Systems and methods for predicting transplant rejection

Abstract

Computer-implemented methods and systems for predicting transplant rejection are disclosed herein. The method and system may calculate a predicted probability of whether a transplant rejection will occur or will occur in the transplant recipient based on the score. The score may be calculated based on transplant recipient data and one or more parameter weights. The transplant recipient data may include free DNA of a transplant donor source (dd-cfDNA) and one or more other types of parameters, such as one or more clinical parameters, one or more functional parameters, one or more immunological parameters, one or more transplant recipient characteristics, or one or more transplant characteristics. In some embodiments, the parameters used to calculate the predicted probability do not include histological parameters.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of U.S. Provisional Application No. 63 / 348,971, filed on June 3, 2022, and U.S. Provisional Application No. 63 / 358,484, filed on July 5, 2022, both of which are hereby incorporated by reference in their entirety. Technical Field

[0003] The present disclosure generally relates to systems and methods for determining the status of an allograft, including predicting transplant rejection. Background Art

[0004] Transplantation of cells, tissues, parts, or whole organs is a life-saving medical procedure when an individual experiences acute organ failure or suffers from certain malignancies. Many organs, including but not limited to the heart, kidneys, liver, lungs, and pancreas, can be successfully transplanted, and one of the most commonly performed types of organ transplants today is the kidney transplant.

[0005] When non-autologous (allogeneic) cells, tissues or organs (allogeneic transplants) are transplanted into a recipient, the recipient's immune system will recognize the allograft as a foreign body and activate various mechanisms to reject the allograft. Therefore, it is necessary to suppress such immune responses medically to minimize the risk of transplant rejection. After transplantation, the state of the transplant can be monitored by a variety of clinical laboratory diagnostic tests, which may include invasive histopathological assessments of transplant biopsies. However, histopathological assessments (e.g., biopsies) only provide information about the current rejection state of the allograft, and lack the ability to provide prognostic and / or predictive risk assessments for future allograft dysfunction and / or allograft rejection.

[0006] Physicians or medical professionals may have their own criteria for measuring the contribution of measured information to the overall assessment of allograft status. The measured information may be collected from various clinical laboratory diagnostic tests, demographic information, and other parameters. Objective and consistent quantification of transplant rejection risk, optionally compared to a reference set of allograft status, will help guide treatment options, such as immunosuppressive therapy and daily clinical care.

[0007] As provided by the present disclosure, there is a need for systems and methods for predicting transplant rejection based on objective, comprehensive, consistent, and comparable assessments that will ultimately improve diagnostic accuracy and reliability. Summary of the invention

[0008] A computer-implemented method for determining the risk of transplant rejection using a machine learning system is disclosed. The method includes: receiving transplant recipient data of a transplant recipient including a set of parameters via a computer or input function, the set of parameters including donor-derived free DNA (dd-cfDNA); receiving one or more parameter weights; calculating a score based on the transplant recipient data and the one or more parameter weights; and calculating the predicted probability of whether transplant rejection will occur or the extent to which it will occur in the transplant recipient based on the score. Additionally or alternatively, in some embodiments, the set of parameters of the transplant recipient data also includes one or more of the following: one or more clinical parameters, including the time to evaluation after transplantation; one or more functional parameters, including estimated glomerular filtration rate (eGFR), creatinine or proteinuria; one or more immunological parameters, including donor-specific antibody mean fluorescence intensity or anti-human leukocyte antigen (HLA) mismatch number; one or more transplant recipient characteristics, including transplant recipient age or donor organ infection information; or one or more transplant characteristics, including previous transplant information or previous rejection information. Additionally or alternatively, in some embodiments, the set of parameters does not include histological parameters. Additionally or alternatively, in some embodiments, the computer-implemented method further comprises: generating a projection of the transplant recipient data in a reference set, wherein the reference set comprises one or more other transplant recipients having one or more common characteristics. Additionally or alternatively, in some embodiments, calculating the score comprises: for each parameter weight, multiplying the parameter weight by the corresponding parameter of the transplant recipient data; and calculating the score based on the sum of the multiplications. Additionally or alternatively, in some embodiments, calculating the predicted probability comprises: determining an intercept of a multivariate logistic regression model; and calculating the predicted probability based on the score and the intercept. Additionally or alternatively, in some embodiments, the one or more parameter weights are received from a machine learning model that is trained to: obtain a cohort data set including a first set of model parameters and cohort transplant rejection information of transplant recipients in the cohort, wherein the first set of model parameters includes dd-cfDNA; analyze the first set of model parameters for associations between the cohort data set and the corresponding cohort transplant rejection information, wherein the first set of model parameters are analyzed individually; select a second set of model parameters from the first set of model parameters, wherein the second set of model parameters meets one or more first criteria; select a third set of model parameters from the second set of model parameters, wherein the third set of model parameters includes independent variables associated with transplant rejection and meets one or more second criteria; and generate one or more parameter weights corresponding to the third set of model parameters for the cohort data set.Additionally or alternatively, in some embodiments, the first set of model parameters also includes one or more of the following: one or more clinical parameters, including renal allograft dysfunction, time since last transplant rejection, or time from transplant to evaluation; one or more functional parameters, including estimated glomerular filtration rate (eGFR) or proteinuria; one or more immunological parameters, including donor-specific antibody mean fluorescence intensity or anti-human leukocyte antigen (HLA) mismatch number; one or more recipient and donor characteristics, including recipient age, recipient gender, or donor organ infection information; or one or more transplant characteristics, including donor age, donor gender, donor type, previous transplant information, cold ischemia time, or dual transplant kidney information. Additionally or alternatively, in some embodiments, the second set of model parameters includes dd-cfDNA, allogeneic graft dysfunction, recent transplant rejection information, time to evaluation after transplantation, estimated glomerular filtration rate (eGFR), proteinuria, donor-specific antibody mean fluorescence intensity, recipient age, recipient gender, donor age, donor gender, donor type, previous transplant information, cold ischemia time, dual transplant information, and anti-human leukocyte antigen (HLA) mismatch number. Additionally or alternatively, in some embodiments, wherein the third set of model parameters includes dd-cfDNA, estimated glomerular filtration rate (eGFR), graft dysfunction, recent transplant rejection information, and donor-specific antibody mean fluorescence intensity. Additionally or alternatively, in some embodiments, the machine-learning model trained to analyze the first set of model parameters for association analysis includes a machine learning model trained to analyze whether the parameters in the first set of model parameters distinguish or distinguish between whether there is transplant rejection or not in the cohort transplant rejection information. Additionally or alternatively, in some embodiments, the one or more first criteria or the one or more second criteria include a model parameter having a confidence interval greater than or equal to a confidence interval threshold or a p-value less than a p-value threshold. Additionally or alternatively, in some embodiments, the confidence interval threshold is 95% and the p-value threshold is 0.2. Additionally or alternatively, in some embodiments, the one or more first criteria include the number of model parameters in the second set of model parameters being less than a threshold number. Additionally or alternatively, in some embodiments, the machine learning model trained to analyze the first set of model parameters for association includes a machine learning model trained to reduce the dimension of the cohort data set based on the presence or absence of transplant rejection in the cohort transplant rejection information. Additionally or alternatively, in some embodiments, the machine-learning model trained to analyze the first set of model parameters for association includes a machine learning model trained to determine the association of dd-cfDNA with one or more of the following: the cause of end-stage renal disease or the type of transplant rejection.Additionally or alternatively, in some embodiments, the machine learning model trained to analyze the first set of model parameters includes a machine learning model trained to reduce the dimension of the cohort data set based on the type of transplant rejection. Additionally or alternatively, in some embodiments, the machine-learning model trained to select the third set of model parameters includes being trained to: perform backward selection by individually analyzing whether or to what extent the parameters in the second set of model parameters distinguish between the presence or absence of transplant rejection in the cohort transplant rejection information; and compare the individual analyses to select the third set of model parameters. Additionally or alternatively, in some embodiments, the one or more second criteria include that the number of model parameters in the third set of model parameters is less than a threshold number.

[0009] The present disclosure relates to a system for classifying the status of a transplant. The system may include: a scoring unit, the scoring unit: receiving transplant recipient data of a transplant recipient, the transplant recipient data including

[0010] A set of parameters, the set of parameters including donor-derived free DNA (dd-cfDNA); receiving one or more parameter weights; calculating a score based on the transplant recipient data and the one or more parameter weights; and calculating a predicted probability of whether transplant rejection will occur or the extent to which it will occur in the transplant recipient based on the score. The system may include one or more data processors and a non-transient computer-readable storage medium containing instructions, which, when executed on one or more data processors, cause one or more data processors to perform part or all of one or more methods disclosed herein. In some embodiments, the system includes a non-transient computer-readable storage medium containing instructions, which, when executed on one or more data processors, cause one or more data processors to perform part or all of one or more methods disclosed herein and / or part or all of one or more processes.

[0011] A computer program product is disclosed. The computer program product may be tangibly embodied in a non-transitory machine-readable storage medium and includes instructions configured to cause one or more data processors to perform part or all of one or more methods disclosed herein. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 An example system for predicting transplant rejection according to an embodiment of the present disclosure is shown.

[0013] Figure 2 A flow chart of an example method for calculating a predicted probability of transplant rejection in a transplant recipient and / or generating a projection of transplant recipient data in a reference set according to embodiments of the present disclosure is shown.

[0014] Figure 3AAn example user interface displaying text boxes and input boxes according to an embodiment of the present disclosure is shown.

[0015] Figure 3B An example user interface displaying example predicted probabilities and projections is shown according to an embodiment of the present disclosure.

[0016] Figure 3C and Figure 3D An example user interface for displaying predicted probabilities and projections for additional example transplant recipients is shown in accordance with an embodiment of the present disclosure.

[0017] Figure 4A An example system for generating parameter weights according to an embodiment of the present disclosure is shown.

[0018] Figure 4B A flowchart of an example method performed by a machine learning model according to an embodiment of the present disclosure is shown.

[0019] Figure 5 An example data table of a second set of parameters selected from a first set of parameters for a cohort data set according to an embodiment of the present disclosure is shown.

[0020] Figure 6 An example data table of a third set of parameters selected from the second set of parameters for a cohort data set according to an embodiment of the present disclosure is shown.

[0021] Figure 7 An example device implementing the above disclosed systems and methods according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0022] The present disclosure is based, at least in part, on the development of computer-implemented methods and systems for predicting transplant rejection.

[0023] Predicting the risk of allograft rejection in transplant recipients based on objective, comprehensive, consistent, and comparable assessments would allow transplant recipients to be categorized and treated according to their overall risk of allograft rejection, which in turn would improve routine clinical care, avoid unnecessary invasive procedures, and prolong allograft survival.

[0024] The predicted probability of whether transplant rejection will occur or will occur in a transplant recipient can be calculated based on a score. The score can be calculated based on transplant recipient data and one or more parameter weights. The transplant recipient data may include free DNA (dd-cfDNA) from a transplant donor source and one or more other types of parameters, such as one or more clinical parameters, one or more functional parameters, one or more immunological parameters, one or more transplant recipient characteristics, or one or more transplant characteristics. In some embodiments, these parameters for calculating the predicted probability do not include histological parameters.

[0025] The predicted probability can be used by a physician or medical expert. The physician or medical expert can input transplant recipient data into the interface. The scoring unit can receive the transplant recipient data and calculate the score based on the transplant recipient data and one or more parameter weights. The scoring unit can receive the parameter weights through a trained machine learning model. The scoring unit can also calculate the predicted probability. The predicted probability can be a binary indication (e.g., yes or no) or a quantitative value (e.g., 80%) indicating the extent to which transplant rejection will occur in the transplant recipient. The predicted probability can be provided on a graphical user interface displayed to the physician or medical expert. The predicted probability can be an objective measure for supplementing or replacing the evaluation of the physician or medical expert.

[0026] The predicted probability can be provided by a medical analysis tool that is easily accessible to a physician or medical expert. The medical analysis tool can display the predicted probability, projection, or both on a user interface. The predicted probability can be an accurate and quantifiable measure of the allograft status.

[0027] By quantifying the predictions, predicted probabilities and projections can become objective and more consistent. Predicted probabilities can be used to accurately compare the status of an allograft at one time point and another time point. Additionally or alternatively, quantification can be used as a guide to determine treatment options and related timing. In order to provide consistency, reliability, and granularity, embodiments of the present disclosure may include computer-implemented tools and methods for evaluating measurements from transplant recipients. Systematic evaluations may help to better characterize the response of transplant recipients to treatment and help provide information for the subsequent management of transplant recipients. The results of machine learning models and medical analysis tools can be more reproducible, so that differences between transplant recipients or between different measurement times for a given transplant recipient can be reduced.

[0028] The one or more parameter weights may be generated by a machine learning model that is trained to obtain a data set including a set of parameters and transplant rejection information from transplant recipients in a cohort. The machine learning model may analyze the parameters and perform one or more selection steps to select a subset of the parameters. The machine learning model may then generate parameter weights corresponding to the selected subset of parameters.

[0029] The machine learning model can be trained to select parameters related to the status of the allograft (e.g., predicted probability of failure). The machine learning model can receive a cohort data set from a cohort (such as a derivative cohort). The cohort data set may include parameters related or unrelated to allograft failure. In some embodiments, the parameters may have different degrees of association. The machine learning model may select those parameters with the highest degree of association with transplant rejection. In some embodiments, the machine learning model may generate parameter weights based on the degree of association. The parameters most related to allograft failure may be weighted more.

[0030] The following description is presented to enable those skilled in the art to make and use various embodiments. Descriptions of specific devices, techniques, and applications are provided only as examples. These examples are only used to provide background information to help understand the examples. Therefore, for those of ordinary skill in the art, the implementation of the examples may not rely on some or all of the specific details. Other applications are also possible, so the following examples should not be considered restrictive. For those of ordinary skill in the art, various modifications to the examples described herein will be apparent, and without departing from the essence and scope of the various embodiments, the general principles defined herein may be applied to other examples and applications. Therefore, the various embodiments are not intended to be limited to the examples described herein, but should be given a scope consistent with the claims.

[0031] Various techniques and process steps will be described in detail, with reference to the examples of the accompanying diagrams. In the following description, numerous specific details are listed to provide a comprehensive understanding of one or more aspects and / or features described or mentioned herein. However, for those of ordinary skill in the art, the implementation of one or more aspects and / or features described or mentioned herein may not rely on these specific details. In other cases, well-known process steps and / or structures are not described in detail to avoid obscuring certain aspects and / or features described or mentioned herein.

[0032] In the following description of the examples, reference is made to the accompanying drawings, which are part of the present disclosure and show by way of illustration specific examples that can be implemented. It should be understood that other examples can be used and structural changes can be made without departing from the scope of the disclosed examples.

[0033] The terms used in the various embodiments described herein are only used to describe specific embodiments and are not intended to be limiting. As used in the specification and the appended claims describing the various embodiments, the singular forms of "one", "a kind of" and "the" are also intended to include plural forms, unless the context clearly indicates otherwise different. It should be understood at the same time that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the listed related items. It is further understood that the terms "including", "comprising", "consisting of" and / or "consisting of" are used in this specification to indicate the presence of the features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or their groups.

[0034] Example system for predicting transplant rejection

[0035] Figure 1An example system 100 for predicting transplant rejection according to an embodiment of the present disclosure is shown. The system 100 may include an interface 160 and a scoring unit 170. The examples of the present disclosure may include some or all of the components shown in the figure, or other components not shown in the figure. The system 100 may be, for example, a medical analysis tool. A physician or medical expert may use the medical analysis tool to help monitor and / or classify the state of an allograft in a transplant recipient, and to monitor and / or recommend adjustments to an immunosuppressive therapy administered or to be administered to a transplant recipient. Monitoring the state of an allograft involves analyzing multiple aspects of providing useful information about the physiological state or health state of the allograft. The method of the present disclosure may be used to predict the probability of transplant rejection based on measured information indicating the state of an allograft. The predicted probability may be a quantitative percentage reflecting the probability that transplant rejection will occur in a transplant recipient.

[0036] Interface 160 may receive user input of transplant recipient data (e.g., input from a physician or medical professional). Example transplant recipient data may include information from laboratory testing related to transplant donor-derived cell-free DNA (dd-cfDNA); information at one or more time points regarding: creatinine levels in plasma, serum, and / or urine, proteinuria, estimated glomerular filtration rate, time to evaluation after transplant, transplant recipient characteristics (such as age and sex), information about previous transplants, information about previous transplant rejection events, etc. Interface 160 is discussed in more detail below.

[0037] Scoring unit 170 may be a tool for evaluating transplant recipient data (e.g., information obtained from a transplant recipient's blood and / or urine sample from laboratory tests or information from a biopsy). Scoring unit 170 may receive one or more parameter weights 190 (e.g., from Figure 4A The machine learning model 150 shown in FIG. 1 and the transplant recipient data. Scoring unit 170 can calculate the status of the allogeneic transplant recipient. The status of the allogeneic transplant can include a predicted probability or a projection. Scoring unit 170 can output the predicted probability and / or projection 180.

[0038] Figure 2A flow chart of an example method for calculating a predicted probability of transplant rejection in a transplant recipient and / or generating a projection of transplant recipient data in a reference set according to an embodiment of the present disclosure is shown. Method 200 may include step 202, wherein system 100 may receive transplant recipient data. The transplant recipient data may be received by, for example, interface 160. The transplant recipient data may be data related to the transplant recipient. The transplant recipient data may include measurement information from the transplant recipient. Example measurement information may include, but is not limited to, information about the following at one or more time points: creatinine levels in plasma, serum and / or urine, proteinuria, urine albumin, urine microalbumin, urine protein, estimated glomerular filtration rate (eGFR), urine albumin-creatinine ratio, blood urea nitrogen, serum sodium, serum potassium, serum chloride, serum bicarbonate, serum calcium, serum albumin, complete blood count panel, liver function panel, lipid distribution panel, coagulation panel, magnesium, phosphorus, brain natriuretic peptide, hemoglobin, uric acid, endostatin, number of HLA mismatches, mean fluorescence intensity (MFI) of donor-specific antibodies (DSA), and transplant recipient characteristics, such as the age of the transplant recipient, the time from transplant to evaluation, whether the transplant recipient has had a previous transplant, information about systemic infection, such as information about viral infection, such as BK virus infection. Optionally, the measurement information may also include information about whether the transplant recipient has previously experienced a transplant rejection event. In some embodiments, the evaluation time may be the duration (e.g., number of years) between when the measurement information is extracted and when the transplant occurs.

[0039] In step 204, the system may receive one or more parameter weights. For example, one or more parameter weights may be received from a machine learning model. As discussed in more detail below, the machine learning model may be trained to generate parameter weights based on various input parameters (such as a transplant recipient cohort data set and corresponding cohort transplant rejection information). In various embodiments, the machine learning model or algorithm used to analyze the various input parameters may include, but is not limited to, logistic regression; regularized classification models such as Ridge, lasso, and elastic network; nearest reduced centroid; gradient boosting machine; random forest; support vector machine; k nearest neighbor; neural network, etc.

[0040] In step 206, the system may use the scoring unit 170 to calculate a score based on the transplant recipient data and parameter weights. The transplant recipient data may include a set of parameters. The set of parameters may include at least donor-derived free DNA (dd-cfDNA). In some embodiments, the set of parameters may include parameters related to information about whether the transplant recipient has previously experienced a transplant rejection event. The parameter weight may correspond to the set of parameters. In some embodiments, each parameter may have a corresponding parameter weight. In some embodiments, each parameter weight may indicate the degree of association of the parameter with transplant rejection. For example, a higher parameter weight may indicate a higher association of the parameter with transplant rejection. The score may be calculated based on the transplant recipient data and the parameter weights. In some embodiments, the score may be calculated by adding together multiple multiplications. Each multiplication may be for each parameter weight, including multiplying the parameter weight by the corresponding parameter of the transplant recipient data. The generation of weights will be discussed in more detail below.

[0041] In step 208, the system can determine the state of the allograft, such as health state. Health state can be a state indicating allograft tolerance or allograft rejection or their possibility. In some embodiments, the determination of the state of the allograft can include calculating the predicted transplant rejection probability and / or generating a projection. The predicted probability can be a numerical value (e.g., percentage) indicating whether transplant rejection will occur or will occur in a transplant recipient based on a score. In some embodiments, calculating the predicted probability includes calculating the probability according to the score. In some embodiments, calculating the predicted probability includes determining the intercept of a multivariate logistic regression model, and calculating the predicted probability according to the score and the intercept. The predicted probability can be represented by a numerical value, a level or category indicating a numerical value, a binary indicator, etc. In some embodiments, the predicted probability and / or projection can indicate the current risk of transplant rejection in a transplant recipient.

[0042] The projection can be a visual aid for illustrating the predicted probability of a transplant recipient in a reference set. The reference set can include information from one or more other transplant recipients having one or more common characteristics (such as time to evaluation after transplantation).

[0043] Embodiments of the present disclosure may include repeating one or more steps in method 200 and / or method 400 (discussed below). Although the description and illustrations show that specific steps of the method are performed in a specific order, the steps of the method may be performed in other orders that are not described or shown. Additionally or alternatively, embodiments of the present disclosure may include performing all, some, or none of the steps of method 200 and / or method 400, where appropriate. Further, although certain components, devices, or systems are described as performing the steps of method 200 and / or method 400, any suitable combination of components, devices, or systems (including combinations not explicitly disclosed) may be used to perform these steps.

[0044] In some embodiments, the system can output the predicted probability and / or projection, such as displaying the predicted probability and / or projection on a user interface. The user interface can be included in a medical analysis tool that is easily accessible and immediately provides the status of the allograft to the physician or medical specialist. Figure 3A An example user interface showing text boxes and input boxes according to an embodiment of the present disclosure is shown. User interface 300 can be a user interface (UI) displayed on a display of a device (e.g., a mobile phone, a tablet computer, a laptop computer, etc.). In some embodiments, user interface 300 can be accessed by having a user navigate to a website or application page.

[0045] The user interface 300 may include one or more text boxes 304, one or more input boxes 308, or both. The text of a given text box 304 may be associated with the type of information that the user is to enter in the corresponding input box 308. For example, a text box 304A may display "Time from transplant to evaluation (years)". The system may receive input from a user (e.g., a physician, nurse, medical assistant, medical specialist, etc.) in a corresponding input box 308A. As another example, a text box 304B may display "Age of patient (years)", and a corresponding input box 308B may be used by the user to enter corresponding transplant recipient data. The transplant recipient data may include a (third) set of parameters for calculating a predicted probability of whether or to what extent transplant rejection will occur in a transplant recipient. As shown, example transplant recipient data may include one or more of the following parameters: time from transplant to assessment ("Time from transplant to assessment (years)"), age of the transplant recipient ("Patient age (years)"), whether the transplant recipient has had a previous transplant such as a previous kidney transplant ("Previous kidney transplant"), information about systemic infections such as BK virus ("BK virus (log)"), whether the transplant recipient has had a recent rejection ("Recent rejection"), eGFR ("eGFR mL / min / 1.73m 2”), information about serum, plasma and / or urine creatinine values ​​(“Previous Creatinine (mg / L)”), current creatinine values ​​(“Current Creatinine (mg / L)”), proteinuria values ​​(“Proteinuria (g / g)”), number of HLA mismatches (“HLA mismatches”), MFIDSA (“MFIDSA”), or percentage of dd-cfDNA (“dd-cfDNA (%)”) at one or more time points.

[0046] The user interface 300 may include one or more text boxes 306 that provide additional information to the text box 304, such as evaluation time, transplant recipient characteristics, transplant recipient data, transplant characteristics, recent rejection, functional parameters, and / or immunological parameters.

[0047] Additionally or alternatively, the user interface may include one or more graphical user interface buttons 310. The user interface buttons 310 and input box 308 may be interactive, enabling the user to input data and parameters, such as evaluation time, transplant recipient characteristics, transplant recipient data, transplant characteristics, recent rejection, functional parameters, and / or immunological parameters. After the user enters the information into the input box 308, the user may, for example, activate the system to calculate the predicted probability and / or generate the projection 180 by clicking a "Submit" graphical user interface button 310. For example, Figure 3B The direction and magnitude of the projected data and / or parameters in the two-dimensional plot shown in -D may provide further insights to elucidate or explain the rejection mechanisms in transplant recipients and guide corresponding patient management and treatment strategies.

[0048] Figure 3B An example user interface showing example predicted probabilities and projections according to an embodiment of the present disclosure is shown. User interface 350 may include something like ( Figure 3A ) text boxes and input boxes of the user interface 300. Figure 3B In the example shown, the transplant recipient data has the parameters shown in Table 1.

[0049] Parameter Group Transplant recipient data Time from transplant to evaluation 1 year Age of transplant recipient (patient) 50 years old Previous Kidney Transplant Information no BK virus information 0 Recent rejection incidents no eGFR <![CDATA[70mL / min / 1.73m 2 <!-- 7 -->]]> Previous creatinine 1mg / L Current creatinine 1.1mg / L Proteinuria 0g / g HLA mismatch 2 MFIDSA 0 dd-cfDNA 0.02％

[0050] Table 1. Example parameters and transplant recipient data

[0051] User interface 350 may also include one or more text boxes and / or one or more graphical representations. Text box 314 may provide an output of the predicted probability, and graphical representation 316 may provide a projected visual aid. For example, as shown, based on example parameters and transplant recipient data, the probability of rejection for a transplant patient is 0.8%.

[0052] Figure 3C and Figure 3DAn example user interface for displaying predicted probabilities and projections for additional example transplant recipients is shown in accordance with an embodiment of the present disclosure. Figure 3C In the example transplant recipient, a 50-year-old female received a transplant two years ago. The transplant recipient had no recent rejection or donor organ infection, such as BK virus infection, but had a previous kidney transplant. Her previous creatinine was 0.7 mg / L, but her current creatinine is 1.2 mg / L, indicating renal dysfunction. Her eGFR is 48 mL / min / 1.73 m 2 , and proteinuria is 1 g / g. The number of HLA mismatches is three, the anti-HLA DSA MFI is 7000, and the dd-cfDNA is 2%. The system calculates a predicted probability of 80.9% and can classify her as having a high risk of rejection.

[0053] exist Figure 3D The example transplant recipient is a 52-year-old female receiving her second kidney transplant with no prior recent rejection. The time from transplant to evaluation is three years. The transplant recipient's previous and current creatinine values ​​are 0.5 mg / L and 0.8 mg / L, respectively; the eGFR is 48 mL / min / 1.73 m 2 , and proteinuria is 0.5 g / g. The number of HLA mismatches is three. The patient has no MFIDSA, and dd-cfDNA is 1%. The calculated predicted probability for this transplant recipient is 21%, as shown in the figure.

[0054] As described above, the system 100 (e.g., a medical analysis tool) may generate one or more parameter weights. In some embodiments, the one or more parameter weights may be generated by the system 100. The parameter weights are used to calculate a predicted probability of transplant rejection or projection for a given transplant recipient.

[0055] Figure 4A An example system for generating parameter weights according to an embodiment of the present disclosure is shown. System 450 may include biomarker unit 120 , baseline characteristic unit 130 , database 140 , and machine learning model 150 .

[0056] The biomarker unit 120 may be configured to measure one or more characteristics of a sample from a transplant recipient. Example characteristics may include, but are not limited to, donor-derived free DNA (dd-cfDNA), anti-human leukocyte antigen (HLA) donor-specific antibodies (DSA), and creatinine levels. dd-cfDNA may be expressed as a percentage of total free DNA or as an absolute concentration. Anti-HLA DSA may refer to the presence of donor-specific anti-HLA antibodies in a transplant recipient. Creatinine levels refer to the amount of chemical waste filtered by the kidneys of a transplant recipient. In some embodiments, a blood sample and corresponding characteristics may be obtained at the same time as a biopsy.

[0057] In some embodiments, the characteristics of samples from transplant recipients can be determined according to an experimental (laboratory) workflow involving extraction of free DNA, including total free DNA, i.e., free DNA from transplant recipients and transplants, from blood, plasma, serum, and / or urine samples obtained from transplant recipients in derivation cohorts and validation cohorts (these cohorts will be discussed in more detail below). In some embodiments, the level or amount of transplant donor-derived cfDNA (dd-cfDNA) can be determined, involving targeted amplification and targeted high-throughput sequencing of selected polymorphic markers (e.g., selected single nucleotide polymorphisms (SNPs)), as described in U.S. Patent Application Nos. 14 / 658,061, filed March 13, 2015, and 17 / 351,040, filed June 17, 2021, respectively, which are hereby incorporated by reference in their entirety. Polymorphic markers represent loci in which two or more alternative nucleic acid sequences or alleles appear due to changes in one or more bases, one or more insertions, one or more duplications, one or more deletions, and variations thereof. Therefore, in some embodiments, the level or amount of cfDNA (dd-cfDNA) derived from the transplant donor can be determined, involving targeted analysis of alternative polymorphic markers, such as short tandem repeats (STR), restriction fragment length polymorphisms (RFLP), variable number of tandem repeats (VNTR's), hypervariable regions, microsatellites, dinucleotide repeats, trinucleotide repeats, tetranucleotide repeats, simple sequence repeats, and insertion elements. In some embodiments, dd-cfDNA can be quantified as a percentage or absolute concentration of total cfDNA. In some embodiments, the level or amount and characteristics of dd-cfDNA from a sample of a transplant recipient can be determined after receiving experimental data (such as sequencing reads) or other data-related information (such as quality control-related data, results, genotype information, SNP mutation rates, etc.) from a database or other non-experimental source.

[0058] Additionally or alternatively, the biomarker unit 120 may determine the mean fluorescence intensity (MFI) of the DSA. The MFI may indicate the intensity of donor-specific antibodies. In some embodiments, the beads may be classified according to a predetermined normalized MFI, such as less than 500, 500-3000, 3000-6000, and greater than 6000. The single antigen flow bead assay can be used to determine whether there is DSA for one or more antigens (e.g., HLA-A, HLA-B, HLA-Cw, HLA-DR, HLA-DQ, HLA-DP, etc.). Embodiments of the present disclosure may include identifying HLA antigens using HLA typing of transplant recipients and donors. Parameters for predicting the probability of transplant rejection may include one or more immunological variables, such as circulating anti-HLA DSA.

[0059] In some embodiments, the biomarker unit 120 may measure or calculate one or more functional parameters. One non-limiting example functional parameter is estimated glomerular filtration rate (eGFR). Glomerular filtration rate (GFR) refers to the rate at which the kidneys filter blood and can be indicative of their kidney function. Another non-limiting example functional parameter is proteinuria, which is the level of excess protein in the urine of a transplant recipient. Yet another example functional parameter is the time from transplant to (risk) assessment. In some embodiments, the time of risk assessment can be the time when a biopsy or blood sample is extracted or measured from a transplant recipient.

[0060] Baseline characteristics unit 130 may be configured to receive, store and / or determine one or more baseline characteristics specific to a given transplant recipient. Example baseline characteristics may include, but are not limited to, donor comorbidities, recipient comorbidities, recipient characteristics (e.g., age, sex, height, weight), causes of end-stage renal disease (including but not limited to glomerulopathy, polycystic kidney disease, diabetes, vascular disease, and others), previous transplant information (including information about previous transplants), dual transplant information (including dual kidney transplant information), donor characteristics (e.g., age, sex, height, weight, deceased, extended donor criteria, etc.), and transplant characteristics (e.g., cold ischemia time, HLA-A / B / DR mismatch, ABO incompatible transplants, graft weight, etc.). Parameters for predicted probability of transplant rejection may include one or more baseline characteristics.

[0061] The database 140 may be configured to store one or more data sets based on data from the biomarker unit 120 and / or the baseline characteristic unit 130. For example, the database 140 may store cohort data sets, such as a derivation cohort data set and a validation cohort data set. The cohort data set may include measurement information of a sample obtained from a transplant recipient, which is a recipient of an allogeneic transplant (e.g., an organ transplant, a tissue transplant, a cell transplant, etc.) from a donor. The derivation cohort data set may include data from a transplant recipient having a first characteristic (e.g., receiving a transplant during a first time period), and the validation cohort data set may include data from a transplant recipient having a second characteristic (e.g., receiving a transplant during a second time period). In some embodiments, one or more parameters (e.g., baseline characteristics, average dd-cfDNA levels or concentrations, diagnoses, transplant rejection information, etc.) of the transplant recipients in the derivation cohort may be similar to the baseline characteristics of the transplant recipients in the validation cohort (e.g., the mean plus or minus a certain percentage deviation).

[0062] Transplanted organs may include, for example, hearts, kidneys, lungs, livers, pancreas, corneas, organ systems, vascularized composite allograft transplants, intestinal transplants, or other solid organs, and combinations thereof. The transplants received by the recipient from the donor may also include other allogeneic transplants, such as bone marrow transplants, pancreatic islet cells, stem cells, skin tissue, skin cells, or xenografts.

[0063] In some embodiments, the allograft is a cell allograft, for example, a transplant comprising allogeneic cells derived from a donor. These include, but are not limited to, cells taken directly from a donor to be applied to a recipient, cells taken from a donor and genetically engineered before being applied to a recipient, cells taken from a donor and cultured before being applied to a recipient, cells taken from a donor and subjected to a manufacturing process before being applied to a recipient, and any combination thereof. Cells may also be stored before being applied to a recipient ("ready-made" cells).

[0064] The recipient of the transplant may have received one or more of a variety of allogeneic cells. Allogeneic cells may include, but are not limited to, blood cells, stem cells, cardiomyocytes, neurons, lymphocytes, NK cells, NKT cells, T regulatory cells, macrophages, dendritic cells, and islet cells. In some embodiments, allogeneic cells are allogeneic blood cells. Allogeneic blood cells may include hematopoietic stem cells (HSC), T cells, B cells and CAR T cells, NK cells, NKT cells, or TIL. In some embodiments, allogeneic cells are allogeneic T cells. In some embodiments, allogeneic cells are administered as bone marrow, cord blood, or purified allogeneic cells. In some embodiments, allogeneic cells are bone marrow cells. In some embodiments, allogeneic cells are cord blood cells. In some embodiments, allogeneic cells are allogeneic CAR T cells, allogeneic universal CAR T cells (ie, when CAR is combined with an antibody that binds to a specific antigen), allogeneic split CAR T cells (ie, when a dimerizer activates CAR T cell function), allogeneic activatable CAR T cells, allogeneic suppressive CAR T cells, allogeneic multiphase CAR T cells (ie, when CAR must be combined with a variety of specific antigens and / or agents to induce T cell activation), allogeneic tumor infiltrating lymphocytes, allogeneic regulatory T cells, allogeneic genetically modified T cells, or allogeneic T cells with genetically modified or synthetic T cell receptors (TCR), virus-specific T cells (eg, EBV, HPV, BKV, CMV, etc.), antigen-specific T cells, neoantigen-specific T cells, or any cells separated from a donor. In some embodiments, allogeneic cells are derived from donors. In some embodiments, allogeneic cells are cell allografts.

[0065] Database 140 may also store cohort transplant rejection information. Cohort transplant rejection information may include rejection results of transplant recipients in the corresponding cohort. In some embodiments, the rejection results may be based on whether the allogeneic transplant history of the transplant recipient shows an injury pattern that meets the Banff standard for active AMR (A-AMR), chronic active AMR (CA-AMR), acute TCMR or chronic active TCMR (CA-TCMR). The cohort data set obtained from database 140 may include data corresponding to individual transplant recipients in the cohort and / or representative data (e.g., mean, average, median, percentage, etc.) of a group of transplant recipients in the cohort (including all or less than all transplant recipients in the cohort).

[0066] The machine learning model 150 can be configured to receive a cohort data set from the database 140, analyze one or more sets of parameters associated with the data set, select one or more sets of parameters, and generate one or more parameter weights. The machine learning model 150 can be trained to identify associations between the cohort data set and the status of the allograft, and then generate parameter weights based on the identified associations. The machine learning model 150 can reduce the set of parameters used to generate the weights by performing one or more selection steps.

[0067] Figure 4B A flow chart of an example method performed by a machine learning model according to an embodiment of the present disclosure is shown. Method 400 may include obtaining a cohort data set from, for example, database 150 in step 402. The cohort data set may include a first set of parameters and cohort rejection information for transplant recipients in the cohort. The cohort data set may be data obtained by one or more units (e.g., biomarker unit 120 and baseline characteristics unit 130). The first set of parameters may include, but are not limited to, dd-cfDNA and one or more of the following: clinical parameters, functional parameters, immunological parameters, recipient characteristics, or transplant characteristics.

[0068] Clinical parameters may include allograft dysfunction, time since last transplant rejection, whether any previous rejection occurred, or time since transplant until assessment. Allograft dysfunction, such as renal allograft dysfunction, may refer to an increase in serum creatinine of more than 0.3 mg / liter or more than 50% from baseline serum creatinine. Baseline serum creatinine may be the lowest serum creatinine value for a given transplant recipient during, for example, the month prior to assessment, or the last known serum creatinine.

[0069] Functional parameters may include eGFR, creatinine, or proteinuria. Immunological parameters may include anti-human leukocyte antigen (HLA) donor-specific antibody mean fluorescence intensity or HLA mismatch number. Recipient characteristics may include recipient age or recipient gender. Transplant characteristics may include transplant quality, donor age, donor gender, donor type (living relative, deceased relative, living non-relative, deceased non-relative), donor weight, donor height, previous transplant information (e.g., previous kidney transplant information), cold ischemia time, or dual transplant information (e.g., dual transplant kidney information).

[0070] In step 404, the machine learning model 150 may analyze the first set of parameters for associations between the cohort data set and the corresponding cohort transplant rejection information. For each parameter in the first set of parameters, the machine learning model may determine whether there is an association with the corresponding cohort transplant rejection information. This step may include analyzing whether the parameters in the first set of parameters distinguish between the presence of transplant rejection or the absence of transplant rejection in the rejection information. In some embodiments, the first set of parameters may be analyzed individually from each other. That is, each parameter may be analyzed without considering the other parameters in the first set of parameters.

[0071] As a non-limiting example, the cohort can be a derivative cohort including 637 transplant recipients. The mean from the cohort data set is shown in Table 2. The machine-learning model 150 can analyze the diagnosis of the transplant recipient to determine that a specific parameter is not associated with transplant rejection. For example, among the 637 transplant recipients, 85 were diagnosed with active AMR, 23 were chronic AMR, seven were inactive AMR, 16 were acute TCMR, three were chronic active TCMR, seven were mixed rejection, 12 were borderline lesions, 14 were viral nephritis, 12 were glomerulonephritis without rejection, 12 were FSGS, 219 were IFTA, and 227 were non-specific lesions. The machine learning model can determine that there is little or no distinction between the presence or absence of transplant rejection. As another example, the machine learning model 150 can analyze anti-HLA DSA MFI to determine that the parameter is associated with transplant rejection. For example, among 637 transplant recipients, 383 transplant recipients had an anti-HLA DSA MFI of less than 500, 194 transplant recipients had an anti-HLA DSA MFI between 500-3000, 27 transplant recipients had an anti-HLA DSA MFI between 3000-6000, and 33 transplant recipients had an anti-HLA DSA MFI greater than 6000. The machine learning model determined that there was an association between the anti-HLA DSA MFI parameter and the presence of transplant rejection in the cohort dataset.

[0072] A dd-cfDNA level or concentration above a threshold or cutoff value may be associated with transplant rejection. In some embodiments, analyzing the first set of model parameters for association includes determining an association between the dd-cfDNA level or concentration and one or more of the following: a cause of end-stage renal disease or a type of transplant rejection.

[0073] In some embodiments, the machine learning model 150 may determine that there is a relatively low association between dd-cfDNA and one or more histological parameters. Embodiments of the present disclosure include parameter sets for calculating scores and prediction probabilities and / or generating projections that do not include histological parameters.

[0074] In step 406, the machine learning model 150 may select a second set of parameters from the first set of parameters. The second set of parameters may be selected based on satisfying one or more (first) criteria. The machine learning model 150 may select one parameter at a time for evaluation. For example, the machine learning model 150 may evaluate the first parameter to determine whether it satisfies the first criterion. The machine learning 150 may then evaluate the second parameter and determine whether it satisfies the first criterion. In some embodiments, the analysis of the first set of parameters (step 404) and the selection (step 406) may be performed together so that the results from the analysis may lead to the selection.

[0075] The selection of parameters (including the first group of parameters, the second group of parameters and / or the third group of parameters) can make there be an association between the selected parameters and transplant rejection. The level of association between the parameter and transplant rejection can be represented by one or more statistical probabilities, such as odds ratio (OR), confidence interval (CI) or p value. The odds ratio can quantify the strength of association between the parameter and transplant rejection. The confidence interval can represent the probability of the parameter in a certain interval near the mean plus or minus the standard deviation. For example, a 95% confidence interval can mean that 95% of the data for a given parameter have a value near the mean plus or minus the standard deviation.

[0076] The p-value can be a measure of the true likelihood of a difference between two sets of data. The p-value can represent the difference between the presence of transplant rejection (first data set) and the absence of transplant rejection (second data set). A smaller p-value can correspond to a larger difference. For example, a smaller p-value for a corresponding parameter means that the parameter has a greater degree of discrimination between the presence of transplant rejection and the absence of transplant rejection in the rejection information.

[0077] The one or more first criteria may include a confidence interval greater than or equal to a confidence interval threshold, a p-value less than a p-value threshold, an odds ratio greater than an odds ratio threshold, or a parameter of a combination thereof. A threshold value or threshold value generally refers to any predetermined level or range of levels that indicates the association of a parameter with the presence or absence of a risk of transplant rejection in a transplant recipient. A threshold value may take a variety of forms. It may be a single cutoff value, such as a median or mean.

[0078] The confidence interval threshold and the p-value threshold may be predetermined values, such as 95% and 0.2, respectively. In other words, those parameters with a confidence level greater than 95% and a p-value less than 0.2 may be selected to form the second set of parameters.

[0079] Embodiments of the present disclosure may include other criteria for selecting the second set of parameters, such as the number of parameters in the second set of parameters being less than a threshold number of parameters. Unselected parameters may not be considered in subsequent steps, and therefore may not be included in the calculation of the predicted probability. In some embodiments, the number of parameters in the second set of parameters may be less than the number of parameters in the first set of parameters.

[0080] Figure 5 An example data table of a second set of parameters selected from the first set of parameters for a cohort data set according to an embodiment of the present disclosure is shown. Example parameters in the second set of parameters may include, but are not limited to, dd-cfDNA levels or concentrations, allograft dysfunction, recent transplant rejection information, time from transplant-post-to-assessment, eGFR, proteinuria, mean fluorescence intensity of anti-human leukocyte antigen donor-specific antibodies, recipient age, recipient gender, donor age, donor gender, donor type, previous kidney transplant information, cold ischemia time, double transplant kidney information, and HLA mismatch number. Additional parameters may include information from a biopsy.

[0081] Return to reference Figure 4B In step 408, the machine learning model may select a third set of parameters from the second set of parameters. The third set of parameters may include independent variables associated with transplant rejection. In some embodiments, the third set of parameters may be selected based on satisfying one or more second criteria. In some embodiments, the selection of the third set of parameters may include performing a backward selection, wherein the parameters in the second set of parameters may be individually analyzed to determine whether the parameter distinguishes between the presence of transplant rejection or the absence of transplant rejection in the rejection information. Individual analysis may involve temporarily removing the parameter of interest to determine whether it has an effect on the association level. In some embodiments, each parameter may be analyzed, and then these analyses may be compared to select the third set of parameters. For example, the first analysis may involve temporarily removing the eGFR parameter and determining that the association level with the remaining parameter group is low. The machine learning model 150 may select the eGFR parameter as part of the third set of parameters. The second analysis may involve temporarily removing the time parameter from transplant to biopsy, and determining that the association level has not changed significantly, and therefore, the machine-learning model 150 may not select the time parameter from transplant to biopsy as part of the third set of parameters.

[0082] The one or more second criteria may include that the parameter has a confidence interval greater than or equal to the confidence interval threshold or a p-value less than the p-value threshold. In some embodiments, the confidence interval threshold and the p-value threshold may be predetermined values, such as 95% and 0.2, respectively. In other words, those parameters with a confidence level greater than 95% and a p-value less than 0.2 may be selected to form a second set of parameters. In some embodiments, the one or more second criteria may be the same as the one or more first criteria. In other embodiments, the one or more second criteria may have a p-value threshold less than the p-value threshold in the one or more first criteria.

[0083] Additionally or alternatively, other criteria may be used to select the third set of parameters. For example, the machine learning model 150 may select the third set of parameters based on the number of parameters in the third set of parameters being less than a predetermined number of parameters. The selected third set of parameters may be, for example, those parameters with the lowest p-values ​​in the second set of parameters (e.g., N parameters with the lowest p-values). Unselected parameters may not be considered in subsequent steps and therefore may not be included in the calculation of the predicted probability. In some embodiments, the number of parameters in the third set of parameters may be less than the number of parameters in the second set of parameters.

[0084] The machine learning model 150 may determine that a third set of parameters is highly correlated with transplant rejection. For example, the machine learning model 150 may select parameters that have the highest association with transplant rejection. These parameters may include, for example, certain baseline characteristics (e.g., transplant recipient age, previous transplant information, time from transplant to evaluation), immunological variables (e.g., number of HLA mismatches, dd-cfDNA, anti-HLA DSA information), and information about systemic infections of viruses, bacteria, fungi, and parasites that the transplant recipient may have been infected with during or after the transplant process, such as BK virus information. Infectious agents that can cause systemic infection and whose presence or levels can be tested can include, but are not limited to, viruses such as cytomegalovirus, Epstein-Barr virus, Anelloviridae, and BK virus; bacteria such as Pseudomonas aeruginosa, Enterobacteriaceae, Nocardia, Streptococcus pneumonia, Staphyloccous aureus, and Legionella; fungi such as Candida, Aspergillus, Cryptococcus, Pneumocystis carinii; or parasites such as Toxoplasma gondii.

[0085] Figure 6 An example data table of a third set of parameters selected from the second set of parameters for a cohort data set according to an embodiment of the present disclosure is shown. The example third set of parameters may include parameters such as, but not limited to, dd-cfDNA levels or concentrations, allogeneic graft dysfunction, recent transplant rejection information, and anti-HLA DSA MFI.

[0086] exist( Figure 4B In step 410 of the method, the machine learning model may generate one or more parameter weights corresponding to the third set of parameters of the cohort data set. For example, the machine learning model may generate seven parameter weights for seven parameters in the third set of parameters. The parameter weights may be selected and may correspond to the degree of association of each parameter with the allograft status (e.g., the predicted likelihood of allograft failure). For example, a first parameter may have a corresponding first parameter weight, and a second parameter may have a corresponding second parameter weight. The first parameter may have a higher degree of association with the predicted probability than the second parameter, as reflected by the first parameter weight having a higher value than the second parameter weight. Other relationships and methods for determining parameter weights may also be used. The parameter weights may be calculated using a multivariate logistic regression model.

[0087] Embodiments of the present disclosure may include training a machine learning model. The machine learning model may be trained by using a derived data set for a derivative cohort when analyzing a first set of parameters. The machine learning model may receive a derived data set for a derivative cohort and corresponding derived cohort transplant rejection information. The machine learning model may also receive a first set of parameters and may analyze the first set of parameters for an association between the derived data set and the corresponding (derivative cohort) transplant rejection information. The first set of parameters may be analyzed individually.

[0088] During the training phase, the machine learning model may select a second set of parameters from the first set of parameters, wherein the second set of parameters meets one or more first criteria. The machine learning model may then select a third set of parameters from the second set of parameters. The selected third set of parameters may include independent variables associated with transplant rejection and meet one or more second criteria. In some embodiments, the selection of parameters for the third group may be based on a degree of association. In some embodiments, the parameters selected for the third group may have a higher degree of association than unselected parameters. The machine learning model may use the third set of parameters and may generate one or more parameter weights corresponding to the third set of parameters (of the derived data set), as discussed above. The machine learning model may calculate a derivative score based on the third set of parameters of the derived data set and the calculated parameter weights.

[0089] During the validation phase, the machine learning model can be tested by applying one or more parameter weights generated from the derivative data set (during the training phase) to the third set of parameters of the validation data set. The validation phase is used to validate the trained model and ensure that the output of the machine learning model corresponds to the data used to train the model. The machine learning model can calculate a validation score and / or a corresponding allograft state (e.g., a predicted probability) based on the third set of parameters and parameter weights of the validation data set. The performance of the machine learning model can be determined by comparing the derived score and the validation score. In some embodiments, performance can be based on the distinction between the score and the area under its receiver operating characteristic (ROC) curve.

[0090] Embodiments of the present disclosure may include implementing one or more rules for selecting parameters. These rules may be implemented by criteria for one or more selection steps. For example, the criteria may involve a threshold number of parameters, a threshold degree of association, a threshold number of queues, etc.

[0091] If the machine learning model is not adequately trained, the training data (e.g., a derived data set) can be revised to provide feedback to the model. The output of the machine-learning model between training iterations can be evaluated by a physician or medical expert to determine which data in the training data should be revised. The physician or medical expert can revise certain data in areas of potential improvement, such as which parameters should have a higher degree of association.

[0092] Example Administration of Immunosuppressive Therapy

[0093] Immunosuppressive therapy generally refers to the administration of immunosuppressants or other therapeutic agents that suppress the immune response of the transplant recipient to the transplant recipient. Example immunosuppressants may include, for example, anticoagulants, antimalarials, cardiac medications, nonsteroidal anti-inflammatory drugs (NSAIDs) and steroids, including, for example, Ace inhibitors, aspirin, azathioprine, B7RP-1-fc, beta-blockers, sodium bromoquine, campath-1H, celecoxib, chloroquine, corticosteroids, warfarin, cyclophosphamide, cyclosporin A, DHEA, deoxyspergualin, dexamethasone, diclofenac, diflunisal, etodolac, everolimus, FK778, piroxicam, fenoprofen, flurbiprofen, heparin, hydralazine, hydroxychloroquine, CTLA-4 or LFA3 immunoglobulins, ibuprofen, indomethacin, ISAtx-247 , ketoprofen, ketorolac, leflunomide, meclofenamic acid, mefenamic acid, mikrin, 6-mercaptopurine, meloxicam, methotrexate, mizoribine, mycophenolate mofetil, naproxen, oxaprozin, hydroxychloroquine, NOX-100, prednisone, methylprednisolone, rapamycin (sirolimus), sulindac, tacrolimus (FK506), thymocyte globulin, tolmetin, tripelimus, UO126, and antibodies, including, for example, alpha lymphocyte antibodies, adalimumab, anti-CD3, anti-CD25, anti-CD52, anti-IL2R and anti-TAC antibodies, basiliximab, daclizumab, etanercept, hu5C8, infliximab, OKT4 and natalizumab.

[0094] In some embodiments, the lack of change in the predicted probability or the lack of difference in the predicted probability over time can indicate that the immunosuppressive therapy administered to the transplant recipient does not need to be adjusted, or that the immunosuppressive therapy administered can be maintained. The decision whether to maintain the immunosuppressive therapy administered to the transplant recipient can be based on additional clinical factors, such as the health status of the transplant recipient. In some embodiments, the immunosuppressive therapy administered to the transplant recipient is maintained.

[0095] In some embodiments, the adjustment of immunosuppressive therapy comprises changing the type or form of immunosuppressive agent or other immunosuppressive therapy administered to the transplant recipient. In some embodiments, when the transplant recipient is not receiving immunosuppressive therapy, the methods of the present disclosure may indicate the need to start administering immunosuppressive therapy to the transplant recipient.

[0096] Other transplantation-related therapies include treatments or therapies other than transplantation or immunosuppressive therapy, which are administered to transplant recipients to promote the survival of the transplant or to treat transplantation-related symptoms (e.g., cytokine release syndrome, neurotoxicity). Examples of other transplantation-related therapies include, but are not limited to, administration of antibodies, antigen-targeting ligands, non-immunosuppressive drugs, and other agents that stabilize or destabilize components of the transplant that are critical to the activity of the transplant or directly activate or inhibit the activity of one or more transplants. These activities may include the ability to induce an immune response, recognize specific antigens, replicate, and / or repair damaged tissue. Adjusting immunosuppressive therapy may be combined with adjusting, starting, or stopping other transplantation-related therapies.

[0097] The method disclosed herein can predict the probability of transplant rejection in a transplant recipient or provide a projection of risk in a transplant recipient reference set. The predicted probability and / or projection can be used to inform the need to adjust the monitoring of the transplant recipient. Generally speaking, the change in predicted risk over time is instructive for determining whether it is necessary to adjust the monitoring of the transplant recipient. In some embodiments, as described above, determining the status of the transplant is instructive for determining whether it is necessary to adjust the monitoring of the transplant recipient.

[0098] Depending on the status of the transplant, the monitoring of the transplant recipient may be adjusted accordingly. For example, the monitoring may be adjusted by appropriately increasing or decreasing the frequency of monitoring. Monitoring may be adjusted by changing the means of monitoring, for example, by changing the indicators used to monitor the transplant recipient.

[0099] Example system for calculating predicted probability of transplant rejection or generating projections

[0100] The systems and methods discussed above may be implemented via a device. Figure 7 An example device for implementing the above disclosed systems and methods according to an embodiment of the present disclosure is shown. Device 702 may be a portable electronic device, such as a mobile phone, a tablet computer, a laptop computer, or a wearable device. Device 702 may include a processor 704 (e.g., a central processing unit (CPU), a graphics processing unit (GPU) or both), a main memory 706 (e.g., a read-only memory (ROM), a flash memory, a dynamic random access memory (DRAM), such as a synchronous DRAM (SDRAM) or a Rambus DRAM (RDRAM), etc.), and a static memory 708 (e.g., a flash memory, a static random access memory (SRAM), etc.), which components may communicate with each other via a bus 710.

[0101] The device 702 may also include a display 712, an input / output device 714 (e.g., a touch screen), a transceiver 716, and a memory 718. The memory 718 includes a machine-readable medium 720 having stored thereon one or more instruction sets 724 (e.g., software) embodying any one or more of the methodologies or functions described herein. The software may also reside, in whole or in part, within the main memory 706 and / or within the processor 704 during its execution by the computer 702, the main memory 706 and the processor 704 also constituting machine-readable media. The software may also be transmitted or received over a network via a network interface device 722.

[0102] Although the machine-readable medium 720 is shown as a single medium in one embodiment, the term "machine-readable medium" should be understood to include a single medium or multiple media (e.g., a centralized or distributed database and / or associated caches and servers) storing one or more sets of instructions. The term "machine-readable medium" should also be understood to include any medium that can store, encode, or carry a set of instructions for execution by a machine and cause the machine to perform any one or more of the methods of the present invention. Therefore, the term "machine-readable medium" should include, but is not limited to, solid-state memories, optical and magnetic media, and carrier signals.

[0103] The systems and methods described herein and their data may be stored in storage device 718, main memory 706, static memory 708, or a combination thereof. Display 712 may be used to present a user interface to a physician or medical expert, and input / output device 714 may be used to receive input from the physician or medical expert (e.g., clicking on a graphical representation representing a microblog). For example, transceiver 716 may be configured to communicate with a network.

[0104] Although the examples of the present disclosure have been fully described according to the accompanying drawings, it is noted that various changes and modifications will be apparent to those skilled in the art. Such changes and modifications should be understood to be included within the scope of the examples of the present disclosure as defined by the appended claims.

Claims

1. A computer-implemented method for determining risk of transplant rejection using a machine learning system, the method comprising: receiving, via a computer or input function, transplant recipient data of a transplant recipient including a set of parameters including donor-derived cell-free DNA (dd-cfDNA); receiving one or more parameter weights; calculating a score based on the transplant recipient data and the one or more parameter weights; as well as A predicted probability of whether or to what extent transplant rejection will occur in the transplant recipient is calculated based on the score.

2. The computer-implemented method of claim 1, wherein the set of parameters for the transplant recipient data further comprises one or more of: one or more clinical parameters, including time from transplantation to evaluation; one or more functional parameters including estimated glomerular filtration rate (eGFR), creatinine, proteinuria, or a combination thereof; one or more immunological parameters including donor-specific antibody mean fluorescence intensity, anti-human leukocyte antigen (HLA) mismatch number, or both; one or more transplant recipient characteristics, including transplant recipient age, donor organ infection information, or both; One or more transplant characteristics, including prior transplant information, prior rejection information, or a combination thereof. The computer-implemented method of claim 1 , wherein the set of parameters does not include histological parameters.

4. The computer-implemented method of claim 1 , further comprising: A projection of the transplant recipient data into a reference set is generated, wherein the reference set includes one or more other transplant recipients having one or more common characteristics.

5. The computer-implemented method of claim 4, wherein the generated projections are used to explain transplant rejection mechanisms and / or to guide treatment.

6. The computer-implemented method of claim 1 , wherein calculating a score comprises: for each parameter weight, multiplying the parameter weight by the corresponding parameter of the transplant recipient data; as well as The score is calculated based on the sum of the multiplications.

7. The computer-implemented method of claim 1 , wherein calculating the predicted probability comprises: Determine the intercept of the multivariable logistic regression model; as well as The predicted probability is calculated based on the score and the intercept.

8. The computer-implemented method of claim 1 , wherein the one or more parameter weights are received from a machine learning model trained to: obtaining a cohort data set including a first set of model parameters and cohort transplant rejection information of transplant recipients in the cohort; analyzing the first set of model parameters for associations between the cohort data set and corresponding cohort transplant rejection information; selecting one or more subsequent sets of model parameters from the first set of model parameters or a previous set of model parameters; selecting a final set of model parameters from the one or more subsequent sets of model parameters, wherein the final set of model parameters includes independent variables associated with transplant rejection and satisfies one or more second criteria; and The one or more parameter weights corresponding to the last set of model parameters for the cohort data set are generated.

9. The computer-implemented method of claim 8, wherein the first set of model parameters or the one or more sets of subsequent model parameters, or both, include dd-cfDNA, and wherein the one or more sets of subsequent model parameters satisfy one or more first criteria.

10. The computer-implemented method of claim 8, wherein the first set of model parameters further comprises one or more of the following: one or more clinical parameters, including graft dysfunction, time since last graft rejection, time from transplant to evaluation, or a combination thereof; one or more functional parameters including estimated glomerular filtration rate (eGFR), creatinine, proteinuria, or a combination thereof; one or more immunological parameters including donor-specific antibody mean fluorescence intensity, anti-human leukocyte antigen (HLA) mismatch number, or a combination thereof; one or more recipient and donor characteristics, including recipient age, recipient sex, donor organ infection information, or a combination thereof; One or more transplant characteristics, including donor age, donor sex, donor type, previous transplant information, cold ischemia time, dual transplant information, or A combination of them.

11. The computer-implemented method of claim 8, wherein the one or more sets of subsequent model parameters include one or more of: dd-cfDNA, graft dysfunction, recent graft rejection information, time to evaluation after transplantation, estimated glomerular filtration rate (eGFR), proteinuria, mean fluorescence intensity of donor-specific antibodies, recipient age, recipient sex, donor age, donor sex, donor type, previous transplant information, cold ischemia time, dual transplant information, number of anti-human leukocyte antigen (HLA) mismatches, or a combination thereof.

12. The computer-implemented method of claim 8, wherein the final set of model parameters comprises one or more of: dd-cfDNA, estimated glomerular filtration rate (eGFR), graft dysfunction, recent transplant rejection information, donor-specific antibody mean fluorescence intensity, proteinuria, or a combination thereof.

13. The computer-implemented method of claim 8, wherein analyzing the first set of model parameters for association comprises analyzing whether or to what extent parameters in the first set of model parameters distinguish between the presence or absence of transplant rejection in the cohort transplant rejection information.

14. The computer-implemented method of claim 8, wherein the first set of model parameters are analyzed individually.

15. A computer-implemented method according to claim 8 or 9, wherein the one or more first criteria or the one or more second criteria include a model parameter having a confidence interval greater than or equal to a confidence interval threshold or a p-value less than a p-value threshold.

16. The computer-implemented method of claim 15, wherein the confidence interval threshold is 95% and the p-value threshold is 0.

2.

17. The computer-implemented method of claim 9, wherein the one or more first criteria include a number of model parameters in the one or more sets of subsequent model parameters being less than a threshold number.

18. The computer-implemented method of claim 8, wherein analyzing the first set of model parameters for association comprises reducing the dimensionality of the cohort data set based on the presence or absence of transplant rejection in the cohort transplant rejection information.

19. The computer-implemented method of claim 8, wherein analyzing the first set of model parameters for association comprises determining an association between the dd-cfDNA and one or more of: a cause of end-stage renal disease, a type of transplant rejection, or a combination thereof.

20. The computer-implemented method of claim 8, wherein analyzing the first set of model parameters comprises reducing the dimensionality of the cohort dataset based on a type of transplant rejection.

21. The computer-implemented method of claim 8, wherein selecting the last set of model parameters comprises: performing backward selection by analyzing whether or to what extent parameters in the one or more sets of subsequent model parameters discriminate between the presence or absence of transplant rejection in the cohort transplant rejection information; as well as The individual analyses were compared to select the final set of model parameters.

22. The computer-implemented method of claim 8, wherein the one or more second criteria include a number of model parameters in the final set of model parameters being less than a threshold number.

23. A system for classifying the status of a transplant, the system comprising: A scoring unit, wherein the scoring unit: receiving transplant recipient data of a transplant recipient including a set of parameters including donor-derived cell-free DNA (dd-cfDNA); receiving one or more parameter weights; calculating a score based on the transplant recipient data and the one or more parameter weights; as well as A predicted probability of whether or to what extent transplant rejection will occur in the transplant recipient is calculated based on the score.

24. The system of claim 23, wherein the set of parameters of the transplant recipient data further comprises one or more of: one or more clinical parameters, including time from transplantation to evaluation; one or more functional parameters including estimated glomerular filtration rate (eGFR), creatinine, proteinuria, or a combination thereof; one or more immunological parameters including donor-specific antibody mean fluorescence intensity, anti-human leukocyte antigen (HLA) mismatch number, or both; one or more transplant recipient characteristics, including transplant recipient age, donor organ infection information, or both; One or more transplant characteristics, including prior transplant information, prior rejection information, or both.

25. The system of claim 23, wherein the set of parameters does not include histological parameters.

26. The system of claim 23, further comprising means for generating a projection of the transplant recipient data in a reference set, wherein the reference set includes one or more other transplant recipients having one or more common characteristics.

27. The system of claim 26, wherein the generated projections are used to explain transplant rejection mechanisms and / or to guide treatment.

28. The system of claim 23, wherein calculating a score comprises: for each parameter weight, multiplying the parameter weight by the corresponding parameter of the transplant recipient data; as well as The score is calculated based on the sum of the multiplications.

29. The system of claim 23, wherein calculating the predicted probability comprises: Determine the intercept of the multivariable logistic regression model; as well as The predicted probability is calculated based on the score and the intercept.

30. The system of claim 23, wherein the one or more parameter weights are received from a machine learning model trained to: obtaining a cohort data set including a first set of model parameters and cohort transplant rejection information of transplant recipients in the cohort; analyzing the first set of model parameters for associations between the cohort data set and corresponding cohort transplant rejection information; selecting one or more subsequent sets of model parameters from the first set of model parameters or a previous set of model parameters; selecting a final set of model parameters from the one or more subsequent sets of model parameters, wherein the final set of model parameters includes independent variables associated with transplant rejection and satisfies one or more second criteria; and The one or more parameter weights corresponding to the last set of model parameters for the cohort data set are generated.

31. The system of claim 30, wherein the first set of model parameters or the one or more sets of subsequent model parameters, or both, include dd-cfDNA, and wherein the one or more sets of subsequent model parameters satisfy one or more first criteria.

32. The system of claim 30, wherein the first set of model parameters further comprises one or more of the following: one or more clinical parameters including graft dysfunction, time since last graft rejection, time from transplant to evaluation, or a combination thereof; one or more functional parameters including estimated glomerular filtration rate (eGFR), creatinine, proteinuria, or a combination thereof; one or more immunological parameters including donor-specific antibody mean fluorescence intensity, anti-human leukocyte antigen (HLA) mismatch number, or a combination thereof; one or more recipient and donor characteristics, including recipient age, recipient sex, donor organ infection information, or a combination thereof; One or more transplant characteristics, including donor age, donor sex, donor type, previous transplant information, cold ischemia time, dual transplant information, or A combination of them.

33. The system of claim 30, wherein the one or more sets of subsequent model parameters include one or more of: dd-cfDNA, graft dysfunction, recent graft rejection information, time to evaluation after transplantation, estimated glomerular filtration rate (eGFR), proteinuria, donor-specific antibody mean fluorescence intensity, recipient age, recipient sex, donor age, donor sex, donor type, previous transplant information, cold ischemia time, dual transplant information, number of anti-human leukocyte antigen (HLA) mismatches, or a combination thereof.

34. The system of claim 30, wherein the final set of model parameters comprises one or more of: dd-cfDNA, estimated glomerular filtration rate (eGFR), graft dysfunction, recent transplant rejection information, donor-specific antibody mean fluorescence intensity, proteinuria, or a combination thereof.

35. The system of claim 30, wherein analyzing the first set of model parameters for association comprises analyzing whether or to what extent parameters in the first set of model parameters differentiate between the presence or absence of transplant rejection in the cohort transplant rejection information.

36. The system of claim 30 or 31, wherein the one or more first criteria or the one or more second criteria include a model parameter having a confidence interval greater than or equal to a confidence interval threshold or a p-value less than a p-value threshold.

37. The system of claim 36, wherein the confidence interval threshold is 95% and the p-value threshold is 0.

2.

38. The system of claim 31 , wherein the one or more first criteria include a number of model parameters in the one or more sets of subsequent model parameters being less than a threshold number.

39. The system of claim 30, wherein the first set of model parameters are analyzed individually.

40. The system of claim 30, wherein analyzing the first set of model parameters for association comprises reducing a dimensionality of the cohort data set based on the presence or absence of transplant rejection in the cohort transplant rejection information.

41. The system of claim 30, wherein analyzing the first set of model parameters for association comprises determining an association between the dd-cfDNA and one or more of: a cause of end-stage renal disease, a type of transplant rejection, or a combination thereof.

42. The system of claim 30, wherein analyzing the first set of model parameters comprises reducing the dimensionality of the cohort dataset based on a type of transplant rejection.

43. The system of claim 30, wherein selecting the last set of model parameters comprises: performing backward selection by analyzing whether or to what extent parameters in the one or more sets of subsequent model parameters discriminate between the presence or absence of transplant rejection in the cohort transplant rejection information; as well as The individual analyses were compared to select the final set of model parameters.

44. The system of claim 30, wherein the one or more second criteria include a number of model parameters in the final set of model parameters being less than a threshold number.

45. A non-transitory computer-readable storage medium for determining risk of transplant rejection using a machine learning system, the medium storing one or more programs, the one or more programs comprising instructions that, when executed by one or more processors of an electronic device having a display, cause the electronic device to: receiving, via a computer or input function, transplant recipient data of a transplant recipient including a set of parameters including donor-derived cell-free DNA (dd-cfDNA); receiving one or more parameter weights; calculating a score based on the transplant recipient data and the one or more parameter weights; as well as A predicted probability of whether or to what extent transplant rejection will occur in the transplant recipient is calculated based on the score.

46. ​​The computer readable medium of claim 45, wherein the set of parameters for the transplant recipient data further comprises one or more of: one or more clinical parameters, including time from transplantation to evaluation; one or more functional parameters including estimated glomerular filtration rate (eGFR), creatinine, proteinuria, or a combination thereof; one or more immunological parameters including donor-specific antibody mean fluorescence intensity, anti-human leukocyte antigen (HLA) mismatch number, or both; one or more transplant recipient characteristics, including transplant recipient age, donor organ infection information, or both; One or more transplant characteristics, including prior transplant information, prior rejection information, or both.

47. The computer readable medium of claim 45, wherein the set of parameters does not include histological parameters.

48. The computer-readable medium of claim 45, further comprising: A projection of the transplant recipient data into a reference set is generated, wherein the reference set includes one or more other transplant recipients having one or more common characteristics.

49. The computer readable medium of claim 48, wherein the generated projections are used to explain transplant rejection mechanisms and / or to guide treatment.

50. The computer readable medium of claim 45, wherein calculating a score comprises: for each parameter weight, multiplying the parameter weight by the corresponding parameter of the transplant recipient data; as well as The score is calculated based on the sum of the multiplications.

51. The computer readable medium of claim 45, wherein calculating the predicted probability comprises: Determine the intercept of the multivariable logistic regression model; as well as The predicted probability is calculated based on the score and the intercept.

52. The computer-readable medium of claim 45, wherein the one or more parameter weights are received from a machine learning model trained to: obtaining a cohort data set including a first set of model parameters and cohort transplant rejection information of transplant recipients in the cohort; analyzing the first set of model parameters for associations between the cohort data set and corresponding cohort transplant rejection information; selecting one or more subsequent sets of model parameters from the first set of model parameters or a previous set of model parameters; selecting a final set of model parameters from the one or more subsequent sets of model parameters, wherein the final set of model parameters includes independent variables associated with transplant rejection and satisfies one or more second criteria; and The one or more parameter weights corresponding to the last set of model parameters for the cohort data set are generated.

53. The computer-readable medium of claim 52, wherein the first set of model parameters or the one or more sets of subsequent model parameters, or both, comprise dd-cfDNA, and wherein the one or more sets of subsequent model parameters satisfy one or more first criteria.

54. The computer-readable medium of claim 52, wherein the first set of model parameters further comprises one or more of: one or more clinical parameters including graft dysfunction, time since last graft rejection, time from transplant to evaluation, or a combination thereof; one or more functional parameters including estimated glomerular filtration rate (eGFR), creatinine, proteinuria, or a combination thereof; one or more immunological parameters including donor-specific antibody mean fluorescence intensity, anti-human leukocyte antigen (HLA) mismatch number, or a combination thereof; one or more recipient and donor characteristics, including recipient age, recipient sex, donor organ infection information, or a combination thereof; One or more transplant characteristics, including donor age, donor sex, donor type, previous transplant information, cold ischemia time, dual transplant information, or A combination of them.

55. The computer readable medium of claim 52, wherein the one or more sets of subsequent model parameters include one or more of: dd-cfDNA, graft dysfunction, recent graft rejection information, time to evaluation after transplant, estimated glomerular filtration rate (eGFR), proteinuria, donor-specific antibody mean fluorescence intensity, recipient age, recipient sex, donor age, donor sex, donor type, previous transplant information, cold ischemia time, dual transplant information, number of anti-human leukocyte antigen (HLA) mismatches, or a combination thereof.

56. The computer-readable medium of claim 52, wherein the final set of model parameters comprises one or more of: dd-cfDNA, estimated glomerular filtration rate (eGFR), graft dysfunction, recent transplant rejection information, donor-specific antibody mean fluorescence intensity, proteinuria, or a combination thereof.

57. The computer-readable medium of claim 52, wherein analyzing the first set of model parameters for association comprises analyzing whether or to what extent parameters in the first set of model parameters differentiate between the presence or absence of transplant rejection in the cohort transplant rejection information.

58. A computer-readable medium according to claim 52 or 53, wherein the one or more first criteria or the one or more second criteria include a model parameter having a confidence interval greater than or equal to a confidence interval threshold or a p-value less than a p-value threshold.

59. The computer-readable medium of claim 58, wherein the confidence interval threshold is 95% and the p-value threshold is 0.

2.

60. The computer-readable medium of claim 53, wherein the one or more first criteria include a number of model parameters in the one or more sets of subsequent model parameters being less than a threshold number.

61. The computer readable medium of claim 52, wherein analyzing the first set of model parameters for association comprises reducing a dimensionality of the cohort data set based on the presence or absence of transplant rejection in the cohort transplant rejection information.

62. The computer-readable medium of claim 52, wherein analyzing the first set of model parameters for association comprises determining an association between the dd-cfDNA and one or more of: a cause of end-stage renal disease, a type of transplant rejection, or a combination thereof.

63. The computer readable medium of claim 52, wherein analyzing the first set of model parameters comprises reducing the dimensionality of the cohort dataset based on a type of transplant rejection.

64. The computer-readable medium of claim 52, wherein selecting the last set of model parameters comprises: performing backward selection by analyzing whether or to what extent parameters in the one or more sets of subsequent model parameters discriminate between the presence or absence of transplant rejection in the cohort transplant rejection information; as well as The individual analyses were compared to select the final set of model parameters.

65. The computer-readable medium of claim 52, wherein the one or more second criteria include a number of model parameters in the final set of model parameters being less than a threshold number.

Images