Patient population flow modeling

Abstract

Techniques are disclosed for patient population flow modeling in which such modeling may provide insights to future trends in a patient population, e.g., to facilitate allocation of resources to a patient population or notification of treatment suggestions to a patient. A flow model may be used on a dialysis patient population in which patients are grouped into compartments according to a certain criterion (or a given criterion), in which each compartment corresponds to the number of patients in each group, and in which the number of compartments may vary according to the given criterion. Models may then be used to describe slew rates between different compartments, as well as inflow and outflow flows in each compartment. Such models may be used, for example, to study the effect of sodium-glucose cotransporter 2 (SGLT2) inhibitors on the population dynamics of end-stage nephropathy patients.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to U.S. Provisional Patent No. 63 / 345,105, filed on May 24, 2022, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present disclosure relates generally to techniques for modeling the flow of a patient population, e.g., for efficiently and effectively allocating resources to care for a patient population and / or to inform recommendations for patient treatment. Background Art

[0004] Diabetes mellitus (DM) is common in patients with chronic kidney disease (CKD) and is associated with excess cardiovascular (CV) morbidity and mortality. Sodium-glucose cotransporter 2 inhibitors (SGLT2i) may have a beneficial effect on morbidity and mortality in patients with DM, CV disease, and CKD. There is a need for techniques to predict the impact of SGLT2i use, especially on the demographics of dialysis patients. Summary of the invention

[0005] This teaching includes the technology for patient population flow modeling, and this technology can provide valuable insights about the future trend of patient population, so that resources can be appropriately allocated to care for patient population and / or inform treatment suggestions.For example, the flow modeling of population dynamics can be used for dialysis patient population, wherein, according to given attributes or standards (or given standards), patients are grouped. A flow model can be used, wherein, according to given attributes, patients are grouped into compartments, and wherein, each compartment corresponds to the number of patients in each group. According to the attribute of interest, the number of compartments in which the patient population is grouped can vary. Then the flow model can be used to describe the conversion rate between different compartments and the inflow and outflow of each compartment.For example, this model can be used to study the impact of sodium-glucose cotransporter 2 (SGLT2) inhibitors on the dynamics of end-stage renal disease patient populations.

[0006] In one aspect, a computer program product disclosed herein may include computer executable code contained in a non-transitory computer readable medium, which, when executed on one or more computing devices, performs the following steps: creating a plurality of compartments of a dialysis patient from dialysis patient statistics based on one or more shared attributes from a plurality of attributes associated with the dialysis patient; receiving historical data associated with the dialysis patient statistics and the one or more shared attributes; creating a flow model describing one or more dynamic activities between the plurality of compartments, the one or more dynamic activities including transition rates between the compartments, inflow flows into the compartments, and outflow flows out of the compartments over time, wherein the flow model includes a plurality of model parameters, each model parameter being associated with the one or more dynamic activities; formatting the historical data into a first set of model parameters; inputting the first set of model parameters into the flow model; identifying a second set of model parameters, each second model parameter being dependent on a treatment for the dialysis patient; analyzing the flow model to determine a predicted effect of the treatment on the second set of model parameters; and outputting population data for the plurality of compartments from the flow model, wherein a dialysis patient in one or more of the plurality of compartments is given the treatment. Aspects similarly include a method comprising one or more of the foregoing steps performed by executed code.

[0007] Embodiments may include one or more of the following features. Analyzing the flow model may include determining a differential predicted impact of a second model parameter. The computer program product may also include code that, when executed on one or more computing devices, performs a step of providing an initial estimate of one or more second model parameters before analyzing the flow model. The one or more shared attributes may include at least one of a medical diagnosis, a treatment indication, and a current treatment. The computer program product may also include code that, when executed on one or more computing devices, performs a step of outputting population data including time correlation from the flow model. The computer program product may also include code that, when executed on one or more computing devices, performs a step of receiving updated historical data and changing one of a plurality of compartments, a plurality of attributes, and a first set of model parameters based on the updated historical data. Analyzing the flow model may include changing a treatment inclusion rate. Analyzing the flow model may include performing a sensitivity analysis on a plurality of model parameters. The sensitivity analysis may identify one or more model parameters affected by a sodium-glucose cotransporter 2 inhibitor. The treatment may include at least one of a sodium-glucose cotransporter 2 inhibitor medication and dialysis.

[0008] In one aspect, a system disclosed herein may include: a database connected to a network, the database including data related to a plurality of dialysis patients, the data including a plurality of attributes of the plurality of dialysis patients; and a processor and a memory. The memory may store computer executable code contained in a non-transitory computer readable medium, which, when executed by a processor, performs the following steps: creating a plurality of compartments of a dialysis patient from dialysis patient statistics based on one or more shared attributes from a plurality of attributes associated with the dialysis patient; receiving historical data associated with the dialysis patient statistics and the one or more shared attributes; creating a flow model describing one or more dynamic activities between the plurality of compartments, the one or more dynamic activities including transition rates between compartments, inflow flows into compartments, and outflow flows out of compartments over time, wherein the flow model includes a plurality of model parameters, each model parameter being associated with the one or more dynamic activities; formatting the historical data into a first set of model parameters; inputting the first set of model parameters into the flow model; identifying a second set of model parameters, each second model parameter being dependent on a treatment for the dialysis patient; analyzing the flow model to determine a predicted effect of the treatment on the second set of model parameters; and outputting population data for the plurality of compartments from the flow model, wherein a dialysis patient in one or more of the plurality of compartments is given the treatment.

[0009] In one aspect, the methods disclosed herein may include: creating multiple compartments of a dialysis patient from dialysis patient statistics based on one or more shared attributes from a plurality of attributes associated with the dialysis patient; creating a flow model featuring the multiple compartments, the flow model identifying one or more dynamic activity patterns between the compartments; analyzing the flow model to calculate transition rates between the compartments, inflow flows into the compartments, and outflow flows out of the compartments over time; and using the transition rates, inflow flows, and outflow flows to determine a predicted impact of a treatment used by multiple dialysis patients having at least one of the plurality of attributes. Various aspects may similarly include a computer program product comprising computer executable code contained in a non-transitory computer readable medium, which, when executed on one or more computing devices, performs one or more steps of the above method.

[0010] Embodiments may include one or more of the following features. Treatment may include use of a sodium-glucose co-transporter 2 inhibitor. The method may also include providing a recommendation for resource allocation to one or more of a plurality of dialysis patients having at least one of a plurality of attributes based on the predicted impact of treatment. The method may also include predicting end-stage renal disease events. The method may also include determining the prevalence of a particular event for patients within at least one of a plurality of compartments. The particular event may include an end-stage renal disease event. At least a portion of the dialysis patient demographics and a plurality of attributes may be included in the organization's historical data and / or synthesized data. A plurality of compartments may be created from a group of dialysis patient demographics.

[0011] In one aspect, a system disclosed herein may include: a database connected to a network, the database including data related to a plurality of dialysis patients, the data including a plurality of attributes of the plurality of dialysis patients; and a processor and a memory. The memory may store computer executable code contained in a non-transitory computer readable medium, which, when executed by the processor, performs the following steps: creating a plurality of compartments of dialysis patients from a plurality of dialysis patients in the database, wherein the patients in each compartment of the plurality of compartments include one or more shared attributes from the plurality of attributes; creating a flow model featuring the plurality of compartments, the flow model identifying one or more dynamic activity patterns between the compartments; analyzing the flow model to calculate transition rates between the compartments, inflow flows into the compartments, and outflow flows out of the compartments over time; and using the transition rates, inflow flows, and outflow flows to determine a predicted impact of a treatment used by a plurality of dialysis patients having at least one of the plurality of attributes.

[0012]

[0011] These and other features, aspects, and advantages of the present teachings will become better understood with reference to the following description, examples, and appended claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The foregoing and other objects, features and advantages of the devices, systems and methods described herein will become apparent from the following description of specific embodiments thereof, as illustrated in the accompanying drawings. The accompanying drawings are not necessarily drawn to scale, but emphasis is placed on illustrating the principles of the devices, systems and methods described herein. In the accompanying drawings, the same reference numerals generally represent corresponding elements.

[0014] Figure 1 A schematic diagram of a flow model according to a representative embodiment is shown.

[0015] Figure 2 is a flow chart of a method for modeling a patient population, according to a representative embodiment.

[0016] Figure 3A graph illustrating an example of a sensitivity analysis of model parameters according to a representative embodiment.

[0017] Figure 4 Included is a simulated graph showing exemplary effects of a sodium-glucose co-transporter 2 (SGLT2) inhibitor at different times according to a representative embodiment.

[0018] Figure 5 A graph showing changes in an end-stage renal disease (ESRD) patient population over time according to a representative embodiment.

[0019] Figure 6 Included are graphs showing model output simulating the effect of sodium-glucose co-transporter 2 inhibitor treatment in reducing mortality and disease progression rates according to a representative embodiment.

[0020] Figure 7 Included are graphs showing model output simulating the effect of SGLT2 inhibitor treatment in reducing mortality and progression to dialysis rates according to a representative embodiment.

[0021] Figure 8 Included are graphs showing different effects of model parameters according to a representative embodiment.

[0022] Fig. 9 is a flow chart of a method for modeling a patient population, according to a representative embodiment.

[0023] Fig.10 A system for patient population flow modeling according to a representative embodiment is shown. DETAILED DESCRIPTION

[0024] Embodiments will now be described more fully below with reference to the accompanying drawings, in which preferred embodiments are shown. However, the foregoing may be implemented in many different forms and should not be construed as being limited to the illustrated embodiments set forth herein. On the contrary, these illustrated embodiments are provided to convey the scope of the present disclosure to those skilled in the art.

[0025] All documents mentioned herein are incorporated herein by reference in their entirety. References to singular items should be understood to include the plural items, and vice versa, unless otherwise expressly stated or clear from the context. Grammatical conjunctions are intended to express any and all disjunctive and conjunctive combinations of the connected clauses, sentences, words, etc., unless otherwise stated or clear from the context. Thus, the term "or" should generally be understood to mean "and / or" and the like.

[0026] Unless otherwise specified herein, the enumeration of numerical ranges herein is not intended to be limiting, but to indicate any and all values ​​falling within the range individually, and each individual value within the range is incorporated into the specification as if it were individually listed herein. When accompanied by numerical values, the words "approximately", "approximately", etc. should be interpreted as indicating deviations, which are understood by those of ordinary skill in the art and can still operate satisfactorily for the intended purpose. Similarly, when used with reference to physical properties, approximate words such as "approximately", "approximately", or "substantially" should be understood as deviation ranges understood by those of ordinary skill in the art, which can still operate satisfactorily for the corresponding uses, functions, purposes, etc. The range of values ​​and / or numerical values ​​is provided here only as an example and does not constitute a limitation on the scope of the described embodiments. Where a numerical range is provided, they are also intended to include each numerical value within the range, as if proposed individually, unless there is a clear statement to the contrary. The use of any and all examples or exemplary language ("for example", "such as", etc.) provided herein is only to better illustrate the embodiments, rather than to limit the scope of the embodiments. No language in the specification should be construed as indicating any non-claimed element as essential to the practice of the embodiment.

[0027] In the following description, it should be understood that terms such as "first", "second", "top", "bottom", "upper", "lower", etc. are convenient terms and should not be construed as limiting terms unless there is a specific description to the contrary.

[0028] In general, the devices, systems, and methods disclosed herein relate to techniques for patient population flow modeling, and their use for healthcare resource allocation, treatment, and the like. That is, the patient population flow modeling disclosed herein can provide valuable insights to relatively accurately predict future trends in a patient population, for example, to efficiently and effectively allocate resources to care for a patient population and / or provide treatment recommendations to patients. For example, flow modeling of population dynamics can be used for a dialysis patient population, wherein patients are grouped according to given criteria or attributes. In some aspects, a flow model can be used, wherein patients are grouped into compartments according to certain shared attributes, wherein each compartment corresponds to the number of patients in each group, and wherein the number of compartments can vary according to given criteria. The model can then be used to determine the conversion rates between different compartments, as well as the inflow and outflow flows into and out of the compartments. For example, such a model can be used to study the effects of sodium-glucose cotransporter 2 (SGLT2) inhibitors on the dynamics of a dialysis patient population.

[0029] SGLT2 inhibitors are a group of drugs that have beneficial effects on morbidity and mortality in patients with diabetes, cardiovascular (CV) disease, and chronic kidney disease (CKD). SGLT2 inhibitors can reduce cardiovascular events and improve renal outcomes. See, for example, "SGLT2 inhibitors: risk of diabetic ketoacidosis," MIMS (June 30, 2015), available from https: / / www.mims.co.uk / sglt2-inhibitors-risk-diabetic-ketoacidosis / diabetes / arti cle / 1353980, the entire contents of which are incorporated herein by reference. Some examples of renal and cardiovascular outcomes associated with the use of SGLT2 inhibitors are described in AnneMarie B van der Aart-van der Beek, de Boer, RA, and Heerspink, HJ, Nature Reviews, Nephrology, 18: 294-206 (2022), the entire contents of which are incorporated herein by reference.

[0030] Therefore, it should be understood that SGLT2 inhibitor used herein generally includes a class of medicines that can reduce blood sugar, for example, for adults suffering from type 2 diabetes. SGLT2 inhibitor class medicines can include for example canagliflozin, dapagliflozin and empagliflozin, which are usually provided as single component products, and can also be used in combination with other drugs such as metformin. SGLT2 inhibitors can be used to reduce blood sugar by making kidneys excrete sugar from the body through urine. Using the teaching of the present invention, the impact of SGLT2 inhibitors (and / or other drug treatments, therapy, treatment, etc.) in certain patient populations can be determined, wherein, such insights can be used for these same populations or other similar patient populations to be efficiently and effectively treated, prescribe, distribute, etc. Therefore, the target of this teaching can include the ability of the extensive use of prediction SGLT2 inhibitors to the impact of CKD progress and / or to the cascade effect of dialysis population evolution.

[0031] This teaching is generally based on the use of mathematical models, which describe the dynamics of the different stages of a subject from health through metabolism, cardiovascular disease and kidney disease to dialysis. The model can describe the conversion of a subject from health to dialysis. And this conversion can be based on different and roughly known rates, which may be affected by treatment and other factors. Therefore, this teaching can include the development of a favorable model, which provides insights into the impact of SGLT2i on dialysis population counts, wherein historical data (e.g., internal data from an organization) can be used to understand the evolution of dialysis patient quantity over time.

[0032] Figure 1 A schematic diagram of a flow model 100 according to a representative embodiment is shown. As described above, in one aspect, a patient flow model is applied to reveal insights about the development of an SGLT2 inhibited dialysis population. Therefore, for the present teachings, the effects of SGLT2 inhibitors on the dynamics of a dialysis patient population were studied, and it should be understood that the following description describes the study by way of example and not limitation. One purpose of the example investigation is to estimate future trends so that resources available for the care of dialysis patients can be appropriately allocated. Another purpose of the example investigation is to improve decision making around patient treatment and treatment recommendations. To this end, a flow model was developed for dialysis patients, wherein patients are grouped according to a plurality of compartments 110, and wherein each compartment corresponds to the number of patients in each group. A schematic diagram of the flow model 100 is included in Figure 1 In the example schematic diagram, the colony is divided into five compartments 110, that is, the colony includes: no chronic kidney disease (i.e., non-CKD) patient with SGLT2 inhibitor indication, chronic kidney disease (CKD) patient with SGLT2 indication, CKD patient without SGLT2 inhibition indication, occasional dialysis patient and popular dialysis patient. The colony of occasional dialysis and popular dialysis compartments can be collectively referred to as total dialysis colony in this article. The model describes the conversion rate 120 between different compartments, as well as the inflow flow 122 of the inflow compartment 110 and the outflow flow 124 leaving the compartment 110.

[0033] in other words, Figure 1 An example of a model schematic diagram of the flow of patients using SGLT2 inhibitors is shown, wherein the population is grouped into a general population and a dialysis population. The general population is subdivided into three categories, i.e., patients with and without SGLT2 inhibition indications and patients with and without CKD, and the dialysis population is subdivided into occasional dialysis patients and prevalent dialysis patients.

[0034] Mathematical model can be used, and described model combines the current trend of the subgroup population of common colony and dialysis patient.In order to simplify the colony statistical characteristics, colony can be divided into the colony group with SGLT2i indication and the colony group without SGLT2i indication.For example, the colony with SGLT2i indication can include obesity and diabetic patients, and the colony without SGLT2i indication can include the patient with other potential CKD pathogenesis, for example the genetic cause of CKD.Use these classifications, the non-CKD patient with SGLT2i indication can leave described compartment by death, or progresses to the CKD classification with SGLT2i indication and leaves described compartment.

[0035] The flow model may include multiple model parameters 130, each model parameter being related to dynamic activities such as the transition rate 120 between compartments over time, the inflow rate 122 into a compartment, or the outflow rate 124 out of a compartment. For example, in the flow model 100 shown in the figure, the model parameters 130 include: "Λ1", representing the inflow rate 122 of new patients into the compartment 110 "non-CKD with SGLT2i indication"; "α", representing the transition of patients between the compartment 110 "CKD with SGLT2i indication" and the compartment 110 "CKD without SGLT2i indication"; and "μ4", representing the outflow rate 124 of patients out of the compartment 110 "incidental dialysis" due to death. Along Figure 1 The arrows indicate additional model parameters 130. In the figure, arrows pointing toward compartment 110 indicate patient gains (e.g., inflow flow 122), and arrows pointing away from compartment 110 indicate patient losses from compartment 110 (e.g., outflow flow 124). The dashed arrows represent model parameters 130 that are expected to be affected by SGLT2 inhibitors. These include: "μ1", representing the outflow flow of patients out of the compartment "non-CKD with SGLT2i indication" due to death; "γ1", representing the transition of patients between the compartment "non-CKD with SGLT2i indication" and the compartment "CKD with SGLT2i indication"; "μ2", representing the outflow flow of patients out of the compartment "CKD with SGLT2i indication" due to death; and "d1", representing the transition of patients between the compartment "CKD with SGLT2i indication" and the compartment "incidental dialysis". Some model parameters 130 associated with the transition rate 120 between the compartments 110 may indicate a unidirectional transition (e.g., d1), while other model parameters 130 may indicate a bidirectional transition (e.g., α). In general, the model parameters 130 associated with the inflow rate 122 into the compartment 110 or the outflow rate 124 out of the compartment 110 represent a unidirectional flow of the patient population.

[0036] The flow model 100 may include transitions between compartments 110, ultimately leading to a dialysis population. The model can be used to predict end-stage renal disease (ESRD) events and their prevalence. Previous estimates from ESRD studies can be used to improve estimates of different ratios (e.g., τ1 - incidental dialysis outflow flow, or τ2 - prevalent dialysis outflow flow due to organ transplantation). Using these ratios, it can be shown that the model accurately describes the population dynamics of ESRD events and their prevalence (see also below for Figure 5 for discussion).

[0037] Figure 2 is a flow chart of a method 200 for modeling a patient population according to a representative embodiment. The method 200 may utilize any of the models described herein, such as those described in reference Figure 1 The flow model 100 described herein. The method 200 may be performed using a system (e.g., reference Fig.10 In general, method 200 represents a technique for analyzing patient population dynamics in response to changes in flow model parameters (wherein the model parameters may, for example, be affected by a particular treatment, in other words, by a particular treatment applied to the patient).

[0038] As shown in step 202, method 200 may include creating compartments, such as Figure 1 Multiple compartments 110 of dialysis patients shown. Dialysis patients may be associated with multiple attributes. Attributes can describe, for example, medical diagnoses or conditions (e.g., CKD, diabetes (DM), heart conditions, etc.); treatment indications or lack of treatment indications (e.g., SGLT2 indications, non-indications for SGLT2); current treatments (e.g., occasional dialysis, popular dialysis, etc.); biological attributes, such as age, gender, genetic factors, height, weight, other population demographic data, etc.; attributes that may have an impact on treatment, such as place of residence, physical ability, etc.; and others. Each compartment can be based on one or more shared attributes of patients within the compartment. In one example, each of the multiple compartments can include medical diagnoses and treatment indications shared by patients within the compartment. In another example, each of the multiple compartments can include current treatments and biological attributes shared by patients within the compartment. The technician will understand that the structure of the compartments and / or the selection of shared attributes included in each compartment can be selected based on the specific determinations and / or predictions that the technician expects to obtain from the model.

[0039] Population statistics for use in flow models, such as dialysis patient statistics, etc., may be retrieved from a database, such as any of the databases described herein. For example, a treatment provider, medical practitioner, equipment supplier, etc. may store information related to a plurality of patients in a database, wherein such a database (or another available database) may also include attributes thereof that may be used to segment populations as described herein. Such a database and / or another database may also or alternatively include historical data as described below.

[0040] As shown in step 204, method 200 may include receiving historical data related to dialysis patient demographics and / or one or more shared attributes. For example, the historical data may relate to the prevalence of a certain attribute in a patient population, the transition rate between compartments (e.g., Figure 1 The historical data may be obtained from, for example, medical or other relevant literature, internal data of an organization, and / or other sources. The historical data may be received by a computing resource of the system, such as Fig.10A remote computing resource 1020 of the system 1000; and / or may be stored in a database of the system, such as a database 1030 of the system 1000.

[0041] As shown in step 206, method 200 may include creating a flow model that describes one or more dynamic activities between multiple compartments (e.g., flow model 100 that describes dynamic activities between compartments 110). The dynamic activities described by the flow model may include transition rates between compartments over time (e.g., transition rate 120), rates of flow into compartments (e.g., inflow rate 122), and / or rates of flow out of compartments (e.g., outflow rate 124). In a basic example of such a flow model, the model may include bidirectional transition rates between all combinations of two compartments, at least one inflow rate into each compartment, and at least one outflow rate out of each compartment. Thus, such a model will take into account all possible dynamic activities of a patient associated with multiple compartments. Thus, in general, a flow model may include multiple model parameters, each model parameter being associated with one or more of these dynamic activities. In a more refined example of a flow model, for example Figure 1 In the flow model 100, prior knowledge about the possible or probable flow of patients between compartments can be used to create the flow model (e.g., depending on the properties of the compartments, it may be impossible or unreasonable for patients to switch between all possible combinations of compartments). In some aspects, the flow model can describe the flow of patients between compartments based on time correlation, for example, the flow model can describe the rate of transition between two specific compartments based on the number of patients transitioned per patient population per unit time (e.g., N / 1000 / year). The flow model can also or alternatively describe other factors that affect the patient population within a compartment.

[0042] As shown in step 208, the method 200 may include formatting the historical data into a first set of model parameters. The step may include one or more of the following steps: data preprocessing (e.g., normalization or scaling of the data), extracting relevant features or variables from the raw data, data encoding (e.g., encoding categorical or text data into digital representations), formatting the data into an appropriate input format required by the model (e.g., ensuring that the data matches the expected data type and data structure of the model), etc. In addition, the specific aspects of formatting the historical data for the flow model may vary depending on the programming language and / or framework used to implement the flow model.

[0043] As shown in step 210, method 200 may include inputting a first set of model parameters into a flow model, for example, where the first set of model parameters is based on historical data. Depending on the specific model configuration, the steps may include any of: initializing the flow model, establishing necessary configurations for the model, and model training. The steps may also include passing the first set of model parameters as input variables to one or more functions or methods of an input layer representing the flow model. In some cases, inputting the first set of model parameters may also or alternatively include batching data for efficient processing, manipulating data streams or real-time inputs, and ensuring that model parameters are fed to the model in the correct order. This may also or alternatively include using synthetic data (e.g., see https: / / en.wikipedia.org / wiki / Synthetic_data, where it should be understood that medical data may be protected, so "synthetic" data sets are used instead).

[0044] As shown in step 212, method 200 may include identifying a second set of model parameters. The second set of model parameters may include parameters that depend on the specific scenario being analyzed. For example, each second model parameter may depend on treatment of a group of dialysis patients, such as treatment with SGLT2i. Figure 1 In the flow model 100, the second model parameter set may include: γ1, representing the progression of patients to CKD; d1, representing the progression of patients to dialysis; μ1, representing the mortality rate of patients with DM or cardiovascular disease; and μ2, representing the mortality rate of patients with CKD. With the introduction of SGLT2i therapy, any of these parameters may decrease or slow down.

[0045] As shown in step 214, method 200 may include providing an initial estimate of one or more second model parameters. Depending on the specific type of model implementation (e.g., a machine learning model), the steps may be performed optionally. For example, the initial estimate may be derived from available data such as historical data. As the model progresses, the second model parameters may be updated based on the initial estimate.

[0046] As shown in step 216, method 200 may include analyzing the flow model to determine the predicted impact of treatment on the second model parameter set (e.g., in the case of flow model 100, the predicted impact of treatment with SGLT2 inhibitors). The step may include, for example, analyzing the model by considering a single medical effect (e.g., the impact of reducing CKD patient mortality, or the impact of reducing dialysis progression rate). The step may also or alternatively include determining the differential predicted impact of the second model parameter. For example, with reference to flow model 100, the impact of SGLT2i on dialysis population counts may be enhanced to varying degrees by reducing mortality in the CKD population (second model parameter μ2), which may have the effect of increasing the dialysis population, and progressing from the CKD stage to dialysis (second model parameter d1), which may have the effect of reducing the dialysis population. Analyzing the flow model may further include changing the treatment inclusion rate. For example, different portions of the patient population included in the compartment with SGLT2i treatment indications may be given the indicated treatment (e.g., in different model scenarios, 20%, 50%, 100% or other portions of the population may be given treatment). Thus, observable combinations for determining the predicted impact of a treatment by analyzing the flow model may include: no change; faster / slower progression, same mortality rate; same progression, higher / lower mortality rate; or faster / slower progression, higher / lower mortality rate.

[0047] The analysis flow model can also or alternatively include multiple model parameters (e.g., the first model parameter set, the second model parameter set or both) being subjected to sensitivity analysis. This method can provide how the change of parameter value affects the prediction or other output understanding of the model. For example, the sensitivity analysis of flow model 100 can identify one or more model parameters affected by SGLT2 inhibitors. Sensitivity analysis can, for example, include single parameter sensitivity analysis, multi-parameter sensitivity analysis, Monte Carlo simulation, global sensitivity analysis, etc.

[0048] As shown in step 218, the method 200 may include outputting population data from the flow model. For example, the flow model 100 may output population data for multiple compartments 110. The population data output may include one or more compartments having patients (e.g., dialysis patients) that are modeled as receiving a particular treatment (e.g., SGLT2i treatment). For example, scenarios may be modeled for different acceptance rates (the percentage of the patient population that actually receives treatment in a compartment with an indication for treatment). A scenario with a 0% acceptance rate (no patients receiving treatment) may be helpful in assessing baseline conditions. Other scenarios may include non-zero acceptance rates, such as, for example, regarding Figure 4 The population data output may include the population of each compartment after a predetermined period of time (e.g., Figure 41, 5, 10 and 15 years of population data output are shown in FIG. 1 ). In some cases, the population data output may include time correlations, in other words, the population data may include time-related ratios or may be a function of time. Figure 6 An example of population data as a function of time is shown and described, where graphs 630 and 660 show a dialysis population over a 0-40 month time period.

[0049] In some cases, method 200 may include iterative processing of one or more steps described herein. For example, after initially inputting a first set of model parameters based on historical data (or synthetic data) in step 210, a user or system may receive updated historical data in a manner similar to that described in step 204. The user or system may then perform any other steps of method 200 again based on the updated historical data. Thus, the method may include changing one or more of the plurality of compartments, the plurality of attributes, and the first set of model parameters based on the updated historical data.

[0050] It should be understood that the method 200 may be performed using a computer program product. For example, a computer program product comprising computer executable code contained in a non-transitory computer readable medium, when executed on one or more computing devices, the code can perform any steps of method 200, including, for example: creating a plurality of compartments of a dialysis patient from dialysis patient statistics based on one or more shared attributes from a plurality of attributes associated with the dialysis patient; receiving historical data associated with the dialysis patient statistics and the one or more shared attributes; creating a flow model describing one or more dynamic activities between the plurality of compartments, the one or more dynamic activities including transition rates between the compartments, inflow flows into the compartments, and outflow flows out of the compartments over time, wherein the flow model comprises a plurality of model parameters, each model parameter being associated with the one or more dynamic activities; formatting the historical data into a first set of model parameters; inputting the first set of model parameters into the flow model; identifying a second set of model parameters, each second model parameter being dependent on a treatment for the dialysis patient; analyzing the flow model to determine a predicted effect of the treatment on the second set of model parameters; and outputting population data for the plurality of compartments from the flow model, wherein a dialysis patient in one or more of the plurality of compartments is given the treatment. It should also be understood that the method 200 can be implemented using a system, such as any of the systems described herein. For example, such a system may include a database, a processor, and a memory, wherein the memory stores computer executable code contained in a non-transitory computer readable medium, which, when executed by the processor, performs the steps of the method 200.

[0051] Figure 3A flow model according to a representative embodiment is shown (eg, Figure 1 Graph 300 of an example of a sensitivity analysis of model parameters of the flow model 100 of FIG. 1 with respect to the total dialysis population. Thus, the model parameters 330 correspond to Figure 1 Model parameters 130. The stars or asterisks in the figure represent parameters affected by SGLT2 inhibitors, specifically: d1, γ1, μ2 and μ1. Therefore, as shown in the figure, multiple sensitivity analyses were performed to determine the impact of parameter changes on the total dialysis population. As indicated by the size of sensitivity bar 302, several parameters are predicted to have a relatively strong impact (e.g., d2, d1, γ2, μ5, μ2, and Λ2) on the total dialysis population. However, among the four parameters affected by SGLT2 inhibitors, only two parameters (d1 and μ2, as shown by the double asterisks) are expected to have a relatively strong impact on the total dialysis population. Therefore, the sensitivity analysis shows that changes in d1 and μ2 values ​​may have a relatively significant impact on the prediction of population changes caused by the use of SGLT2 inhibitors.

[0052] Figure 4 Included is a simulation chart showing an exemplary effect of a sodium-glucose cotransporter 2 (SGLT2) inhibitor at different times according to a representative embodiment. Specifically, Figure 400 shows the effect at 1 year from the start of treatment, Figure 410 shows the effect at 5 years from the start of treatment, Figure 420 shows the effect at 10 years from the start of treatment, and Figure 440 shows the effect at 15 years from the start of treatment. In each chart, the x axis represents the acceptance rate (the percentage of the patient population receiving treatment), wherein the baseline rate is 0%, and the highest rate shown is 18.15%. The y axis of each chart represents the percentage change relative to the baseline in the total population of dialysis patients. As shown in Figures 400 and 410, it can be expected that the dialysis population will decrease in the short term (for example, 1-5 years show a negative percentage change relative to the baseline). In the short term, the absolute change relative to the baseline also increases over time (in other words, the percentage decrease (chart 410) after 5 years is greater than the percentage decrease (chart 400) after 1 year). These results may be attributed to the slowed progress of the patient receiving treatment from the CKD stage to the dialysis population. However, over a longer period (10-15 years) the population trend reverses, as shown in graphs 420 and 430. The percent change from baseline shows an increase in both the year 10 graph 420 and the year 15 graph 430. The results may be attributed to a decrease in mortality within the dialysis population among the treated patients (e.g., a decrease in outflow 124 due to death as indicated by parameters μ4 and / or μ5).

[0053] Figure 5510 shows a graph of an end-stage renal disease (ESRD) patient population over time according to a representative embodiment. Graph 510 shows episodic dialysis patients (e.g., Figure 1 Graph 520 shows the data of the prevalent dialysis patients (e.g., Figure 1 10 (a “prevalent dialysis” patient population) (wherein incident dialysis patients are defined as patients who started dialysis within the previous three months and prevalent dialysis patients are defined as patients who have been on dialysis for more than three months). Graphs 510 and 520 provide a comparison of model output with historical data, where scatter points 512 and 522 represent historical data, lines 514 and 524 are model outputs, and dashed lines 516 and 526 represent 95% confidence intervals. The model output indicated by lines 514 and 524 shows example outputs from a flow model (e.g., flow model 100) that includes time-dependent population data.

[0054] Figure 6 Included are graphs showing model output simulating the effect of sodium-glucose cotransporter 2 (SGLT2) inhibitor therapy in reducing mortality and disease progression according to a representative embodiment. Figure 1 The flow model 100 described in the embodiment of the present invention models multiple example scenarios. The flow model 100 is analyzed by changing one of the multiple model parameters 130 at a time to determine the predicted impact of SGLT2i treatment (in other words, in each scenario, a single model parameter is changed, while the other model parameters remain unchanged). Charts 610, 620, and 630 show the output of modeling the impact of reducing the mortality rate (μ1 of the flow model 100) of non-CKD patients with SGLT2i indications. Each of the charts 610, 620, and 630 shows the model output relative to the percentage reduction of μ1; specifically, in the simulation shown, μ1 is reduced by 0%, 5%, 10%, 15%, 20%, 25%, and 30%. A 0% change in baseline conditions or μ1 means that SGLT2i treatment is not given. Chart 610 shows the multiple changes in the dialysis population relative to the initial conditions. Chart 620 shows the percentage change relative to the baseline at the 40th month of the simulation. Graph 630 shows the fold change from baseline for the dialysis population over the time period of 0-40 months.

[0055] Graphs 640, 650, and 660 show the output of modeling the effect of reducing the progression rate of non-CKD patients with SGLT2i indications to CKD (γ1 of flow model 100). Each of graphs 640, 650, and 660 shows the model output of the percentage reduction relative to γ1; specifically, in the simulation shown, γ1 is reduced by 0%-30%. Baseline condition-0% change in γ1-means that SGLT2i treatment is not given. Graph 640 shows the fold change of the dialysis population relative to the initial condition. Graph 650 shows the percentage change relative to the baseline at the 40th month of the simulation. Graph 660 shows the fold change of the dialysis population relative to the baseline over a period of 0-40 months.

[0056] As shown in the figure and in the sensitivity analysis (see Figure 3 ), changes in model parameters μ1 or γ1 had relatively small effects on changes in the total dialysis population. Specifically, a 30% decrease in non-CKD mortality (μ1) was observed to increase the total dialysis population by 0.03%, while a similar decrease in CKD progression rate (γ1) decreased the total dialysis population by approximately 0.9%.

[0057] Figure 7 Included are graphs showing model output simulating the effect of SGLT2 inhibitor therapy in reducing mortality and progression to dialysis rates according to a representative embodiment. Figure 1 The flow model 100 described in the embodiment of the present invention models a plurality of example scenarios and performs the same Figure 6 Similar analysis described. Charts 710, 720 and 730 show the output of modeling the impact of reduced mortality (μ2 of flow model 100) of CKD patients with SGLT2i indications. Each of charts 710, 720 and 730 shows the model output of μ2 reduction relative to 0-30%. Baseline conditions or 0% change of μ2 indicate that SGLT2i treatment is not given. Chart 710 shows the multiple changes of the dialysis population relative to initial conditions. Chart 720 shows the percentage change of the dialysis population relative to baseline at the 40th month of simulation. Chart 730 shows the multiple changes of the dialysis population relative to baseline in the time period of 0-40 months. As shown in the figure, it is expected that after 40 months, the reduction of CKD mortality (μ2) will increase the total dialysis population by 3.5% (because the population not affected by mortality may progress to dialysis).

[0058] Charts 740, 750 and 760 show the output of modeling the effect of reducing the progression rate (d1 of flow model 100) of CKD patients with SGLT2i indications to occasional dialysis. In the simulation shown, the model parameter d1 was reduced by 0%-30%. Baseline conditions again meant that no SGLT2i treatment was given. Chart 740 shows the fold change of the dialysis population relative to the initial conditions. Chart 750 shows the percentage change of the dialysis population relative to the baseline at the 40th month of the simulation. Chart 760 shows the fold change of the dialysis population relative to the baseline over the time period of 0-40 months. It is observed that a 30% reduction in the progression rate d1 can be expected to reduce the total dialysis population by up to 11% at 40 months. Compared to Figure 6 As a result, Figure 7 The model results show a more significant impact on the dialysis population dynamics, which also corresponds to Figure 3 Indication of sensitivity analysis of (showing relatively high sensitivity to changes in parameters μ2 and d1).

[0059] Figure 8 Included is a graph showing different effects of model parameters according to a representative embodiment. Figure 1 A combined analysis of the flow model 100 of FIG. 810 in which the model parameters μ2 (mortality rate in CKD patients with an SGLT2i indication) and d1 (progression rate to dialysis in CKD patients with an SGLT2i indication) were reduced over a range of 0%-100%. Graph 810 shows the percentage change in the dialysis population after 40 months, represented by a gradient (variable stippled shading) depending on the percentage reduction in d1 (x-axis) and the percentage reduction in μ2 (y-axis). Graph 820 shows an enlarged view of region 812 of graph 810 showing the changes in μ2 and d1 between 0-30%. As shown in FIG. Figure 7 As discussed in , the model outputs of graphs 810 and 820 can be used to more deeply analyze the different effects of the parameters μ2 (expected increase in dialysis population) and d1 (expected decrease in dialysis population). For example, a 30% decrease in both d1 and μ2 can be expected to reduce the total dialysis population by more than 8%; a 10% decrease in both d1 and μ2 can be expected to reduce the total dialysis population by about 2%; a 50% decrease in both d1 and μ2 can be expected to reduce the total dialysis population by about 15%; and so on.

[0060] Fig. 9 is a flow chart of a method 900 for modeling a patient population according to a representative embodiment. The method 900 may utilize any model or technique described herein, such as reference Figure 1 Described flow model 100. Generally speaking, method 900 represents a technique for analyzing a patient population using a flow model and providing recommendations based on the analysis for, among other things, allocation of healthcare resources, treatments, and the like.

[0061] As shown in step 902, method 900 may include creating compartments, such as Figure 1 The multiple compartments 110 of the dialysis patient are shown. Step 902 may be similar to Figure 2 The method 200 of step 202 may be described in detail herein and may therefore include any features described with reference thereto. Multiple compartments may be generated from a set of demographic profiles of dialysis patients (e.g., a subset or a full set of dialysis patients treated at a particular institution). For example, compartments (e.g., compartments including patients having a particular medical diagnosis, treatment indication, biological attribute, same or similar population demographic information, etc.) may be created from the demographic profiles of dialysis patients based on one or more shared attributes from a plurality of attributes associated with the dialysis patients. In some cases, at least a portion of the demographic profiles of the dialysis patients and multiple attributes may be included in historical data of the organization (e.g., historical data described with reference to step 204 of the method 200).

[0062] As shown in step 904, method 900 may include creating a flow model (e.g., flow model 100 describing dynamic activity patterns between compartments 110) that features multiple compartments and identifies one or more dynamic activity patterns between compartments. Step 904 may be similar to Figure 2 Step 206 of method 200 and thus may include any features described with reference thereto.

[0063] As shown in step 906, method 900 may include analyzing the flow model, for example, calculating the transition rate between the compartments, the inflow rate into the compartment, and / or the outflow rate out of the compartment over time. Step 906 may include comparing the reference Figure 2 Step 216 of method 200 may be similar analysis techniques to those described, and thus may include any features described with reference thereto.

[0064] As shown in step 908, method 900 may include determining a predicted impact, such as a predicted impact of a treatment used by a plurality of dialysis patients. Figure 1 As discussed above with respect to the flow model 100 of FIG. 1 , treatment may include the use of a sodium-glucose cotransporter 2 (SGLT2) inhibitor. Step 908 may include the use of a sodium-glucose cotransporter 2 (SGLT2) inhibitor. Figure 2 The method 200 of step 216 may include determining techniques similar to those described in step 216 of the method 200, and thus may include any features described with reference thereto. For example, the predicted impact may be determined using one of the conversion rate, the inflow rate, and / or the outflow rate. The predicted impact may be determined for patients having a particular shared attribute or set of attributes. The step may also or alternatively include predicting a particular health outcome or event, such as an end-stage renal disease (ESRD) event (this type of prediction will be referred to as Figure 6-8discussed in more detail).

[0065] As shown in step 910, method 900 may include providing recommendations based on the predicted impact of the treatment (e.g., as determined in step 908). One type of recommendation may include a recommendation for resource allocation to one or more of a plurality of dialysis patients (e.g., where the predicted impact of treatment with SGLT2i is an increase in the dialysis population, the recommendation may include increasing the resources required to perform dialysis on the patient population). The step may also include taking action based on the provided recommendations - in the above example, taking action based on the recommendation to increase resources may include providing additional equipment, facilities, funding, etc. to the patient population in the affected compartment. Another type of recommendation may include recommending a type of treatment, treatment plan, etc. to a particular patient population.

[0066] As shown in step 912, method 900 may include determining a prevalence of a particular event for patients within at least one of the plurality of compartments. Figure 1 In the flow model 100 of FIG. 1 , specific events may include end-stage renal disease (ESRD) events (eg, transition to compartment 110 "incidental dialysis" or "prevalent dialysis"). Other types of events may include conversion to CKD, heart failure or other cardiovascular events, stroke, etc.

[0067] It should be understood that method 900 can be performed using a computer program product. For example, a computer program product including a computer executable code contained in a non-transitory computer readable medium, when executed on one or more computing devices, the code can perform any steps of method 900, including, for example: creating multiple compartments of a dialysis patient from dialysis patient statistics based on one or more shared attributes from multiple attributes associated with the dialysis patient; creating a flow model featuring multiple compartments, the flow model identifying one or more dynamic activity patterns between compartments; analyzing the flow model to calculate the conversion rate between compartments over time, the inflow flow into the compartment, and the outflow flow out of the compartment; and using the conversion rate, the inflow flow, and the outflow flow to determine the predicted impact of the treatment used by multiple dialysis patients with at least one attribute of the multiple attributes. It should also be understood that method 900 can be implemented using a system, such as any system described herein. For example, such a system can include a database, a processor, and a memory, wherein the memory stores a computer executable code contained in a non-transitory computer readable medium, and when executed by the processor, the code performs the steps of method 900.

[0068] Example

[0069] A further description of the simulated impact of SGLT2 inhibitors on U.S. dialysis statistics will now be provided, wherein: Figure 1-9Aspects of the example can be summarized. Sensitivity analysis identified four SGLT2i-related parameters that affected dialysis statistics: mortality and progression of CKD to dialysis in CKD patients had significant effects, while CKD mortality and progression to CKD had marginal effects (see Figure 1 and Figure 3 ). Figure 6-8 Predicted dialysis statistics over 40 months when CKD mortality and progression of CKD to dialysis were reduced by 30% are shown.

[0070] Table 1 below shows that a 20% SGLT2i uptake rate in CKD reduces dialysis statistics at year 5 from 1.280 to 1.269 times. Within ≤9 years, SGLT2i reduces dialysis statistics based on drug uptake rate. Interestingly, this trend reverses after 10 years, resulting in an increase in dialysis statistics.

[0071]

[0072] Table 1

[0073] Therefore, Table 1 shows the fold change in dialysis statistics for four different SGLT2i acceptance rates and the corresponding combined effects on CKD mortality and CKD progression to dialysis. For example, a 20% acceptance rate is equivalent to a 6.6% reduction in CKD mortality and a 4.58% reduction in CKD progression to dialysis. Note that after 10 years, dialysis statistics increase with SGLT2i acceptance.

[0074] Thus, the use of SGLT2i appears to dynamically affect dialysis statistics. In the first nine years, dialysis statistics decrease; after this period, they increase. Using the teachings of the present invention, the impact of SGLT2i acceptance rates on dialysis statistics over time can be similarly studied.

[0075] As described herein, any of the methods and techniques described above can be performed on a system, such as a system specifically configured for patient population flow modeling. An example of such a system is described below.

[0076] Fig.10 A system for patient population flow modeling according to a representative embodiment is shown. In general, system 1000 can include a networked environment, wherein a data network 1002 interconnects multiple participating devices and / or users in a communication relationship. Participating devices can include, for example, any number of user devices 1010, remote computing resources 1020, databases 1030, and other resources 1040.

[0077] The data network 1002 may be any network or internetwork suitable for communicating data and information between participants of the system 1000. This may include a public network such as the Internet, a private network, a telecommunication network such as the public switched telephone network, or a cellular network using third generation (e.g., 3G or IMT-2000), fourth generation (e.g., LTE (E-UTRA) or WiMAX-Advanced (IEEE802.16m)), fifth generation (e.g., 5G), and / or other technologies, as well as any of a variety of enterprise area or local area networks and other switches, routers, hubs, gateways, etc. that may be used to communicate data between participants of the system 1000.

[0078] Each participant of the data network 1002 may include a suitable network interface, including, for example, a network interface card, which term is used broadly herein to include any hardware suitable for establishing and maintaining wired and / or wireless communications (as well as software, firmware, etc. that controls its operation). The network interface card may include, but is not limited to, a wired Ethernet network interface card ("NIC"), a wireless 802.11 network card, a wireless 802.11 USB device, or other hardware for a wired or wireless local area network. The network interface may also or alternatively include cellular network hardware, wide area wireless network hardware, or any other hardware for centralized, self-organizing, peer-to-peer or other radio communications, which may be used to connect to the network and carry data. On the other hand, the network interface may include a serial or USB port to directly connect to a local computing device such as a desktop computer, which in turn provides a more general network connection to the data network 1002. Therefore, it should be understood that any component of the system may include one or more communication interfaces for communicating with other components of the system 1000 (e.g., sending and / or receiving data wired or wirelessly).

[0079] User device 1010 may include any device within system 1000 operated by one or more users 1001 for practicing the techniques contemplated herein. In general, user device 1010 may include processor 1022 and memory 1024, wherein memory 1024 stores computer executable code contained in a non-transitory computer-readable medium, which, when executed by processor 1022, performs one or more steps of any method or technique described herein. Thus, although in Fig.101020, but it will be understood that the processing described herein can be accomplished using one or more other devices that also or alternatively include a processor 1022 and a memory 1024. In some aspects, the user device 1010 includes components of a dialysis machine and / or dialysis system. In this manner, in some aspects, the user 1001 is one or more of a dialysis patient, a dialysis technician, a medical staff member such as a doctor or a nurse, etc. In other aspects, the user device 1010 is a computing device associated with one or more of a medical professional, an insurance provider or the like, a data analyst, etc. The user device 1010 can also or alternatively include any device for managing, monitoring, or otherwise interacting with the tools, platforms, and devices included in the systems and techniques contemplated herein. The user device 1010 can be coupled to a data network 1002, for example, for interacting with one or more other participants in the system 1000.

[0080] By way of example and not limitation, user devices 1010 may include one or more desktop computers, laptop computers, network computers, tablet computers, mobile devices, portable digital assistants, messaging devices, cellular phones, smart phones, portable media or entertainment devices, or any other computing devices that may participate in the system 1000 as contemplated herein. User devices 1010 may also or alternatively include any form of mobile device, such as any wireless, battery-powered device that may be used to interact with the networked system 1000. It will also be appreciated that one of the user devices 1010 may coordinate related functions (e.g., processing some or all of the data, storing data, etc.) as they are performed by another entity, such as one of the remote computing resources 1020 or other resources 1040.

[0081] Each user device 1010 may generally provide a user interface. The user interface may be maintained by an application executed locally on one of the user devices 1010 that receives data from, for example, a remote computing resource 1020 or other resource 1040. In other embodiments, the user interface may be remotely provided and presented on one of the user devices 1010, such as where the remote computing resource 1020 or other resource 1040 includes a web server that provides information via one or more web pages, etc., which may be displayed within a web browser or similar client executed on one of the user devices 1010. The user interface may generally create a suitable visual presentation for user interaction on a display device of one of the user devices 1010, and provide functionality for receiving any suitable form of user input, including, for example, input from a keyboard, mouse, touchpad, touch screen, gestures, or other user input device.

[0082] The remote computing resource 1020 may include, or may be in communication with, a processor 1022 and a memory 1024, wherein the memory 1024 stores code executable by the processor 1022 to perform the various techniques of the present invention. More specifically, the remote computing resource 1020 may be coupled to the data network 1002 and accessible by the user device 1010 via the data network 1002, wherein the remote computing resource 1020 includes a processor 1022 and a memory 1024, wherein the memory 1024 stores code executable by the processor 1022 to perform the steps of the method according to the present teachings.

[0083] The remote computing resource 1020 may also or alternatively include a data storage device, a network interface (and / or other communication interface) and / or other processing circuits. In the following description, when describing the function or configuration of the remote computing resource 1020, this is intended to include the corresponding function or configuration of the processor 1022 of the remote computing resource 1020 (e.g., by programming), or communicate with the remote computing resource 1020. In general, the remote computing resource 1020 (or its processor 1022 or a processor 1022 communicating therewith) can perform various processing tasks related to the patient population flow modeling discussed here. For example, the remote computing resource 1020 can manage information received from one or more user devices 1010 and / or databases 1030, and provide related support functions, process one or more data sets, communicate with other resources 1040, store data, etc. The remote computing resource 1020 may also or alternatively include a back-end algorithm that reacts to the actions performed by the user 1001 at one or more user devices 1010. The back-end algorithm may also or alternatively be located elsewhere in the system 1000.

[0084] The remote computing resource 1020 may also or alternatively include a network server or similar front end that facilitates the ability of the user device 1010 to access the remote computing resource 1020 or other components of the system 1000 over the network. The remote computing resource 1020 may also or alternatively communicate with other resources 1040 to obtain information provided to the user 1001 through a user interface on the user device 1010. In the event that the user 1001 specifies certain criteria for data processing, the information may be used by the remote computing resource 1020 (and any associated algorithms) to access other resources 1040. In this case, additional processing may be usefully performed, such as suggesting certain data processing operations and techniques.

[0085] The remote computing resource 1020 may also or alternatively maintain or otherwise communicate with a content database 1030, such as patient data 1032 associated with a plurality of dialysis patients, and / or patient data 1032 including a plurality of attributes associated with a plurality of dialysis patients. Thus, the database 1030 may be used to store any raw and / or processed / normalized data as described herein, for example, for use by another component in the system 1000 (e.g., the remote computing resource 1020 and / or the user device 1010). In one aspect, the remote computing resource 1020 may include a database 1030 of patient data 1032, and the remote computing resource 1020 may act as a server that provides a platform for patient population flow modeling, providing support services and / or outputs associated with support services, such as services, information, and / or recommendations related to resource allocation, treatment, other logistical support, etc.

[0086] The remote computing resource 1020 may also or alternatively be configured to manage access to certain content (e.g., for an enterprise associated with the user 1001 of the user device 1010). In one aspect, the remote computing resource 1020 may manage access of the user device 1010 to components of the system 1000 based on input from the user 1001.

[0087] Other resources 1040 may include any resource that may be usefully employed in the devices, systems, and methods described herein. For example, other resources 1040 may include, but are not limited to, other data networks, human participants (e.g., programmers, researchers, annotators, medical personnel, insurance providers, other medical (or medical-related) support service providers, analysts, etc.), sensors (e.g., audio or visual sensors), data mining tools, computing tools, data monitoring tools, etc. Other resources 1040 may also or alternatively include any other software or hardware resources that may be usefully employed in networked applications as contemplated herein. For example, other resources 1040 may include a payment processing server or platform for authorizing payment for access, content, or feature purchases, etc. On the other hand, other resources 1040 may include a certificate server or other security resource for third-party identity authentication, data encryption or decryption, etc. On the other hand, other resources 1040 may include a desktop computer or the like that is co-located with one of the user device 1010 and / or remote computing resources 1020 (e.g., on the same local area network as the user device 1010 and / or remote computing resource 1020, or directly coupled to the user device 1010 and / or remote computing resource 1020 via a serial or USB cable). In this case, other resources 1040 may provide supplementary functionality for the user device 1010 and / or remote computing resource 1020. Other resources 1040 may also or alternatively include supplementary resources, such as scanners, cameras, printers, input devices, medical equipment, and the like.

[0088] Other resources 1040 may also or alternatively include one or more network servers that provide network-based access to any other participants in system 1000. Although depicted as separate network entities, it will be readily appreciated that other resources 1040 (e.g., web servers) may also or alternatively be logically and / or physically associated with one of the other devices described herein, and may, for example, include or provide a user interface for web access to remote computing resources 1020 or databases 1030 in a manner that allows a user to interact, for example, from user device 1010 over data network 1002.

[0089] It will be understood that the participants in the system 1000 may include any hardware or software to perform the various functions described herein. For example, one or more of the user device 1010 and other resources 1040 may include a memory 1024 and a processor 1022.

[0090] The various components of the networked system 1000 described above can be arranged and configured to support the techniques described herein in various ways. For example, in one aspect, the system 1000 includes: a database 1030 connected to the network 1002, the database 1030 including patient data 1032 associated with a plurality of dialysis patients, the data including a plurality of attributes of the plurality of dialysis patients; and a processor 1022 and a memory 1024. The memory 1024 can store computer executable code contained in a non-transitory computer-readable medium, which, when executed by the processor 1024, performs the following steps: creating a plurality of compartments of a dialysis patient from dialysis patient statistics (e.g., in the patient data 1032) based on one or more shared attributes from a plurality of attributes associated with the dialysis patient, wherein the attributes may also or alternatively be included in the patient data 1032; receiving historical data (e.g., in the patient data 1032) associated with the dialysis patient statistics and the one or more shared attributes; creating a flow model describing one or more dynamic activities between the plurality of compartments, the one or more dynamic The activities include transition rates between chambers, inflow flows into chambers, and outflow flows out of chambers over time, wherein the flow model includes multiple model parameters, each model parameter is related to the one or more dynamic activities; formatting historical data into a first set of model parameters; inputting the first set of model parameters into the flow model; identifying a second set of model parameters, each second model parameter depends on a treatment for a dialysis patient; analyzing the flow model to determine a predicted effect of the treatment on the second set of model parameters; and outputting population data for the multiple chambers from the flow model, wherein a dialysis patient in one or more of the multiple chambers is given a treatment.

[0091] In another aspect, the system 1000 may include: a database 1030 connected to the network 1002, the database 1030 including patient data 1032 associated with a plurality of dialysis patients (or similar patients), the data including a plurality of attributes of the plurality of dialysis patients; and a processor 1022 and a memory 1024. The memory 1024 may store computer executable code contained in a non-transitory computer readable medium, which, when executed by the processor 1022, performs the following steps: creating a plurality of compartments of dialysis patients from the plurality of dialysis patients in the database 1030, wherein the patients in each compartment of the plurality of compartments include one or more shared attributes from the plurality of attributes; creating a flow model featuring the plurality of compartments, the flow model identifying one or more dynamic activity patterns between the compartments; analyzing the flow model to calculate transition rates between the compartments, inflow flows into the compartments, and outflow flows out of the compartments over time; and using the transition rates, inflow flows, and outflow flows to determine a predicted impact of a treatment used by the plurality of dialysis patients having at least one of the plurality of attributes.

[0092] The above-mentioned systems, devices, methods, processes, etc. can be implemented with hardware, software, or any combination of these suitable for a specific application. Hardware can include general-purpose computers and / or special computing devices. This includes implementation in one or more microprocessors, microcontrollers, embedded microcontrollers, programmable digital signal processors or other programmable devices or processing circuits and internal and / or external memories. This can also or alternatively include one or more application-specific integrated circuits, programmable gate arrays, programmable array logic components, or any other one or more devices that can be configured to process electronic signals. It should also be understood that the implementation of the above-mentioned process or device can include computer executable code created using a structured programming language such as C, an object-oriented programming language such as C++, or any other high-level or low-level programming language (including assembly language, hardware description language, and database programming language and technology), which can be stored, compiled, or interpreted to run on one of the above-mentioned devices, as well as a heterogeneous combination of processors, processor architectures, or combinations of different hardware and software. On the other hand, the method can be implemented in a system that performs its steps, and can be distributed across devices in a variety of ways. At the same time, processing can be distributed across devices such as the various systems described above, or all functions can be integrated into dedicated stand-alone devices or other hardware. On the other hand, the means for performing the steps associated with the above-described processes may include any of the hardware and / or software described above. All such permutations and combinations are intended to fall within the scope of the present disclosure.

[0093] Embodiments disclosed herein may include a computer program product including computer executable or computer usable code that, when executed on one or more computing devices, performs any and / or all of the steps described herein. The code may be stored in a non-transitory manner in a computer memory, which may be a memory from which the program is executed (e.g., a random access memory associated with a processor), or a storage device such as a disk drive, flash memory, or any other optical, electromagnetic, magnetic, infrared, or other device or combination of devices. On the other hand, any of the systems and methods described above may be implemented in any suitable transmission or propagation medium that carries the computer executable code and / or any input or output from the computer executable code.

[0094] For the purpose of explanation, the foregoing description has been described with reference to specific embodiments. However, the above illustrative discussions are not intended to be exhaustive or to limit the disclosure to the precise forms disclosed. In light of the above teachings, many modifications and variations are possible.

[0095] Unless the context clearly requires otherwise, throughout the description, the words "include," "comprising," "containing," and the like should be interpreted in an inclusive sense, rather than an exclusive or exhaustive sense; that is, in the sense of "including, but not limited to." Additionally, the words "herein," "herein," "hereafter," "above," "below," and words of similar meaning refer to this application as a whole and not to any particular portions of this application.

[0096] It should be understood that the above-described devices, systems, and methods are set forth as examples and not limitations. For example, with respect to the methods provided above, in the absence of explicit indications to the contrary, the disclosed steps may be modified, supplemented, omitted, and / or reordered without departing from the scope of the present disclosure. Many variations, additions, omissions, and other modifications will be apparent to one of ordinary skill in the art. In addition, the order or presentation of the method steps in the above description and accompanying drawings is not intended to require such an order in which the steps are performed, unless a specific order is explicitly required or is clear from the context.

[0097] The method steps of the embodiments described herein are intended to include any suitable methods for causing these method steps to be performed consistent with the patentability of the claims below, unless a different meaning is explicitly provided or a different meaning is clear from the context. Thus, for example, performing step X includes any suitable method for causing another party such as a remote user, a remote processing resource (e.g., a server or cloud computing), or a machine to perform step X. Similarly, performing steps X, Y, and Z may include any method for directing or controlling any combination of such other individuals or resources to perform steps X, Y, and Z to obtain the benefits of such steps. Therefore, the method steps of the embodiments described herein are intended to include any suitable methods for causing one or more other parties or entities to perform these steps consistent with the patentability of the attached claims, unless a different meaning is explicitly provided or a different meaning is clear from the context. These parties or entities do not need to be directed or controlled by any other party or entity, nor do they need to be located in a specific jurisdiction.

[0098] Thus, while particular embodiments have been shown and described, it will be apparent to those skilled in the art that various changes and modifications in form and details may be made without departing from the spirit and scope of the disclosure, and such changes and modifications are intended to form a part of the present invention as defined by the appended claims which are to be interpreted in the broadest sense permitted by law.

Claims

1. A computer program product comprising computer executable code embodied in a non-transitory computer readable medium, which, when executed on one or more computing devices, performs the following steps: creating a plurality of compartments of dialysis patients from dialysis patient demographics based on one or more shared attributes from a plurality of attributes associated with the dialysis patients; receiving historical data related to dialysis patient demographics and the one or more shared attributes; creating a flow model describing one or more dynamic activities between the plurality of compartments, the one or more dynamic activities comprising transition rates between compartments, inflow rates into compartments, and outflow rates out of compartments over time, wherein the flow model comprises a plurality of model parameters, each model parameter being associated with the one or more dynamic activities; formatting historical data into a first model parameter set; inputting the first set of model parameters into a flow model; identifying a set of second model parameters, each second model parameter being dependent on a treatment of the dialysis patient; analyzing the flow model to determine a predicted effect of the treatment on the second set of model parameters; and Population data for the plurality of compartments is output from the flow model, wherein a dialysis patient in one or more compartments of the plurality of compartments is administered treatment.

2. The computer program product according to claim 1, wherein: Analyzing the flow model includes determining a differential predicted impact of the second model parameters.

3. The computer program product of any one of claims 1-2, further comprising code which, when executed on one or more computing devices, performs the step of providing an initial estimate of one or more second model parameters prior to analyzing the flow model.

4. The computer program product according to any one of claims 1 to 3, wherein: The one or more shared attributes include at least one of a medical diagnosis, a treatment indication, and a current treatment.

5. A computer program product according to any one of claims 1-4, further comprising code which, when executed on one or more computing devices, performs the step of outputting population data including time correlation from the flow model.

6. A computer program product according to any one of claims 1-5, wherein the computer program product further comprises code which, when executed on one or more computing devices, performs the steps of receiving updated historical data and changing one of the plurality of compartments, the plurality of properties and the first set of model parameters based on the updated historical data.

7. The computer program product according to any one of claims 1 to 6, wherein: Analyzing the flow model includes varying treatment inclusion rates.

8. The computer program product according to any one of claims 1 to 7, wherein: Analyzing the flow model includes performing a sensitivity analysis on the plurality of model parameters.

9. The computer program product according to claim 8, wherein: The sensitivity analysis identifies one or more model parameters that are affected by a sodium-glucose co-transporter 2 inhibitor.

10. The computer program product according to any one of claims 1 to 9, wherein: The treatment comprises at least one of sodium-glucose co-transporter 2 inhibitor medication and dialysis.

11. A method comprising: creating a plurality of compartments of dialysis patients from dialysis patient demographics based on one or more shared attributes from a plurality of attributes associated with the dialysis patients; receiving historical data related to dialysis patient demographics and the one or more shared attributes; creating a flow model describing one or more dynamic activities between the plurality of compartments, the one or more dynamic activities comprising transition rates between compartments, inflow rates into compartments, and outflow rates out of compartments over time, wherein the flow model comprises a plurality of model parameters, each model parameter being associated with the one or more dynamic activities; formatting historical data into a first model parameter set; inputting the first set of model parameters into a flow model; identifying a set of second model parameters, each second model parameter being dependent on a treatment of the dialysis patient; analyzing the flow model to determine a predicted effect of the treatment on the second set of model parameters; and Population data for the plurality of compartments is output from the flow model, wherein a dialysis patient in one or more compartments of the plurality of compartments is administered treatment.

12. The method according to claim 11, wherein: Analyzing the flow model includes determining a differential predicted impact of the second model parameters.

13. The method of any one of claims 11-12, further comprising, prior to analyzing the flow model, providing an initial estimate of one or more second model parameters.

14. The method according to any one of claims 11 to 13, wherein: The one or more shared attributes include at least one of a medical diagnosis, a treatment indication, and a current treatment.

15. The method of any one of claims 11-14, further comprising outputting population data including time correlation from the flow model.

16. The method of any one of claims 11-15, further comprising receiving updated historical data and changing one of the plurality of compartments, the plurality of properties, and the first set of model parameters based on the updated historical data.

17. The method according to any one of claims 11 to 16, wherein: Analyzing the flow model includes varying treatment inclusion rates.

18. The method according to any one of claims 11 to 17, wherein: Analyzing the flow model includes performing a sensitivity analysis on the plurality of model parameters.

19. The method according to claim 18, wherein: The sensitivity analysis identifies one or more model parameters that are affected by a sodium-glucose co-transporter 2 inhibitor.

20. The method according to any one of claims 11 to 19, wherein: The treatment comprises at least one of sodium-glucose co-transporter 2 inhibitor medication and dialysis.

21. A system comprising: a database connected to the network, the database including data related to a plurality of dialysis patients, the data including a plurality of attributes of the plurality of dialysis patients; and A processor and a memory storing computer executable code contained in a non-transitory computer readable medium, which, when executed by the processor, performs the following steps: creating a plurality of compartments of the dialysis patient from dialysis patient statistics based on one or more shared attributes from the plurality of attributes associated with the dialysis patient; receiving historical data related to dialysis patient demographics and the one or more shared attributes; creating a flow model describing one or more dynamic activities between the plurality of compartments, the one or more dynamic activities comprising transition rates between compartments, inflow rates into compartments, and outflow rates out of compartments over time, wherein the flow model comprises a plurality of model parameters, each model parameter being associated with the one or more dynamic activities; formatting historical data into a first model parameter set; inputting the first set of model parameters into a flow model; identifying a set of second model parameters, each second model parameter being dependent on a treatment of the dialysis patient; analyzing the flow model to determine a predicted effect of the treatment on the second set of model parameters; and Population data for the plurality of compartments is output from the flow model, wherein a dialysis patient in one or more compartments of the plurality of compartments is administered treatment.

22. A method comprising: creating a plurality of compartments of dialysis patients from dialysis patient demographics based on one or more shared attributes from a plurality of attributes associated with the dialysis patients; creating a flow model characterized by the plurality of compartments, the flow model identifying one or more dynamic activity patterns between the compartments; analyzing the flow model to calculate transition rates between compartments, inflow rates into compartments, and outflow rates out of compartments over time; and The conversion rate, the inflow rate, and the outflow rate are used to determine a predicted impact of a therapy used by a plurality of dialysis patients having at least one of the plurality of attributes.

23. The method according to claim 22, wherein: The treatment involves the use of a sodium-glucose co-transporter 2 inhibitor.

24. The method of any one of claims 22-23, further comprising providing a recommendation for resource allocation to one or more of the plurality of dialysis patients having at least one of the plurality of attributes based on the predicted impact of the treatment.

25. The method of any one of claims 22-24, further comprising predicting an end-stage renal disease event.

26. The method of any one of claims 22-25, further comprising determining a prevalence of a specific event in patients within at least one of the plurality of compartments.

27. The method according to claim 26, wherein: The specific events include end-stage renal disease events.

28. The method according to any one of claims 22 to 27, wherein: At least a portion of the dialysis patient demographics and the plurality of attributes are included within the organization's historical data.

29. The method according to any one of claims 22 to 28, wherein: The plurality of compartments are created from a group of dialysis patient demographics.

30. A computer program product comprising computer executable code embodied in a non-transitory computer readable medium, which, when executed on one or more computing devices, performs the following steps: creating a plurality of compartments of dialysis patients from dialysis patient demographics based on one or more shared attributes from a plurality of attributes associated with the dialysis patients; creating a flow model characterized by the plurality of compartments, the flow model identifying one or more dynamic activity patterns between the compartments; analyzing the flow model to calculate transition rates between compartments, inflow rates into compartments, and outflow rates out of compartments over time; and The conversion rate, the inflow rate, and the outflow rate are used to determine a predicted impact of a therapy used by a plurality of dialysis patients having at least one of the plurality of attributes.

31. The computer program product of claim 30, wherein: The treatment involves the use of a sodium-glucose co-transporter 2 inhibitor.

32. A computer program product according to any one of claims 30-31, wherein the computer program product further comprises code which, when executed on one or more computing devices, performs the following steps: providing a recommendation for resource allocation to one or more dialysis patients among the plurality of dialysis patients having at least one of the plurality of attributes based on the predicted impact of the treatment.

33. The computer program product of any one of claims 30-32, further comprising code that, when executed on one or more computing devices, performs the step of predicting an end-stage renal disease event.

34. A computer program product according to any one of claims 30-33, further comprising code that, when executed on one or more computing devices, performs the step of determining the prevalence of a specific event for patients within at least one of the plurality of compartments.

35. The computer program product of claim 34, wherein: The specific events include end-stage renal disease events.

36. A computer program product according to any one of claims 30 to 35, wherein: At least a portion of the dialysis patient demographics and the plurality of attributes are included within the organization's historical data.

37. A computer program product according to any one of claims 30 to 36, wherein: The plurality of compartments are created from a group of dialysis patient demographics.

38. A system comprising: a database connected to the network, the database including data related to a plurality of dialysis patients, the data including a plurality of attributes of the plurality of dialysis patients; and A processor and a memory storing computer executable code contained in a non-transitory computer readable medium, which, when executed by the processor, performs the following steps: creating a plurality of compartments of dialysis patients from a plurality of dialysis patients in a database, wherein the patients within each compartment of the plurality of compartments include one or more shared attributes from the plurality of attributes; creating a flow model characterized by the plurality of compartments, the flow model identifying one or more dynamic activity patterns between the compartments; analyzing the flow model to calculate transition rates between compartments, inflow flux into compartments, and outflow flux out of compartments over time; and The conversion rate, the inflow rate, and the outflow rate are used to determine a predicted impact of a therapy used by a plurality of dialysis patients having at least one of the plurality of attributes.

Images