Optimal drug therapy for multiple hemodynamic control

Abstract

Systems and methods for improved hemodynamic controls are disclosed herein. The systems and methods may include receiving, by a computing system, a first input including a vector representation of a desired level of at least one cardiovascular parameter; receiving, by the computing system, a second input including a vector representation of a cardiovascular state of a patient; receiving, by the computing system, a third input including a matrix representation of a plurality of drugs; optimizing, by the computing system, an amount of each drug from the plurality of drugs; and controlling, by the computing system, a response of the cardiovascular parameters and hemodynamics into desired ranges.

Description

OPTIMAL DRUG THERAPY FOR MULTIPLE HEMODYNAMIC CONTROLCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to U.S. Provisional Application No. 63 / 571,847, filed March 29, 2024, which is hereby incorporated by reference in its entirety.FIELD

[0002] The present disclosure is generally directed to systems and methods for improved hemodynamic control. In particular, the present disclosure is directed to obtaining a desired hemodynamic response based on optimized input drugs against the present patient’s condition.BACKGROUND

[0003] Ischemic heart disease is the leading cause of death worldwide. Treatment of acute heart failure (AHF) resulting from ischemic insult is often a challenging clinical scenario, where management of blood flow and pressure within the cardiovascular (CV) system is crucial for improving patient symptoms, enhancing organ perfusion, slowing the progression of heart failure, and potentially saving lives. Minimizing myocardial oxygen consumption (M702) is preferable to alleviate myocardial ischemia, reduce infarct size, and improve prognosis. Beta-blockers, which are known to lower MV02, are difficult to use under compromised hemodynamics because their negative inotropic and chronotropic effects could further deteriorate hemodynamics. Thus, the optimal therapy has remained a long-lasting challenge for AHF treatment.

[0004] In addition, clinical deployment of previous systems has been infeasible due to reliance on clinically infeasible measurements of the hemodynamics. These systems are therefore unable to operate effectively as there are different uncertainties and variables from patient to patient. While they may simulate the hemodynamic response to therapy, they do not operate well in the real-world clinical setting.SUMMARY

[0005] In some embodiments, a method of hemodynamic control is provided. The method may include receiving, by a computing system, a first input comprising a vector representation of a desired level of at least one cardiovascular parameter. The method may further include receiving, by the computing system, a second input comprising a vector representation of a cardiovascular state of a patient, wherein the cardiovascular state comprises a level of a plurality of cardiovascular parameters. The method may further include receiving, by the computing system, a third input comprising a matrix representation of a plurality of drugs, wherein the matrix representation includes an effect on the plurality of cardiovascular parameters of the plurality of drugs. The method may further include optimizing, by the computing system, an amount of each drug from the plurality of drugs based on the first input, the second input, and the third input. The method may further include controlling, by the computing system, a response of the cardiovascular parameters and hemodynamics, wherein thecontrolling is based on at least the amount of each drug, and wherein the controlling includes a determination of a level of the at least one cardiovascular parameter in relation to the desired level.

[0006] In some embodiments, a system may be provided. The system may include a non-transitory storage medium storing computer program instructions and a processor configured to execute the computer program instructions to cause operations. The operations may include receiving, by a computing system, a first input comprising a vector representation of a desired level of at least one cardiovascular parameter. The operations may further include receiving, by the computing system, a second input comprising a vector representation of a cardiovascular state of a patient, wherein the cardiovascular state comprises a level of a plurality of cardiovascular parameters. The operations may further include receiving, by the computing system, a third input comprising a matrix representation of a plurality of drugs, wherein the matrix representation includes an effect on the plurality of cardiovascular parameters of the plurality of drugs. The operations may further include optimizing, by the computing system, an amount of each drug from the plurality of drugs based on the first input, the second input, and the third input. The operations may further include controlling, by the computing system, a response of the cardiovascular parameters and hemodynamics, wherein the controlling is based on at least the amount of each drug, and wherein the controlling includes a determination of a level of the at least one cardiovascular parameter in relation to the desired level.

[0007] In some embodiments, a non-transitory storage medium storing computer program instructions may be provided. The computer program instructions that when executed may cause a computing system to perform operations. The operations may include receiving, by a computing system, a first input comprising a vector representation of a desired level of at least one cardiovascular parameter. The operations may further include receiving, by the computing system, a second input comprising a vector representation of a cardiovascular state of a patient, wherein the cardiovascular state comprises a level of a plurality of cardiovascular parameters. The operations may further include receiving, by the computing system, a third input comprising a matrix representation of a plurality of drugs, wherein the matrix representation includes an effect on the plurality of cardiovascular parameters of the plurality of drugs. The operations may further include optimizing, by the computing system, an amount of each drug from the plurality of drugs based on the first input, the second input, and the third input. The operations may further include controlling, by the computing system, a response of the cardiovascular parameters and hemodynamics, wherein the controlling is based on at least the amount of each drug, and wherein the controlling includes a determination of a level of the at least one cardiovascular parameter in relation to the desired level.BRIEF DESCRIPTION OF THE FIGURES

[0008] The accompanying drawings, which are incorporated herein and form part of the specification, illustrate the present disclosure and, together with the description, further serve to explainthe principles of the present disclosure and to enable a person skilled in the relevant art(s) to make and use embodiments described herein.

[0009] FIG. 1 depicts a block diagram of an illustrative computing environment, in accordance with example embodiments.

[0010] FIG. 2 depicts a flowchart of an illustrative system of hemodynamic control, in accordance with example embodiments.

[0011] FIG. 3 depicts a schematic representation of a CV model, in accordance with example embodiments.

[0012] FIG. 4 depicts an illustrative system of simulating hemodynamic control, in accordance with example embodiments.

[0013] FIG. 5 depicts an illustrative system of hemodynamic control, in accordance with example embodiments.

[0014] FIG. 6 depicts a flowchart of an illustrative method of hemodynamic control, in accordance with example embodiments.

[0015] FIG. 7 depicts a block diagram of an example computing device, in accordance with example embodiments.

[0016] The features of the present disclosure will become more apparent from the detailed description set forth below when taken in conjunction with the drawings, in which like reference characters identify corresponding elements throughout. In the drawings, like reference numbers generally indicate identical, functionally similar, and / or structurally similar elements. Additionally, generally, the left-most digit(s) of a reference number identifies the drawing in which the reference number first appears. Unless otherwise indicated, the drawings provided throughout the disclosure should not be interpreted as to-scale drawings.DETAILED DESCRIPTION

[0017] The present disclosure is generally directed to systems and methods for improved hemodynamic control. In particular, the present disclosure is directed to obtaining a desired hemodynamic response based on optimized input drugs against the present patient’s condition.

[0018] Disclosed herein is systems and methods for improved hemodynamic control. Embodiments can include a system of drug therapy. Embodiments can include a method of drug therapy. As discussed above, conventional systems are not feasible in the clinical setting. In addition, the optimal AHF treatment has been a long-lasting challenge. The one or more techniques disclosed herein improve upon conventional methods by utilizing a discrete and feasible measurement feedback such that the system is not relying on continuous measurements, which are infeasible in the clinical setting. In the clinical setting, an amount of drugs can be optimized to guide the CV metrics to a safe level. The amount can be simulated with various baroreflex responses to determine how the drugs will affect the hemodynamics across a range of patients. The determination can serve as a verification of the optimizedamount prior to injecting the drugs into the patient. In addition, the system can model an optimal therapy which minimizes MVO2while also keeping the other CV metrics at manageable levels. Therefore, the clinical feasibility and accuracy of cardiac monitoring and therapy that use the disclosed embodiments is significantly improved in comparison to the conventional systems. This improved clinical feasibility can support not only clinical decision making, for example, adjusting drug dosages in a current clinician cardiac therapy, but also closed-loop hemodynamic control systems that need to account for patient variability.

[0019] FIG. 1 is a block diagram illustrating an illustrative computing environment 100 for controlling the hemodynamics of a patient, according to example embodiments. As shown, the computing environment 100 may be based on a client-server model, with a server 135 connected to at least one client device 180. The computing environment 100 can include a patient monitoring system 110 and a drug dispensing system 120 communicatively coupled to a server 135. In some embodiments, the patient monitoring system 110 and the drug dispensing system 120 can be considered clients to the server 135. It should, however, be understood that the client-server model is just for illustration and ease of explanation and should not be considered limiting. Therefore, any type of computing environment performing the functionality disclosed herein should be considered within the scope of this disclosure. Furthermore, the individual components of the computing environment 100 are just illustrative and computing environments with alternative, additional, or fewer number of components should be considered within the scope of this disclosure.

[0020] The computing environment 100 may be generally in a clinical setting to monitor hemodynamics for cardiac patients such as patients with AHF. In some example use cases, the server 135 may store different software modules 140 that may be accessed by the clients 180, patient monitoring system 110, and drug dispensing system 120 using the network 130. The clients 180 themselves may have standalone applications (not shown) to access the software modules 140. Alternatively, the clients 180 may access the software modules 140 through a browser application, for example. Similarly, the patient monitoring system 110 and the drug dispensing system 120 may access the software modules 140 through any type of firmware and / or software installed in the patient monitoring system 110 and the drug dispensing system 120. In some embodiments, the patient monitoring system 110 and the drug dispensing system 120 may communicate with the server 135 using one or more of the clients 180.

[0021] The hardware of the server 135 storing the software modules 140 may include any kind of computing device. For example, the server 135 may include any kind of computing device, including but not limited to a server computer, a desktop computer, a laptop computer, a tablet computer, a smartphone. The server 135 may not necessarily be at a single location and may be realized by a network of computers. Furthermore, the server 135 may not necessarily be co-located within the clinical settingitself and may be hosted by a third-party cloud computing provider. Therefore, any kind of server 135 should be considered within the scope of this disclosure.

[0022] As described above, the clients 180, the patient monitoring system 110, and / or the drug dispensing system 120 may access the server 135 through the network 130. The network 130 may include any combination of one or more packet switching networks (e.g., an IP based network) and one or more circuit switching networks (e.g., a cellular telephony network). Some non-limiting examples of the network 130 include a local area network, a metropolitan area network, a wide area network such as the Internet, etc. Similarly, non-limiting examples of the clients 180 may include a desktop terminal (e.g., desktop terminal 180a), a laptop computer (e.g., a laptop computer 180b), a tablet computer (e.g., a tablet computer 180c), a smartphone (e.g., a smartphone 180d), etc. Any type of computing device that allows an access to the server 135 through the network 130 should be considered within the scope of this disclosure. Furthermore, the functionality described within this disclosure can be distributed in any fashion, i.e., functionality of the server 135 may be performed by one or more clients 180 and vice versa.

[0023] The patient monitoring system 110 may include any combination of diagnostic and therapeutical devices used for cardiac patients. For instance, the patient monitoring system 110 may include cardiac monitors, Holter ECG monitors, cardiac echo devices, cardiac nuclear stress test devices, cardiac catheters, pulmonary artery catheters including a balloon tip, cardiac drug infusing devices, external pacemakers, arterial lines, heart rate monitors, and / or any other type of cardiac diagnostic and therapeutic devices. Although a single patient monitoring system 110 is shown, any number of monitoring systems is to be considered within the scope of this disclosure. Furthermore, one patient monitoring system 110 may not necessarily be localized within a single device and may include a combination of devices (and constituent software / firmware) distributed throughout the clinical setting. Additionally, the functionality between the patient monitoring system 110 and the server 135 may be interchangeable, for example, some of the software modules 140 implemented in the server 135 may be implemented by the patient monitoring system 110. In some embodiments, the patient monitoring system 110 may implement a closed-loop hemodynamic control system that controls the amount of drug infused in response to monitored hemodynamics.

[0024] The drug dispensing system 120 may include any combination of drug injection devices used for cardiac patients. For instance, the drug dispensing system 120 may include continuous intravenous systems, intravenous systems, cardiac drug infusing devices, and / or any other type of drug infusing systems. Although a single drug dispensing system 120 is shown, any number of dispensing systems is to be considered within the scope of this disclosure. Furthermore, one drug dispensing system 120 may not necessarily be localized within a single device and may include a combination of devices (and constituent software / firmware) distributed throughout the clinical setting. Additionally, the functionality between the drug dispensing system 120 and the server 135 may be interchangeable, for example, someof the software modules 140 implemented in the server 135 may be implemented by the drug dispensing system 120. In some embodiments, the drug dispensing system 120 may implement a closed-loop hemodynamic control system that controls the amount of drug infused in response to monitored hemodynamics. In some embodiments, the drug dispensing system 120 can dispense a plurality of drugs into the patient substantially simultaneously.

[0025] As described above, the server 135 may include multiple software modules. FIG. 1 shows some non-limiting example software modules: a cardiac data input module 150, a CV metric calculation module 152, a CV parameter calculation module 154, a closed-loop hemodynamic control module 156, an optimal dosage calculation module 158, a model development and simulation module 160, and an experimental data ingestion module 162. It should be understood that this described modularization of the server 135 functionality is just for the ease of explanation and should not be considered limiting. Therefore, any kind of alternative modularization should be considered within the scope of this disclosure.

[0026] The cardiac data input module 150 may receive cardiac data from the clients 180 and the patient monitoring system 110. The received cardiac data may include any kind of cardiac data measured or estimated in the clinical setting. For instance, the cardiac data may include left ventricular end- diastolic pressure and volume and end-systolic pressure and volume that may be generated by echocardiography. The cardiac data may further include the compliance of both the pulmonary circulation and the systemic circulation. The cardiac data may further include pulmonary capillary wedge pressure and cardiac output measured through pulmonary artery catheterization. The cardiac data may further include cardiac output measured through thermodilution and heart rate measured through ECG. Additionally, the received cardiac data may include current CV metrics for a patient and target CV metrics. For instance, as the current CV metrics, cardiac data input module 150 may receive one or more of the current measurements of left atrial pressure, right atrial pressure, cardiac output, mean arterial pressure, or myocardial oxygen consumption. Similarly, as the target CV metrics, the cardiac data input module 150 may receive one or more of the desired measurements of left atrial pressure, right atrial pressure, cardiac output, mean arterial pressure, or myocardial oxygen consumption. The CV metrics data, in addition to other data, may be used for enabling a closed-loop hemodynamic control module. Additionally, the received cardiac data can include current CV parameters for a patient and target CV parameters. For instance, as the current CV parameters, cardiac data input module 150 may receive measurements of heart rate. The CV parameters data, in addition to other data, may be used for enabling a closed loop hemodynamic control module. In some embodiments, the cardiac data input module 150 may support real-time data input (e.g., for closed-loop hemodynamic control), where the server 135 processes the received cardiac data in real-time. In other embodiments, the cardiac data input module 150 may support batch processing, where individual cardiac data are batched (e.g., buffered or stored), and the processing may be performed together for the batched data (e.g., during off-peak hoursfor the server 135). Therefore, the cardiac data input module 150 may manage the receipt of cardiac data from the clients 180 and the patient monitoring system 110 for any type of processing.

[0027] The CV metrics calculation module 152 may calculate CV metrics using the analytical models disclosed throughout this disclosure. In some embodiments, the CV metrics may include one or more of mean arterial pressure, left atrial pressure, right atrial pressure, cardiac output, and myocardial oxygen consumption. In some embodiments, the CV metrics calculation module 152 may calculate MAP as an index of mean arterial pressure, PLAas an index of left atrial pressure, PRAas an index of right atrial pressure, CO as an index of cardiac output, and MV02as an index of myocardial oxygen consumption. Such CV metrics calculations may be based on end-diastolic pressure and volume, end- systolic pressure and volume, the resistance of pulmonary venous return, the compliance of the pulmonary circulation and the systemic circulation, the stressed blood volume, the heart rate, the cardiac contractility, the systemic vascular resistance, and the body weight. Additionally, the CV metrics calculations may be based on pulmonary capillary wedge pressure, thermodilution, and / or measurements taken of the mean arterial pressure by an arterial line. These measurements may be passed on to the CV metric calculation module 152 by the cardiac data input module 150.

[0028] The CV parameters calculation module 154 may calculate CV metrics using the analytical models disclosed throughout this disclosure. In some embodiments, the CV parameters may include one or more of systemic vascular resistance, pulmonary vascular resistance, left ventricular cardiac contractility, right ventricular cardiac contractility, heart rate, and stressed blood volume. In some embodiments, the CV parameter calculation module 154 may calculate Rsas an index of systemic vascular resistance, Rpas an index of pulmonary vascular resistance, Eg as an index of left ventricular cardiac contractility,as an index of right ventricular cardiac contractility, HR as an index of heart rate, and SBV as an index of stressed blood volume. Such CV parameter calculations may be based on left ventricular end-diastolic pressure and volume, right ventricular end-diastolic pressure and volume, mean arterial pressure, cardiac output, left atrial pressure, right atrial pressure, myocardial oxygen consumption. Additionally, the CV parameters calculations may be based on pulmonary capillary wedge pressure, cardiac output measured by thermodilution, mean arterial pressure measured by an arterial line, mean pulmonary pressure measured by a pulmonary arterial catheter, and heart rate. These measurements may be passed on to the CV parameter calculation module 154 by the cardiac data input module 150.

[0029] The closed- loop hemodynamic control module 156 may implement an automatic infusion of an optimal combination of drugs (e.g., calculated by the optimal dosage calculation module 158). That is, the closed-loop hemodynamic control module 156 may regularly monitor the CV metrics calculated by the CV metric calculation module 152, and based on this monitoring, transmit instructions to thedrug dispensing system 120 to infuse the optimal combination of drugs. This automatic infusion may not necessarily require clinician intervention to keep a patient within a desired range of hemodynamics.

[0030] The optimal dosage calculation module 158 may calculate optimal dosage based on the CV metrics and / or CV parameters by the CV metric calculation module 152 and / or the CV parameter calculation module 154, respectively. For example, the optimal dosage calculation module 158 may compare the calculated and / or measured CV metrics and / or CV parameters against a target baseline and / or received desired CV metrics and / or CV parameters and invoke one or more analytical models disclosed herein to calculate the optimal dosage of drugs. The optimal dosage calculation module 158 may consider the different effects (e.g., a first drug may cause a change in one direction for a CV metric and a second drug may cause a change in an opposite direction) to generate an optimal combination.

[0031] The model development and simulation module 160 may allow a model developer to develop and simulate one or more analytical modules. For instance, the model development and simulation module 160 may provide an interface, e.g., a graphical user interface, for the model developer to define one or more analytical models. Furthermore, the model development and simulation module 160 may allow the model developer to upload and / or port a pre-defined analytical module to the server 135. The model development and simulation module 160 may therefore generally provide any kind of computing environment support to develop the analytical models described throughout this disclosure.

[0032] The model development and simulation module 160 may further allow the model developer to simulate the analytical models. The simulations may include, for example, numerical simulation, where collected numerical data may be used on the analytical models to observe the outputs. The simulations may produce, for example, numerical data, graphical data, and / or any other type of output data. The model development and simulation module 160 may generally allow for validations of the analytical models based on these simulations (e.g., to determine whether the analytical models perform as desired with simulated scenarios).

[0033] The experimental data ingestion module 162 may ingest experimental data used for model development. For instance, the experimental data may include measured CV parameters and / or metrics of animals. Such experimental data may be used by the model development and simulation module 160 to simulate the analytical models. Other experimental data may include a detailed experimental data containing both inputs and outputs, and can be used to compare the real-world results with the simulated results. In yet another example, the experimental data may include a continuous stream of data as the patients are being treated in clinical settings, which may be used to continuously modify and / or refine the analytical models. Therefore, the experimental data ingestion module 162 may receive any kind of real-world numerical data that may be used to develop, refine, and / or modify the analytical modules disclosed throughout this disclosure.

[0034] After one or more analytical models have been developed and validated, clinicians may use the software modules 140 within the server 135 in the therapy of patients such as AHF patients. In anexample operation of determining left ventricular cardiac contractility, a clinician may use the patient monitoring system 110 to non-invasively measure a single point of left ventricular end-diastolic volume and pressure using echocardiography techniques. This measurement may either be entered by the clinician to a client 180 to be transmitted to the server 135 and / or directly transmitted by the patient monitoring system 110 to the server 135. The clinician may further measure pulmonary capillary wedge pressure and cardiac output using a pulmonary artery catheterization and the thermodilution method, respectively, (which may be functionally supported by the patient monitoring system 110). The thermodilution method may include injecting a defined amount of cold fluid in the bloodstream and measuring the temperature change a separate point to determine the cardiac output. These measurements too may be transmitted to the server 135 through a client 180 and / or the patient monitoring system 110. The cardiac data input module 150 may receive these measurements, perform pre-processing as needed, and provide them to one or more of the CV metric calculation module 152 and / or the CV parameter calculation module 154. The CV metric calculation module 152 and / or the CV parameter calculation module 154 may use these measurements to estimate the CV metrics and / or the CV parameters. These estimated CV metrics and / or CV parameters may be used by the optimal dosage calculation module 158 to provide a recommended dosage to the clinician (e.g., on a client 180 and / or on the patient monitoring system 110). In some embodiments, the estimated CV metrics and / or CV parameters may be used by the closed-loop hemodynamic control module 156 to provide signals to the drug dispensing system 120 for an infusion based on the optimal dosage.

[0035] In various embodiments, the stages of the illustrative computing environment 100 can provide unidirectional or bidirectional communications (as indicated in FIG. 1) by and between the patient monitoring system 110 and the server 135 and between the drug dispensing system 120 and the server 135. In various embodiments, one or more of the stages can operate in a serial or parallel manner with other stages of the computing environment 100. It can further be noted that the depicted architecture for the computing environment 100 is simply intended for illustrative purposes and that the computing environment 100 can be arranged differently (i.e., components or stages can be connected in different manners) or include additional components or stages.

[0036] FIG. 2 is a block diagram illustrating an illustrative system 200 of hemodynamic control, according to example embodiments. The system 200 may include an input, u, a state determination, x. and an output, y. CV parameter calculation module 154 can determine an initial state, xQ, of a patient based on CV parameter data and / or CV metric data from the cardiac data input module 150, which can be gathered by the patient monitoring system 110. The state of the patient can include at least one of systemic vascular resistance (Rs), pulmonary vascular resistance (Rp), left ventricular cardiac contractility, right ventricular cardiac contractility, heart rate (HR), and stressed blood volume (SBV). The cardiac contractility can be represented by end-systolic elastance (Ees). Thus, the left ventricularcardiac contractility can be represented by E^, and the right ventricular cardiac contractility can be represented by E^.

[0037] The input can include a list of drugs along with an amount for each drug. For some of the drugs, the amount can be zero. In some embodiments, the list of drugs can include, but is not limited to, a positive inotrope, a vasopressor, a vasodilator, a beta-blocker, a fluid, and / or a diuretic. In some embodiments, the beta-blocker amount can be set at a non-zero value and the other drug amounts can be determined in order to offset the potential negative effects of the beta-blocker.

[0038] Based on the initial state of the patient and a matrix representation of the effect of each of the drugs on each of the CV parameters, an end state, x, of the patient can be predicted. For example, the state of the patient at time step k can be represented by the following equation: x [fc] = xQ+ Bu [fc] , where x0is the initial CV parameters, B is a matrix representation of the effect of each of the drugs on the CV parameters and u [fc] is a vector representation of an amount of each drug. The current state, x[ / c], can represent factors that affect the patient’s overall hemodynamics. In some embodiments, x[ / c] can be a vector representation of the levels of each of the included CV parameters.

[0039] The CV metrics, which represent the hemodynamics of the patient, can be determined by discrete measuring and / or based on the CV parameters. In some embodiments, the patient monitoring system 110 can measure one or more of the CV metrics as described in FIG. 1. In some embodiments, the CV metrics can include, but is not limited to, at least one of mean arterial pressure (MAP), cardiac output (CO), mean left atrial pressure (PLA), myocardial oxygen consumption (MV02), mean right atrial pressure (PRA), and mean pulmonary arterial pressure (PAP). The CV metrics can be represented by the output (y [k]) of the system 200.

[0040] The averaged outcome of hemodynamics can be determined by circulatory equilibrium, which is the state of balance in the circulatory system of the patient, involving the heart, blood vessels, and blood. For example, a CV metric calculation module 152 and / or a CV parameter calculation module 154 can compute the equilibrium point by determining the intersection of the Frank-Starling Curve and the Guyton’s Venous Return Curve. For example, the equilibrium point can be represented by the solution of the simultaneous nonlinear equations: / (x[k], y[k]) = 0 (in Fig. 2). For example, the equilibrium point can be represented by solving the following equations:where aed, fled, and Vdare the end-diastolic pressure -volume relationship parameters, F()is the end- systolic pressure-volume relationship, Rvpis the resistance for pulmonary venous return, andCpand Csare the compliance in the pulmonary circulation and the compliance of the systemic circulation, respectively.Additionally, if both the left ventricular and the right ventricular measurements are included, a CV metric calculation module 152 and / or a CV parameter calculation module 154 can compute the equilibrium point three dimensionally. For example, the equilibrium point can be represented by solving the following equations:where Rvsis the resistance for systemic venous return.Further, MAP can be determined based on Rs, PRA, and CO. For example, MAP can be represented by the following equation:MAP - PRA= RsCO.In some embodiments, PAP can be determined based on Rp, PLA. and CO. For example, PAP can be represented by the following equation:(PAP - PLA) = RpCO.

[0041] MVO2can be determined based on the mechanical energy generated by ventricular contraction. For example, left ventricular MV02can be represented by the following equation:MV02= G40PVA + B0E + CQ)HR, where PVA is the normalized pressure-volume area per 100 g of the left ventricle, and Ao, Bo, and Coare constants which can be represented by the following chart:In some embodiments, PVA can be represented by the following equation:PVA =where BW is the body weight in kilograms.

[0042] Due to the correlation of CV parameters and CV metrics, if certain CV metrics are desired, the CV parameters can be adjusted using drugs. A drug dispensing system 120 can inject a patient with an amount of drugs determined by an optimal dosage calculation module 158 to affect the CV parameters by a target amount. The change in the CV parameters in turn causes a change in the CV metrics. In some embodiments, the desired CV metrics can be a target range. In some embodiments, the system 200 can gradually control the desired CV metrics such that for each time step k there can be a different desired CV metric range. In some embodiments, a closed-loop hemodynamic control module 156 can gradually control the CV metrics via the drug dispensing system 120 based on measurements taken by a patient monitoring system 110, CV parameters calculated by a CV parameter calculation module 154 based on CV metrics and / or CV parameters stored by the cardiac data input module 150, and an amount of drugs calculated by an optimal dosage calculation module 158. In some embodiments, a model development and simulation module 160 can be instructed by a client 180 to adjust at least one of the CV metrics at a pre-determined rate. The model development and simulation module 160 can predict outcomes of the CV metrics using various drugs and can utilize an optimal dosage calculation module 158 to determine an amount of drugs that can attain the predetermined rate of adjusting the CV metrics.

[0043] In some embodiments, the gradual control can incrementally control the CV metrics to an appropriate level for each CV metric that is deemed safe. This appropriate level can be known as the final desired value. In addition, the model development and simulation module 160 can predict the CV metrics based on the state of the patient and an amount of the drugs used as input. This allows for safe control of the hemodynamics. For example, during AHF, the CV metrics can be at dangerous levels. However, flooding the patient with drugs can have adverse effects on the patient. Therefore, a measured approach can be beneficial. Predicting the CV metrics using a model development and simulation module 160 prior to inj ecting the patient with drugs can help with determining if the proposed optimized amount of each of the drugs would be dangerous or would be beneficial to the recovery of the patient. In some embodiments, the model development and simulation module 160 can be instructed to minimize the patient’s MV02, since that has been shown to improve the prognosis of the patient. In some embodiments, the model development and simulation module 160 can be instructed to adjust the levels of the CV metrics such that they are within Subset I of the Forrester Classifications. For example, the levels of an illustrative set of CV metrics within Subset I of the Forrester Classifications can be represented by the following limits:CO > 2.20, PLA< 18.0, and 70.0 < MAP < 100.

[0044] FIG. 3 illustrates a schematic representation of an illustrative CV model 300, according to example embodiments. The CV model 300 can be used by a model development and simulation module160 to model and simulate the hemodynamic response to amounts of drugs determined by an optimal dosage calculation module 158. The CV model 300 can be a part of a hemodynamic simulator, as described below in conjunction with FIG. 4.

[0045] In CV model 300, the vascular compliance and resistance can be represented by capacitors and resistors, respectively. Contraction of each heart chamber can be represented by a time-varying elastance function. The heart valves can be represented by at least one of diodes and resistors. The systemic and pulmonary circulations, which can each include a characteristic impedance along with at least one of arterial, capillary, and venous resistances and compliances, can be represented by modified Windkessel vascular components. The CV model 300 can allow simulation of time-varying pressures and flows throughout the CV system. The CV model 300 can also allow for modulation of parameters based on at least one of the simulated drug infusions and baroreflex.

[0046] FIG. 4 illustrates a system 400 of simulating hemodynamic control, according to example embodiments. A server 135 can input a desired state, xd, of a patient into the system 400. In some embodiments, a client 180 can input the desired state of the patient into the system 400. In some embodiments, a closed-loop hemodynamic control module 156 can input the desired state of the patient into the system 400 based on stored desired values. In some embodiments, an optimal dosage calculation module 158 can input the desired state of the patient into the system 400 based on stored desired values. In some embodiments, the desired state, xd, can be a vector representation including a value for each included CV parameter. In some embodiments, the desired state, xd, can include ranges of values. A CV parameter calculation module 154 can determine an initial state, x0, of a patient based on CV parameter data and / or CV metric data from the cardiac data input module 150, which can be gathered by the patient monitoring system 110. In some embodiments, x0can be determined by measuring the patient’s CV parameters and / or CV metrics, as described in FIG. 1. In some embodiments, a patient monitoring system 110 can discretely measure one or more of the patient’s CV parameters and store the measurements in the system 400 as initial state xQ. In some embodiments, the patient monitoring system 110 can discretely measure one or more of the patient’s CV metrics. In some embodiments, the measurements may be input to a server 135 through a cardiac data input module 150. A CV parameter calculation module 154 can calculate one or more of the CV parameters, which can be stored in the system 400 as initial state x0, based on one or more of the CV metrics. In some embodiments, initial state (x0) can include a combination of the CV parameter measurements and the CV parameter calculations. In some embodiments, the CV parameter calculation module 154 can update xQin the system 400 periodically. For example, if a patient has a higher risk of AHF, the patient’s CV parameters can be monitored such that if the patient does experience AHF, the system 400 can be prepared to control the patient’s hemodynamics.

[0047] The feedforward controller can predict an amount of each drug to inject into the patient to control the patient’s hemodynamics. For example, the amount and the combinations of drug infusion can be optimized by solving the following optimization problem: minU f Iwhere Uff is the vector of normalized inputs Uff .[0] / uL. u is the upper bound of each drug, xdand xdare the lower and upper desired bounds for x, A^is Rs, x2is Ees, x3is HR, x4is SBV, ydis the desired hemodynamics, y4is MAP, y2is CO, y3is PLA, {S} is the pre-defined set of contraindicated or clinically irrational pairsis the tuning parameter for drug selection. In some embodiments, the optimal dosage calculation module 158 can be instructed to minimize the patient’s MVO2, since that has been shown to improve the prognosis of the patient. For example, the amount and the combinations of drug infusion can be optimized by solving the following optimization problem:where W1, w2, W3 , w4are the weights for tuning. The server 135 can input the optimized amount of each drug to a hemodynamic simulator.In a further example, the amount and the combinations of drug infusion can be optimized by solving the following optimization problem:whereVvare the left ventricular end-diastolic pressure-volume relationship parameters, Ppanc^V arethe right ventricular end-diastolic pressure-volume relationship parameters, the left ventricular end-systolic pressure-volume relationship, and V^is the right ventricular end-systolic pressure-volume relationship, Xjjs Rs, x2is Rp, x3is E^ , x4x5

[0048] In some embodiments, the amount of each drug can be limited by drug dosage limitations (u), clinically appropriate parameter ranges, and contraindications of the drugs. In some embodiments, the feedforward controller may use the optimal dosage calculation module 158 to determine an optimized amount for each drug. In some embodiments, the initial optimized drug amount predicted by the feedforward controller can be held constant during the operation of the hemodynamic control, such that a new drug amount is not predicted at each time increment k. The server 135 can input the optimized amount of each drug to a hemodynamic simulator.

[0049] The hemodynamic simulator can simulate a patient’s response to the input drugs. In some embodiments, the hemodynamic simulator can include the CV model 300 described in FIG. 3. In some embodiments, the hemodynamic simulator may be a component of model development and simulation module 160. In some embodiments, the hemodynamic simulator can include a baroreflex simulator. The baroreflex in the human body is a control system for maintaining a stable circulation in response to external disturbances. In some cases of patients with AHF, the arterial baroreflex mechanism is impaired, which introduces uncertainty in simulating the patient’s response to the drugs. In some embodiments, the simulator can include at least one of a representation of a normal baroreflex and arepresentation of a baroreflex dysfunction. In some embodiments, the hemodynamic simulator can predict CV parameter levels based on the input drugs and the current state of the patient. In some embodiments, the hemodynamic simulator can predict CV metrics based on the predicted CV parameters. In some embodiments, the hemodynamic simulator can include a CV metric calculation module 152 which can predict the CV metrics based on the predicted CV parameters.

[0050] The system 400 can discretely sample the patient’s CV parameters and / or CV metrics to determine the actual state of the patient prior to injecting more drugs. This discrete sampling can help to identify the remaining error caused by disturbances such as the baroreflex. The gap between the desired CV parameter values and the measured values determined by the discrete sampling can be input into the feedback controller. In some embodiments, the CV parameter measurements are determined by the CV parameter calculation module 154 based on CV metric measurements. In some embodiments, the CV metric measurements are the predicted CV metrics. In some embodiments, a patient monitoring system 110 can discretely measure the CV metrics.

[0051] The feedback controller can determine an amount of each drug to inject into the patient to control the patient’s hemodynamics based on the results of the previous injection. For example, the amount and the combinations of drug infusion can be optimized by solving the following optimization problem:where ft, [ / c] is the vector of normalized value by Ufb. [ / c] / u,, e[ / c] is the error between the desired value and the measured value at time k, and Kpand Ktare the gains for proportional -integral control.In a further example, the amount and the combinations of drug infusion can be optimized by solving the following optimization problem:J3isLA ■>and TT isPRA -Optimal dosage calculation module 158 can add the drug amount optimized by the feedforward controller to the drug amount optimized by a feedback controller. In some embodiments, the optimal dosage calculation module 158 can include the feedforward controller and the feedback controller. In some embodiments, the drug amount optimized by the feedback controller can be zero. For example, the total drug input can be represented by the following equation: u[k] = Uff + Ufb [k].In some embodiments, the feedback controller may use the optimal dosage calculation module 158 to determine an amount for each drug. In some embodiments, the closed-loop hemodynamic control module 156 may include the system 400.

[0052] FIG. 5 illustrates a system 500 of hemodynamic control, according to example embodiments. System 500 may receive, as input, desired levels of CV metrics, yd. In some embodiments, the desired levels can be generated by a client 180. In some embodiments, the desired levels can be predetermined values based on the Forrester Classifications as described in FIG. 2. In some embodiments, the predetermined values can be stored in and used by the optimal dosage calculation module 158, the closed-loop hemodynamic control module 156, and / or the model development and simulation module 160. The system 500 can perform analytical mapping to map the desired levels of the CV metrics, yd, to levels of CV parameters, xd, which can be known as desired levels of CV parameters. In some embodiments, the CV parameter calculation module 154 can perform the analytical mapping of the desired levels of the CV metrics to the levels of CV parameters. In some embodiments, the analytical mapping can be based on the system 200 as described in FIG. 2.

[0053] Optimal dosage calculation module 158 can determine the difference between a current state of a patient, represented by the CV parameters x [ / <] , and the desired levels of CV parameters, xd. For example, the difference between the current state of the patient and the desired levels of CV parameters can be represented by the following equation:Ax[ / c] = xd— x[ / c].In some embodiments, x [Zc] can be an initial state of the patient, xQ. In some embodiments, x[ / c] can be determined by measuring at least one of the CV parameters of the patient. In some embodiments, the CV parameter calculation module 154 can calculate at least a portion of x[ / c] based on one or more CV metrics measurements. In some embodiments, Ax[ / c] can be a vector representation of the difference between the current state of the patient and the desired levels of the CV parameters.

[0054] Optimal dosage calculation module 158 can determine an amount of each of a list of drugs to inject into the patient. In some embodiments, the optimal dosage calculation module 158 can include a feedforward controller and a feedback controller substantially similar to the feedforward controller and feedback controller of system 400. In some embodiments, the optimal dosage calculation module 158 can output a vector representation, u[ / c], of an amount of each drug. A person of skill in the art will understand that any number of drugs is contemplated in this system. In some embodiments, u[ / c] can include an amount for each of six drugs. In some embodiments, at least a portion of u[ / c] can be zero.

[0055] A simulator can receive u[ / c] as input. In some embodiments, the simulator may include a CV digital twin. The CV digital twin can include the CV characteristics of the patient and can include the CV model as shown in FIG. 3. In some embodiments, the simulator can predict at least one of the CV parameters and the CV metrics of the patient. In some embodiments, the simulator can be the model development and simulation module 160. In some embodiments, the simulator may use the CV metric calculation module 152 and / or CV parameter calculation module 154 to predict the CV parameters and / or the CV metrics of the patient.

[0056] Drug dispensing system 120 can inject the amounts of each drug represented by u[ / c] into a patient. In some embodiments, the system 500 can simulate a response to the drug unput and inject a real plant (patient) with the optimized drug amount sequentially or substantially concurrently. In some embodiments, the system 500 can simulate a response prior to injecting the patient to predict if the amounts of each drug will result in a safe state for the patient. In some embodiments, the system 500 can simulate a response and inject the patient substantially concurrently. In some embodiments, the drug dispensing system 120 may inject the drugs into the patient. In some embodiments, the server 135 can issue a command to the drug dispensing system 120 to inject the drugs into the patient. In some embodiments, the drug dispensing system 120 can inject the drugs substantially simultaneously.

[0057] A patient monitoring system 110 can perform discrete measurements of the patient. In some embodiments, the measurements can relate to the CV metrics. For example, MAP can be measured byan arterial line which can be placed in a radial artery, a femoral artery, or a brachial artery. For example, PLAcan be indirectly assessed by a pulmonary artery catheter. The pulmonary artery catheter can include a balloon at a tip of the catheter that when inflated wedges a small pulmonary artery branch. For example, CO can be measured by a thermodilution method, which can involve the injection of a defined amount of cold fluid into the bloodstream. In some embodiments, the current CV metrics can be represented by y [k], In some embodiments, the patient monitoring system 110 may discretely measure one or more of the CV metrics. In some embodiments, the outcome of the simulation, represented by y [k], can be included in the feedback loop.

[0058] CV parameter calculation module 154 can estimate or determine a current state of a patient based on the discrete measurements of the CV metrics and / or the CV parameters. In some embodiments, the current state either estimated or determined by the CV parameter calculation module 154 can be used as an input for the optimal dosage calculation module 158 to determine an optimal amount of each drug. In some embodiments, a state of the patient can be determined by measuring the CV metrics of the patient and calculating the CV parameters based on the equations for circulatory equilibrium discussed in FIG. 2. In some embodiments, the CV parameter calculation module 154 may calculate a state of the patient. In some embodiments, the server 135 can run through the system 500 a plurality of times until the discrete measurements taken of the patient indicate that the at least one CV metric is at a safe level, as described in system 200. As one skilled in the art will understand, there can be different amounts of each drug each time through the system 500.

[0059] In some embodiments, the system 500 can include a drug library. The simulator and the optimal dosage calculation module 158 can communicate with a drug library to determine a preferred combination of drugs for the patient.

[0060] FIG. 6 is a flowchart illustrating a method 600 of hemodynamic control, according to example embodiments. Method 600 may begin at step 610.

[0061] At step 610, a computer system can receive a first input comprising a vector representation of a desired level of at least one CV parameter. In some embodiments, the computer system can receive a vector representation of a desired level of at least one CV metric which can be analytically mapped to a vector representation of at least one CV parameter to serve as the first input. In some embodiments, a CV parameter calculation module 154 can analytically map the at least one CV metric to the at least one CV parameter. In some embodiments, the analytical mapping can include calculations as described in FIG. 2.

[0062] At step 620, the computer system can receive a second input comprising a vector representation of a CV state of a patient. The CV state of the patient can include at least one CV parameter. In some embodiments, the at least one CV parameter can be measured and input into the system through the patient monitoring system 110 and the cardiac data input module 150. In some embodiments, the at least one CV parameter can be calculated based on at least one CV metric throughthe CV parameter calculation module 154. In some embodiments, the at least one CV metric can be measured and input into the system through the patient monitoring system 110 and the cardiac data input module 150.

[0063] In some embodiments, the measuring can include measuring as described in FIG. 1. For instance, the patient monitoring system 110 may include cardiac monitors, Holter ECG monitors, cardiac echo devices, cardiac nuclear stress test devices, cardiac catheters, pulmonary artery catheters including a balloon tip, cardiac drug infusing devices, external pacemakers, arterial lines, heart rate monitors, and / or any other type of cardiac diagnostic and therapeutic devices. The received cardiac data may include any kind of cardiac data measured or estimated in the clinical setting. For instance, the cardiac data may include left ventricular end-diastolic pressure and volume and end-systolic pressure and volume that may be generated by echocardiography. The cardiac data may further include the compliance of both the pulmonary circulation and the systemic circulation. The cardiac data may further include pulmonary capillary wedge pressure and cardiac output measured through pulmonary artery catheterization. The cardiac data may further include cardiac output measured through thermodilution and heart rate measured through ECG. Additionally, the received cardiac data may include current CV metrics for a patient and target CV metrics. For instance, as the current CV metrics, cardiac data input module 150 may receive one or more of the current measurements of left atrial pressure, right atrial pressure, cardiac output, mean arterial pressure, or myocardial oxygen consumption. Similarly, as the target CV metrics, the cardiac data input module 150 may receive one or more of the desired measurements of left atrial pressure, right atrial pressure, cardiac output, mean arterial pressure, or myocardial oxygen consumption. For example, MAP can be measured by an arterial line which can be placed in a radial artery, a femoral artery, or a brachial artery. For example, PLAcan be indirectly assessed by a pulmonary artery catheter. The pulmonary artery catheter can include a balloon at a tip of the catheter that when inflated wedges a small pulmonary artery branch. For example, CO can be measured by a thermodilution method, which can involve the injection of a defined amount of cold fluid into the bloodstream. Additionally, the received cardiac data can include current CV parameters for a patient and target CV parameters. For instance, as the current CV parameters, cardiac data input module 150 may receive measurements of heart rate.

[0064] In some embodiments, the calculating can include calculations as described in system 200. The averaged outcome of hemodynamics can be determined by circulatory equilibrium, which is the state of balance in the circulatory system of the patient, involving the heart, blood vessels, and blood. For example, a CV metric calculation module 152 and / or a CV parameter calculation module 154 can compute the equilibrium point by determining the intersection of the Frank-Starling Curve and the Guyton’s Venous Return Curve. For example, the equilibrium point can be represented by solving the following equations:Additionally, if both the left ventricular and the right ventricular measurements are included, a CV metric calculation module 152 and / or a CV parameter calculation module 154 can compute the equilibrium point three dimensionally. For example, the equilibrium point can be represented by solving the following equations:Further, MAP can be determined based on Rs, PRA- and CO. For example, MAP can be represented by the following equation:MAP - PRA= RsCO.In some embodiments, PAP can be determined based on R , PLA, and CO. For example, PAP can be represented by the following equation: PAP - PLA) = RpCO.MV02can be determined based on the mechanical energy generated by ventricular contraction. For example, MV 02can be represented by the following equation:MV02= Q40PVA + B0Ees+ C HRIn some embodiments, PVA can be represented by the following equation:PVA =

[0065] At step 630, the computer system can receive a third input comprising a matrix representation of a plurality of drugs. The matrix representation can include the effect on the plurality of CV parameters of the plurality of drugs. In some embodiments, the matrix representation can be a pre -determined matrix. In some embodiments, the matrix can be developed by the closed-loop hemodynamic control module 156 based on stored effects of certain drugs on the CV parameters.

[0066] At step 640, the computer system can optimize an amount of each drug from the plurality of drugs. In some embodiments, the amount of at least one drug can be zero. In some embodiments, an optimal dosage calculation module 158 can optimize the amount of each drug. In some embodiments, the optimization can be based on the calculations described in system 400.

[0067] At step 650, the computer system can control a response of the at least one CV parameters. The controlling can be based on at least the amount of each drug. In some embodiments, the controlling can be based on at least the current state of the patient. In some embodiments, the controlling includes a determination of a level of the at least one CV parameter in relation to the desired level of the at least one CV parameter. In some embodiments, a model development and simulation module 160 can determine the response of the CV parameters.

[0068] In some embodiments, the computer system can control a response of at least one CV metric. In some embodiments, a CV metric calculation module 152 can determine the response of at least one CV metric based on the determined response of the at least one CV parameter.

[0069] FIG. 7 shows a block diagram of an example computing device 700 that implements various features and processes, according to example embodiments of this disclosure. For example, computing device 700 may function as the server 135, the clients 180, the patient monitoring system 110, the drug dispensing system 120, or a portion or combination thereof in some embodiments. Additionally, the computing device 700 may partially or wholly host and deploy CV model 300. The computing device 700 may also perform one or more steps of the method 600. The computing device 700 is implemented on any electronic device that runs software applications derived from compiled instructions, including without limitation personal computers, servers, smart phones, media players, electronic tablets, game consoles, email devices, etc. In some implementations, the computing device 700 includes one or more processors 702, one or more input devices 704, one or more display devices 706, one or more network interfaces 708, and one or more computer-readable media 712. Each of these components is be coupled by a bus 710.

[0070] Display device 706 includes any display technology, including but not limited to display devices using Liquid Crystal Display (LCD) or Light Emitting Diode (LED) technology. Processor(s) 702 uses any processor technology, including but not limited to graphics processors and multi-core processors. Input device 704 includes any known input device technology, including but not limited to a keyboard (including a virtual keyboard), mouse, track ball, and touch-sensitive pad or display. Bus 710 includes any internal or external bus technology, including but not limited to ISA, EISA, PCI, PCI Express, USB, Serial ATA or FireWire. Computer-readable medium 712 includes any non-transitory computer readable medium that provides instructions to processor(s) 702 for execution, including without limitation, non-volatile storage media (e.g., optical disks, magnetic disks, flash drives, etc.), or volatile media (e.g., SDRAM, ROM, etc.).

[0071] Computer-readable medium 712 includes various instructions 714 for implementing an operating system (e.g., Mac OS®, Windows®, Linux). The operating system may be multi-user, multiprocessing, multitasking, multithreading, real-time, and the like. The operating system performs basic tasks, including but not limited to: recognizing input from input device 704; sending output to display device 706; keeping track of files and directories on computer-readable medium 712; controlling peripheral devices (e.g., disk drives, printers, etc.) which can be controlled directly or through an I / O controller; and managing traffic on bus 710. Network communications instructions 716 establish and maintain network connections (e.g., software for implementing communication protocols, such as TCP / IP, HTTP, Ethernet, telephony, etc.).

[0072] CV metrics calculation instructions 718 includes instructions that implement the disclosed process for calculating CV metrics for clinical decision making and / or closed loop hemodynamic control system, as described throughout this disclosure. CV parameters calculation instructions 720 includes instructions that implement the disclosed process for calculating CV parameters for clinical decision making and / or closed loop hemodynamic control system, as described throughout this disclosure. Application(s) 722 may comprise an application that uses or implements the processes described herein and / or other processes. The processes may also be implemented in the operating system.

[0073] The described features may be implemented in one or more computer programs that may be executable on a programmable system including at least one programmable processor coupled to receive data and instructions from, and to transmit 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 certain activity or bring about a certain result. A computer program may be written in any form of programming language (e.g., Objective-C, Java), including compiled or interpreted languages, and it may be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. In one embodiment, this may include Python. The computer programs therefore are polyglots.

[0074] Suitable processors for the execution of a program of instructions may include, by way of example, both general and special purpose microprocessors, and the sole processor or one of multiple processors or cores, of any kind of computer. Generally, a processor may receive instructions and data from a read-only memory or a random access memory or both. The essential elements of a computer may include a processor for executing instructions and 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 include 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; magnetooptical disks; and CD-ROM and DVD-ROM disks. The processor and the memory may be supplemented by, or incorporated in, ASICs (application-specific integrated circuits).

[0075] To provide for interaction with a user, the features 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 and a keyboard and a pointing device such as a mouse or a trackball by which the user can provide input to the computer.

[0076] The features may be implemented in a computer system that includes a back-end component, such as a data server, or that includes a middleware component, such as an application server or an Internet server, or that includes a front-end component, such as a client computer having a graphical user interface or an Internet browser, or any combination thereof. The components of the system may be connected by any form or medium of digital data communication such as a communication network. Examples of communication networks include, e.g., a telephone network, a LAN, a WAN, and the computers and networks forming the Internet.

[0077] The computer system may include clients and servers. A client and server may generally be remote from each other and may typically interact through a network. The relationship of client and server may arise by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

[0078] One or more features or steps of the disclosed embodiments may be implemented using an API. An API may define one or more parameters that are passed between a calling application and other software code (e.g., an operating system, library routine, function) that provides a service, that provides data, or that performs an operation or a computation.

[0079] The API may be implemented as one or more calls in program code that send or receive one or more parameters through a parameter list or other structure based on a call convention defined in an API specification document. A parameter may be a constant, a key, a data structure, an object, an object class, a variable, a data type, a pointer, an array, a list, or another call. API calls and parameters may be implemented in any programming language. The programming language may define the vocabulary and calling convention that a programmer will employ to access functions supporting the API.

[0080] In some implementations, an API call may report to an application the capabilities of a device running the application, such as input capability, output capability, processing capability, power capability, communications capability, etc.

[0081] Additional examples of the presently described method and device embodiments are suggested according to the structures and techniques described herein. Other non-limiting examples may be configured to operate separately or can be combined in any permutation or combination with any one or more of the other examples provided above or throughout the present disclosure.

[0082] It will be appreciated by those skilled in the art that the present disclosure can be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The presently disclosed embodiments are therefore considered in all respects to be illustrative and not restricted. The scope of the disclosure is indicated by the appended claims rather than the foregoing description and all changes that come within the meaning and range and equivalence thereof are intended to be embraced therein.

[0083] It should be noted that the terms “including” and “comprising” should be interpreted as meaning “including, but not limited to”. If not already set forth explicitly in the claims, the term “a” should be interpreted as “at least one” and “the”, “said”, etc. should be interpreted as “the at least one”, “said at least one”, etc. Furthermore, it is the Applicant's intent that only claims that include the express language "means for" or "step for" be interpreted under 35 U.S.C. 112(f). Claims that do not expressly include the phrase "means for" or "step for" are not to be interpreted under 35 U.S.C. 112(f).

Claims

CLAIMS1. A method of hemodynamic control, comprising: receiving, by a computing system, a first input comprising a vector representation of a desired level of at least one cardiovascular parameter; receiving, by the computing system, a second input comprising a vector representation of a cardiovascular state of a patient, wherein the cardiovascular state comprises a level of a plurality of cardiovascular parameters; receiving, by the computing system, a third input comprising a matrix representation of a plurality of drugs, wherein the matrix representation includes an effect on the plurality of cardiovascular parameters of the plurality of drugs; optimizing, by the computing system, an amount of each drug from the plurality of drugs based on the first input, the second input, and the third input; and controlling, by the computing system, a response of the plurality of cardiovascular parameters and hemodynamics, wherein the controlling is based on at least the amount of each drug, and wherein the controlling includes a determination of a level of the at least one cardiovascular parameter in relation to the desired level.

2. The method of claim 1, wherein the optimizing the amount of each drug from the plurality of drugs is further based on minimizing at least one CV metric of a plurality of CV metrics comprising the hemodynamics.

3. The method of claim 1, wherein the amount of each drug is a first amount of each drug, wherein the cardiovascular state is a first cardiovascular state, and wherein the level of the plurality of cardiovascular parameters is a first level, the method further comprising: determining, by the computing system, a second cardiovascular state of the patient, wherein the second cardiovascular state comprises a second level of at least one of the plurality of cardiovascular parameters; and determining, by the computing system, a second amount of each drug from the plurality of drugs for substantially simultaneous injection, wherein the determining is based on the matrix representation of the plurality of drugs and the second cardiovascular state.

4. The method of claim 3, wherein the substantially simultaneous injection comprises the first amount of each drug and the second amount of each drug.

5. The method of claim 3, wherein the determining the second cardiovascular state comprises:measuring at least one of a plurality of cardiovascular metrics; and calculating at least one of the plurality of cardiovascular parameters based on the at least one of the plurality of cardiovascular metrics.

6. The method of claim 3, further comprising: issuing, by the computing system, a command to inject the patient with the first amount and the second amount of each drug; determining by the computing system, a third cardiovascular state of the patient, wherein the third cardiovascular state comprises a third level of at least one of the plurality of cardiovascular parameters; optimizing, by the computing system, a third amount of each drug from the plurality of drugs based on the third cardiovascular state; and issuing, by the computing system, a command to inject the patient with the first amount and the third amount of each drug.

7. The method of claim 1, further comprising: receiving, by the computing system, a fourth input comprising a vector representation of a desired level of at least one cardiovascular metric, wherein the first input is determined by analytically mapping the fourth input to at least one cardiovascular parameter.

8. A system comprising: a non-transitory storage medium storing computer program instructions; and a processor configured to execute the computer program instructions to cause operations comprising: receiving, by a computing system, a first input comprising a vector representation of a desired level of at least one cardiovascular parameter; receiving, by the computing system, a second input comprising a vector representation of a cardiovascular state of a patient, wherein the cardiovascular state comprises a plurality of cardiovascular parameters; receiving, by the computing system, a third input comprising a matrix representation of a plurality of drugs, wherein the matrix representation includes an effect on the plurality of cardiovascular parameters of the plurality of drugs; optimizing, by the computing system, an amount of each drug from the plurality of drugs based on the first input, the second input, and the third input; and controlling, by the computing system, a response of the plurality of cardiovascular parameters and hemodynamics, wherein the controlling is based on at least the amount of eachdrug, and wherein the controlling includes a determination of a level of the at least one cardiovascular parameter in relation to the desired level.

9. The system of claim 8, wherein optimizing the amount of each drug from the plurality of drugs is further based on minimizing at least one CV metric of a plurality of CV metrics comprising the hemodynamics.

10. The system of claim 8, wherein the amount of each drug is a first amount of each drug, wherein the cardiovascular state is a first cardiovascular state, and wherein the level of the plurality of cardiovascular parameters is a first level, the operations further comprising: determining, by the computing system, a second cardiovascular state of the patient, wherein the second cardiovascular state comprises a second level of at least one of the plurality of cardiovascular parameters; and determining, by the computing system, a second amount of each drug from the plurality of drugs for substantially simultaneous injection, wherein the determining is based on the matrix representation of the plurality of drugs and the second cardiovascular state.

11. The system of claim 10, wherein the substantially simultaneous injection comprises the first amount of each drug and the second amount of each drug.

12. The system of claim 10, wherein the determining the second cardiovascular state comprises: measuring at least one of a plurality of cardiovascular metrics; and calculating at least one of the plurality of cardiovascular parameters based on the at least one of the plurality of cardiovascular metrics.

13. The system of claim 10, the operations further comprising: issuing, by the computing system, a command to inject the patient with the first amount and the second amount of each drug; determining by the computing system, a third cardiovascular state of the patient, wherein the third cardiovascular state comprises a third level of at least one of the plurality of cardiovascular parameters; optimizing, by the computing system, a third amount of each drug from the plurality of drugs based on the third cardiovascular state; and issuing, by the computing system, a command to inject the patient with the first amount and the third amount of each drug.

14. The system of claim 8, the operations further comprising: receiving, by the computing system, a fourth input comprising a vector representation of a desired level of at least one cardiovascular metric, wherein the first input is determined by analytically mapping the at least one cardiovascular metric to at least one cardiovascular parameter.

15. A non-transitory storage medium storing computer program instructions that when executed causes a computing system to perform operations comprising: receiving, by the computing system, a first input comprising a vector representation of a desired level of at least one cardiovascular parameter; receiving, by the computing system, a second input comprising a vector representation of a cardiovascular state of a patient, wherein the cardiovascular state comprises a plurality of cardiovascular parameters; receiving, by the computing system, a third input comprising a matrix representation of a plurality of drugs, wherein the matrix representation includes an effect on the plurality of cardiovascular parameters of the plurality of drugs; optimizing, by the computing system, an amount of each drug from the plurality of drugs based on the first input, the second input, and the third input; and controlling, by the computing system, a response of the plurality of cardiovascular parameters and hemodynamics, wherein the controlling is based on at least the amount of each drug, and wherein the controlling includes a determination of a level of the at least one cardiovascular parameter in relation to the desired level.

16. The non-transitory storage medium of claim 15, wherein optimizing the amount of each drug from the plurality of drugs is further based on minimizing at least one CV metric of a plurality of CV metrics comprising the hemodynamics.

17. The non-transitory storage medium of claim 15, wherein the amount of each drug is a first amount of each drug, wherein the cardiovascular state is a first cardiovascular state, and wherein the level of the plurality of cardiovascular parameters is a first level, the operations further comprising: determining, by the computing system, a second cardiovascular state of the patient, wherein the second cardiovascular state comprises a second level of at least one of the plurality of cardiovascular parameters; and determining, by the computing system, a second amount of each drug from the plurality of drugs for substantially simultaneous injection, wherein the determining is based on the matrix representation of the plurality of drugs and the second cardiovascular state.

18. The non-transitory storage medium of claim 17, wherein the substantially simultaneous injection comprises the first amount of each drug and the second amount of each drug.

19. The non-transitory storage medium of claim 17, the operations further comprising: issuing, by the computing system, a command to inject the patient with the first amount and the second amount of each drug; determining by the computing system, a third cardiovascular state of the patient, wherein the third cardiovascular state comprises a third level of at least one of the plurality of cardiovascular parameters; optimizing, by the computing system, a third amount of each drug from the plurality of drugs based on the third cardiovascular state; and issuing, by the computing system, a command to inject the patient with the first amount and the third amount of each drug.

20. The non-transitory storage medium of claim 15, the operations further comprising: receiving, by the computing system, a fourth input comprising a vector representation of a desired level of at least one cardiovascular metric, wherein the first input is determined by analytically mapping the at least one cardiovascular metric to at least one cardiovascular parameter.

Images