Optimization of drug combinations for the treatment of acute heart failure

Abstract

The embodiments disclosed herein can include an operation of receiving a plurality of current cardiovascular function metrics of a patient and a plurality of candidate drugs to be used to reach a plurality of desired cardiovascular function metrics, and an operation of determining an optimal dosage of the plurality of candidate drugs to reach the plurality of desired cardiovascular function metrics. Determining can include optimizing a dosage combination of the plurality of candidate drugs to reach a plurality of desired cardiovascular parameters corresponding to the plurality of desired cardiovascular function metrics from a plurality of current cardiovascular parameters corresponding to the plurality of current cardiovascular function metrics, and mapping a plurality of desired cardiovascular function metrics from the plurality of desired cardiovascular parameters and a plurality of current cardiovascular function metrics from the plurality of current cardiovascular parameters. The operation can further include outputting an optimal dosage of the plurality of candidate drugs.

Description

Technical Field

[0001] Cross - reference to Related Applications This application claims priority from U.S. Provisional Patent Application No. 63 / 346,143, filed on May 26, 2022, entitled "Optimizing Drug Combinations for Treating Acute Heart Failure", which is hereby incorporated by reference in its entirety.

[0002] This disclosure relates to determining optimal combinations of drugs for treating acute heart failure, and more particularly, to linearly optimizing drug combinations to achieve desired cardiovascular parameters that map to desired cardiovascular function metrics for patients with acute heart failure.

Background Art

[0003] Acute heart failure is caused by various factors and thus generally requires complex pharmacotherapy (also referred to as dosing) using multiple drugs. Some examples of drugs for treating acute heart failure include inotropic agents such as dobutamine, vasopressors such as norepinephrine, vasodilators such as sodium nitroprusside, fluids such as dextran, diuretics such as furosemide, and the like. Each of these drugs can treat different differentiated aspects of acute heart failure. To treat acute heart failure more effectively, it is desirable to optimally combine these drugs. An exemplary optimal combination may include the minimum amount of drugs that treat the corresponding condition while minimizing side effects.

[0004] However, discovering such an optimal combination involves several technical challenges. The pharmacological effect of each drug in the combination is complex in itself, and this complexity rapidly increases when multiple drugs are involved. One challenge is to understand and utilize the complex dependencies / causal relationships between drugs, cardiovascular parameters, and cardiovascular performance metrics. Another challenge is to discover the optimal combination within dosage limits while taking into account the unclear interactions between different dosages.

[0005] Technical solutions have been devised to address these technical problems, but these solutions remain unsatisfactory. In general, conventional technical solutions are based on a single-input single-output (SISO) paradigm of how drugs promote outcomes based on a patient's pathophysiology. For example, one study evaluates the effect of norepinephrine on mean arterial pressure. However, SISO is only for a single drug to promote a single type of outcome and is not designed to handle scenarios of multiple drugs, let alone the optimal combination of multiple drugs. Multiple SISO control studies have also been conducted, but these studies are unable to and have not considered the unknown interactions between multiple different SISO systems.

[0006] Therefore, clinical judgment of the optimal combination of drugs is driven by trial and error and guesswork and is inherently inaccurate. Such an undesirable situation is causing unnecessary suffering to patients. The health outcomes are not as desirable, and the mortality rate among heart failure patients remains unduly high. Therefore, significant improvements in systems, methods, and devices for assisting clinical judgment regarding the optimal combination of drugs in acute heart failure patients are desired. SUMMARY OF THE INVENTION

[0007] In some embodiments, a computer-readable non-transitory storage medium storing computer program instructions is provided. The computer program instructions, when executed, can cause operations including receiving a plurality of current cardiovascular function metrics of a patient and a plurality of candidate drugs to be used to reach a plurality of desired cardiovascular function metrics, and determining an optimal dosage of the plurality of candidate drugs to reach the plurality of desired cardiovascular function metrics. Determining can include optimizing a dosage combination of the plurality of candidate drugs to reach a plurality of desired cardiovascular parameters corresponding to the plurality of desired cardiovascular function metrics from a plurality of current cardiovascular parameters corresponding to the plurality of current cardiovascular function metrics, and mapping a plurality of desired cardiovascular function metrics from the plurality of desired cardiovascular parameters and a plurality of current cardiovascular function metrics from the plurality of current cardiovascular parameters. The operations can further include outputting an optimal dosage of the plurality of candidate drugs.

[0008] In some embodiments, a computer-implemented method is provided. The method can include receiving a plurality of current cardiovascular function metrics of a patient and a plurality of candidate drugs to be used to reach a plurality of desired cardiovascular function metrics, and determining an optimal dosage of the plurality of candidate drugs to reach the plurality of desired cardiovascular function metrics. Determining can include optimizing a dosage combination of the plurality of candidate drugs to reach a plurality of desired cardiovascular parameters corresponding to the plurality of desired cardiovascular function metrics from a plurality of current cardiovascular parameters corresponding to the plurality of current cardiovascular function metrics, and mapping a plurality of desired cardiovascular function metrics from the plurality of desired cardiovascular parameters and a plurality of current cardiovascular function metrics from the plurality of current cardiovascular parameters. The method can further include outputting an optimal dosage of the plurality of candidate drugs.

[0009] In some embodiments, a system is provided. The system can include a non-transitory computer-readable medium storing computer program instructions and one or more processors configured to execute the computer program instructions to cause an operation. The operation can include receiving a plurality of current cardiovascular function metrics of a patient and a plurality of candidate drugs to be used to reach a plurality of desired cardiovascular function metrics, and determining an optimal dosage of the plurality of candidate drugs to reach the plurality of desired cardiovascular function metrics. Determining can include optimizing a dosage combination of the plurality of candidate drugs to reach a plurality of desired cardiovascular parameters corresponding to the plurality of desired cardiovascular function metrics from a plurality of current cardiovascular parameters corresponding to the plurality of current cardiovascular function metrics, and mapping a plurality of desired cardiovascular function metrics from the plurality of desired cardiovascular parameters and a plurality of current cardiovascular function metrics from the plurality of current cardiovascular parameters. The operation can further include outputting the optimal dosage of the plurality of candidate drugs.

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

[0011] The figures are intended to illustrate exemplary embodiments, but it is understood that the present disclosure is not limited to the configurations and devices shown in the drawings. In the figures, the same reference numerals identify at least generally similar elements.

[0012] The embodiments described herein solve the above-described technical problems and can also provide other solutions. An exemplary optimal drug combination is calculated based on decomposing the cardiovascular system into a first model having cardiovascular parameters affected by the drug combination and a second model having a mapping between the cardiovascular parameters and the cardiovascular function metrics. The first model provides constraints for linearly optimizing the drug combination along with the maximum dose level, and the second model provides a mapping between the cardiovascular parameters and the cardiovascular function metrics. Thus, the mapping can determine whether a patient is treatable with a drug combination, for example, when the combination results in a cardiovascular function metric outside the target range.

[0013] FIG. 1 shows an exemplary computing environment 100 for assisting in clinical judgment in drug treatment for acute heart failure patients, according to an exemplary embodiment of the present disclosure. As shown, the computing environment 100 may be based on a client-server model having a server 102 connected to a plurality of clients 106a - 106d (generally referred to as clients 106 or collectively referred to as clients 106) via a network 104. However, it should be understood that the client-server model is merely exemplary and for ease of illustration and should not be considered limiting. Thus, any type of computing environment that implements the functions disclosed herein should be considered within the scope of the present disclosure. Further, the individual components of the computing environment 100 are merely exemplary, and alternative, additional, or fewer components should be considered within the scope of the present disclosure.

[0014] The computing environment 100 may generally be within a clinical setting for assessing clinical judgment regarding acute heart failure patients. In some exemplary user cases, the server 102 may store various software modules that can be accessed by the clients 106 using the network 104. The clients 106 themselves may have a stand-alone application (not shown) for accessing the software modules. Alternatively, the clients 106 may access the software modules, for example, through a browser application.

[0015] The hardware of server 102 may represent any type of computing device. For example, server 102 may include, without limitation, any type of computing device including, but not limited to, a server computer, a desktop computer, a laptop computer, a tablet computer, a smartphone. Server 102 does not necessarily have to be in a single location and may be implemented by a network of computers. Further, server 102 does not necessarily have to be in the same location within the clinical site itself and may be hosted by a third-party cloud computing provider. Accordingly, any type of server 102 should be considered to be within the scope of the present disclosure.

[0016] As described above, client 106 can access server 102 through network 104. Network 104 may include any combination of one or more packet-switched networks (e.g., IP-based networks) and one or more circuit-switched networks (e.g., cellular telephone networks). Some non-limiting examples of network 104 include local area networks, metropolitan area networks, wide area networks such as the Internet, etc. Similarly, non-limiting examples of client 106 may include desktop terminals (e.g., desktop terminal 106a), laptop computers (e.g., laptop computer 106b), tablet computers (e.g., tablet computer 106c), smartphones (e.g., smartphone 106d), etc. Any type of computing device that enables access to server 102 through network 104 should be considered to be within the scope of the present disclosure. Further, the functions described within the present disclosure can be distributed in any manner, i.e., the functions of server 102 may be performed by one or more clients 106 and vice versa.

[0017] Server 102 can include a drug optimization system 110 that can be configured to generate an optimal drug dosage for a patient based on the received cardiovascular function metric data of the patient. For example, the drug optimization system 110 can generate an optimal dosage of a drug for prescribing to a patient to achieve a desired cardiovascular function metric based on the current measurement of the cardiovascular function metric.

[0018] In some embodiments, the drug optimization system 110 can include one or more modules for generating a recommended combination of drugs to reach a desired cardiovascular function metric from the current cardiovascular function metric. The drug optimization system 110 can include a drug infusion module 120 and a mapping module 130. As will be described in more detail below, the drug infusion module 120 can be configured to deploy a first analytical model representing the transition from the current cardiovascular parameters (corresponding to the current cardiovascular function metric) to the desired cardiovascular parameters (corresponding to the desired cardiovascular function metric). The mapping module 130 can be configured to deploy a second analytical model that can provide a mapping between the current set of cardiovascular parameters and the current set of cardiovascular function metrics, and can also provide a mapping between the target set of cardiovascular parameters and the target set of cardiovascular function metrics.

[0019] After one or more analysis models have been developed and validated, a clinician can use the drug optimization system 110 to assist in his or her clinical decision-making process regarding patients with acute heart failure. In some exemplary operations, the clinician uses an interface within the client 106 to input current cardiovascular function metrics such as left atrial pressure, cardiac output, and mean atrial pressure, as described throughout this disclosure. Alternatively or additionally, the clinician may input current cardiovascular parameters. The client 106 can then transmit the input metrics to the server 102 through the network 104. The drug optimization system 110 can calculate a recommended dosage for the current cardiovascular function metric with respect to the desired cardiovascular function metric (in some embodiments, the clinician can provide the desired cardiovascular function metric along with the current cardiovascular function metric).

[0020] FIG. 2 shows details of the drug infusion module 120 and the mapping module 130 according to an exemplary embodiment of the present disclosure. It should be understood that the details shown are illustrative and should not be considered limiting. That is, each of the drug infusion module 120 and the mapping module 130 may have other components and / or other processes that are considered to be within the scope of the present disclosure.

[0021] As shown, the drug infusion module 120 can include a first analysis model configured to map current cardiovascular parameters 202 to desired cardiovascular parameters 204 by using an optimal drug combination 210. The mapping module 130 can include a second analysis model configured to map current cardiovascular parameters 202 to corresponding current cardiovascular function metrics and perform a mapping between the desired cardiovascular parameters 204 and the corresponding desired cardiovascular function metric 208. The optimal drug combination 210 can cause a measurable change in the cardiovascular parameters in the drug infusion module 120, but the mapping module 130 is configured to enable a clinician to interact with the drug optimization system using the cardiovascular function metrics.

[0022] Accordingly, the embodiments disclosed herein can be based on the determination of an optimal input (e.g., optimal drug combination 210) of candidate drugs in the drug infusion module 120, and as a result, can generate a desired output (e.g., desired cardiovascular function metric 208) using the mapping module 130. The optimal drug combination 210 can be represented as a vector u = [u1, u2, u3, u4, u5] T where each element can correspond to a drug. For example, u1 may correspond to a positive inotrope, u2 may correspond to a vasopressor, u3 may correspond to a vasodilator, u4 may correspond to a fluid, and u5 may correspond to a diuretic. However, it should be understood that these are merely exemplary drugs forming an exemplary optimal drug combination 210 and should not be considered limiting. Accordingly, a generalized input vector u = [u1, …… u n T should be considered to be within the scope of the present disclosure.

[0023] In some embodiments, the desired cardiovascular function metric 208 is the mean arterial pressure (MAP), the left atrial pressure (P LA ​) and may include cardiac output (CO). The desired cardiovascular function metric is the desired output vector y d = [MAP, P LA , CO] T can be represented by. It should also be understood that these cardiovascular function metrics are merely examples, and other cardiovascular function metrics should be considered within the scope of the present disclosure. Thus, similar to the input vector u, the desired output vector y d can also be generalized to a vector having n elements.

[0024] The drug infusion module 120 and the mapping module 130 can represent a cardiovascular system that simulates the behavior (or cardiovascular behavior) of the heart of a mammal (e.g., human) using a first analysis model and a second analysis model. For example, the drug infusion module 120 and the mapping module 130 can simulate how the heart responds to an optimal drug combination 210 as indicated by a drug and / or combination of drugs, e.g., the input vector u = [u1, …… u n T .

[0025] In some embodiments, the operation of the drug infusion module 120 is linearly represented as x = Bu + x0, where x0 can be the initial state before drug infusion (e.g., the current cardiovascular parameter 202), u = [u1, …… u n T can be a drug combination (e.g., the optimal drug combination 210) that can model the effect of drug infusion on cardiovascular parameters, B can be an interaction matrix (e.g., a drug library), and x can be the state after drug infusion (e.g., the desired cardiovascular parameter 204). As an example of the cardiovascular parameter of x (not to be interpreted as the only parameter), the x0 state is the systemic vascular resistance (R S ), myocardial contractility (E es ​​) may include heart rate (HR) and stroke blood volume (SBV). The desired state (x d ) after drug injection is x d = [R S , E es , HR, SBV] T and can be expressed as such.

[0026] The mapping module 130 can be based on a hemodynamic analysis model represented by y = h(x), where y is the desired cardiovascular function metric output 208, and x is the desired cardiovascular parameter 204 state generated by the drug injection module 120. That is, the mapping module can map the cardiovascular parameters in state x to the desired cardiovascular behavior (as indicated by the desired cardiovascular function metric 208). For example, the optimal drug combination 210 can change the initial state of the cardiovascular parameters (i.e., the current cardiovascular parameters 202) to the desired cardiovascular parameters 204 (i.e., x0 ∈ X → x d ∈ X), thereby changing the mapped current cardiovascular function metric 206 to the desired cardiovascular function metric 208 (i.e., y0 ∈ Y → y d ∈ Y).

[0027] In some embodiments, the drug injection module 120 can model multiple dependencies of concurrent drug injections when the drug effects converge. In the case of a 5-drug combination, the input drugs can be defined as u := [u1,..., u5] T ∈ R 5 as described above. Table 1 below shows exemplary drugs with maximum dose constraints.

[0028]

Table 1

[0029]

Number

[0030] Using the same notation, the determination of the optimal drug combination 210 is subject to the constraints x d - x0 = Bu * and

Number

Number

[0031] However, the desired state x d of the cardiovascular parameters from the desired state y d of the cardiovascular function metric is a mapping function (y d ∈Y → x dObtaining (∈X) can be a difficult problem because it is essentially difficult due to the inverse non-linear relationship between the two spaces and their dimensional differences. The embodiments disclosed herein analytically solve for X→Y and then numerically obtain y d ∈Y→x d ∈X, thereby overcoming this problem.

[0032] FIG. 3 shows a solution system 300 consisting of an analytical solution of the mapping function utilized by the mapping module 130 and a subsequent numerical solution, according to an exemplary embodiment of the present disclosure. The analytical solution X→Y from the desired state 302 (i.e., the desired cardiovascular parameter 204) to the desired output 304 (i.e., the desired cardiovascular function metric 208) can be by using the Frank-Starling curve and Guyton's venous return curve.

[0033] The Frank-Starling curve can define the relationship between CO and P LA as follows.

Equation

[0034] Guyton's venous return curve can be defined as follows.

Equation

[0035] Assuming that the total loaded blood volume (SBV) is distributed by the compliance ratio between the systemic circulation and the pulmonary circulation, V p can be given by the following.

Equation

[0036] Solving Equations (1) and (4) as a system of non-linear equations using the Lambert function, an analytical solution can be obtained as a function of only the cardiovascular parameters, as follows. [Number] MAP = R s CO [mmHg] In the formula, W(.) is defined as the Lambert function. [Number]

[0037] The numerical solution can utilize the analytical solution and simulate various patient scenarios (x) and outcomes (y). In particular, by filtering the Y database within the desired outcome range, y d , x d can be identified. Table 306 shows an example of such filtering. Table 306 shows the state parameter 308 (x) and the output parameter 310 (y). The filtering is performed to select the output parameter 310 within the range and map the selected output parameter to the state parameter 308.

[0038] Figure 4 shows an exemplary solution system 400 for numerical solution from input cardiovascular parameters for outputting cardiovascular function metrics utilized by the mapping module 130, according to an exemplary embodiment of the present disclosure. Table 402 shows MAP, P LAshows the range of control targets for a cardiovascular function metric Y, including a heart rate (HR) and a cardiac index (CI). As shown, there can be two control targets, control target 1 and control target 2. Graph 404 shows the two-dimensional regions corresponding to control target 1 and control target 2. In particular, region 406 corresponds to control target 1 and region 408 corresponds to control target 2. Regions 406 and 408 are used to select cardiovascular parameters corresponding to the control target cardiovascular function metric and discard the rest, such that the input cardiovascular parameter x can be filtered out.

[0039] For example, Table 414a shows cardiovascular parameters 410 that can generate a cardiovascular function metric within control target 1, as indicated by label 412. Similarly, Table 414b shows cardiovascular parameters 410 that generate a cardiovascular function metric within control target 2, as indicated by label 412. Additionally, Table 414c shows cardiovascular parameters 410 that do not generate a cardiovascular function metric in either control target 1 or control target 2, as indicated by label 412.

[0040] FIG. 5 shows a flowchart of an exemplary method 500, based on an exemplary embodiment of the present disclosure. The exemplary method 500 may be implemented by any combination of the components of the computing environment 100 shown in FIG. 1. It should be understood that the steps of method 500 are merely examples and should not be considered limiting. Methods having additional, alternative, or fewer steps should be considered to be within the scope of the present disclosure.

[0041] Method 500 can start at step 502. At step 502, server 102 can receive an input of a cardiovascular system function metric. For example, a desktop terminal within a hospital terminal may be used by a clinician to input a cardiovascular system function metric. Alternatively, the clinician may input a cardiovascular system function metric on a smartphone or tablet computer. The cardiovascular system function metric may include, for example, a current cardiovascular system function metric and / or a target cardiovascular system function metric. It should be understood that the clinician may input current cardiovascular system parameters instead of or in addition to the current cardiovascular system function metric.

[0042] At step 504, server 102 can calculate an optimal drug combination based on the target cardiovascular system function metric. In some embodiments, regardless of the modality of input of the desired cardiovascular system function metric, server 102 can perform step 504 for calculating an optimal drug combination based on the target cardiovascular system function metric. For example, drug optimization system 110 can deploy drug infusion module 120 to determine an optimal drug combination to reach the target cardiovascular system metric from the current cardiovascular system metric. Drug optimization system 110 can deploy mapping module 130 to map current cardiovascular system parameters to the current cardiovascular system function metric and map target cardiovascular system parameters to the target cardiovascular system function metric.

[0043] In step 506, server 102 can output (e.g., at the requester device) an optimal drug combination for assisting clinical judgment. That is, a clinician can rely on the tested and simulated models to assist in judgment and not rely much on guesswork. In some embodiments, server 102 may not necessarily be able to calculate the optimal drug calculation. For example, the described analytical models may be out of range for a particular patient. In these cases, server 102 may output an indication that the patient is untreatable.

[0044] FIG. 6 shows an exemplary system 600 for treatment possibility simulation according to an exemplary embodiment of the present disclosure. The treatment possibility simulation may be implemented by the drug optimization system 110 shown in FIG. 1. Constant parameters may be selected for the treatment possibility simulation. Table II below shows exemplary parameters.

[0045] [Table 2]

[0046] Patients can be categorized into four subsets: subset I (warm & dry), subset II (warm & wet), subset III (cold & dry), and subset IV (cold & wet) according to the Forrester classification. Table 602 shows the statistics of the patient (both cardiovascular parameters and cardiovascular function metrics) before drug infusion. In Table 602, the cardiac index (CI) is defined as CO / body surface area (BSA). The BSA herein may be set to the average value of 1.6 m 2 and can be set to the average value.

[0047] Therapeutic potential analysis can be used to confirm the validity of the proposed optimization system. Based on Table 402 shown in FIG. 4, two control goals were selected. Based on the selection of the control goals, the therapeutic potential analysis can generate three results. (1) Treatable for Goal 1, when the optimal solution is achievable for at least one of the randomly selected patients in Control Goal 1. (2) Treatable for Goal 2, when the patient is not treatable for Goal 1 and the optimal solution is achievable for at least one of the randomly selected patients in Control Goal 2. (3) Untreatable, when the patient is not treatable for either Goal 1 or Goal 2. Graph 604 shows the results for two cardiovascular function metrics P LA and CI. Within Graph 604, the result for Goal 1 is shown as 608 and the result for Goal 2 is shown as 606. Graph 610 shows the MAP statistics before and after for each of the Goal 1 patients, Goal 2 patients, and untreatable patients. Graph 612 shows the P LA statistics before and after for each of the Goal 1 patients, Goal 2 patients, and untreatable patients. Graph 614 shows the CI statistics before and after for each of the Goal 1 patients, Goal 2 patients, and untreatable patients. Thus, the embodiments disclosed herein can also generate whether a patient population is treatable or whether alternative non-drug (e.g., mechanical type) treatments may be devised.

[0048] FIG. 7 shows exemplary graphs 702-718 for pathophysiological scenario analysis according to an exemplary embodiment of the present disclosure. The pathophysiological scenario analysis may be performed by the drug optimization system 110 shown in FIG. 1. The pathophysiological scenario analysis includes (1) warm & wet patients in subset II [R s = 1.4, E es = 2.5, HR = 80, SBV = 3500], (2) cold & dry patients in subset III [= 1.0, = 1.5, HR = 100, SBV = 800], and (3) cold & wet patients in subset IV: [R s = 1.4, E esIt can be for three patient scenarios of [[ID=]], HR = 120, and SBV = 2700. Graph 702 (cardiovascular parameter R s )), 704 (cardiovascular parameter E es ), 706 (cardiovascular parameter HR), and 708 (cardiovascular parameter SBV) each show the initial state, target 1 state, and target 2 state of three patients. Graphs 710, 712, 714, 716, and 718 show the adjusted (or optimized) drug infusions (target 1, target 2, and maximum dose) for each patient in subsets II, III, and IV. In particular, graph 710 shows the optimized amount of dobutamine (DOB), graph 712 shows the optimized amount of norepinephrine (NE), graph 714 shows the optimized amount of sodium nitroprusside (SNP), graph 716 shows the optimized amount of dextran (DEX), and graph 718 shows the optimized amount of furosemide (FRO). As shown, the optimized drugs are below the maximum dose and within the recommended clinical use guidelines.

[0049] FIG. 8 shows a block diagram of an exemplary computing device 800 that implements various functions and processes according to an exemplary embodiment of the present disclosure. For example, in some embodiments, computing device 800 may function as server 102 and client 106, or a portion or combination thereof. Computing device 800 may also perform one or more steps of method 500. Computing device 800 is implemented on any electronic device that operates a software application derived from compiled instructions, including, but not limited to, personal computers, servers, smartphones, media players, electronic tablets, game consoles, email devices, and the like. In some embodiments, computing device 800 includes one or more processors 802, one or more input devices 804, one or more display devices 806, one or more network interfaces 808, and one or more computer-readable media 812. Each of these components is coupled by bus 810.

[0050] The display device 806 includes any display technology, including but not limited to a display device using liquid crystal display (LCD) or light emitting diode (LED) technology. The processor 802 uses any processor technology, including but not limited to a graphics processor and a multi-core processor. The input device 804 includes any known input device technology, including but not limited to a keyboard (including a virtual keyboard), a mouse, a trackball, and a touch sensor type pad or display. The bus 810 includes any internal or external bus technology, including but not limited to ISA, EISA, PCI, PCI Express, USB, Serial ATA, or FireWire. The computer-readable medium 812 includes any non-transitory computer-readable medium that provides instructions to the processor 802 for execution, including but not limited to non-volatile memory media (e.g., optical disks, magnetic disks, flash drives, etc.) or volatile media (e.g., SDRAM, ROM, etc.).

[0051] The computer-readable medium 812 includes various instructions 814 for implementing an operating system (e.g., Mac OS®, Windows®, Linux®). The operating system may be multi-user, multi-processing, multi-tasking, multi-threading, real-time, etc. The operating system performs basic tasks including, but not limited to, recognition of input from the input device 804, transmission of output to the display device 806, tracking of files and directories on the computer-readable medium 812, control of peripheral devices (e.g., disk drives, printers, etc.) that can be controlled directly or through an I / O controller, and management of traffic on the bus 810. The network communication instructions 816 establish and maintain a network connection (e.g., software for implementing communication protocols such as TCP / IP, HTTP, Ethernet, telephone communication, etc.).

[0052] The drug optimization system 818 includes instructions for performing the disclosed process for determining an optimal combination of drugs for heart failure patients as described throughout this disclosure. The application 820 can include applications that use or perform the processes described herein and / or other processes. The process may also be implemented within an operating system.

[0053] The described features can be implemented in one or more computer programs executable on a programmable system including at least one programmable processor coupled to receive data and instructions from, and to send data and instructions to, a data storage system, at least one input device, and at least one output device. A computer program is a set of instructions that can be used directly or indirectly in a computer to perform a particular activity or to cause a particular result. The computer program can be described in any form of programming language, including a compiled or interpreted language (e.g., Objective-C, Java), and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. In one embodiment, this may include Python. Thus, the computer program is multilingual.

[0054] Processors suitable for the execution of a command program may include, by way of example, both general-purpose and special-purpose microprocessors, as well as any one of the processors or cores of a single computer or multiple processors or cores of any type. Generally, a processor can receive instructions and data from read-only memory, random access memory, or both. Essential elements of a computer can include a processor for executing instructions, as well as one or more memories for storing instructions and data. Generally, a computer may also include or be operatively coupled to communicate with one or more mass storage devices for storing data files, such devices including magnetic disks such as internal hard disks and removable disks, magneto-optical disks, and optical disks. Storage devices suitable for tangibly embodying computer program instructions and data may include all forms of non-volatile memory, including, by way of example, semiconductor memory devices such as EPROM, EEPROM, and flash memory devices, magnetic disks such as internal hard disks and removable disks, magneto-optical disks, and CD-ROM and DVD-ROM disks. The processor and memory may be supplemented or incorporated by an ASIC (application specific integrated circuit).

[0055] To enable interaction with a user, the above functions may be implemented on a computer having a display device such as a CRT (cathode ray tube) or LCD (liquid crystal display) monitor for displaying information to the user, a keyboard by which the user can provide input to the computer, and a pointing device such as a mouse or trackball.

[0056] The above features can be implemented in a computer system including front-end components such as a client computer having a graphical user interface or an Internet browser, or a combination thereof, or including middleware components such as an application server or an Internet server, or including back-end components such as a data server. The components of the system may be connected by digital data communication in any form or medium such as a communication network. Examples of communication networks include, for example, telephone networks, LANs, WANs, and the computers and networks forming the Internet.

[0057] The computer system may include clients and servers. The clients and servers may generally be remote from each other and typically may interact through a network. The relationship between the client and the server may be created by computer programs operating on respective computers and having a client-server relationship with each other.

[0058] One or more functions or steps of the disclosed embodiments may be implemented using an API. The API can define one or more parameters passed between a calling application and other software code (e.g., an operating system, library routines, functions) that provides a service, provides data, or performs an operation or calculation.

[0059] The API may be implemented as one or more calls within program code that send or receive one or more parameters through a parameter list or other structure based on the calling convention defined in the API specification. The parameters may be constants, keys, data structures, objects, object classes, variables, data types, pointers, arrays, lists, or another call. The API calls and parameters may be implemented in any programming language. The programming language can define the vocabulary and calling convention that a programmer uses to access the functions supported by the API.

[0060] In some embodiments, the API call can report to the application the functions of the device that operate the application, such as input functions, output functions, processing functions, power functions, communication functions, and the like.

[0061] Additional examples of the method and device embodiments described herein are suggested in accordance with the structures and techniques described herein. Other non-limiting examples may be configured to operate separately or may be combined in any substitution or combination with any one or more of the other examples given above or throughout this disclosure.

[0062] It will be understood by those skilled in the art that the present disclosure can be embodied in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments disclosed herein are to be considered in all respects as illustrative and not restrictive. The scope of the present disclosure is indicated by the appended claims rather than the foregoing description, and it is intended that all changes which come within the meaning and range of equivalency of the claims are to be embraced.

[0063] It should be noted that the terms "comprising" and "including" are to be construed to mean "including, but not limited to". When not already expressly recited within the claims, the term "a" shall be construed to mean "at least one", and terms such as "the", "said", etc. shall be construed to mean "at least one of the", "said at least one of the", etc. Further, it is applicant's intent that only claims containing the explicit language "means for" or "steps for" be construed under 35 U.S.C. § 112(f). Claims that do not explicitly contain the phrase "means for" or "steps for" should not be construed under 35 U.S.C. § 112(f).

Claims

1. A computer-readable non-transitory storage medium storing computer program instructions, which when executed, receive a plurality of current cardiovascular function metrics of a patient and a plurality of candidate drugs to be used to reach a plurality of desired cardiovascular function metrics, determine an optimal dosage of the plurality of candidate drugs to reach the plurality of desired cardiovascular function metrics, optimize a dosage combination of the plurality of candidate drugs to reach a plurality of desired cardiovascular parameters corresponding to the plurality of desired cardiovascular function metrics from a plurality of current cardiovascular parameters corresponding to the plurality of current cardiovascular function metrics, map the plurality of desired cardiovascular function metrics from the plurality of desired cardiovascular parameters and the plurality of current cardiovascular function metrics from the plurality of current cardiovascular parameters, including determining, output the optimal dosage of the plurality of candidate drugs, and cause operations including. A computer-readable non-transitory storage medium.

2. The computer-readable non-transitory storage medium according to claim 1, wherein the plurality of current cardiovascular function metrics and the plurality of desired cardiovascular function metrics include one or more of mean arterial pressure, left atrial pressure, cardiac output, or cardiac index.

3. The computer-readable non-transitory storage medium according to claim 1, wherein the plurality of current cardiovascular parameters and the plurality of desired cardiovascular parameters include one or more of systemic vascular resistance, myocardial contractility, heart rate, or preload blood volume.

4. The computer-readable non-transitory storage medium according to claim 1, wherein the plurality of candidate drugs include at least one of inotropic agents, vasopressors, vasodilators, fluids, or diuretics.

5. The computer-readable non-transitory storage medium according to claim 1, wherein the optimal dosage of the plurality of candidate drugs is constrained by a linear relationship among the plurality of candidate drugs, the plurality of current cardiovascular parameters, and the plurality of desired cardiovascular parameters.

6. The computer-readable non-transitory storage medium according to claim 1, wherein the optimal dosage of the plurality of candidate drugs is constrained by a maximum dosage limit for each of the plurality of candidate drugs.

7. The mapping of the plurality of desired cardiovascular function metrics from the plurality of desired cardiovascular parameters is based on hemodynamic analysis, the computer-readable non-transitory storage medium according to claim 1.

8. The hemodynamic analysis includes analytically deriving the plurality of desired cardiovascular function metrics from the plurality of desired cardiovascular parameters, the computer-readable non-transitory storage medium according to claim 7.

9. The hemodynamic analysis includes numerically determining the plurality of desired cardiovascular parameters based on filtering using the plurality of desired cardiovascular function metrics, the computer-readable non-transitory storage medium according to claim 7.

10. Outputting the optimal dosages of the plurality of candidate drugs includes displaying the optimal dosages on a screen, the computer-readable non-transitory storage medium according to claim 1.

11. A computer-implemented method comprising: receiving a plurality of current cardiovascular function metrics of a patient and a plurality of candidate drugs to be used to reach a plurality of desired cardiovascular function metrics; determining optimal dosages of the plurality of candidate drugs to reach the plurality of desired cardiovascular function metrics, optimizing dosage combinations of the plurality of candidate drugs to reach a plurality of desired cardiovascular parameters corresponding to the plurality of desired cardiovascular function metrics from a plurality of current cardiovascular parameters corresponding to the plurality of current cardiovascular function metrics; mapping the plurality of desired cardiovascular function metrics from the plurality of desired cardiovascular parameters and the plurality of current cardiovascular function metrics from the plurality of current cardiovascular parameters; including determining; and outputting the optimal dosages of the plurality of candidate drugs. A computer-implemented method.

12. The plurality of current cardiovascular function metrics and the plurality of desired cardiovascular function metrics include one or more of mean arterial pressure, left atrial pressure, cardiac output, or cardiac index, the computer-implemented method according to claim 11.

13. The plurality of current cardiovascular parameters and the plurality of desired cardiovascular parameters include one or more of systemic vascular resistance, myocardial contractility, heart rate, or preload blood volume, the computer-implemented method according to claim 11.

14. The computer-implemented method according to claim 11, wherein the plurality of candidate drugs includes at least one of a positive inotropic agent, a vasopressor, a vasodilator, a fluid, or a diuretic.

15. The computer-implemented method according to claim 11, wherein the optimal dosages of the plurality of candidate drugs are constrained by a linear relationship between the plurality of candidate drugs, the plurality of current cardiovascular parameters, and the plurality of desired cardiovascular parameters.

16. The computer-implemented method according to claim 11, wherein the optimal dosages of the plurality of candidate drugs are constrained by the maximum dosage limit of each of the plurality of candidate drugs.

17. The computer-implemented method according to claim 11, wherein the mapping of the plurality of desired cardiovascular function metrics from the plurality of desired cardiovascular parameters is based on hemodynamic analysis.

18. The computer-implemented method according to claim 17, wherein the hemodynamic analysis includes analytically deriving the plurality of desired cardiovascular function metrics from the plurality of desired cardiovascular parameters.

19. The computer-implemented method according to claim 17, wherein the hemodynamic analysis includes numerically determining the plurality of desired cardiovascular parameters based on filtering using the plurality of desired cardiovascular function metrics.

20. A system comprising: a non-transitory computer-readable medium storing computer program instructions; and one or more processors configured to execute the computer program instructions to cause operations including: receiving a plurality of current cardiovascular function metrics of a patient and a plurality of candidate drugs to be used to reach a plurality of desired cardiovascular function metrics; determining optimal dosages of the plurality of candidate drugs to reach the plurality of desired cardiovascular function metrics; optimizing dosage combinations of the plurality of candidate drugs to reach a plurality of desired cardiovascular parameters corresponding to the plurality of desired cardiovascular function metrics from a plurality of current cardiovascular parameters corresponding to the plurality of current cardiovascular function metrics; and mapping the plurality of desired cardiovascular function metrics from the plurality of desired cardiovascular parameters and the plurality of current cardiovascular function metrics from the plurality of current cardiovascular parameters. ​ determining, including; outputting the optimal dosages of the plurality of candidate drugs; A system including.

Images