases such as aGVHD. At the same time, based on the research results of the present invention, a platelet trajectory calculator is developed, and a unique aGVHD risk assessment model is constructed, making the technical solution of the present invention more valuable for clinical practical applications. Description of the drawings

[0043] Figure 1 It is the predicted risk nomogram of acute graft-versus-host disease (aGVHD) constructed in the embodiment of the present disclosure;

[0044] Figure 2 It is the result diagram of the trajectory group classification of hemoglobin and platelets when directly applying the vanilla GBTM algorithm in the embodiment of the present disclosure;

[0045] Figure 3 It is the result diagram of the occurrence of aGVHD in different hemoglobin trajectory groups when directly applying the vanilla GBTM algorithm in the embodiment of the present disclosure;

[0046] Figure 4 It is the result diagram of the occurrence of aGVHD in different platelet trajectory groups when directly applying the vanilla GBTM algorithm in the embodiment of the present disclosure;

[0047] Figure 5This is the result graph of the occurrence of severe aGVHD in different platelet trajectory groups when directly applying the vanilla GBTM algorithm in the embodiments of the present disclosure;

[0048] Figure 6 This is the result graph of the classification of platelet trajectory groups when applying the two-stage GBTM algorithm in the embodiments of the present disclosure;

[0049] Figure 7 This is the result graph of the occurrence of severe aGVHD in different platelet trajectory groups of two cohorts when applying the two-stage GBTM algorithm in the embodiments of the present disclosure;

[0050] Figure 8 This is the result graph of the occurrence of severe aGVHD in different risk groups of two cohorts when applying the constructed acute graft-versus-host disease (aGVHD) prediction risk model in the embodiments of the present disclosure. Detailed implementation manners

[0051] The present invention discloses the use of a platelet trajectory calculator in constructing an acute graft-versus-host disease (aGVHD) risk assessment model. Those skilled in the art can draw on the content of this article and appropriately improve the process parameters to achieve it. It should be particularly noted that all similar substitutions and modifications are obvious to those skilled in the art, and they are all regarded as included in the present invention. And those related can obviously make changes or appropriate alterations and combinations to the content described herein without departing from the content, spirit and scope of the present invention to implement and apply the technology of the present invention.

[0052] In the present invention, unless otherwise specified, scientific and technical terms used herein have the meanings commonly understood by those skilled in the art. Unless otherwise clearly stated, throughout the specification and claims, the term "comprising" or its variations such as "including" or "having" etc. will be understood to include the stated elements or components, without excluding other elements or other components. The term "a" ( "an" and "the") includes plural referents. The term "plural" means two or more. Terms such as "such as", "for example" etc. are intended to indicate exemplary embodiments and are not intended to limit the scope of the present disclosure.

[0053] In the present disclosure, when a value range is provided, it should be understood that unless the context clearly indicates otherwise, the endpoints are included in the range and each intermediate value between the upper and lower limits of the range and any other specified value or intermediate value within the specified range and any value within the smaller range between the specified values are covered.

[0054] In the present disclosure, the term "about" generally refers to a variation within the range of 0.5% - 10% above or below a specified value, for example, within the range of 0.5%, 1%, 1.5%, 2%, 2.5%, 3%, 3.5%, 4%, 4.5%, 5%, 5.5%, 6%, 6.5%, 7%, 7.5%, 8%, 8.5%, 9%, 9.5%, or 10% above or below the specified value.

[0055] In the present disclosure, unless otherwise specified, scientific and technical terms used herein have the meanings commonly understood by those skilled in the art. Definitions of common terms in molecular biology can be found in Lewin’s GENES, Twelfth Edition, Jocelyn E. Krebs, Elliott S. Goldstein, Stephen T. Kilpatrick, Publisher: Jones & Bartlett Learning. Definitions of common terms in biochemistry can be found in Lehninger Principles of Biochemistry, Eighth Edition, David L. Nelson, Michael M. Cox, Publisher: W.H. Freeman. Definitions of common terms in cell biology can be found in Molecular Biology of the Cell, Sixth Edition, Bruce Alberts, Alexander Johnson, Julian Lewis, David Morgan, Martin Raff, Keith Roberts, Peter Walter, Publisher: Garland Science. Definitions of common terms in genetics can be found in Genetics: Analysis of Genes and Genomes, Eighth Edition, Daniel L. Hartl, Maryellen Ruvolo, Publisher: Jones & Bartlett Learning.

[0056] Unless otherwise specified, experimental techniques herein employ conventional techniques of immunology, biochemistry, chemistry, molecular biology, microbiology, cell biology, genomics, and recombinant DNA, which can be found in standard books such as Molecular Cloning: A Laboratory Manual; Cell Biology: A Laboratory Handbook, etc.

[0057] Definition:

[0058] The term "platelet" in the present disclosure refers to the progeny cells produced by bone marrow megakaryocytes and released into the peripheral blood, which have the function of hemostasis and blood coagulation. The normal engraftment and reconstitution of platelets are important indicators for judging the success of hematopoietic reconstitution after transplantation in patients. There are different platelet reconstitution patterns in patients after HSCT. Among them, poor platelet reconstitution will significantly reduce the overall survival of patients after transplantation. In the case of aGVHD, patients usually have lower platelet counts, higher platelet transfusion requirements, and even slower platelet recovery and reconstitution rates, resulting in a shortened overall survival after transplantation.

[0059] The term "platelet count trajectory" in the present disclosure has the same or very similar meaning as "platelet number trajectory" and "platelet trajectory", and can be used interchangeably in the present disclosure. Usually, the platelet count or platelet number refers to the absolute number of platelets. The platelet count / number trajectory is the change of platelet number over a period of time, which can be characterized and analyzed using an appropriate trajectory model. For example, the joint latent class model (JLCM), etc. In some embodiments of the present disclosure, the group-based trajectory modeling (GBTM) is used to group and characterize the platelet trajectory.

[0060] Group-Based Trajectory Modeling (GBTM), namely group-based trajectory modeling, also known as latent class growth model (LCGM), is an effective method for analyzing longitudinal data. GBTM was proposed by DANIELS.NAGIN and elaborated in the article "Analyzing Developmental Trajectories: A Semiparametric, Group-Based Approach" (Psychol Methods, 1999, 4(2): 139-157.). It is a semi-parametric finite mixture model that can classify the trajectories of a group of people and generate several representative movement trajectory models, and then analyze each trajectory model to understand people's movement characteristics, physiological levels, risk levels, etc. The core idea of GBTM is to divide the population into several groups, and the people in each group have similar movement patterns or development trajectories, which are used to describe and predict their future trajectories, so as to provide a more scientific basis for the health management of individuals and groups. GBTM is widely used in the biomedical field to study the change trajectories of biomarkers over time, evaluate the heterogeneity of clinical interventions, and predict the relationships between biomarkers and clinical events in different fields. At the same time, by drawing the occurrence and development trajectory map of diseases, GBTM helps to evaluate the effectiveness of clinical interventions and identify high-risk groups of diseases.

[0061] The term "platelet trajectory calculator" in the present disclosure may also be referred to as "platelet trajectory model", which is a mathematical or computational model used to describe and analyze the movement trajectories of platelets in blood or blood vessels. Common modeling methods include, for example, hydrodynamic simulation methods, cell mechanics models, image processing techniques, etc. Those skilled in the art can construct it according to the methods in the prior art. For example, Chen J, Gao X, Shen S, et al. disclosed a platelet trajectory model in Association of longitudinal platelet count trajectory with ICU mortality: A multi-cohort study. Front Immunol. 2022;13:936662. Another example is the platelet trajectory model disclosed by Ye Q, Wang X, Xu X, Chen J, Christiani DC, Chen F, et al. in Serial platelet count as a dynamic prediction marker of hospital mortality among septic patients. Burns Trauma. 2024;12:tkae016. In one embodiment of the present disclosure, the inventors converted the constructed platelet trajectory model into the form of a web calculator for convenient use. The construction of this web calculator can be achieved by using known methods in the prior art.

[0062] The term "acute graft-versus-host disease" in the present disclosure can be used interchangeably with "aGVHD", "acute GVHD", "typical acute graft-versus-host disease", and "typical acute GVHD" in the present disclosure, and refers to graft-versus-host disease that develops in the graft recipient within approximately 100 days after transplantation and exhibits clinical features commonly associated with acute graft-versus-host disease, including but not limited to, inflammation and tissue damage in the skin, oral and genital mucosa, eyes, intestines, liver, lungs, joints, and muscles. GVDH was discussed in Nassereddine, Anticancer Research, 37(4): 1547-1555 (2017).

[0063] The term "Glucksberg criteria" in the present disclosure is a severity grading criteria for clinical acute GVHD commonly used internationally (Przepiorka D, Weisdorf D, Martin P, et al. 1994 Consensus Conference on Acute GVHD Grading[J]. Bone Marrow Transplant, 1995, 15(6):825 - 828.). It is formulated based on the impact of acute GVHD on non - relapse - related death after transplantation. The total grading is formed after separately scoring acute GVHD of the skin, gastrointestinal tract, and liver. The existing modified Glucksberg criteria are shown in Table 1 below.

[0064] Table 1 Modified Glucksberg Grading Criteria for Acute Graft - Versus - Host Disease (GVHD)

[0065]

[0066] The severe acute graft - versus - host disease (GVHD) described in the present disclosure refers to grades III - IV according to the Glucksberg grading criteria.

[0067] The term "prediction risk nomogram" (Nomogram) in the present disclosure, also known as nomograph or alignment diagram, is a quantitative analysis diagram that represents the functional relationship between multiple variables with scaled line segments in a plane coordinate. The basic principle of the prediction risk nomogram is to construct a multi - factor regression model (such as Cox regression, Logistic regression, etc.). According to the contribution degree of each influencing factor to the outcome variable in the model (i.e., the magnitude of the regression coefficient), scores are assigned to each value level of each influencing factor. Then, these scores are plotted on the same plane in a certain proportion to form scaled line segments. When in use, the scores of each variable can be found and added to get the total score. Finally, through the functional conversion relationship between the total score and the probability of the occurrence of the outcome event, the predicted value of the outcome event of this individual is calculated. In an embodiment of the present disclosure, the obtained aGVHD prediction risk nomogram is as Figure 1 shown, and the said prediction risk nomogram alone or in combination with other prediction models constitutes the acute graft - versus - host disease (aGVHD) risk assessment model described in the present disclosure. Examples

[0068] To enable those skilled in the art to better understand the technical solutions of the present invention, the present invention will be further described in detail below in conjunction with specific examples.

[0069] The research objects in this example:

[0070] The subjects in this example were AML (AML-CR) patients who achieved complete remission. These patients received HID-HSCT at the Institute of Hematology, Chinese Academy of Medical Sciences from January 2017 to March 2023. A total of 276 patients were included and divided into a training cohort (165 cases) and a validation cohort (111 cases).

[0071] The primary endpoint of the study in this example was the occurrence of aGVHD, and the secondary endpoint was the cumulative incidence of aGVHD within 100 days. The grading of aGVHD referred to the Glucksberg criteria.

[0072] 1. Using the GBTM model, the early post-transplant platelet and hemoglobin trajectories were divided into 3 groups.

[0073] Absolute neutrophil, hemoglobin, and platelet data within the time range from day 0 to day 10 after transplantation were collected to explore whether patients showed obvious dynamic changes in the early post-transplant period. Group-based trajectory modeling (GBTM) is an unsupervised clustering machine learning model implemented through the "traj" package. We used this method to characterize the evolution of the above blood cell counts over time and evaluated the association between trajectory membership and the occurrence of aGVHD. The modeling method is as follows:

[0074] Let y = (y0, y1, y2,..., yT) represent the observed trajectory over time from 0 to T.

[0075] In the context of GBTM, y is modeled as a mixture of multivariate Gaussian distributions as follows:

[0076]

[0077]

[0078] Here, the (T + 1)-dimensional mean vector mk of the k-th cluster is a quadratic function of time t, and different groups have different coefficient sets:

[0079]

[0080] If all parameters are available:

[0081]

[0082] Then, given an observed sequence Y, the posterior probability that Y belongs to class K can be calculated as follows:

[0083] The denominator in (1) is a normalization constant and does not need to be explicitly calculated. Instead, (2) can be calculated for k = 1, ..., K and then the results can be normalized. In (2), wk is incorporated into the exponential component because in practice, all calculations are usually performed within the exponential component.

[0084] Results:

[0085] When directly applying the vanilla GBTM algorithm, the results revealed a model with K = 3 classes, indicating that hemoglobin and platelets can be divided into high, medium, and low trajectory groups (see Figure 2 ). When examining the association with the occurrence of aGVHD, no significant differences were observed among different hemoglobin trajectory groups (see Figure 3 ). However, although the difference in the incidence of overall aGVHD among the three platelet trajectory groups was small (see Figure 4 ), they showed a significant cumulative incidence of severe aGVHD. Notably, the cumulative incidences of severe aGVHD in the low, medium, and high platelet trajectory groups were 21.4%, 10.9%, and 6.7% respectively. The platelet trajectory showed an obvious trend (see Figure 5 ).

[0086] 2. The two-stage decision tree method (two-stage) reveals the association between platelet trajectory and the occurrence of severe aGVHD.

[0087] Furthermore, in this embodiment, a two-stage decision tree method is developed to mathematically reconstruct the platelet trajectory. This method yields a better Bayesian Information Criterion (BIC), indicating an improvement in model fitting. Based on this new model, it is possible to identify significant dynamic changes in patients' platelets at an early stage after transplantation (see Figure 6 ). Importantly, a statistically significant difference in the incidence of severe aGVHD was observed among the three platelet trajectory groups, which was not obvious in the original GBTM model. The modeling method is as follows:

[0088] Two-Stage Group Trajectory Modeling:

[0089] Step 1: In this initial stage, set K = 2 and use (2) to assign the observed trajectories to one of two groups: not Group 3 (k = 1) or Group 3 (k = 2).

[0090] The model parameters for this stage are as follows:

[0091] Step 2: For the trajectories assigned to the "non-Group 3" category in Step 1, use (2) to further divide them into two subgroups: Group 1 (k = 1) or Group 2 (k = 2).

[0092] The model parameters at this stage are as follows:

[0093] The probabilities of the observed trajectories belonging to these three groups can be calculated as follows:

[0094] .

[0095] Results:

[0096] To verify the above findings, the patient cohort was divided into a training cohort and a test cohort. In the training cohort consisting of 165 patients, 30 patients developed severe aGVHD. Compared with the high platelet trajectory group, the incidence of severe aGVHD was significantly higher in the low platelet trajectory group (28.6% and 4.9% respectively, P values were all < 0.001), while no significant difference was observed in other aGVHD groups. In addition, among the 30 patients with severe aGVHD, 18 patients (60%) showed low platelet trajectories in the early post-transplant period, while 2 patients (6.7%) showed high platelet trajectories. To further confirm these findings, patients from the validation cohort were included in a two-stage trajectory modeling. The analysis revealed three different platelet trajectories in the early post-transplant period. Consistently, compared with patients in the high platelet trajectory group, patients in the low platelet trajectory group showed a higher incidence and proportion of severe aGVHD. These findings highlight the utility of the two-stage decision tree method in identifying meaningful platelet trajectories and their correlation with the risk of severe aGVHD after HSCT.

[0097] 3. Develop a web calculator based on the above method.

[0098] 4. Acute graft-versus-host disease (aGVHD) risk assessment model.

[0099] 1) Prove that platelet trajectory is an independent risk factor for aGVHD.

[0100] The unique clinical outcomes associated with platelet trajectories suggest the potential utility of platelet trajectories as a risk factor for the development of aGVHD. To evaluate this possibility, a COX proportional hazards regression model was established in this example. Considering competing risks, the Fine-Gray test was used to estimate the cumulative incidence of aGVHD, with recurrence and death within 100 days as competing events. Statistical significance was defined at the 0.05 level.

[0101] In the factor regression analysis of this example, previously reported clinically relevant factors or factors showing univariate associations with the outcome were included in the multivariate Cox proportional hazards regression model. Given the limited number of available events, great care was taken in variable selection to ensure the simplicity of the final model. The results of the univariate analysis showed that platelet trajectory rather than other factors was a risk factor for the development of aGVHD, especially severe aGVHD (P = 0.001, HR [95%CI] = 0.403 [0.231 - 0.702]). When platelet trajectory and previously reported factors were included in the multivariate analysis, even after adjusting for other factors, platelet trajectory remained an independent risk factor for aGVHD, especially severe aGVHD (P = 0.004, HR [95%CI] = 0.454[0.257−0.771]). HR [95%CI] = 0.312 [0.130−0.752]). Further analysis of the cumulative incidence of aGVHD, especially severe aGVHD, in the training and validation groups showed that patients in the low platelet trajectory group had a higher incidence of severe aGVHD at 100 days (28.6%, 25.8%), while the incidence in the high trajectory group was significantly lower, at 4.9% and 4.5% respectively, in the two cohorts (see Figure 7 ). There were statistically significant differences in the incidence of severe aGVHD between the two trajectory groups (P = 0.009, P = 0.011). Interestingly, it was found that platelet trajectory was not associated with the occurrence of overall aGVHD. Therefore, low platelet trajectory in the early post-transplant period is a risk factor for the development of aGVHD, especially severe aGVHD, but not a risk factor for overall aGVHD.

[0102] 2) Prove that combining platelet trajectory with other factors can better predict the occurrence of severe aGVHD.

[0103] This example attempted to determine whether combining platelet trajectory with other factors related to aGVHD could enhance the predictive ability for the onset of aGVHD, especially severe aGVHD. The analysis in this example involved evaluating the cumulative incidence of aGVHD by combining these comprehensive factors. In this example, risk factors for the occurrence of aGVHD reported in previous literature were selected for multivariate nomogram modeling, weights were assigned, and the risk population was redefined. The results of the study in this example yielded a notable observation: when combined with a low platelet trajectory, the incidence of severe aGVHD could be significantly increased ( Figure 8 ). This emphasizes the complexity of predicting aGVHD, especially severe aGVHD, and suggests that the predictive value derived from platelet trajectory itself may be robust.

[0104] 3) The way to establish the predictive risk nomogram.

[0105] See Figure 1 . Among them,

[0106] The first row is the score scale, and the score range is 0 - 100;

[0107] The second row is the age, and the numerical range is 5 - 65 years old;

[0108] The third row is the transplantation type, including PB+BM (peripheral blood + bone marrow), PB (peripheral blood);

[0109] The fourth row is the gender of the donor and recipient, including other (non-female donor to male), female for male;

[0110] The fifth row is the prevention plan for acute aGVDH: including FK506 (tacrolimus), other (non-tacrolimus);

[0111] The sixth row is the total number of mononuclear cells, and the numerical range is 2 - 30;

[0112] The seventh row is the number of CD34+ cells, and the numerical range is 0 - 18;

[0113] The eighth row is the platelet trajectory, including 1 (low trajectory group), 2 (medium trajectory group), 3 (high trajectory group);

[0114] The ninth row is the total score, which is the sum of the scores from the second row to the eighth row, and the score range is 0~350;

[0115] The tenth row is the risk prediction value of severe aGVHD, which corresponds to the ninth row.

[0116] 4) Construct a risk assessment model for acute graft-versus-host disease (aGVHD).

[0117] The above is only the preferred embodiment of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. Use of a platelet trajectory calculator or a platelet trajectory model in constructing an acute graft-versus-host disease risk assessment model, characterized in that: The platelet trajectory calculator or the platelet trajectory model is modeled using the platelet count of patients who achieve complete remission after allogeneic hematopoietic stem cell transplantation. The platelet trajectory calculator or the platelet trajectory model is an independent risk factor for predicting or assessing the risk of acute graft-versus-host disease in patients after allogeneic hematopoietic stem cell transplantation.

2. The use according to claim 1, characterized in that The platelet trajectory is the platelet trajectory of the patient from day 0 to before the occurrence of acute graft-versus-host disease after allogeneic hematopoietic stem cell transplantation.

3. The use according to claim 2, characterized in that: The platelet trajectory is the platelet count trajectory of the patient from day 0 to day 10 after allogeneic hematopoietic stem cell transplantation.

4. The use according to any one of claims 1 to 3, characterized in that: The acute graft-versus-host disease is produced after patients with acute myeloid leukemia are treated with allogeneic hematopoietic stem cell transplantation.

5. The use according to claim 1, characterized in that: The acute graft-versus-host disease is severe acute graft-versus-host disease, and the severe acute graft-versus-host disease is grade 3-4 according to the Glucksberg standard.

6. The use according to claim 1, characterized in that: The method for constructing the platelet trajectory calculator or the platelet trajectory model comprises the following steps: S1: The platelet trajectories are divided into three groups using the GBTM model, which are low platelet count trajectory group, medium platelet count trajectory group and high platelet count trajectory group. The calculation of y belongs to The posterior probability of the class is as follows: ， in, =3, y = (y0, y1, y2, . . . , yT ) represents the trajectory observed from time 0 to T, m kt is a quadratic function of time t, with different sets of coefficients for different groups: ， are all the parameters that have; S2: Reconstruct the model obtained in S1 using a two-stage decision tree method: First, in the initial stage, set = 2 and use formula (2) in S1 to classify the observed trajectories into one of the following two groups: =1 or Group 3 =2, Then in the second stage, for the trajectories assigned to the non-group 3 categories in the initial stage, they are further divided into two subgroups using formula (2) in S1: Group 1 =1 or Group 2 =2; S3: The probability of obtaining the three groups of observation trajectories is calculated as follows: ； ； 。 7. The use according to claim 6, characterized in that The model parameters in the initial stage of S2 are: ； ； ； The model parameters of the second stage in S2 are: ； ； 。 8. A method for constructing an acute graft-versus-host disease risk assessment model, characterized in that: include: Step 1) Collect the patient’s clinical data; Step 2) determining predictive variables of the risk assessment model, wherein the predictive variables include platelet trajectory; Step 3) establishing a GVHD prediction risk nomogram using the predictor variables described in step 2); Step 4) constructing the acute graft-versus-host disease risk assessment model using the aGVHD prediction risk nomogram obtained in step 3), The platelet trajectory is an independent risk factor in the predicted risk nomogram.

9. The construction method according to claim 8, characterized in that: The predictor variables in step 2) also include known aGVHD risk factors, which are selected from patient age, transplant type, donor-recipient gender pair, aGVHD prevention regimen that the patient has been administered, total mononuclear cell count or CD34 + One or more of a number of cells.

10. The construction method according to claim 8 or 9, characterized in that: The acute graft-versus-host disease is produced after patients with acute myeloid leukemia are treated with allogeneic hematopoietic stem cell transplantation.

11. Use of a platelet trajectory calculator or a platelet trajectory model in the preparation of a product for assessing the prognosis of treatment of acute myeloid leukemia, characterized in that: The platelet trajectory calculator or the platelet trajectory model is modeled using the platelet count of patients who have achieved complete remission after allogeneic hematopoietic stem cell transplantation. The platelet trajectory calculator or platelet trajectory model is an independent risk factor for predicting or assessing the risk of acute graft-versus-host disease in patients after allogeneic hematopoietic stem cell transplantation.

12. A device for assessing the risk of acute graft-versus-host disease, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor; When the computer program is executed by the processor, the acute graft-versus-host disease risk assessment model constructed by the construction method described in any one of claims 8 to 10 is run.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an acute graft-versus-host disease risk assessment model program constructed by the construction method as described in any one of claims 8 to 10, and when the program is executed by the processor, the function of the device as described in claim 12 is realized.

Images