Systems and methods for determining fluid responsiveness

Abstract

A system for determining fluid responsiveness of a patient includes a hemodynamic sensor that produces, on an ongoing basis, a hemodynamic sensor signal representative of a right ventricular pressure (RVP) waveform of the patient and an integrated hardware unit. The integrated hardware unit includes a processor, a memory, and a display including a user interface. The memory includes instructions that, when executed by the processor, cause the system to receive the hemodynamic sensor signal representative of the RVP waveform of the patient, convert the RVP waveform of the patient into an estimate of a blood flow waveform of the patient, determine a stroke volume variation (SVV) of the patient based on the estimate of the blood flow waveform of the patient to generate a determined SVV, and output, to the display, an indication of a fluid responsiveness status of the patient that is based on the determined SVV.

Description

[0001]Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 SYSTEMS AND METHODS FOR DETERMINING FLUID RESPONSIVENESS CROSS-REFERENCE TO RELATED APPLICATION(S) This application claims the benefit of U.S. Provisional Application No. 63 / 569,414, filed March 25, 2024, and entitled “SYSTEMS AND METHODS FOR DETERMINING FLUID RESPONSIVENESS,” the disclosure of which is hereby incorporated by reference in its entirety. BACKGROUND The present disclosure relates generally to hemodynamic monitoring and, in particular, to determining fluid responsiveness of a patient using monitored hemodynamic data. Fluid responsiveness is an important clinical parameter that can be indicative of patient responsiveness (i.e., experiencing an increase in stroke volume) to an increase in fluid loading (i.e., preload) of the heart. One standard method for assessing fluid responsiveness involves a fluid challenge, where a bolus of fluid is given to the patient, or a specific maneuver (e.g., a passive leg raise) is performed, and stroke volume is tracked. An increase of at least 10-15% in stroke volume typically indicates that the patient is fluid responsive, and no increase (or less than a 10% increase) indicates that the patient is not fluid responsive. Another standard method of assessing fluid responsiveness—and an alternative to administering a fluid challenge—uses surrogates of stroke volume variation to look at the variation in stroke volume due to preload changes caused by inspiration and expiration. SUMMARY In one example, a system for determining fluid responsiveness of a patient includes a hemodynamic sensor that produces, on an ongoing basis, a hemodynamic sensor signal representative of a right ventricular pressure (RVP) waveform of the patient and an integrated hardware unit. The integrated hardware unit includes a system processor, a system memory, and a display including a user interface. The system memory includes instructions that, when executed by the system processor, cause the system to receive the hemodynamic sensor signal representative of the RVP waveform of the patient, convert the RVP waveform of the patient into an estimate of a blood flow waveform of the patient, determine a stroke volume variation (SVV) of the patient based on the estimate of the blood flow waveform of the patient to generate a determined SVV of the patient, and output, to the display, an indication of a fluid responsiveness status of the patient that is based on the determined SVV of the patient. Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 In another example, a system for determining fluid responsiveness of a patient includes a hemodynamic sensor that produces, on an ongoing basis, a hemodynamic sensor signal representative of a right ventricular pressure (RVP) waveform of the patient and an integrated hardware unit. The integrated hardware unit includes a system processor, a system memory, and a display including a user interface. The system memory includes instructions that, when executed by the system processor, cause the system to receive the hemodynamic sensor signal representative of the RVP waveform of the patient, convert the RVP waveform of the patient into an estimate of a blood flow waveform of the patient, and determine a stroke volume variation (SVV) of the patient based on the estimate of the blood flow waveform of the patient to generate a determined SVV of the patient. The instructions further cause the system to extract one or more features from the RVP waveform of the patient and estimate a preload status of the patient using a right ventricular end diastolic pressure (RVEDP) extracted from the RVP waveform. The instructions further cause the system to generate a fluid responsiveness index based on the preload status and the determined SVV of the patient, the fluid responsiveness index indicating that the patient is fluid responsive when the RVEDP is below a lower threshold and indicating the patient is not fluid responsive when the RVEDP is above an upper threshold, and output an indication of the fluid responsiveness index to the display. In another example, a system for determining fluid responsiveness of a patient includes a hemodynamic sensor that produces, on an ongoing basis, a hemodynamic sensor signal representative of a right ventricular pressure (RVP) waveform of the patient and an integrated hardware unit. The integrated hardware unit includes a system processor, a system memory, and a display including a user interface. The system memory includes instructions that, when executed by the system processor, cause the system to receive the hemodynamic sensor signal representative of the RVP waveform of the patient, convert the RVP waveform of the patient into an estimate of a blood flow waveform of the patient, and determine a stroke volume variation (SVV) of the patient based on the estimate of the blood flow waveform of the patient to generate a determined SVV of the patient. The instructions further cause the system to extract features from the RVP waveform of the patient, determine a second SVV of the patient based on the features extracted from the RVP waveform of the patient using a regression model to generate a second determined SVV of the patient, combine the determined SVV and the second determined SVV to generate a composite SVV, and estimate a preload status of the patient using a right ventricular end diastolic pressure (RVEDP) extracted from the RVP waveform. The instructions further Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 cause the system to generate a fluid responsiveness index based on the preload status and the composite SVV, the fluid responsiveness index indicating that the patient is fluid responsive when the RVEDP is below a lower threshold and indicating the patient is not fluid responsive when the RVEDP is above an upper threshold, and output an indication of the fluid responsiveness index to the display. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a schematic block diagram illustrating an example hemodynamic monitoring system that determines fluid responsiveness for a patient based on hemodynamic data. FIG. 2 is a perspective view of an example hemodynamic monitor that analyzes a right ventricular pressure waveform and a pulmonary artery pressure waveform to determine fluid responsiveness for the patient. FIG. 3 is a perspective view of an example catheter that can be inserted in the patient and connected to one or more hemodynamic sensors for providing hemodynamic data to the hemodynamic monitor. FIG. 4 is a perspective view of an example minimally invasive pressure sensor that can be attached to the patient for sensing hemodynamic data representative of a right ventricular pressure or a pulmonary artery pressure of the patient. FIG. 5 is a perspective view of an example oximetry module for receiving oximetry data from a catheter inserted within the patient. FIG. 6 is a schematic block diagram illustrating inputs and outputs for modules of the hemodynamic monitoring system. FIG.7 is a graph illustrating an example right ventricular pressure waveform trace including example indicia indicative of blood flow and cardiac output. FIG. 8 is a graph illustrating an example pulmonary artery pressure waveform trace including example indicia indicative of blood flow and cardiac output. FIG. 9 is a schematic block diagram illustrating a validation module, as shown in FIG.1. FIG. 10 is a graph illustrating an example right ventricular pressure waveform trace including indicia indicative of catheter placement and data quality. FIG. 11 is a graph illustrating an example right ventricular pressure waveform trace and an example pulmonary artery pressure waveform trace including example indicia indicative of catheter placement and data quality. Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 FIG. 12 is a schematic block diagram illustrating a flow module, as shown in FIG.1. FIG.13 is a schematic block diagram illustrating a right ventricular pressure waveform transforming into a processed flow waveform via the flow module. FIG. 14 is a schematic block diagram illustrating an autoencoder model of the flow module. FIG.15 is a schematic diagram illustrating filters of the autoencoder model. FIG. 16 is a flow diagram illustrating an example process for training the autoencoder model to predict human blood flow based on the right ventricular pressure waveform. FIG. 17 is a schematic block diagram illustrating an SVVAE module, as shown in FIG.1. FIG. 18 is a schematic block diagram illustrating estimation of stroke volume from the processed flow waveform via the SVVAE module. FIG. 19 is a schematic block diagram illustrating an SVVLR module, as shown in FIG.1. FIG. 20 is a schematic block diagram illustrating reference and current features used as inputs to a regression model of the SVVLR module. FIG.21 is a schematic diagram illustrating a reference time window at peak inspiration and a current time window at peak expiration. FIG. 22 is a schematic diagram illustrating multiple windows and multiple corresponding beats. FIG. 23 is a schematic block diagram illustrating an SVVcompmodule, as shown in FIG.1. FIG.24 is a schematic block diagram illustrating a filter sub-module of the SVVcomp module. FIG.25A is a graph illustrating an example predicted value of the filter sub- module over time. FIG.25B is a graph illustrating an example measured value of the filter sub- module over time. FIG.25C is a graph illustrating an example filtered value from the filter sub- module over time. FIG. 26 is a schematic block diagram illustrating a fluid responsiveness index module, as shown in FIG.1. Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 FIG.27 is a graph illustrating right ventricular end diastolic pressure values over time for an animal model. FIG. 28 is a flow diagram illustrating an example process associated with the fluid responsiveness index module. DETAILED DESCRIPTION As described herein, a hemodynamic monitoring system according to techniques of this disclosure implements a series of modules to determine fluid responsiveness for a patient. The hemodynamic monitoring system utilizes a catheter and hemodynamic sensors to generate a right ventricular pressure (“RVP”) waveform and, optionally, a pulmonary artery pressure (“PAP”) waveform for input into modules of the hemodynamic monitoring system to estimate stroke volume variation (SVV) from estimated beat-to-beat flow. The system can determine fluid responsiveness of the patient during operation of the hemodynamic monitoring system in, e.g., an operating room (OR), an intensive care unit (ICU), or other patient care environment. Medical workers can use the fluid responsiveness information to improve patient care. Hemodynamic Monitoring System (FIGS.1-8) FIG.1 is a schematic block diagram of hemodynamic monitoring system 10 that determines fluid responsiveness for a patient based on hemodynamic data. FIG. 1 shows hemodynamic monitoring system 10, including hemodynamic monitor 12 and hemodynamic sensors 14 (including hemodynamic sensors 14A, 14B, 14C, and 14D). Hemodynamic monitor 12 includes system processor 20, system memory 22, display 24, analog-to-digital converter (ADC) 26, and digital-to-analog converter (DAC) 28. System memory 22 includes fluid responsiveness software code 30, which includes RVP features module 32, PAP features module 34, validation module 36, flow module 38, SVVAE module 40, SVVLRmodule 42, SVVcompmodule 44, and fluid responsiveness index module 45. Display 24 includes user interface 46, which includes control elements 48 and sensory alarm 50. FIG.1 also shows patient 16, healthcare worker 18, and catheter 54. As illustrated in FIG. 1, hemodynamic monitoring system 10 includes hemodynamic monitor 12 and hemodynamic sensors 14 (including hemodynamic sensors 14A, 14B, 14C, and 14D). Hemodynamic monitoring system 10 can be implemented within a patient care environment, such as an ICU, an OR, or other patient care environment, for monitoring a hemodynamic condition of a patient. As illustrated in FIG. 1, the patient care environment can include patient 16 and healthcare worker 18 trained to utilize hemodynamic monitoring system 10. Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 Hemodynamic monitor 12, as described below with respect to FIG. 2, can be an integrated hardware unit that includes system processor 20, system memory 22, display 24, ADC 26, and DAC 28. In other examples, any one or more components and / or described functionality of hemodynamic monitor 12 can be distributed among multiple hardware units. For instance, in some examples, display 24 can be a separate display device that is remote from and operatively coupled with hemodynamic monitor 12. Likewise, at least a portion of data processing within hemodynamic monitoring system 10 can occur via a smart cable that is connected between a catheter (e.g., catheter 54) or sensor and hemodynamic monitor 12. In general, though illustrated and described in the example of FIG.1 as an integrated hardware unit, it should be understood that hemodynamic monitor 12 can include any combination of devices and components that are electrically, communicatively, or otherwise operatively connected to perform functionality attributed herein to hemodynamic monitor 12. As illustrated in FIG. 1, system memory 22 stores fluid responsiveness software code 30. Fluid responsiveness software code 30 includes RVP features module 32, PAP features module 34, validation module 36, flow module 38, SVVAE module 40, SVVLRmodule 42, SVVcompmodule 44, and fluid responsiveness index module 45. Display 24 provides user interface 46, which includes control elements 48 that enable user interaction with hemodynamic monitor 12 and / or other components of hemodynamic monitoring system 10. User interface 46, as illustrated in FIG. 1, also provides sensory alarm 50 to provide warning to medical personnel based on the fluid responsiveness or other hemodynamic status of patient 16, as is further described below. Hemodynamic sensors 14 can be attached to patient 16 to sense hemodynamic data representative of an RVP waveform, a PAP waveform, blood oxygen saturation (labeled “SvO2” in FIG. 1), or cardiac output of patient 16 or any combination of these hemodynamic data. Hemodynamic sensors 14 are operatively connected to hemodynamic monitor 12 (e.g., electrically and / or communicatively connected via wired or wireless connection, or both) to provide the sensed hemodynamic data to hemodynamic monitor 12. In some examples, hemodynamic sensors 14 provide the hemodynamic data of patient 16 to hemodynamic monitor 12 as an analog signal, which is converted by ADC 26 to digital hemodynamic data representative of the RVP waveform and / or the PAP waveform. In other examples, hemodynamic sensors 14 can provide the sensed hemodynamic data to hemodynamic monitor 12 in digital form, in which case hemodynamic monitor 12 may not include or utilize ADC 26. In yet other examples, Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 hemodynamic sensors 14 can provide the hemodynamic data of patient 16 to hemodynamic monitor 12 as an analog signal, which is analyzed in its analog form by hemodynamic monitor 12. Hemodynamic sensors 14 can include one or more non-invasive, minimally invasive, or invasive sensors attached to patient 16. For instance, hemodynamic sensors 14 can take the form of invasive hemodynamic sensor 14A, such as second pressure transducer 14A that provides RVP waveform data sensed at right ventricle port 68C located within the right ventricle of the patient’s heart (shown in FIG.4). Hemodynamic sensors 14 can take the form of invasive hemodynamic sensor 14B, such as oximetry module 14B that provides blood oxygen saturation data within the pulmonary artery based on light pulses emitted from module 14B into the pulmonary artery and reflected, returned, and received by module 14B via optical connector 62 (shown in FIG. 5) of catheter 54. In yet other examples, hemodynamic sensors 14 can take the form of non-invasive hemodynamic sensors. In some examples, hemodynamic sensors 14 can be attached non-invasively at an extremity of patient 16, such as a forehead, a wrist, an arm, a finger, an ankle, a toe, or other extremity of patient 16. Hemodynamic sensors 14 can also take the form of other invasive, minimally invasive, or non-invasive hemodynamic sensors. In certain examples, hemodynamic sensors 14 can be configured to sense RVP, PAP, or both right ventricular and pulmonary artery pressures of patient 16. In some instances, hemodynamic sensors 14 may also be used to sense cardiac output of the patient, blood oxygen saturation within the pulmonary artery, or both cardiac output and blood oxygen saturations in addition to right ventricular and pulmonary artery pressures. For instance, one or more hemodynamic sensors 14 can be attached to patient 16 via a radial arterial catheter inserted into an arm of patient 16. In other examples, one or more hemodynamic sensors 14 can be attached to patient 16 via a femoral arterial catheter inserted into a leg of patient 16. Such techniques can similarly enable multiple hemodynamic sensors 14 to provide substantially continuous beat-to-beat monitoring of the RVP and PAP as well as monitoring of cardiac output, and blood oxygen saturation of patient 16, or any combination of these hemodynamic data, over an extended period of time, such as minutes or hours. System processor 20 executes fluid responsiveness software code 30, which implements RVP features module 32, PAP features module 34, validation module 36, flow module 38, SVVAE module 40, SVVLR module 42, SVVcomp module 44, and fluid responsiveness index module 45, which utilize the RVP waveform and, optionally, the PAP Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 waveform to estimate beat-to-beat flow, estimate SVV from the estimated beat-to-beat flow, and determine fluid responsiveness for patient 16. Examples of system processor 20 can include any one or more of a microprocessor, a controller, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other equivalent discrete or integrated logic circuitry. System memory 22 can be configured to store information within hemodynamic monitor 12 during operation. System memory 22, in some examples, is described as computer-readable storage media. In some examples, a computer-readable storage medium can include a non-transitory medium. The term “non-transitory” can indicate that the storage medium is not embodied in a carrier wave or a propagated signal. In certain examples, a non-transitory storage medium can store data that can, over time, change (e.g., in RAM or cache). System memory 22 can include volatile and non-volatile computer-readable memories. Examples of volatile memories can include random access memories (RAM), dynamic random-access memories (DRAM), static random-access memories (SRAM), and other forms of volatile memories. Examples of non-volatile memories can include, e.g., magnetic hard discs, optical discs, flash memories, or forms of electrically programmable memories (EPROM) or electrically erasable and programmable (EEPROM) memories. Display 24 can be a liquid crystal display (LCD), a light-emitting diode (LED) display, an organic light-emitting diode (OLED) display, or other display device suitable for providing information to users in graphical form. User interface 46 can include graphical and / or physical control elements that enable user input to interact with hemodynamic monitor 12 and / or other components of hemodynamic monitoring system 10. In some examples, user interface 46 can take the form of a graphical user interface (GUI) that presents graphical control elements presented at, e.g., a touch-sensitive and / or presence sensitive display screen of display 24. In such examples, user input can be received in the form of gesture input, such as touch gestures, scroll gestures, zoom gestures, or other gesture input. In certain examples, user interface 46 can take the form of and / or include physical control elements, such as a physical buttons, keys, knobs, or other physical control elements configured to receive user input to interact with components of hemodynamic monitoring system 10. In operation, one or more hemodynamic sensors 14 are connected to hemodynamic monitor 12 and catheter 54. Hemodynamic sensor 14A senses hemodynamic data representative of an RVP waveform, a PAP waveform, and / or another Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 blood pressure waveform of patient 16. Hemodynamic sensor 14A provides the hemodynamic data (e.g., as analog sensor data) to hemodynamic monitor 12. ADC 26 converts the analog hemodynamic data to digital hemodynamic data representative of the RVP waveform, the PAP waveform, and / or another blood pressure waveform of patient 16. System processor 20 executes fluid responsiveness software code 30 to determine, using the received hemodynamic data, fluid responsiveness for patient 16. For instance, system processor 20 can execute flow module 38 of fluid responsiveness software code 30 to estimate beat-to-beat flow based on the RVP waveform. Fluid responsiveness software code 30 uses SVVAE module 40 to determine a first estimate of SVV of patient 16 from the beat-to-beat flow using an autoencoder model. Fluid responsiveness software code 30 uses SVVLR module 42 to determine a second estimate of SVV of patient 16 based on one or more features of the RVP waveform and / or the PAP waveform using a regression model. Fluid responsiveness software code 30 uses SVVcomp module 44 to determine a composite SVV from multiple estimates of SVV. Fluid responsiveness software code 30 uses fluid responsiveness index module 45 to determine a fluid responsiveness index using an estimate of preload status (such as based on a right ventricular end diastolic pressure or other suitable features of the RVP waveform or the PAP waveform) and an estimate of SVV of patient 16. Monitoring hemodynamic variables of a patient and assessing fluid responsiveness can improve patient care, with goal-directed fluid therapy being associated with improvements to patient outcomes. Hemodynamic monitor 12 uses hemodynamic sensors 14 and fluid responsiveness software code 30 to assess the hemodynamic state, including the fluid responsiveness status, of patient 16. Accordingly, hemodynamic monitor 12 informs healthcare worker 18 of the fluid responsiveness status of patient 16, thereby enabling timely and effective patient care. The prediction of fluid responsiveness by hemodynamic monitor 12 is more accurate and effective compared to traditional methods of predicting fluid responsiveness. SVV is one metric that has traditionally been used to predict whether a patient will be fluid responsive. This prediction can be a binary decision, such as: (1) fluid responsive if SVV is above a certain percentage; or (2) not fluid responsive if SVV is below a certain percentage. In some examples, the prediction can be based on trends in SVV. SVV is typically assessed in a clinical setting using a radial or femoral pressure waveform. SVV is also typically a parameter that is estimated from other pressure features, such as pulse pressure variation (PPV), which are used as surrogates of SVV to approximate the Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 true SVV because there has not been a way to directly measure SVV without relying on imaging techniques. Generally, in goal-directed therapy approaches, clinicians will determine whether to administer fluid or to not administer fluid based on these surrogates of SVV. A fluid challenge or passive leg raise may be performed thereafter to verify the patient’s fluid responsiveness status. However, performing an intervention to verify a patient’s fluid responsiveness status might happen too late, especially in situations where the verification shows that the patient is not actually fluid responsive but fluid has already been administered based on the SVV surrogate-based determination. According to some studies, current techniques for assessing fluid responsiveness can be inaccurate in around 50% of clinical cases where the prediction of fluid responsiveness was verified with administration of fluid. The administration of fluid when a patient will not be fluid responsive can be harmful to the patient. According to techniques of this disclosure, hemodynamic monitor 12 is able to produce a truer (or more accurate) estimate of SVV based on beat-to-beat flow. This is different from traditional techniques that use a surrogate of SVV from pressure data or simply use another pressure feature directly. The SVV estimated by hemodynamic monitor 12 is derived from beat-to-beat flow, which provides actual stroke volumes for each heartbeat, and, therefore, is a more accurate or true estimate of SVV compared to estimates using traditional techniques. Additionally, normal SVV is caused by variations in respiration (inspiration and expiration) that cause slight variations in the amount of blood flow back to the heart. An estimate of SVV derived from RVP, according to techniques of this disclosure, can be more effective in low tidal volume and spontaneous breathing patients where the respiratory effect on pressure is minimal in radial or femoral pressure measurements but present in RVP. That is, there will be a higher signal-to-noise ratio for SVV that is derived from RVP compared to SVV derived from radial or femoral pressure measurements. Fluid responsiveness assessment can be considered a two-part inquiry that involves both consideration of SVV and also changes in preload (volume back to the heart). Unlike current methods to determine fluid responsiveness, which typically do not account for changes in preload because this information cannot be determined from radial pressure measurements, hemodynamic monitor 12 can determine a preload status based on features of the RVP waveform and use the preload status in conjunction with the estimate of SVV to provide a more accurate determination of fluid responsiveness. Accordingly, hemodynamic monitor 12 is able to assess both contributing factors (SVV and preload) and Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 effectively predict fluid responsiveness in a wider range of patient hemodynamic conditions. Hemodynamic monitor 12 is shown in FIG.2. Catheter 54 is shown in FIG. 3. An example of a minimally invasive pressure sensor is shown in FIG. 4. An example of an oximetry module is shown in FIG.5. FIG. 2 is a perspective view of hemodynamic monitor 12 that analyzes the RVP waveform and the PAP waveform to determine fluid responsiveness for patient 16. As illustrated in FIG.2, hemodynamic monitor 12 includes display 24 that, in the example of FIG. 1, presents a graphical user interface 46 including control elements 48 (e.g., graphical control elements) that enable user interaction with hemodynamic monitor 12. Hemodynamic monitor 12 can also include a plurality of input and / or output (I / O) connectors 52 configured for wired connection (e.g., electrical and / or communicative connection) with one or more peripheral components, such as one or more hemodynamic sensors 14. While the example of FIG. 2 illustrates five separate I / O connectors 52, it should be understood that in other examples, hemodynamic monitor 12 can include fewer than five I / O connectors 52 or greater than five I / O connectors 52. In yet other examples, hemodynamic monitor 12 may not include I / O connectors 52, but rather may communicate wirelessly with various peripheral devices. As described with respect to FIG.1, hemodynamic monitor 12 includes one or more system processors 20 and computer-readable system memory 22 that stores fluid responsiveness software code 30, which is executable to determine fluid responsiveness for patient 16. Hemodynamic monitor 12 can receive sensed hemodynamic data representative of an RVP waveform and a PAP waveform, such as via one or more hemodynamic sensors 14 connected to hemodynamic monitor 12 via I / O connectors 52. Hemodynamic monitor 12 executes fluid responsiveness software code 30 to estimate beat-to-beat flow using the received hemodynamic data, estimate SVV from the estimated beat-to-beat flow, and determine fluid responsiveness for patient 16, as is further described below. As illustrated in FIG. 1, hemodynamic monitor 12 can present a graphical user interface at display 24. Display 24 can be an LCD, an LED display, an OLED display, or other display device suitable for providing information to users in graphical form. In some examples, such as the example of FIG.2, display 24 can be a touch-sensitive and / or presence-sensitive display device configured to receive user input in the form of gestures, such as touch gestures, scroll gestures, zoom gestures, swipe gestures, or other gesture input. Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 Hemodynamic monitor 12 receives hemodynamic data from patient 16 via one or more hemodynamic sensors 14A, 14B, 14C, and 14D (collectively, hemodynamic sensors 14). In response to receiving hemodynamic data of patient 16, hemodynamic monitor 12 executes fluid responsiveness software code 30 to determine fluid responsiveness for patient 16 and display the fluid responsiveness information or other information on display 24. In some examples, hemodynamic monitor 12 can invoke a sensory alarm, such as an audible alarm, a haptic alarm, or other sensory alarm (for example, sensory alarm 50, as shown in FIG.1) in response to determining that patient 16 will be fluid responsive. Accordingly, hemodynamic monitor 12 can alert medical personnel of a fluid responsiveness status of patient 16. FIG. 3 is a perspective view of catheter 54 that can be inserted into patient 16 and connected to one or more hemodynamic sensors 14 for providing hemodynamic data to hemodynamic monitor 12. For example, catheter 54 may be connected to one or more pressure-sensing hemodynamic sensors 14A for detecting RVP, PAP, or both right ventricular and pulmonary artery pressures of patient 16. Additionally, catheter 54 may interface with oximetry module 14B for sensing mixed venous oxygen saturation of patient 16. Protected by sheath 56, catheter 54 includes multiple lumens 58 that place fluid connectors 60, optical connector 62, thermistor connector 64, and thermal filament connector 66 in communication with one of ports 68, an embedded hemodynamic sensor 14C (e.g., a thermistor), or an embedded hemodynamic sensor 14D (e.g., a thermal filament). To facilitate insertion of catheter 54 within patient 16, or for certain hemodynamic measurements, catheter 54 includes balloon 70 located at tip 72 of catheter 54. As shown in FIG. 3, catheter 54 includes distal port connector 60A communicating with port 68A at tip 72. Proximal injectate connector 60B communicates with proximal port 68B disposed approximately 30 cm from tip 72 and can be used for dispensing fluids and drugs into the patient’s heart. Right ventricular pacing connector 60C communicates with right ventricle port 68C, which may be spaced approximately 19 cm from tip 72 or approximately 12 to 13 cm from tip 72. Connector 60C can be used for sensing RVP. Thermistor connector 64 electrically connects to hemodynamic sensor 14C (e.g., the thermistor) installed near tip 72 of catheter 54 for measuring core blood temperature within the pulmonary artery. In some examples of catheter 54, thermal filament connector 66 electrically connects to hemodynamic sensor 14D (e.g., the thermal filament) embedded within catheter 54 located within the patient’s right ventricle. In some Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 examples, catheter 54 does not include a thermal filament or corresponding thermal filament connector 66. Balloon connector 60D communicates with balloon 70 and with the use of syringe 74 can be used to inflate and deflate balloon 70. After insertion into patient 16, e.g., via an introducer, distal port connector 60A and right ventricular pacing connector 60C can be connected to separate pressure transducer sensors 14A. A first pressure transducer 14A provides PAP waveform data sensed at distal port 68A located within the pulmonary artery of the patient’s heart to hemodynamic monitor 12, while a second pressure transducer 14A provides RVP waveform data sensed at right ventricle port 68C located within the right ventricle of the patient’s heart to hemodynamic monitor 12. Blood oxygen saturation data within the pulmonary artery can be provided by oximetry module 14B based on light pulses emitted from oximetry module 14B into the pulmonary artery and reflected light returns received by oximetry module 14B via optical connector 62 of catheter 54. Additionally, utilizing thermal filament connector 66 and thermistor connector 64 and associated cabling, hemodynamic monitor 12 can receive cardiac output data of patient 16 using, for example, a thermal dilution technique. The cardiac output measured via the thermal filament and corresponding thermal filament connector 66 can be considered a continuous cardiac output (labeled “CCO” in FIG. 1). If catheter 54 does not include a thermal filament, cardiac output can be determined using a thermistor after injecting a fluid bolus (or a set of boluses) of known volume and temperature via proximal injectate port 68B using the thermal dilution technique. The cardiac output measured via the thermistor and corresponding thermistor connector 64 after injection of the fluid bolus can be considered an intermittent cardiac output (labeled “ICO” in FIG.1). Intermittent cardiac output measurements can be obtained at a frequency that is on the order of, e.g., minutes, hours, several hours, or even longer intervals, depending on the level of monitoring a patient requires. For example, a clinician may administer a bolus set of 3-4 fluid boluses, where one fluid bolus of the set is administered approximately every minute such that the complete bolus set lasts around three minutes. In one example, fluid boluses can be administered very frequently, such as every minute or every few minutes, when a clinician is assessing a patient's responsiveness to medication or another medical intervention. In another example, fluid boluses can be administered less frequently, such as every hour, every six hours, etc., if a patient is relatively stable in the ICU. Accordingly, catheter 54 can be used to provide a continuous cardiac output and / or an intermittent cardiac output, as described below with reference to FIGS.16 and 19-22. Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 Catheter 54 is one example of a catheter that can be used to measure RVP, PAP, continuous cardiac output and / or intermittent cardiac output. In other examples, any catheter configured to measure RVP, PAP, continuous cardiac output and / or intermittent cardiac output can be used. FIG. 4 is a perspective view of hemodynamic sensor 14A that can be attached to patient 16 for sensing hemodynamic data representative of RVP or PAP of patient 16. As illustrated in FIG. 4, hemodynamic sensor 14A includes housing 76, fluid input port 78, catheter-side fluid port 80, and I / O cable 82. Fluid input port 78 is configured to be connected via tubing or other hydraulic connection to a fluid source, such as a saline bag or other fluid input source. Catheter-side fluid port 80 is configured to be connected via tubing or other hydraulic connection to a catheter (e.g., a radial arterial catheter or a femoral arterial catheter) that is inserted into an arm of the patient (i.e., a radial arterial catheter) or a leg of the patient (i.e., a femoral arterial catheter). I / O cable 82 is configured to connect to hemodynamic monitor 12 via, e.g., one or more of I / O connectors 52 (shown in FIG. 2). Housing 76 of hemodynamic sensor 14A encloses one or more pressure transducers, communication circuitry, processing circuity, and corresponding electronic components to sense fluid pressure corresponding to the RVP or PAP of patient 16 that is transmitted to hemodynamic monitor 12 (shown in FIG.2) via I / O cable 82. In operation, a column of fluid (e.g., saline solution) is introduced from a fluid source (e.g., a saline bag) through hemodynamic sensor 14A via fluid input port 78 to catheter-side fluid port 80 toward the catheter inserted into patient 16. RVP or PAP is communicated through the fluid column to pressure sensors located within housing 76 which sense the pressure of the fluid column. Hemodynamic sensor 14A translates the sensed pressure of the fluid column to an electrical signal via the pressure transducers and outputs the corresponding electrical signal to hemodynamic monitor 12 (shown in FIG.1) via I / O cable 82. Hemodynamic sensor 14 therefore transmits analog sensor data (or a digital representation of the analog sensor data) to hemodynamic monitor 12 (shown in FIG. 1) that is representative of substantially continuous beat-to-beat monitoring of the RVP or PAP of patient 16. FIG.5 is a perspective view of oximetry module 14B for receiving oximetry data from a catheter inserted within patient 16. As depicted in FIG.5, hemodynamic sensor 14B includes an optical transmitter and an optical receiver arranged to communicate to a catheter via I / O connector 84 installed within housing 86 and accessible via protective door 88. Within housing 86, hemodynamic sensor 14B, as depicted by FIG. 5, includes Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 communication circuitry, processing circuity, and corresponding electronic components to sense blood oxygen saturation data derived from optical light emissions transmitted via a catheter into a patient and corresponding light returns received from patient 16 via the catheter. An electrical signal indicative of the patient blood oxygen saturation levels is transmitted to hemodynamic monitor 12 via cable 90 and connector 92, which interfaces with one of I / O connectors 52 (shown in FIG.2). FIG.6 is a schematic block diagram illustrating inputs and outputs for each module of hemodynamic monitoring system 10. Although hemodynamic monitoring system 10 has been described as including catheter 54, any suitable catheter may be used with hemodynamic monitoring system 10. FIG. 6 shows RVP features module 32, PAP features module 34, validation module 36, flow module 38, SVVAE module 40 (a module that estimates SVV based on an autoencoder model), SVVLR module 42 (a module that estimates SVV using a regression model), SVVcomp module 44 (a module that combines one or more estimates of SVV), fluid responsiveness index module 45 (a module that determines a fluid responsiveness index using an estimate of preload status and an estimate of SVV), and output device 102. Each of RVP features module 32, PAP features module 34, validation module 36, flow module 38, SVVAEmodule 40, SVVLRmodule 42, SVVcompmodule 44, and fluid responsiveness index module 45 is a functional module of fluid responsiveness software code 30, as shown in FIG. 1. Although fluid responsiveness software code 30 is described herein as being divided into eight modules, in other examples, the functionality of fluid responsiveness software code 30 could also be described as more or fewer modules, which could depend, in some examples, on how the code is written or organized. Additionally, any modules and / or sub-modules could also be entirely separate collections of code. The modules of fluid responsiveness software code 30 will be described sequentially; however, these modules can also include overlapping or interspersed functionality. RVP features module 32 is a first module of fluid responsiveness software code 30 in hemodynamic monitoring system 10. RVP features module 32 includes methods in code for extracting features (“RVP features”) from an RVP waveform. RVP features module 32 receives an RVP waveform as an input. The RVP waveform corresponds to hemodynamic data sensed by one of hemodynamic sensors 14A and received by hemodynamic monitor 12. The sensed hemodynamic data to which the RVP waveform corresponds is passed to RVP features module 32. RVP features module 32 extracts one or more RVP features from the RVP waveform. RVP features module 32 outputs the one Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 or more RVP features to validation module 36. RVP features module 32 also outputs the one or more RVP features to SVVLRmodule 42 and fluid responsiveness index module 45. PAP features module 34 is a second module of fluid responsiveness software code 30 in hemodynamic monitoring system 10. PAP features module 34 includes methods in code for extracting features (“PAP features”) from a PAP waveform. PAP features module 34 receives a PAP waveform as an input. The PAP waveform corresponds to hemodynamic data sensed by one of hemodynamic sensors 14A and received by hemodynamic monitor 12. The hemodynamic data to which the PAP waveform corresponds is passed to PAP features module 34. PAP features module 34 extracts one or more PAP features from the PAP waveform. PAP features module 34 outputs the one or more PAP features to validation module 36. PAP features module 34 also outputs the one or more PAP features to SVVLR module 42 and fluid responsiveness index module 45. Validation module 36 is a third module of fluid responsiveness software code 30 in hemodynamic monitoring system 10. Validation module 36 includes methods in code for cleaning data and ensuring the RVP waveform and the PAP waveform are valid and reliable. Validation module 36 receives the RVP waveform, the PAP waveform, the one or more RVP features, and the one or more PAP features as inputs. The sensed hemodynamic data to which the RVP waveform and the PAP waveform correspond is passed to validation module 36. The one or more RVP features are fed to validation module 36 from RVP features module 32. Likewise, the one or more PAP features are fed to validation module 36 from PAP features module 34. Validation module 36 outputs instructions indicating whether the RVP waveform and the PAP waveform are valid or not valid to the modules contained in the dashed line box shown in FIG. 6 (i.e., flow module 38, SVVAE module 40, SVVLR module 42, SVVcomp module 44, and fluid responsiveness index module 45) and can output the determination indicating whether the RVP waveform and the PAP waveform are valid to output device 102, such as display 24 (shown in FIG. 1). For example, an instruction indicating that the RVP waveform is valid could take the form of an instruction indicating “RVP_valid=true,” and an instruction indicating that the RVP waveform is not valid could take the form of an instruction indicating “RVP_valid=false.” Likewise, an instruction indicating that the PAP waveform is valid could take the form of an instruction indicating “PAP_valid=true,” and an instruction indicating that the PAP waveform is not valid could take the form of an instruction indicating “PAP_valid=false.” An instruction that the RVP waveform and the PAP waveform are valid means that the hemodynamic data corresponding to the RVP waveform Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 and the PAP waveform is valid for further processing by the modules contained in the dashed line box. An instruction that the RVP waveform and the PAP waveform are not valid means that the hemodynamic data corresponding to the RVP waveform and the PAP waveform is not valid for further processing. Validation module 36 also outputs a smoothed RVP waveform to flow module 38 and outputs the one or more RVP features and the one or more PAP features to fluid responsiveness index module 45. Flow module 38 is a fourth module of fluid responsiveness software code 30 in hemodynamic monitoring system 10. Flow module 38 includes methods in code for estimating a beat-to-beat blood flow waveform from the RVP waveform using an autoencoder model. Flow module 38 receives the RVP waveform as an input. The sensed hemodynamic data to which the RVP waveform corresponds is passed to flow module 38. Flow module 38 can also receive the smoothed RVP waveform from validation module 36. Flow module 38 outputs instructions indicating whether the estimated blood flow waveform (or the “processed flow waveform”) is valid to SVVAE module 40 and can output the determination indicating whether the processed flow waveform is valid to output device 102, such as display 24 (shown in FIG.1). For example, an instruction indicating that the processed flow waveform is valid could take the form of an instruction indicating “Flow_valid=true,” and an instruction indicating that the processed flow waveform is not valid could take the form of an instruction indicating “Flow_valid=false. An instruction that the processed flow waveform is valid means that the estimated blood flow waveform is valid for further processing by SVVAEmodule 40. An instruction that the processed flow waveform is not valid means that the estimated blood flow waveform is not valid for further processing. Flow module 38 further outputs the processed flow waveform to SVVAEmodule 40. Flow module 38 can also output the processed flow waveform to output device 102. SVVAE module 40 is a fifth module of fluid responsiveness software code 30 in hemodynamic monitoring system 10. SVVAE module 40 includes methods in code for deriving SVV from the estimated blood flow waveform. SVVAEmodule 40 receives the processed flow waveform as an input. The processed flow waveform is fed to SVVAE module 40 from flow module 38. SVVAEmodule 40 also receives an instruction from flow module 38 indicating whether the processed flow waveform is valid or not valid such that SVVAEmodule 40 can proceed or not proceed accordingly. SVVAEmodule 40 outputs an autoencoder-derived SVV (“SVVAE”) to SVVLR module 42, SVVcomp module 44, and fluid Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 responsiveness index module 45. SVVAEmodule 40 can also output SVVAEto output device 102. SVVLR module 42 is a sixth module of fluid responsiveness software code 30 in hemodynamic monitoring system 10. SVVLRmodule 42 includes methods in code for estimating SVV based on one or more RVP features and PAP features using a linear regression model. SVVLRmodule 42 receives one or more RVP features and PAP features as inputs. The one or more RVP features are fed to SVVLR module 42 from RVP features module 32 or validation module 36. Likewise, the one or more PAP features are fed to SVVLR module 42 from PAP features module 34 or validation module 36. SVVLR module 42 outputs a linear regression-derived SVV (“SVVLR”) to SVVcompmodule 44 and fluid responsiveness index module 45. SVVLR module 42 can also output SVVLR to output device 102. SVVcomp module 44 is a seventh module of fluid responsiveness software code 30 in hemodynamic monitoring system 10. SVVcomp module 44 includes methods in code for combining estimates of SVV into a composite SVV (“SVVcomp”). In one example, SVVcomp module 44 filters SVV estimates via a Kalman filter algorithm to produce the combined estimate. SVVcompmodule 44 receives SVVAE, SVVLR, and, optionally, an additional estimate of SVV (“SVVadd”) as inputs. SVVAE is fed to SVVcomp module 44 from SVVAEmodule 40. SVVLRis fed to SVVcompmodule 44 from SVVLRmodule 42. In some examples, SVVadd can be an estimate of SVV from a pulse pressure variation that is derived from a femoral or radial pressure measurement. In other examples, SVVaddcan be an estimate of SVV from another model that is fed into SVVcomp module 44. SVVcomp module 44 outputs SVVcompto fluid responsiveness index module 45. SVVcompmodule 44 can also output SVVcomp to output device 102. Fluid responsiveness index module 45 is an eighth module of fluid responsiveness software code 30 in hemodynamic monitoring system 10. Fluid responsiveness index module 45 includes methods in code for determining a fluid responsiveness index (“IFR”) using an estimate of preload status of patient 16 and an estimate of SVV. Fluid responsiveness index module 45 receives one or more RVP features, SVVAE, SVVLR, and SVVcompas inputs. The one or more RVP features are fed to fluid responsiveness index module 45 from RVP features module 32 or validation module 36. SVVAEis fed to fluid responsiveness index module 45 from SVVAEmodule 40. SVVLRis fed to fluid responsiveness index module 45 from SVVLR module 42. SVVcomp is fed to Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 fluid responsiveness index module 45 from SVVcompmodule 44. Fluid responsiveness index module 45 outputs IFRto output device 102. Output device 102 is a device for receiving outputs from the modules of fluid responsiveness software code 30. Output device 102 can include display 24, as shown in FIG.1. For example, output device 102 can receive final estimates of beat-to-beat flow, SVV, and / or IFRfor display via display 24. Output device 102 can receive outputs from flow module 38, SVVAE module 40, SVVLR module 42, SVVcomp module 44, and fluid responsiveness index module 45. More specifically, output device 102 receives the processed flow waveform, SVVAE, SVVLR, SVVcomp, and IFR. Each of these outputs can be displayed via display 24 as corresponding graphs representing the values over time. Healthcare worker 18 can interpret the value of SVVAE, SVVLR, and / or SVVcomp from output device 102 to make a clinical decision for patient 16. In some examples, healthcare worker 18 can compare the value of SVVAE, SVVLR, and / or SVVcomp to a threshold. For example, if the estimate of SVV is greater than a threshold value, then patient 16 can be considered fluid responsive, and if the estimate of SVV is less than the threshold value, then patient 16 can be considered not fluid responsive. Additionally or alternatively, output device 102 could display an indication of a fluid responsiveness status of patient 16 based on predefined SVV threshold information from fluid responsiveness software code 30. In some examples, healthcare worker 18 can also review the values of SVVAE, SVVLR, and / or SVVcomp over time to determine if trends in SVV for patient 16 match expected changes based on whether fluid was administered. Additionally or alternatively, output device 102 can display an indication of a fluid responsiveness status of patient 16 based on predefined SVV trend information (or expected SVV trend conditions) from fluid responsiveness software code 30. In addition to SVV, healthcare worker 18 can use IFRfrom output device 102 to obtain additional information about the fluid responsiveness status of patient 16. Although several modules are illustrated in FIG.6 as having multiple inputs and outputs, some of the inputs and outputs are optional, and many configurations of hemodynamic monitoring system 10 (as shown in FIG.1) are possible. In some examples, the PAP waveform and PAP features may not be used. In some examples, an estimate of SVV for patient 16 (as shown in FIG. 1) can be output from any one or more of SVVAE module 40, SVVLRmodule 42, and SVVcompmodule 44, in addition or alternatively to outputting IFR from fluid responsiveness index module 45. These configurations can Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 depend, for example, on the combination of hemodynamic sensors 14 (as shown in FIG.1) used or the desired output. Each module of hemodynamic monitoring system 10 will be described in greater detail in turn below. RVP features module 32 will be described with reference to FIG. 7. PAP features module 34 will be described with reference to FIG. 8. Validation module 36 will be described with reference to FIGS. 9-11. Flow module 38 will be described with reference to FIGS. 12-16. SVVAE module 40 will be described with reference to FIGS.17-18. SVVLRmodule 42 will be described with reference to FIGS.19- 22. SVVcomp module 44 will be described with reference to FIGS. 23-25C. Fluid responsiveness index module 45 will be described with reference to FIGS.26-28. FIG.7 is a graph illustrating RVP waveform trace 104 including indicia 106, 108, 110, 112, 114, 116, 118, and 120. In FIG.7, RVP waveform trace 104 is an example of an RVP waveform, which corresponds to hemodynamic data sensed by one of hemodynamic sensors 14A and received by hemodynamic monitor 12. RVP waveform trace 104 (represented via digital hemodynamic data) can include various indicia indicative of blood flow and SVV for patient 16. One or more RVP features are extracted from the RVP waveform via RVP features module 32, as discussed above with respect to FIG. 1. Prior to extracting indicia from the RVP waveform, beat detector algorithms identify the start and end of individual heartbeats for each waveform. RVP beat detection algorithms identify the start of the heartbeat based on the maximum RVP, the minimum RVP, the maximum or minimum rate of change in RVP, and / or the second derivative with respect to time in the RVP. After heartbeat identification within the RVP waveform, various indicia of blood flow and SVV can be extracted from the waveform on an on-going, beat-to-beat basis. Indicium 106 of RVP waveform trace 104 corresponds to the minimum diastolic pressure. Indicium 108 of RVP waveform trace 104 corresponds to the end diastolic pressure. Indicium 110 of RVP waveform trace 104 corresponds to the maximum systolic pressure. Indicium 112 of RVP waveform trace 104 corresponds to the end systolic pressure. Slope S1 is the slope of RVP waveform trace 104, which may also provide indicia. Slope S1 is depicted at one location but is representative of multiple slopes that may be determined at multiple locations along RVP waveform trace 104. For instance, indicium 114, corresponding to the maximum pressure rate of change with respect to time (dP / dt) during systolic rise, and indicium 116, corresponding to the minimum pressure rate of change with respect to time (dP / dt) during the relaxation period after end systole, are Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 further example indicia. Similarly, the second time derivative of RVP waveform trace 104 may be determined at any location along RVP waveform trace 104 and used as indicia. Other exemplary indicia include RVP gradients, or the difference in pressure at different times during diastolic or systolic phase. For example, indicium 118 corresponds to the diastolic gradient, or the difference between minimum diastolic pressure (indicium 106) and end diastolic pressure (indicium 108). Indicium 120 corresponds to the right ventricular pulse pressure, or a pressure gradient equal to the difference between end diastolic pressure (indicium 108) and maximum systolic pressure (indicium 110). Additional indicia can be extracted from RVP waveform trace 104 by fluid responsiveness software code 30 based on RVP waveform trace 104 during various intervals, for example, using RVP features module 32. For instance, systolic rise (indicia 108-110), systolic decay (indicia 110-112), isovolumetric relaxation (indicia 112-106), diastolic phase (indicia 106-108), and the heartbeat interval (between indicia 106) can be determined by fluid responsiveness software code 30. Such indicia may include the mean RVP during one of the above-referenced intervals. FIG.8 is a graph illustrating PAP waveform trace 122 including indicia 124, 126, 128, 130, and 132. In FIG. 8, PAP waveform trace 122 is an example of a PAP waveform, which corresponds to hemodynamic data sensed by one of hemodynamic sensors 14A and received by hemodynamic monitor 12. PAP waveform trace 122 (represented via digital hemodynamic data) can include various indicia indicative of blood flow and SVV for patient 16. One or more PAP features are extracted from the PAP waveform via PAP features module 34, as discussed above with respect to FIG.1. Prior to extracting indicia from the PAP waveform, beat detector algorithms identify the start and end of individual heartbeats for each waveform. PAP beat detection algorithms identify the start of the heartbeat based on the maximum PAP, the minimum PAP, the maximum or minimum rate of change in PAP, and / or the second derivative with respect to time in the PAP. After heartbeat identification within the PAP waveform, various indicia of blood flow and SVV can be extracted from the waveform on an on-going, beat-to-beat basis. Indicium 124 of PAP waveform trace 122 corresponds to the start of a heartbeat. Indicium 126 of PAP waveform trace 122 corresponds to the maximum systolic pressure marking the end of systolic rise. Indicium 128 of PAP waveform trace 122 corresponds to the presence and pressure of the dicrotic notch marking the end of systolic decay. Indicium 130 of PAP waveform trace 122 corresponds to the minimum diastolic pressure of the heartbeat of patient 16. The mean PAP can also be an indicium. PAP Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 gradients, or pressure differences between points of the PAP waveform trace 122, can be indicia. For instance, indicium 132 corresponds to pulmonary pulse pressure, or the difference between minimum diastolic pressure (indicium 130) and maximum systolic pressure (indicium 126). S2 is the slope of PAP waveform trace 122, which may also provide indicia. Slope S2 is depicted at one location but is representative of multiple slopes that may be determined at multiple locations along PAP waveform trace 122. For instance, indicia may include the maximum and / or minimum time derivative of PAP waveform trace 122. Additional indicia can be extracted from PAP waveform trace 122 by fluid responsiveness software code 30 based on PAP waveform trace 122 during various intervals, for example, using PAP features module 34. For instance, the interval from the maximum systolic pressure at indicium 126 to the diastole at indicium 128 and the interval from the start of the heartbeat at indicium 124 to the diastole at indicium 130 can be extracted from PAP waveform trace 122. Fluid responsiveness software code 30 may identify additional indicia from PAP waveform trace 122 during various intervals. For instance, systolic rise (indicia 124-126), systolic decay (indicia 126-128), systolic phase (indicia 124-128), diastolic phase (indicia 128-130), and the heartbeat interval (between indicia 124) can be determined by flow and cardiac output software code 30. Such indicia may include the mean PAP during one of the above-referenced intervals. The area under the curve of PAP waveform trace 122 and the standard deviations of PAP waveform trace 122 determined for the above-referenced intervals can also serve as additional indicia for patient 16. Validation Module (FIGS.9-11) FIG.9 is a schematic block diagram illustrating validation module 36, which includes signal quality detector 134 and decision block 136. FIG.10 is a graph illustrating RVP waveform trace 137 including indicia 108 and 110, which are indicative of the placement of and data quality from catheter 54 (shown in FIG. 3). FIG. 11 is a graph illustrating RVP waveform trace 104 and PAP waveform trace 122 including indicia 110, 126, 138, 140, and 142, which are indicative of the placement of and data quality from catheter 54. FIGS. 9, 10, and 11 will be discussed together. Validation module 36 uses data from an RVP waveform and a PAP waveform to detect and continuously monitor catheter 54 placement issues and signal-quality issues, which affect data quality. Validation module 36 filters, or cleans, data and ensures the RVP waveform, the PAP waveform, the one or more RVP features, and the one or more PAP features are Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 valid and reliable. The one or more RVP features of the RVP waveform and the one or more PAP features of the PAP waveform that are derived from RVP features module 32 and PAP features module 34, respectively, are inputs for validation module 36. The RVP waveform and the PAP waveform are also input into validation module 36. Validation module 36 analyzes the RVP waveform and the PAP waveform in ten-second segments. The segments of the RVP waveform and the PAP waveform may be about ten seconds (e.g., 9.5 seconds to 10.5 seconds) or any other suitable time segment. Validation module 36 can be implemented within a patient care environment, such as an ICU, an OR, or another patient care environment. Validation module 36 refines data collected from catheter 54 and determines whether catheter 54 is placed correctly to yield data of high quality via signal quality detector 134 and decision block 136. As such, validation module 36 determines whether data from catheter 54 is usable for further analysis, such as for flow module 38, SVVLR module 42, and fluid responsiveness index module 45. The one or more RVP features and the one or more PAP features are input into signal quality detector 134. Signal quality detector 134 cleans data generated from the one or more RVP features and the one or more PAP features and assigns RVP signal quality index (“SQIRVP”) and PAP signal quality index (“SQIPAP”) to each ten-second segment of each of the RVP waveform and the PAP waveform, respectively. Signal quality detector 134 checks for the standard deviation of the one or more RVP features and the one or more PAP features, artifacts in the RVP waveform and the PAP waveform, and the standard deviation of features that represent differences between the RVP waveform and the PAP waveform. Signal quality detector 134 consumes the one or more RVP features and the one or more PAP features, utilizing a signal quality algorithm to analyze data by comparing the one or more RVP features and the one or more PAP features against designated value ranges for the one or more RVP features and the one or more PAP features, respectively. When both the RVP waveform and the PAP waveform are present, features can be compared between waveforms, and features that represent differences between waveforms can be analyzed. The designated value ranges correspond to physiological limits plus system tolerance, or the standard deviation for each of the one or more RVP features, the one or more PAP features, and features representing differences between the RVP waveform and the PAP waveform. Signal quality detector 134 also checks data quality by comparing the one or more RVP features to the one or more PAP features. As such, the designated value ranges can be used to identify artifacts in the RVP waveform and the PAP Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 waveform, such as excluded beats or noise, and signal quality issues, such as an underdamp or overdamp signal. Data outside of the designated value ranges, such as a negative pressure, an inordinately high pressure, or maximum systolic pressure 126 of PAP waveform trace 122 that is higher than maximum systolic pressure 110 of RVP waveform trace 104, represents data that is not possible physiologically. Values outside of the designated value ranges represent erroneous data. Signal quality detector 134 cleans data, smoothing out the RVP waveform and the PAP waveform by removing erroneous data. Signal quality detector 134 assigns SQIRVPand SQIPAP to each ten-second segment of the RVP waveform and the PAP waveform based on the amount of detected erroneous data. Signal quality detector 134 outputs SQIRVPand a SQIPAP to decision block 136. Erroneous data (identified by features being outside the designated value ranges) in each ten-second segment of analyzed the RVP waveform and the PAP waveform is removed from the ten-second segment on a beat level, or any other suitable level. If the RVP waveform is valid (e.g., “RVP_valid=true”) and / or the PAP waveform is valid (e.g., “PAP_valid=true”), the portion of the remaining ten-second segment of the RVP waveform and / or segment of the PAP waveform and the associated one or more RVP features and / or PAP features, respectively, are passed on for further analysis. FIG. 10 illustrates an example RVP waveform trace 137 that may be analyzed by signal quality detector 134. Signal quality detector 134 analyzes one or more RVP features of RVP waveform trace 137. RVP waveform trace 137 is another example of an RVP waveform, similar to RVP waveform trace 104 shown in FIG. 7. In this example, signal quality detector 134 compares end diastolic pressures 108 and maximum systolic pressures 110 of each beat of RVP waveform trace 137 against the designated value ranges for RVP end diastolic pressure 108 and RVP maximum systolic pressure 110, respectively. Data from each beat, from RVP end diastolic pressure 108 to the subsequent RVP end diastolic pressure 108 or from RVP maximum systolic pressure 110 to the subsequent RVP maximum systolic pressure 110, is analyzed against corresponding designated value ranges. RVP waveform trace 137 includes end diastolic pressure exclusion 108E and maximum systolic pressure exclusion 110E. FIG.10 shows a beat of RVP waveform trace 137 extending from RVP end diastolic pressure 108 to the subsequent RVP end diastolic pressure 108 or extending from RVP maximum systolic pressure 110 to the maximum systolic pressure 110. Signal quality detector 134 detects and flags, via the signal quality algorithm, beats including data outside Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 of the designated value ranges and removes those beats. As such, end diastolic pressure exclusion 108E and maximum systolic pressure exclusion 110E, are removed, or excluded from further analysis, as they are within beats from the segment shown in RVP waveform trace 137 that contain erroneous data and are removed from the segment of the RVP waveform. As seen in FIG. 10, the beat from maximum systolic pressure 110 to the subsequent maximum systolic pressure exclusion 110E includes pressure values outside of the designated value ranges as RVP waveform trace 137 includes an artifact, noise, preceding end diastolic pressure exclusion 108E. As a result, signal quality detector 134 flags and excludes the beat (maximum systolic pressure 110 to the maximum systolic pressure exclusion 110E in RVP waveform trace 137), and all data from the beat is discarded from the RVP waveform. End diastolic pressure exclusion 108E, which is within said beat, is an end diastolic pressure measurement that is excluded from further analysis. As further seen in FIG. 10, the beat from end diastolic pressure exclusion 108E to the subsequent end diastolic pressure 108 in RVP waveform trace 137 includes a sharp drop in pressure following maximum systolic pressure exclusion 110E that is outside of the designated value range The sharp drop in pressure in RVP waveform trace 137 after maximum systolic pressure exclusion 110E is outside of the designated value range as it is physiologically unexpected for the pressure to decrease that quickly following maximum systolic pressure 110. As a result, signal quality detector 134 flags and excludes the beat, and all data from the beat (end diastolic pressure exclusion 108E to the subsequent end diastolic pressure 108 in RVP waveform trace 137) is discarded from the RVP waveform. Maximum systolic pressure exclusion 110E, which is within said beat, is a maximum systolic pressure measurement that is excluded from further analysis. The beats are excluded from the segment of the RVP waveform corresponding to RVP waveform trace 137 prior to forwarding the segment of the RVP waveform, including associated RVP features, to subsequent modules, thereby cleaning the RVP waveform. Signal quality detector 134 uses the excluded beats from maximum systolic pressure 110 to the maximum systolic pressure exclusion 110E and from end diastolic pressure exclusion 108E to the subsequent end diastolic pressure 108, which contain the noise and the sharp drop in pressure, in determining SQIRVP. Signal quality detector 134 can analyze the PAP waveform in a similar way using the PAP features to clean and analyze the PAP waveform. Designated value ranges may also correspond to differences between the one or more RVP features and the one or more PAP features when both the RVP waveform and the PAP waveform are available. Further, various features can be derived from Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 differences between the RVP waveform and the PAP waveform, the examined features depending on whether the RVP waveform and the PAP waveform are synchronous or asynchronous. Values outside of the designated value ranges represent erroneous data. As seen in FIG. 11, signal quality detector 134 can analyze features representing differences between one or more RVP features of RVP waveform trace 104 and one or more PAP features of PAP waveform trace 122. RVP waveform trace 104 is synchronized with PAP waveform trace 122. RVP waveform trace 104 is an example of an RVP waveform, and PAP waveform trace 122 is an example of a PAP waveform. In this example, signal quality detector 134 analyzes pulse transit time 138, systolic gradient 140, and mean pressure 142. Indicium 110 is determined from RVP waveform trace 104. Indicium 110 is the maximum systolic pressure, or the end of systolic rise, of RVP waveform trace 104. Indicium 126 is determined from PAP waveform trace 122. Indicium 126 is the maximum systolic pressure, or the end of systolic rise, of PAP waveform trace 122. Indicia 138, 140, and 142 are determined from differences between RVP waveform trace 104 and PAP waveform trace 122. Indicium 138 is the pulse transit time, or the time elapsed between the maximum systolic pressure (indicium 110) of RVP waveform trace 104 and the maximum systolic pressure (indicium 126) of PAP waveform trace 122. Pulse transit time 138 represents the delay between the RVP waveform and the PAP waveform, or the time difference between when beats are detected in both the RVP waveform and the PAP waveform. Indicium 140 is the systolic gradient, or the pressure gradient between maximum systolic pressure (indicium 110) of RVP waveform trace 104 and maximum systolic pressure (indicium 126) of PAP waveform trace 122. Indicium 142 is the mean pressure of PAP waveform trace 122 and RVP waveform trace 104. Signal quality detector 134 compares pulse transit time 138, systolic gradient 140, and mean pressure 142 against the designated value ranges for pulse transit time 138, systolic gradient 140, and mean pressure 142, respectively. Signal quality detector 134 can also check for other differences between features of synchronous RVP waveform trace 104 and PAP waveform trace 122, such as a difference between maximum systolic pressure 110 of RVP waveform trace 104 and maximum systolic pressure 126 of PAP waveform trace 122 or a difference between the heart rate computed from the RVP features and the heart rate computed from the PAP features. For example, if the RVP waveform indicates the presence of five heartbeats and a synchronous PAP waveform indicates the presence of ten heartbeats in the same time window, signal quality detector Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 134 would detect that the data from that segment of the RVP waveform and / or the PAP waveform is not valid. If RVP waveform trace 104 and PAP waveform trace 122 are asynchronous, signal quality detector 134 can analyze other additional RVP features and PAP features, such as the change in pulse transit time between RVP waveform trace 104 and PAP waveform trace 122. Signal quality detector 134 detects and flags, via the signal quality algorithm, any errors, or values outside of the designated value ranges, for each indicium. Signal quality detector 134 excludes beats from the RVP waveform and the PAP waveform corresponding to beats from RVP waveform trace 104 and PAP waveform trace 122 that include flagged data containing errors prior to forwarding the RVP waveform, the PAP waveform, the one or more RVP features, and the one or more PAP features to subsequent modules, thereby cleaning the RVP waveform and the PAP waveform. Signal quality detector 134 uses any errors in indicia identified based on differences between the one or more RVP features and the one or more PAP features, such as pulse transit time 138, systolic gradient 140, and mean pressure 142, in determining SQIRVP and SQIPAP. Indicium 138, 140, and 142, among other parameters determined or derived from RVP waveform trace 104 and PAP waveform trace 122, provide additional data by which signal quality detector 134 can analyze the RVP waveform and the PAP waveform. As such, analyzing both the RVP waveform and the PAP waveform enables a more comprehensive evaluation of data quality, resulting in a more accurate analysis. As discussed above, signal quality detector 134 uses such information in addition to the one or more RVP features and the one or more PAP features from ten-second intervals of the RVP waveform and the PAP waveform, respectively, to determine SQIRVP, SQIPAP, and a combined RVP and PAP signal quality algorithm (“SQICOMB”) via the signal quality algorithm. Signal quality detector 134 assigns SQIRVP, SQIPAP, and SQICOMBbased on the one or more RVP features, the one or more PAP features, and features representing differences between the RVP waveform and the PAP waveform, respectively. SQIRVPand SQIPAPare values that indicate the quality of the respective segments of waveforms, or the extent of deviation in the one or more RVP features and the one or more PAP features computed from ten-second segments of the RVP waveform and the PAP waveform, respectively. For example, signal quality detector 134 may assign a signal quality index of zero to five (0 to 5), with zero (0) being the highest quality and five (5) being the lowest quality. SQIRVP and SQIPAP may be any suitable numeric range. Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 Signal quality detector 134 compares the one or more RVP features of the RVP waveform and the one or more PAP features of the PAP waveform against designated value ranges for the RVP features and designated value ranges for the PAP features, respectively, as discussed above. Signal quality detector 134 assigns SQIRVPand SQIPAPto each of the RVP waveform and the PAP waveform based on how close various RVP features and PAP features, respectively, are to the designed value ranges. The RVP waveform and the PAP waveform may be assigned SQIRVP and SQIPAP, respectively, having values of two to five (2 to 5) if the one or more RVP features and the one or more PAP features, respectively, are not within the designated value ranges. The RVP waveform and the PAP waveform may be assigned SQIRVPand SQIPAP, respectively, having values of zero to one (0 to 1) if the one or more RVP features and the one or more PAP features, respectively, are within the designated value ranges. Signal quality detector 134 outputs SQIRVP and SQIPAP to decision block 136. SQIRVP and SQIPAP are fed into decision block 136 of validation module 36, which determines whether the ten-second segments of the RVP waveform and the PAP waveform are valid. Decision block 136 may output the determinations to output device 102 (shown in FIG.6), which can be, for example, display 24 (shown in FIG.1). Decision block 136 is a binary system, assigning a zero (0) to the RVP waveform and the PAP waveform with RVP features and PAP features, respectively, that are not within designated value ranges and assigning a one (1) to the RVP waveform and the PAP waveform with RVP features and PAP features, respectively, that are within designated value ranges. For example, when the RVP features and the PAP features have a signal quality index of two to five (2 to 5), decision block 136 assigns a zero (0) to the RVP waveform and the PAP waveform, respectively. When the RVP features and the PAP features have a signal quality index of zero or one (0 or 1), decision block 136 assigns a one (1) to the RVP waveform and the PAP waveform, respectively. If SQIRVP is assigned a zero (0), decision block 136 determines that the RVP waveform is not valid (e.g., “RVP_valid=false”). This is indicated by the arrow labeled “No” in FIG. 9. The determination that the RVP waveform is not valid can be sent from decision block 136 to a display, which may show an “INVALID RVP WAVEFORM” reading. If SQIRVP is assigned a one (1), decision block 136 determines that the RVP waveform is valid (e.g., “RVP_valid=true”). This is indicated by the arrow labeled “Yes” in FIG. 9. The determination that the RVP waveform is valid can be sent from decision block 136 to a display, which may show a “VALID RVP WAVEFORM” reading. Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 Validation module 36 can also output instructions that indicate whether the RVP waveform is valid or not valid to the modules contained in the dashed line box shown in FIG. 6 (i.e., flow module 38, SVVAE module 40, SVVLR module 42, SVVcomp module 44, and fluid responsiveness index module 45). Subsequent modules can proceed using data from the filtered ten-second segment of the RVP waveform when the RVP waveform is valid and cannot proceed using data from the RVP waveform when the RVP waveform is not valid. If SQIPAP is assigned a zero (0), decision block 136 determines that the PAP waveform is not valid (e.g., “PAP_valid=false”). This is indicated by the arrow labeled “No” in FIG. 9. The determination that the PAP waveform is not valid can be sent from decision block 136 to a display, which may show an “INVALID PAP WAVEFORM” reading. If SQIPAP is assigned a one (1), decision block 136 determines that the PAP waveform is valid (e.g., “PAP_valid=true”). This is indicated by the arrow labeled “Yes” in FIG. 9. The determination that the PAP waveform is valid can be sent from decision block 136 to a display, which may show a “VALID PAP WAVEFORM” reading. Validation module 36 can also output instructions that indicate whether the PAP waveform is valid or not valid to the modules contained in the dashed line box shown in FIG.6 (i.e., flow module 38, SVVAEmodule 40, SVVLRmodule 42, SVVcompmodule 44, and fluid responsiveness index module 45). Subsequent modules can proceed using data from the filtered ten-second segment of the PAP waveform when the PAP waveform is valid and cannot proceed using data from the PAP waveform when the RVP waveform is not valid. SQICOMBis generated the same way using the features representing differences between the RVP waveform and the PAP waveform. SQICOMB can be used by decision block 136 to further analyze the validity of the ten-second segment of the RVP waveform and / or the ten-second segment of the PAP waveform. If the RVP waveform and / or the PAP waveform is valid, catheter 54 is correctly placed, and the one or more RVP features, the RVP waveform, the one or more PAP features, and the PAP waveform are of high quality (i.e., few artifacts and are suitable for further processing and analysis). If the RVP waveform is valid and the PAP waveform is not valid, the one or more RVP features and the RVP waveform may still be of high quality, with few artifacts, and may still be acceptable for further processing and analysis. For example, if SQICOMB is assigned a one (1) and SQIRVP is assigned a one (1), the RVP waveform is still valid, and the one or more RVP features and the RVP waveform are of high quality and acceptable for further analysis. For example, validation module 36 can output a smoothed RVP waveform to flow module 38 for determining blood flow. If the Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 RVP waveform is not valid, alone or in combination with the PAP waveform being not valid, catheter 54 is incorrectly placed or signal-quality issues are occurring, and catheter 54 should be adjusted. The one or more RVP features and the RVP waveform and / or the one or more PAP features and the PAP waveform derived from incorrectly placed catheter 54 are of low quality and are rejected as unacceptable for further analysis. Validation module 36 determines whether signal quality is sufficient and catheter 54 is operating within physiological limits. In some examples, validation module 36 continuously monitors the placement of catheter 54 via the signal quality. Validation module 36 analyzes one or more RVP features of the RVP waveform and one or more PAP features of the PAP waveform to determine whether catheter 54 is correctly placed and thus collecting accurate data to yield a valid RVP waveform and PAP waveform from which blood flow and SVV estimates can be derived. For example, if the RVP waveform or the PAP waveform is a flat line, catheter 54 may not be properly connected to hemodynamic monitor 12, and blood flow and SVV cannot be derived. Additionally, if values of the RVP waveform or the PAP waveform are above or below the designated value ranges, catheter 54 may be improperly placed and delivering data indicative of central venous pressure instead of RVP and / or PAP, respectively. If data is above or below designated value ranges, data is of poor quality and should not be used, and catheter 54 should be adjusted. If data is within designated value ranges, data is of high quality and may be used for further analysis, such as in a further module. Thus, identifying and monitoring placement issues and / or other data quality issues in real-time is important for notifying clinicians and disabling output of erroneous information. Flow Module (FIGS.12-16) FIG.12 is a schematic block diagram illustrating flow module 38. FIG.13 is a schematic block diagram illustrating an RVP waveform transforming into a processed flow waveform via flow module 38. FIGS.12 and 13 will be discussed together. The RVP waveform is input into flow module 38 to predict blood flow dynamics. Flow module 38 includes autoencoder model (or “autoencoder”) 144, flow filter 146, and decision block 148. Flow module 38 receives the RVP waveform as an input and outputs a processed flow waveform, which is an estimate of a waveform of processed blood flow for patient 16, and processed blood flow signal quality index (“SQIflow”). Flow module 38 may receive a smoothed, or cleaned, RVP waveform from validation module 36, as discussed above with respect to FIGS.9-11. Additionally, the RVP waveform can be normalized for Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 each patient (e.g., patient 16, as shown in FIG.1) such that absolute values of RVP are not preserved or analyzed in flow module 38 (and SVVAEmodule 40, as shown in FIG.17) and only relative RVP values and the shape of the RVP waveform are used. As seen in FIG. 13, the RVP waveform is transformed into the processed waveform via flow module 38. The RVP waveform is transformed into an estimate of a waveform of raw blood flow (or “raw flow waveform”) by autoencoder model 144. The raw flow waveform is subsequently transformed into the processed flow waveform via flow filter 146. The raw flow waveform is processed to reflect physiological expectations of blood flow and generate SQIflow. Autoencoder model 144 and flow filter 146 each analyze ten-second intervals of the RVP waveform and the raw flow waveform, respectively, to generate a beat-to-beat processed flow waveform. In some examples, flow module 38 continuously outputs the processed flow waveform. Autoencoder model 144 has an input of the RVP waveform and an output of the raw flow waveform. Autoencoder model 144 is a deep-learning-based model, which works successfully when patient 16 has both low and high cardiac output. Autoencoder model 144 is trained to convert the RVP waveform into the raw flow waveform, as discussed below with respect to FIG. 16. Autoencoder model 144 outputs the raw flow waveform to flow filter 146. Flow filter 146 receives the raw flow waveform as an input from autoencoder model 144 and outputs the processed flow waveform and SQIflow. Flow filter 146 filters, or cleans, the raw flow waveform by comparing features of the raw flow waveform against designated value ranges for blood flow that correspond to physiological limits. As such, flow filter 146 filters the raw flow waveform to remove, or exclude, from the processed waveform artifacts or physiological inaccuracies, such as a negative flow, flow values in the thousands, or square-shaped flow, and inconsistencies, such as an inordinate, or very quick, increase in flow or inordinately dissimilar flow per beat. As a result, flow filter 146 yields a smoother, more consistent, and more accurate blood flow waveform, the processed flow waveform. As such, the processed flow waveform from flow filter 146 is more accurate and physiologically reasonable than the raw flow waveform. Flow filter 146 determines and assigns SQIflow to the processed flow waveform. SQIflowis a value that indicates the quality of the processed flow waveform. Flow filter 146 compares the raw flow waveform against designated value ranges for blood flow, as discussed above, to output SQIflowin addition to the processed flow waveform. Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 Flow filter 146 assigns SQIflowto the processed flow waveform based on the amount of physiological inaccuracies and / or inconsistencies, or erroneous data, detected and removed from the raw flow waveform. For example, the processed flow waveform may be assigned SQIflow, between zero and five (0 and 5), with zero (0) being the highest quality and five (5) being the lowest quality. SQIflow may be any suitable numeric range. Flow filter 146 compares the raw flow waveform to designated value ranges for blood flow. Flow filter 146 assigns SQIflow to the processed flow waveform based on how close the raw flow waveform is to designated value ranges. The processed flow waveform may be assigned SQIflow having values of two to five (2 to 5) if the raw flow waveform is not within or close to all or some designated value ranges. The processed flow waveform may be assigned SQIflow having values of zero to one (0 to 1) if the raw flow waveform is within or close to all designated value ranges. Flow filter 146 outputs SQIflow to decision block 148. SQIflow is fed into decision block 148 of flow module 38, which determines whether the processed flow waveform is valid. Decision block 148 may output the determination that the processed flow waveform is valid or not valid to output device 102 (shown in FIG. 6), which can be, for example, display 24 (shown in FIG. 1). Decision block 148 is a binary system, assigning a zero (0) to a processed flow waveform that is not within designated value ranges and assigning a one (1) to a processed flow waveform that is within designated value ranges. For example, when SQIflowhas a value of two to five (2 to 5), decision block 148 assigns a zero (0) to the processed flow waveform. When SQIflow has a value of zero or one (0 or 1), decision block 148 assigns a one (1) to the processed flow waveform. If SQIflowis assigned a zero (0), decision block 148 determines that the processed flow waveform is not valid (e.g., “Flow_valid=false”). This is indicated by the arrow labeled “No” in FIG.12. The determination that the processed flow waveform is not valid can be sent from decision block 148 to a display, which may show an “INVALID BLOOD FLOW” reading. If SQIflow is assigned a one (1), decision block 148 determines that the processed flow waveform is valid (e.g., “Flow_valid=true”). This is indicated by the arrow labeled “Yes” in FIG.12. The determination that the processed flow waveform is valid can be sent from decision block 148 to a display, which may show a “VALID BLOOD FLOW” reading. Flow module 38 can also output instructions that indicate whether the processed flow waveform is valid or not valid to SVVAEmodule 40, which can use the valid processed flow waveform as an input. Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 If the processed flow waveform is valid, the processed flow waveform is of high quality and is acceptable for further processing and analysis. The valid processed flow waveform can itself also be used to improve patient care. If the processed flow waveform is not valid, the processed flow waveform is of low quality and is rejected for further processing and analysis. Flow module 38 transforms the RVP waveform into the processed flow waveform and determines whether that processed flow waveform is of high quality. A high quality processed flow waveform can be used alone in patient care settings or can be used with other modules to generate cardiac output. FIG.14 is a schematic block diagram illustrating autoencoder model 144 of flow module 38. Autoencoder model 144 includes input 150, filters 152, latent space 154, filters 156, and output 158. Input 150 and filters 152 make up encoder 160, and filters 156 and output 158 make up decoder 162. Input 150 of autoencoder model 144 is a ten-second sample of an RVP waveform. By utilizing a ten-second sample, the sample size is large enough that the waveform is stable and more accurate but small enough that the samples represent a continuous RVP waveform. The ten-second sample of the RVP waveform may be about a ten-second sample (e.g., 9.5 seconds to 10.5 seconds) or any other suitable time sample. Autoencoder model 144 can receive ten-second samples on a rolling basis, for example input 150 of samples are ten-second samples but may be input into autoencoder model 144 every two seconds. Input 150 is encoded via filters 152 of autoencoder model 144 into a condensed version of data from input 150 in latent space 154. Latent space 154 stores condensed data. The condensed data in latent space 154 is then decoded via filters 156 of autoencoder model 144 to become output 158. Output 158 of autoencoder model 144 is a ten-second sample of the raw flow waveform. Autoencoder model 144 is trained to yield a raw flow waveform from an input of an RVP waveform, as described below with respect to FIG.16. As such, encoder 160 of autoencoder model 144 is the portion of autoencoder model 144 that encodes, or compresses, input 150 of the RVP waveform into a smaller number of variables that include all the critical information of input 150 via filters 152. Decoder 162 of autoencoder model 144 takes such compressed encoded information and expands it via filters 156 to create output 158 of the raw flow waveform. Traditionally, blood flow measurements of patient 16 are not available to healthcare worker 18 because of the invasiveness of measuring blood flow in humans. Additionally, traditional autoencoder models are trained to learn a latent space Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 representation of an input, the compressed input from the latent space being expanded into an output that is the same as the input. For example, a traditional autoencoder may have an input of an RVP waveform and would yield an output of an RVP waveform. Autoencoder model 144 is a machine learning model. More specifically, autoencoder model 144 is a deep-learning-based model that is trained to use neural network architecture to convert an RVP waveform into a raw flow waveform, as discussed below with respect to FIG. 16. Autoencoder model 144 can transform an RVP waveform into a raw flow waveform, which can be processed via flow filter 146 to yield a robust processed flow waveform. As such, autoencoder model 144 provides a practical less invasive method for generating estimates of continuous blood flow measurements for patient 16. As a result, blood flow measurements for patient 16 are available for improved patient care. The processed flow waveform can also be used to generate SVV for patient 16, as discussed below with respect to SVVAE module 40. FIG. 15 is a schematic diagram illustrating filters 152 and 156 of encoder 160 and decoder 162, respectively, of autoencoder model 144. Filters 152 of encoder 160 comprise a plurality of filters 152, and filters 156 of decoder 162 comprise a plurality of filters 156. Filters 152 are applied to input 150 of autoencoder model 144. Filters 152 are mathematical operations that transform input 150 of the RVP waveform into compressed data. Data samples of input 150 are reduced by a given factor by each filter 152 until fully compressed data reaches latent space 154. Filters 156 are applied to the compressed information in latent space 154 to yield output 158 of the raw flow waveform. Data samples are expanded by a given factor by each filter 156 until reaching output 158. An algorithm within autoencoder model 144 autogenerates the architecture of filters 152 and filters 156, which are convolutional neural networks with auto-selected convolutions and pooling, based on input 150 and desired output 158. Complex nonlinear relationships exist among filtered data at each filtering layer 152 and 156. In the example of FIG. 15, filters 152 and 156 have an 8-16-32 architecture. A first layer of filters 152 has 8 filters, a second layer of filters 152 has 16 filters, and a third layer of filters 152 has 32 filters. A first layer of filters 156 has 32 filters, a second layer of filters 156 has 16 filters, and a third layer of filters 156 has 8 filters. In the example of FIG. 15, autoencoder model 144 has 12,000 parameters and requires 112 convolution operations. Parameters are determined as autoencoder model 144 is trained. Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 Filters 152 enable the compression and encoding of the RVP waveform. Filters 156 enable the expansion and decoding of compressed data into the raw flow waveform. As a result, filters 152 and 156 of trained autoencoder model 144 can transform the RVP waveform into the raw flow waveform. FIG. 16 is a flow diagram illustrating process 164 for training autoencoder model 144 to predict a human raw flow waveform based on a human RVP waveform. Process 164 for training autoencoder model 144 includes steps 166-178. Once autoencoder model 144 is trained via process 164, autoencoder model 144 is ready for use in flow module 38, as discussed above. In step 166, autoencoder model 144 is trained using a measured RVP waveform of an animal and a measured blood flow of an animal. The animal RVP waveform and the animal blood flow are both known in step 166. Because directly measuring blood flow in a human is too invasive, information is derived from animal studies by directly measuring blood flow in an animal with respect to the known RVP waveform of the same animal. Autoencoder model 144 is trained using the animal RVP waveform as the input and the measured animal blood flow as the output to get an animal trained autoencoder model 144. In step 168, the animal RVP waveform is input into animal trained autoencoder model 144 to generate a predicted animal blood flow. The known animal RVP waveform is input into animal trained autoencoder model 144, and a waveform of the predicted animal blood flow is output from autoencoder model 144. In step 170, the measured animal blood flow is compared to the predicted animal blood flow to validate autoencoder model 144 training. Because both the animal RVP waveform and the associated waveform of measured animal blood flow are known, the predicted animal blood flow from animal trained autoencoder model 144 can be compared against the known directly measured animal blood flow with respect to various portions of the RVP waveform of the animal. Thus, the predicted animal blood flow waveform from autoencoder model 144 is compared to the directly measured animal blood flow waveform. Metrics such as mean square error (MSE), mean absolute error (MAE), correlation, and Bland-Altman analysis are used in the comparison to determine the performance of the autoencoder model 144. In step 172, the predicted animal blood flow from animal trained autoencoder model 144 is determined to be valid or not. If the error between the predicted animal blood flow from animal trained autoencoder model 144 and the directly measured Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 animal blood flow is below a preset threshold value, the training of autoencoder model 144 is determined to be valid. If the autoencoder model 144 training is determined to be valid, process 164 continues to step 174. If the error between the predicted animal blood flow from animal trained autoencoder model 144 and the directly measured animal blood flow is above the preset threshold value, the training of autoencoder model 144 is determined to be invalid. If autoencoder model 144 training is determined to be invalid, process 164 returns to step 166 and begins training autoencoder model 144 again. The MSE or MAE metrics are calculated iteratively during training to adjust the model parameters until convergence (e.g., the MAE or MSE in the minimum). In step 174, a human RVP waveform is input into animal trained autoencoder model 144 to generate a human raw blood flow. A known RVP waveform of a human is input into validated animal trained autoencoder model 144, and a human raw blood flow waveform is output from autoencoder model 144. As such, step 174 is used to generate the shape of the human raw blood flow waveform. Because animal training of autoencoder model 144 was validated, the shape of the human raw blood flow waveform should be consistent with human blood flow (e.g., the human raw blood flow waveform is greater than zero when the RVP waveform indicates that valves are open and is close to zero when the RVP waveform indicates that valves are closed). In step 176, the human raw blood flow waveform is scaled using an intermittent cardiac output to generate a human scaled blood flow. Because the shape of the human raw blood flow waveform is accurate, the human raw blood flow waveform is scaled at step 176 such that the average of the integral of the raw blood flow waveform over each beat is the same as the intermittent cardiac output measured by catheter 54. As such, the amplitude of the human raw blood flow waveform is adjusted. Thus, an accurate estimated raw blood flow waveform is generated, which is the human scaled blood flow waveform. In step 178, autoencoder model 144 is retrained using the human scaled blood flow. Autoencoder model 144 is retrained using the human RVP waveform as the input and the human scaled blood flow waveform as the output to get a human trained autoencoder model 144. Once autoencoder model 144 is retrained using the human scaled blood flow waveform, autoencoder model 144 can be used to generate a human raw blood flow waveform from a human RVP waveform that is not known beforehand. Animal data makes training autoencoder model 144 possible. As a result of training autoencoder model 144 using animal data, autoencoder model 144 can go from the Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 RVP waveform to the raw blood flow waveform, which cannot be measured in humans. The availability of blood flow measurements allows for further analysis of a patient’s condition and improved patient care. SVVAE Module (FIGS.17-18) FIG.17 is a schematic block diagram illustrating SVVAE module 40, which converts the processed flow waveform into SVVAE. FIG.18 is a schematic block diagram illustrating estimation of stroke volume (SV) from the processed flow waveform via SVVAE module 40. FIGS.17-18 will be discussed together. As shown in FIG.17, SVVAEmodule 40 has an input of the processed flow waveform and an output of SVAE and SVVAE. The processed flow waveform is input into SVVAEmodule 40 from flow module 38, which generates the raw flow waveform via autoencoder model 144, filters the raw flow waveform into the processed flow waveform via flow filter 146, and determines that the processed flow waveform is valid via decision block 148, prior to sending the processed flow waveform on to SVVAE module 40. Flow module 38 also sends an instruction indicating whether the processed flow waveform is valid or not valid to SVVAE module 40 so that SVVAE module 40 can proceed (in response to an indication that the processed flow waveform is valid) or not proceed (in response to an indication that the processed flow waveform is not valid). SVVAE module 40 uses the processed flow waveform to derive SVVAEfor patient 16. As shown in FIG. 18, SVVAE module 40 initially determines SV for each beat included in a ten-second (or other duration) window of the processed flow waveform. For example, the example ten-second window of the processed flow waveform shown in FIG. 18 includes fifteen beats, where each beat is represented by the portion of the processed flow waveform extending from an open circle along the bottom of the waveform to the nearest closed (or solid) circle and typically encompassing a peak marked by a shaded circle. The graph in FIG. 18 shows values of SV in units of milliliters (mL) that can correspond to each beat (in this example, there are fifteen) represented in the ten-second window of the processed flow waveform. SV is determined for each beat by determining the average (mean) of flow for each beat. That is, SVVAE module 40 uses the mean flow value calculated from a respective open circle along the bottom of the processed flow waveform to the nearest closed circle. This gives a beat-to-beat SV. In some examples, SVVAEmodule 40 can output the beat-to-beat SV (labeled “SVAE” in FIG. 17) in any suitable form to SVVLR module 42 (shown in FIG. 6). For example, SVAE can be an averaged SV for the ten-second sample. Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 The beat-to-beat SV can be an intermediate computation for SVVAEmodule 40. Once SV is determined for each beat, SVVAEmodule 40 is configured to convert SV into SVV for the ten-second window. SVVAE module 40 calculates SVVAE according to the following general form:^^^^^ = (^^^^^ − ^^^^^)⁄ ^^^^^^ (Equation 1) second sample;^^^^^ is a minimum SV for the ten-second sample; and^^^^^^ is a mean SV for the ten-second sample.In the example graph shown in FIG. 18, the second SV data point is ^^^^^and the third SV data point is ^^^^^. Accordingly, SVVAE module 40 calculates SVVAE from the processed flow waveform. SVVAEis a single value that represents an estimate of SVV for a ten-second portion of the processed flow waveform. SVVAE module 40 can calculate SVVAEevery ten seconds to yield a continuous output of SVVAE. In some examples, samples of the processed flow waveform can be input into SVVAE module 40 more frequently than every ten seconds on a rolling basis, where samples are ten-second samples of the processed flow waveform but may be input into SVVAE module 40 every two seconds. By utilizing a ten-second sample of the processed flow waveform, the sample size is large enough that the SVVAE output is stable and accurate but small enough that the samples represent a continuous output of SVVAE. Having a robust continuous output of SVVAEthat is not delayed is important for frequently updating SVVAEto catch any changes in SVV for patient 16, which improves patient care. SVVAEis an output of SVVAEmodule 40. SVVAEis an estimate of SVV for patient 16. In some examples, SVVAE module 40 can output SVVAE to SVVcomp module 44 and fluid responsiveness index module 45, as well as to output device 102 (shown in FIG. 6). For example, output device 102 can display a graph showing values of SVVAE over time for patient 16. In some examples, SVVAEmodule 40 continuously outputs SVVAE to output device 102 for monitoring the hemodynamic condition of patient 16. In some examples, SVVAEmodule 40 can also determine and output a fluid responsiveness status of patient 16 by comparing SVVAE to predefined SVV threshold or expected trend information. SVVAEis a more accurate estimate of SVV compared to traditional SVV surrogate estimates because it is derived from the processed flow waveform, which is in Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 turn derived from the RVP waveform by autoencoder model 144. SVVAEdoes not rely on surrogate parameters and is instead derived directly from an estimate of flow. Further, using RVP can provide a more accurate SVV estimate due to the larger impact respiration variation has on RVP compared to radial or femoral pressures, as this variation is the main factor impacting SVV. SVVAE module 40 allows for determining a continuous (i.e., constantly or nearly constantly available) SVV. SVVAEis a continuous SVV estimate because it can be updated as quickly as every ten seconds or even more frequently on a rolling basis, such as every two seconds. A continuous SVV estimate, such as SVVLR, can capture fleeting or rapid changes in SVV for patient 16, which improves patient care. Additionally, SVVAEmodule 40 can generally be described as “data agnostic” with respect to absolute pressure values (e.g., absolute values of RVP) because SVVAE can be based on relative RVP and morphology, or shape, of the RVP waveform and does not directly rely on absolute pressure values. This is important because, in practice, absolute pressure values may not always be accurate. For example, a healthcare worker might create some measurement error in the measurement of RVP when leveling a pressure transducer for a patient. As another example, raising or lowering a patient’s bed for surgery or in the ICU can also alter absolute pressure values. SVVAEmodule 40 is able to accurately estimate SVVAE in these situations because it does not directly rely on absolute pressure values. Accordingly, using SVVAEproduced by SVVAEmodule 40 is beneficial for patient care. SVVLR Module (FIGS.19-22) FIG. 19 is a schematic block diagram illustrating SVVLR module 42. FIG. 20 is a schematic block diagram illustrating reference and current features used as inputs to regression model 180 of SVVLR module 42. FIG.21 is a schematic diagram illustrating reference time window Wiat peak inspiration and current time window Wi+nat peak expiration. FIG. 22 is a schematic diagram illustrating multiple windows W1-W14 and multiple corresponding beats B1-B14. FIGS. 19-22 will be discussed together. RVP features and PAP features (including heart rate (labeled “HR” in FIGS. 19-20)), demographic information, and SvO2 are input into SVVLR module 42 to estimate a change in cardiac output and SVV therefrom based on features of the RVP waveform and the PAP waveform. FIGS.19-20 show SVVLR module 42, including regression model 180 and SVV estimator 182. FIG.21 shows reference time window Wi, current time window Wi+n, peak inspiration beat BPI, and peak expiration beat BPE. FIG. 22 shows windows W1-W14 and beats B1-B14. Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 Regression model 180 is a first sub-module of SVVLRmodule 42. Regression model 180 is configured to receive RVP features, PAP features, demographic information, and SvO2 as inputs. Regression model 180 outputs a linear regression estimate of change in cardiac output (“ΔCOLR”) over time for patient 16 (shown in FIG.1). More specifically, regression model 180 outputs ΔCOLR to SVV estimator 182. Regression model 180 is a traditional machine learning model that functions well when the available data is well-distributed rather than multi-modal. For example, patient change in cardiac output data tends to be a homogenous data set, so traditional machine learning techniques, such as regression model 180, can be used successfully to learn across the population. Regression model 180 is trained with a training data set where a change in cardiac output and corresponding changes in features of RVP and PAP waveforms are known for a patient. In examples where demographic information and / or SvO2 will be used, regression model 180 can be trained with a training data set that also includes demographic information and / or SvO2 data corresponding to known change in cardiac output information. Once regression model 180 has been trained, regression model 180 consumes RVP features derived from the RVP waveform by RVP features module 32 (or validation module 36), as shown in FIG.6. Regression model 180 can also consume PAP features derived from the PAP waveform by PAP features module 34, as shown in FIG.6. The RVP features and the PAP features are aggregated over a defined time window (or interval). For example, the RVP features and the PAP features can be aggregated over a time window of ten seconds, which includes multiple heartbeats. In other examples, the RVP features and the PAP features can be aggregated over longer or shorter time windows. RVP features module 32 and PAP features module 34 (shown in FIGS.1 and 6) can extract features for each beat in the time window and then compute an average for each feature for the entire time window. The averaged features for the entire time window can be the form of the RVP features and the PAP features that are consumed by regression model 180. In some examples, regression model 180 only consumes averaged RVP features and PAP features obtained from good (i.e., valid or not discarded) beats in the time window, as determined by validation module 36 (shown in FIG.9). Regression model 180 can use a combined group of RVP features and PAP features. In one example, regression model 180 can use all RVP features derived from the RVP waveform by RVP features module 32 and all PAP features derived from the PAP waveform by PAP features module 34. In other examples, regression model 180 can use Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 only some of the derived RVP features and PAP features. In yet other examples, regression model 180 uses only RVP features and not PAP features. Generally, regression model 180 can use any number or combination of individual RVP features and PAP features. Example RVP features used by regression model 180 include the following: pulse rate (i.e., a pressure-based calculation of heart rate, although, in other examples, heart rate referred from an electrocardiogram or other means could also be used), maximum dP / dt, minimum dP / dt, systole time, systolic pressure, end systolic pressure, end diastolic pressure, pulse pressure, and mean pressure. Example PAP features used by regression model 180 also include the following: pulse rate, maximum dP / dt, minimum dP / dt, systole time, systolic pressure, end systolic pressure, end diastolic pressure, pulse pressure, and mean pressure. Other RVP features and / or PAP features not specifically listed here, such as other pressure- or time-based parameters, can also be used by regression model 180. Features such as pulse rate and systole time are expected to have similar values when derived from either the RVP waveform or the PAP waveform, due to physiology. Thus, in some examples, regression model 180 can use only one source—either the RVP features derived from the RVP waveform or the PAP features derived from the PAP waveform, but not both—for features that are expected to be physiologically similar between the RVP features and the PAP features, and regression model 180 can use both the RVP features and the PAP features for other features that are expected to be physiologically different, such as maximum and minimum dP / dt. In some examples, regression model 180 can also consume demographic information about patient 16. Such demographic information can include age, weight, height, sex (or gender), body mass index (BMI), medical condition(s), etc. Regression model 180 can receive demographic information about patient 16 either from system memory 22 (shown in FIG.1) where it is stored (e.g., in a patient information database) or when entered by healthcare worker 18 at user interface 46 (shown in FIG.1), for example. In some examples, regression model 180 can also consume SvO2 data received via hemodynamic sensor 14B (shown in FIG. 1 and FIG. 5). Overall, several variations of regression model 180 using different combinations of the RVP features, the PAP features, demographic information, and / or SvO2 of patient 16 (i.e., more or less complex variations of regression model 180) are possible without altering the quality of regression model 180. As shown in FIG. 20, regression model 180 uses reference RVP features (“RVPfeat_ref”) that correspond to reference time window Wi and current RVP features (“RVPfeat_current”) that correspond to current time window Wi+n(where “n” represents an Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 arbitrary integer value). RVPfeat_refmake up a first set of individual RVP features and RVPfeat_currentmake up a second set of individual RVP features. Similarly, regression model 180 uses reference PAP features (“PAPfeat_ref”) that correspond to reference time window Wiand current PAP features (“PAPfeat_current”) that correspond to current time window Wi+n. PAPfeat_ref make up a first set of individual PAP features and PAPfeat_current make up a second set of individual PAP features. Reference time window Wi is an initial time interval from which ΔCOLR will be calculated by regression model 180. Reference time window Wiis compared to relatively later time windows (e.g., current time window Wi+n) to calculate ΔCOLR. For example, reference time window Wican be a time interval corresponding to a heartbeat at peak inspiration of the respiratory cycle, as will be described in greater detail below with reference to FIG.21. In other examples, reference time window Wi can be a time interval corresponding to patient 16 first being admitted to an ICU, OR, or other patient care environment. In yet other examples, reference time window Wi can be a time interval corresponding to a first known cardiac output measurement, such as a measurement of intermittent cardiac output, for patient 16. In still other examples, reference time window Wican be any suitable time interval over which the RVP waveform and / or the PAP waveform was obtained. SVVLRmodule 42 can be configured such that reference time window Wican be updated to a new time interval. For example, reference time window Wi can be updated periodically. In some examples, reference time window Wican be updated upon passage of a set amount of time after which RVPfeat_ref and PAPfeat_ref are considered too old. In some examples, reference time window Wican be continuously updated at each time interval for which the RVP waveform and / or the PAP waveform are measured. That is, reference time window Wicould also be designated reference time window W(i+n)-1in such examples because it would be the time interval immediately preceding current time window Wi+n. In other examples, reference time window Wi can be updated at any time, either manually by healthcare worker 18 via user interface 46 or automatically according to instructions in fluid responsiveness software code 30. In yet other examples, reference time window Wiis not updated. As shown in FIG. 20, reference time window Wi is a ten-second (10s) interval and represents a ten-second portion of the RVP waveform. In other examples, e.g., as described in greater detail below with reference to FIGS.21-22, reference time window Wican be a one- to two-second (1-2s) interval corresponding to an individual beat portion Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 of the RVP waveform. In some examples, the length (in units of time) of reference time window Wican be determined based on minimum requirements for proper functioning of SVVAE module 40 or other modules represented in fluid responsiveness software code 30. As such, other lengths of time are possible for reference time window Wi, such as longer or shorter than ten-second intervals. Additionally, the length of current time window Wi+n will be the same as the length of reference time window Wiso that reference time window Wi and current time window Wi+n can be directly compared. Accordingly, current time window Wi+ncan also be a ten-second interval and represent a different ten-second portion of the RVP waveform or can also be a one- to two-second interval corresponding to a later individual beat portion of the RVP waveform. Current time window Wi+n is a current time interval to which ΔCOLR will be calculated by regression model 180. Current time window Wi+n can be any time interval after reference time window Wi. For example, current time window Wi+n can be a time interval corresponding to a heartbeat at peak expiration of the respiratory cycle, as will be described in greater detail below with reference to FIG.21. Current time window Wi+n can correspond to real-time or nearly real-time measurements from patient 16 and, thus, allow regression model 180 to produce a real-time or nearly real-time estimate of change in cardiac output for patient 16. Each individual one of RVPfeat_refand PAPfeat_refcorresponds, respectively, to an individual one of RVPfeat_current or PAPfeat_current. That is, RVPfeat_ref and PAPfeat_ref include the same individual features as RVPfeat_currentand PAPfeat_current, respectively, measured from the corresponding time windows. For example, one of the RVP features used by regression model 180 can be end diastolic pressure 108 derived from the RVP waveform, as shown in FIG. 7. In such an example, regression model 180 uses an end diastolic pressure measurement derived from the RVP waveform during reference time window Wi (i.e., end diastolic pressurew_i) and an end diastolic pressure measurement derived from the RVP waveform during current time window Wi+n (i.e., end diastolic pressurew_i+n). In the same example, end diastolic pressurew_iis one of RVPfeat_refand end diastolic pressurew_i+n is one of RVPfeat_current. Regression model 180 is a linear model configured to include variables based on the RVP features, the PAP features, demographic information, and / or SvO2 for patient 16 multiplied by coefficients to estimate ΔCOLR. More specifically, regression model 180 uses a change between individual features of RVPfeat_ref and PAPfeat_ref for reference time window Wiand corresponding individual features of RVPfeat_currentand Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 PAPfeat_currentfor current time window Wi+nto determine ΔCOLRfrom reference time window Wito current time window Wi+n. The variables used in regression model 180 can take several different forms. The variables used in regression model 180 can include measured or received values of one or more of RVPfeat_ref, PAPfeat_ref, RVPfeat_current, PAPfeat_current, demographic information, and / or SvO2. The variables used in regression model 180 can also include differential variables that represent a difference between one of RVPfeat_current or PAPfeat_current and a corresponding one of RVPfeat_refor PAPfeat_ref. The differential variables can also be represented as a ratio of the difference between a current feature and a reference feature over the reference feature to result in a normalized variable. For example, one differential variable in regression model 180 could be expressed as:(^^^^^^^^^^_^^^ − ^^^^^^^^^^_^) / ^^^^^^^^^^_^.The example differential variable shown above includes the difference between a measured value of heart rate for current time window Wi+nand for reference time window Wi over the measured value of heart rate for reference time window Wi. Similar differential variables can be generated for any pair of one of RVPfeat_current or PAPfeat_current and the corresponding one of RVPfeat_ref or PAPfeat_ref. The variables used in regression model 180 can further include combinatorial variables that represent a combination of one or more measured or received values of RVPfeat_ref, PAPfeat_ref, RVPfeat_current, PAPfeat_current, demographic information, and SvO2, and / or one or more differential variables. For example, one combinatorial variable in regression model 180 could be expressed as: ^(^^^^^^ ^^^^ ^!_"#$% ^^^^^^ ^^^^ ^!_")^^^^^^ ^^^^ & × (^^^^^^^^^^_^^^ × ^)*^+,^-. / ^^_^^^0. variable that uses a reference and current pulse pressure, a measured value of heart rate for current time window Wi+n, and a measured value of systole time for current time window Wi+n. Similar combinatorial variables can be generated for any combination of one or more measured or received values of RVPfeat_ref, PAPfeat_ref, RVPfeat_current, PAPfeat_current, demographic information, and SvO2, and / or one or more differential variables. Terms in regression model 180 include, or are formed of, the variables as described above multiplied by predetermined coefficients. For example, the coefficients can be determined during the training process for regression model 180. Regression model 180 can include any number of terms from 1 to n. Regression model 180 calculates ΔCOLR as the sum of all the terms. The general form of regression model 180 is as follows: Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 12345 = (^6 × 7^,_8^^^6) + (^: × 7^,_8^^^:) + (^; × 7^,_8^^^;) + ⋯ + (^^ ×7^,_8^^^^)(Equation 2) Where, =(^^=>?^@A^^B^ ^^^^ ^!_"#$% ^^=>?^@A^^B^ ^^^^ ^!_") on ones of the RVP features. In other examples, the variables in Equation 2 can be based on ones of the PAP features or can be based on a combination of the RVP features, the PAP features, and / or demographic information. ΔCOLR, as expressed in Equation 2 above, is a value representing percent change in cardiac output from an initial cardiac output corresponding to reference time window Wi to current time window Wi+n. ΔCOLR represents a percent change rather than a Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 magnitude of the change because variables del_feat1through del_feat11are normalized variables. Alternatively, regression model 180 can be configured to compute ΔCOLR as a magnitude of the change by including variables that are not normalized to RVPfeat_refor PAPfeat_ref. For example, one non-normalized differential variable in regression model180 could be expressed as:(MN7^)*^+,.OP^^**Q^^^_^^^ − MN7^)*^+,.OP^^**Q^^^_^),and one non-normalized combinatorial variable in regression model 180 could be expressedas:(^^^^^^^^^^_^^^ − ^^^^^^^^^^_^0 × (^^^^^^^^^^_^^^ × ^)*^+,^-. / ^^_^^^0.that are a non- one such combination could be expressed as:^(C^^ @5^@^!_"#$% C^^ @5^@^!_")C^^ @5^@^!_" & × (MN7^)*^+,.OP^^**Q^^^_^^^ −indicates how much cardiac output has changed between reference time window Wi and current time window Wi+nfor patient 16. ΔCOLRis output from regression model 180 to SVV estimator 182 in SVVLR module 42. SVV estimator 182 is a second sub-module of SVVLRmodule 42. SVV estimator 182 receives ΔCOLRas an input from regression model 180. As described above, ΔCOLR represents a change in cardiac output from reference time window Wi to current time window Wi+n. SVV estimator 182 also receives a heart rate, which is one of the RVP features from RVP features module 32 or one of the PAP features from PAP features module 34 (or from validation module 36), and SVAEfrom SVVAEmodule 40. Additionally or alternatively, SVV estimator 182 can receive an intermittent cardiac output value and calculate a value of SV therefrom. SVV estimator 182 outputs SVVLR, which is an estimate of SVV for patient 16. FIG.21 illustrates a variation of using reference time window Wiand current time window Wi+n to calculate ΔCOLR for a use case where peak inspiration and peak expiration (of the respiratory cycle) are known. In the example shown in FIG.21, SVVLR module 42 uses regression model 180 to calculate ΔCOLR from reference time window Wi to current time window Wi+n where each of reference time window Wi and current time Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 window Wi+nare time intervals corresponding to an individual beat (or approximately an individual beat). Accordingly, RVPfeat_refand RVPfeat_current(and / or PAPfeat_refand PAPfeat_current) are features for the corresponding individual beat. More specifically, reference time window Wicorresponds to peak inspiration beat BPI, and current time window Wi+n corresponds to peak expiration beat BPE. Both peak inspiration beat BPI and peak expiration beat BPEcan be captured within an approximately ten-second sample (or other sample size corresponding to a full respiratory cycle) of the RVP waveform. Calculating ΔCOLRfrom peak inspiration beat BPIto peak expiration beat BPEcaptures the maximum difference in stroke volume across a respiratory cycle for patient 16, which occurs between peak inspiration and expiration of the respiratory cycle. The maximum difference in stroke volume across a respiratory cycle is used to calculate SVVLR, as shown in Equations 3-4 below. FIG.22 illustrates a variation of using reference time window Wi and current time window Wi+n to calculate ΔCOLR for an alternative use case where peak inspiration and peak expiration are not known. In the example shown in FIG. 22, an RVP sample is divided into windows W1-W14, each corresponding to a respective beat B1-B14. Although FIG. 22 shows fourteen windows W1-W14and fourteen beats B1-B14, it should be understood that other examples can include any number of windows and corresponding beats, such as more or fewer than fourteen windows and beats, depending on the length of the RVP sample used. In some examples, the RVP sample can be at least ten seconds. Each of windows W1-W14is a time interval corresponding to an individual beat (or approximately an individual beat). As shown in FIG.22, window W1 corresponds to beat B1, window W2corresponds to beat B2, window W3corresponds to beat B3, etc. From windows W1-W14, one window can be selected as reference time window Wi, and a relatively later window (with respect to the selected reference) can be selected as current time window Wi+n. Accordingly, RVPfeat_ref and RVPfeat_current (and / or PAPfeat_ref and PAPfeat_current) are features for the corresponding individual beat. SVVLRmodule 42 can use all possible combinations of windows W1-W14, where each possible combination includes one window selected as reference time window Wiand a relatively later window selected as current time window Wi+n. For example, when window W3 is selected as reference time window Wi, each of windows W4-W14 (the windows after window W3) can be selected as current time window Wi+n. Likewise, when window W4 is selected as reference time window Wi, each of windows W5-W14 can be selected as current time window Wi+n, and so on, to make each possible combination of Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 reference and current time windows for the RVP sample. In some examples, SVVLRmodule 42 can be configured to only use valid beats from the RVP sample, e.g., as determined by validation module 36 (shown in FIG. 6). SVVLR module 42 can use regression model 180 to calculate ΔCOLRfrom reference time window Wito current time window Wi+n for each possible combination. SVVLR module 42 can further determine the combination that gives the maximum ΔCOLR, which also gives the maximum difference in stroke volume across a respiratory cycle for patient 16. As described previously with reference to FIG. 21, the maximum difference in stroke volume across a respiratory cycle is used to calculate SVVLR (Equations 3-4). For example, assuming the RVP sample is the same in FIG. 22 as FIG. 21, the combination of W4selected as reference time window Wiand W11 selected as current time window Wi+n would produce the maximum ΔCOLR for all the possible combinations. This should represent the difference between peak inspiration and peak expiration without otherwise requiring information about peak inspiration and expiration or the respiratory cycle. Taking FIGS. 21-22 together, SVVLR module 42 can capture the maximum difference in stroke volume between beats for configurations where peak inspiration and expiration are known as well as for configurations where peak inspiration and expiration are not known. SVV estimator 182 calculates SVVLR from ΔCOLR using heart rate according to the following relationship between cardiac output and stroke volume: ∆^^45 = ∆STUVC5 (Equation 3) ∆^^45is the maximum change in stroke volume across a respiratory cycle;∆2345is the change in cardiac output from regression model 180 (e.g., as determined frompeak inspiration to peak expiration according to FIG. 21 or FIG. 22); and^^ is a heart rate (e.g., an average heart rate) that corresponds to the calculated ∆2345.∆^^45 can be converted to SVVLR according to:^^^45 = ∆>WUV>WXYZ ; (Equation 4) ^^ ^[ is a value of SVAE (an intermediate parameter determined by SVVAE module 40, asshown in FIG.19), or a value of SV calculated from an intermittent cardiac output, that corresponds to reference time window Wi(i.e., a reference stroke volume). Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 SVVLRis the output of SVV estimator 182. SVVLRis an estimate of SVV for patient 16 that corresponds to current time window Wi+n. In some examples, SVVLRmodule 42 can output SVVLR from SVV estimator 182 to output device 102, as shown in FIG.6. For example, output device 102 can display a graph showing values of SVVLRover time for patient 16. In some examples, SVVLR module 42 continuously outputs SVVLR to output device 102 for monitoring the hemodynamic condition of patient 16. In some examples, SVVLR can be passed from SVV estimator 182 to SVVcomp module 44 and fluid responsiveness index module 45, as will be described in greater detail below. In some examples, SVVLR module 42 can also determine and output a fluid responsiveness status of patient 16 by comparing SVVLRto predefined SVV threshold or expected trend information. SVVLR module 42 estimates SVV from features of the RVP waveform (and optionally features of the PAP waveform) using regression model 180, which is a different method of estimating an SVV for patient 16 compared to the method described above using autoencoder model 144, as shown in FIGS.12-17. This adds a level of redundancy within hemodynamic monitoring system 10 for estimating SVV. SVVLR module 42 allows for a second calculation of SVV (SVVLR), which can be used in addition to SVVAEto result in a more accurate SVV estimate, as will be described in greater detail below with reference to SVVcompmodule 44 in FIGS. 21-23C. Like with SVVAEmodule 40 described above, another advantage here is that SVVLR module 42 allows for determining a continuous SVV. SVVLRis a continuous SVV estimate because it can be updated as quickly as every ten seconds or even more frequently on a rolling basis, such as every two seconds. A continuous SVV estimate, such as SVVLR, can capture fleeting or rapid changes in SVV for patient 16, which improves patient care. Additionally, like SVVAEmodule 40 described above, SVVLRmodule 42 can be described as “data agnostic” with respect to absolute pressure values (e.g., absolute values of RVP) because both time-based (e.g., heart rate, systole time, etc.) variables and normalized pressure-based (e.g., systolic pressure, pulse pressure, etc.) variables used in SVVLR module 42 are unaffected by errors or bias in absolute pressure values. This is important because, in practice, absolute pressure values may not always be accurate. For example, a healthcare worker might create some measurement error in the measurement of RVP when leveling a pressure transducer for a patient. As another example, raising or lowering a patient’s bed for surgery or in the ICU can also alter absolute pressure values. SVVLRmodule 42 is able to accurately estimate SVVLRin these situations because it can Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 be configured such that it does not directly rely on absolute pressure values. Accordingly, using SVVLRproduced by SVVLRmodule 42 is beneficial for patient care. SVVcomp Module (FIGS.23-25C) FIG.23 is a schematic block diagram illustrating SVVcompmodule 44. FIG. 24 is a schematic block diagram illustrating filter sub-module 184 of SVVcomp module 44. FIGS. 23-24 will be discussed together. As illustrated in FIG. 23, SVVcompmodule 44 includes filter sub-module 184. SVVAE, SVVLR, and, optionally, SVVadd are input into SVVcompmodule 44 to estimate SVVcomp. SVVcompmodule 44 outputs SVVcomp. As illustrated in FIG.24, SVVcomp module 44 includes filter sub-module 184, which includes prediction block 186 and update block 188. SVVAE, SVVLR, and SVVadd(if available) are input into filter sub-module 184 to estimate a filtered SVV (“SVVfiltered”), which is one example of SVVcomp. More specifically, SVVAE, SVVLR, and SVVadd are input into update block 188 of filter sub-module 184. SVVfiltered is output from filter sub-module 184. Generally, SVVcomp module 44 combines multiple estimates of SVV to generate a composite estimate, which is output from SVVcomp module 44 as SVVcomp. SVVcomp can take several different forms. That is, SVVcomp module 44 can be configured to generate SVVcompin several different ways, one of which will be described in greater detail below with reference to FIG. 24. In another example, SVVcomp module 44 can be configured to calculate SVVcompas the average (mean) of available SVV estimates, such as SVVAE, SVVLR, and SVVadd. In some examples, this can be a weighted average based on designated or predetermined weights for SVVAE, SVVLR, and SVVadd. Further details and examples of weighting inputs will be described below with reference to FIG. 25B but are also applicable here. In one, non-limiting example, designated or predetermined weights associated with SVVAE and SVVLR can be based on the relative accuracy (or uncertainty) associated with the two models (i.e., autoencoder model 144, as shown in FIG. 12, and regression model 180, as shown in FIGS. 19-22). In other examples, weights associated with SVVAE and SVVLR may change over time depending on the relative signal quality index (or indices) associated with such methods. In yet another example, SVVcomp module 44 can also compare SVVAE to SVVLRor SVVadd. That is, SVVcompmodule 44 can use SVVLRor SVVaddto validate SVVAE. SVVcomp module 44 can determine SVVAE is valid and output SVVAE as SVVcomp (or, in some examples, apply some adjustment to SVVAEto get SVVcomp) when SVVAEis within a designated or predetermined range of SVVLR or SVVadd. In one example, SVVcomp module 44 can output SVVAEas SVVcompwhen SVVAEis within 10-15% of SVVLRor Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 SVVadd. In such examples, SVVcompmodule 44 can determine that SVVAEis not usable (or not valid) when SVVAEis not within a designated or predetermined range (e.g., 10-15%) of SVVLR or SVVadd. In this way, SVVcomp module 44 can be configured as a quality check on autoencoder model 144, as shown in FIG.12, using regression model 180, as shown in FIGS.19-22. These methods of generating SVVcomp and the method described below with reference to FIG. 24 can be used separately or in any desired combinations to produce a robust estimate of SVV. Referring now to FIG.24, filter sub-module 184 represents a Kalman filter algorithm of SVVcomp module 44. Filter sub-module 184 includes instructions in code for implementing a Kalman filter algorithm to combine (or filter) one or more estimates of SVV into a single, more robust, filtered estimate of SVV. In general, a Kalman filter algorithm predicts the current state of an input variable and then can update that prediction with additional information, such as from measured inputs, to output a filtered estimate. Filter sub-module 184 is configured to predict the current state of SVV for patient 16. Additionally, filter sub-module 184 consumes measured inputs over time. As shown in FIG. 24, measured inputs that can be consumed by filter sub-module 184 include SVVAEand SVVLR, which are estimates of SVV estimated by fluid responsiveness software code 30, and SVVadd, which is any other available estimate of SVV, such as an SVV estimated from pulse pressure variation derived from a femoral or radial pressure measurement. In other examples, SVVadd can be an SVV estimate from another model. In yet other examples, SVVaddis unavailable and / or not used. Each of the measured inputs can include statistical noise and other inaccuracies, which can be represented in the Kalman filter algorithm of filter sub-module 184 as a corresponding uncertainty. Filter sub-module 184 outputs SVVfiltered, which is one example of SVVcomp. The Kalman filter algorithm of filter sub-module 184 can be conceptualized as two distinct phases or steps, including a prediction phase and an update phase. Prediction block 186 represents the prediction phase of filter sub-module 184. The prediction phase of filter sub-module 184 will also be described in greater detail below with reference to FIG. 25A. Update block 188 represents the update phase of filter sub-module 184. As shown in FIG. 24, the measured inputs, including SVVAE, SVVLR, and SVVadd, are input into update block 188. The update phase of filter sub-module 184 will also be described in greater detail below with reference to FIG.25B. At prediction block 186 (i.e., in the prediction phase), filter sub-module 184 predicts SVV for the current time step based on past filtered estimates of SVV from the Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 Kalman filter algorithm (e.g., past values of SVVfiltered, as will be described in greater detail below) using extrapolation (or another prediction model, as will be described below), along with a corresponding prediction uncertainty, resulting in a predicted estimate of SVV. The predicted estimate of SVV generally does not directly include information from current measured inputs. However, the prediction phase of the Kalman filter algorithm of filter sub-module 184 can be initialized with one of the measured inputs for the first iteration of the algorithm. For example, the prediction phase can be initialized with SVVAE, SVVLR, or SVVadd. After initialization, the prediction phase will run using previous filtered estimates, as will be described in greater detail below. The Kalman filter algorithm can also be re-initialized based on predefined rules and triggers, e.g., time elapsed since the last initialization, time elapsed between the last two successive measurements, etc. At update block 188 (i.e., in the update phase), filter sub-module 184 receives and consumes one or more of the measured inputs (e.g., one or more of SVVAE, SVVLR, and SVVadd) and its corresponding measurement (or estimate) uncertainty for the current time step. Once filter sub-module 184 receives a measured input, the predicted estimate of SVV is updated using a weighted average of the prediction and the measurement. More weight is given to estimates with greater certainty and lower uncertainty. The weighted average results in a filtered estimate of SVV that lies between the predicted estimate of SVV and the measured inputs and has a better estimated uncertainty than either alone. This process is repeated at every time step (i.e., every iteration of the Kalman filter algorithm of filter sub-module 184), with the filtered estimate of SVV and its uncertainty from the previous time step informing the prediction phase in the following iteration (i.e., the current time step). Typically, the prediction phase and the update phase alternate, with the predicted estimate of SVV advancing the state at each time step until the next measured input is received and the update phase subsequently incorporating the measured inputs. That is, the Kalman filter algorithm of filter sub-module 184 is configured such that each iteration of the Kalman filter algorithm can include the prediction phase and the update phase. However, if a measured input is unavailable at a particular time step, the corresponding update phase can be skipped, and multiple prediction phases can be carried out in a row. Likewise, if multiple measured inputs are received for the same time step (e.g., SVV estimates from multiple sources, such as more than one of SVVAE, SVVLR, and SVVadd), then multiple update phases can be carried out in a row to further refine the filtered estimate of SVV. Filter sub-module 184 can include an update phase for any one source Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 or any combination of sources of measured inputs. In other words, filter sub-module 184 is configured such that the total number of update phases (which, in some cases, may be zero) per iteration of the Kalman filter algorithm depends on which of the measured inputs are available during that iteration. As will be described in greater detail below with reference to FIG. 25C, filter sub-module 184 produces a filtered estimate of SVV that is generally more accurate than any single one of the measured inputs. The Kalman filter algorithm of filter sub-module 184 is recursive. That is, filter sub-module 184 uses only the filtered estimate of SVV from the previous time step, uncertainty associated with that previous filtered estimate of SVV, and the current measured input to compute the filtered estimate of SVV for the current time step—no other past information is needed. For each time step, the previous filtered estimate of SVV is fed back into prediction block 186 to inform the upcoming prediction of filter sub-module 184. In this way, information about previous measured inputs and their respective uncertainties is still carried into the next prediction because the previous filtered estimate of SVV will have been refined based on the measured inputs from that time step. The final filtered estimate of SVV produced by filter sub-module 184 at each time step is a value of SVVfiltered. SVVfilteredis a filtered representation of SVV for patient 16 (shown in FIG. 1) and is one example of SVVcomp. SVVfiltered is the output of filter sub-module 184 and, therefore, is one possible output of SVVcompmodule 44. In some examples, SVVcomp module 44 can output SVVcomp—estimated in any of the ways described above in this section—to fluid responsiveness index module 45 (shown in FIG. 6). In some examples, SVVcomp module 44 can output SVVcomp to output device 102 (shown in FIG. 6). For example, output device 102 could display a graph showing values of SVVcomp over time for patient 16. In some examples, SVVcomp module 44 continuously outputs SVVcompto output device 102 for monitoring the hemodynamic condition of patient 16. In some examples, SVVcomp module 44 can also determine and output a fluid responsiveness status of patient 16 by comparing SVVcomp to predefined SVV threshold or expected trend information. The Kalman filter algorithm of filter sub-module 184 is a powerful estimator when there are multiple noisy estimates and / or measurements for a variable, such as SVV. Due to the nature of the Kalman filter algorithm, including the prediction phase and the update phase, filter sub-module 184 can effectively handle uncertainty due to noisy measured inputs and produce a more accurate SVVfiltered. Moreover, filter sub-module 184 Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 can operate on SVV estimates received from different sources to merge these into the more accurate SVVfiltered. Filter sub-module 184 can also tolerate receiving asynchronous or sporadic SVV estimates from the different sources. That is, filter sub-module 184 does not require measured inputs from all the possible sources at each time step and can even tolerate not receiving any measured input at all for a particular time step. For example, filter sub- module 184 could be receiving measured inputs from both SVVAE module 40 and SVVLR module 42, and then at some time step, flow module 38 could determine that autoencoder model 144 (as shown in FIG.12) is no longer producing good values, so SVVAE would not be computed for that time step and not fed to filter sub-module 184. In such an example, the Kalman filter algorithm of filter sub-module 184 would automatically adapt to this change and could continue generating SVVfiltered using only the measured input from SVVLR module 42. The Kalman filter algorithm could also automatically re-adapt to using both measured inputs from SVVAE module 40 and SVVLR module 42 at a future time. Likewise, when SVVadd is available (e.g., from a femoral or radial pressure measurement) or if other additional sources of SVV estimates are added to hemodynamic monitoring system 10, these can be readily integrated into the Kalman filter algorithm as additional update phases. Using a Kalman filter algorithm in filter sub-module 184 is very computationally efficient because the Kalman filter algorithm is recursive. Likewise, the recursive nature of the Kalman filter algorithm means it does not merge information in isolation. Instead, the Kalman filter algorithm allows filter sub-module 184 to intelligently combine information using the context of what the filtered estimate of SVV was at the previous time step. In this way, SVVfiltered can be a more accurate estimate of SVV for patient 16. More generally, SVVcomp estimated in any of the ways described above in this section is a more robust estimate of SVV for patient 16 because SVVcomp module 44 is configured to combine multiple sources and types of patient hemodynamic information into a single, composite estimate of SVV. Additionally, like SVVAE module 40 and SVVLR module 42 described above, SVVcompmodule 44 can be described as “data agnostic” with respect to absolute pressure values (e.g., absolute values of RVP) because SVVcomp that is based on SVVAEcan therefore also be based on relative RVP and morphology, or shape, of the RVP waveform, and SVVcomp that is based on SVVLR can likewise be unaffected by absolute pressure values. This is important because, in practice, absolute pressure values Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 may not always be accurate. For example, a healthcare worker might create some measurement error in the measurement of RVP when leveling a pressure transducer for a patient and, as another example, raising or lowering a patient’s bed for surgery or in the ICU can also alter absolute pressure values. SVVcompmodule 44 is able to accurately generate SVVcomp in these situations because it can be configured such that it does not directly rely on absolute pressure values. Accordingly, using SVVcompproduced by SVVcomp module 44 is beneficial for patient care. FIG. 25A is a graph illustrating predicted value p of filter sub-module 184 over time. FIG.25B is a graph illustrating measured value m of filter sub-module 184 over time. FIG.25C is a graph illustrating filtered value f from filter sub-module 184 over time. FIGS. 25A-25C will be discussed together. Taken together, FIGS. 25A-25C are graphs corresponding to the functioning of filter sub-module 184 (shown in FIG. 24) over time, and each of the graphs in FIGS.25A-25C show SVV values over time. Each of the graphs in FIGS. 25A-25C shows the same arbitrary time steps n, n-1, n-2, n-3, and n-4 along the x-axis. Each of time steps n, n-1, n-2, n-3, and n-4 corresponds to a respective iteration of the Kalman filter algorithm of filter sub-module 184. That is, time step n represents the current iteration of filter sub-module 184. Time steps n-1, n-2, n-3, and n-4 represent time steps preceding time step n. For example, time step n-1 is the time step representing the iteration immediately before time step n, time step n-2 is the time step representing the iteration immediately before time step n-1 (and two before time step n), etc. As will be described in greater detail below, each of the graphs in FIGS. 25A-25C also shows SVV values corresponding to the time steps n, n-1, n-2, n-3, and n-4. The SVV values graphed in FIGS. 25A-25C are shown as percentages with no units but, in other examples, could be represented with other units. FIG.25A is a graph that corresponds to the functioning of prediction block 186, as shown in FIG. 24. In FIG. 25A, an SVV value is shown for each of time steps n, n-1, n-2, n-3, and n-4. Predicted value p is the SVV value corresponding to current time step n. Predicted value p is an example value of a predicted estimate of SVV predicted at prediction block 186. The SVV values corresponding to time steps n-1, n-2, n-3, and n-4 can be previous values of SVVfilteredthat can be used in current time step n (or that were used in previous time steps) by prediction block 186 to produce predicted value p that corresponds to current time step n. If any of time steps n-1, n-2, n-3, and n-4 represent the first time step for which predicted value p was calculated, then the SVV values at the previous time steps with respect to that first time step can be measured input values used Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 for initialization instead. Predicted value p at current time step n is illustrated in FIG.25A as connected to the previous value with a dashed line because predicted value p is a predicted estimate of SVV used internally within filter sub-module 184. Unlike the other SVV values shown in FIG.25A for previous time steps, predicted value p is generally not the final filtered output of filter sub-module 184. As shown in FIG.25A, predicted value p has corresponding uncertainty ep. Uncertainty ep represents the uncertainty associated with predicted value p as an estimate of the standard deviation. The uncertainty in predicted value p can be configurable or predetermined for each application of filter sub-module 184 and can depend on the type of prediction that is used. The arrows extending from predicted value p are proportional to the amount of uncertainty in predicted value p. The prediction phase of the Kalman filter algorithm of filter sub-module 184 can be configured as one of several different prediction models to produce predicted value p. In one example, the prediction phase can use extrapolation to compute predicted value p. For example, the prediction phase can use linear extrapolation based on the SVV values for time steps n-1 and n-2 to determine the value of predicted value p at current time step n. Using linear extrapolation in the prediction phase means that the change in SVV (i.e., the slope) between the previous two time steps will be carried over as the same up to current time step n. That is, the slope between the SVV values at time steps n-2 and n-1 is taken to be the same between time steps n-1 and n. In other examples, the prediction phase can use extrapolation techniques with other types of fit functions, such as cubic fit, etc., and by incorporating additional past SVV values (e.g., for time steps n-3, n-4, etc.). For example, prediction block 186 could take the last four values of SVVfilteredand fit a cubic function onto those points to determine predicted value p at current time step n. In yet other examples, such as examples where the system is stable, prediction block 186 could use the value of SVVfiltered for time step n-1 and extrapolate predicted value p at current time n as unchanged from (i.e., the same as) the value of SVVfiltered for time step n-1. Each of the prediction models described above uses the rate of change of SVV, e.g., by extrapolation, to make a prediction about the current value of SVV for patient 16. Moreover, each of the prediction models is based on the underlying assumption that the change in SVV within the measurement time window (e.g., a ten-second interval) can be represented by a single aggregate or average value. FIG.25B is a graph that corresponds to the functioning of update block 188, as shown in FIG.24. In FIG.25B, an SVV value is shown for each of time steps n, n-1, n- Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 2, n-3, and n-4. Measured value m is the SVV value corresponding to current time step n. Measured value m is an example value of a measured input received by filter sub-module 184 at update block 188. As described above, the measured input can be any one (or more, although only one is shown in FIG. 25B for simplicity) of SVVAE, SVVLR, or SVVadd. Measured value m is used by update block 188 to update predicted value p for current time step n. The SVV values corresponding to time steps n-1, n-2, n-3, and n-4 are previous measured input values that were used in previous time steps by update block 188 to update previous predicated estimates of SVV for the respective time steps. FIG. 25B shows SVV values from a single source, such as one of SVVAE module 40, SVVLRmodule 42, or another source. That is, measured value m is one of SVVAE, SVVLR, or SVVadd. In this example, the Kalman filter algorithm of filter sub- module 184 would only have one update phase using measured value m. In other examples where SVV values are received from multiple sources, there would be multiple measured values m at current time step n. As shown in FIG.25B, measured value m has corresponding uncertainty em. Uncertainty em represents the uncertainty in measured value m as an estimate of the standard deviation. The uncertainty in measured value m can be configurable or predetermined for each application of filter sub-module 184 and can depend on the type of measured input that is used. The arrows extending from measured value m are proportional to the amount of uncertainty in measured value m. Uncertainty em can be the same or different from uncertainty ep, depending on how the respective uncertainties are determined. In the update phase or phases of the Kalman filter algorithm of filter sub- module 184, predicted value p and measured value m are dynamically or adaptively weighted to generate filtered value f, as shown in FIG. 25C. This weighting can result in an uncertainty associated with filtered value f at current time step n that is expected to be the same or less than either of uncertainty ep or uncertainty em. When the Kalman filter algorithm of filter sub-module 184 is initialized, uncertainty epand uncertainty emare specified. If there are multiple sources of measured inputs (e.g., SVVAE module 40, SVVLR module 42, and / or another source), each source can have a different associated uncertainty em. Uncertainty epof predicted value p includes uncertainty associated with the prediction model and any uncertainty associated with past values of SVVfilteredthat were used to determine predicted value p. Accordingly, once filter sub-module 184 has determined predicted value p and received measured value m for current time step n, filter sub-module 184 also has information about corresponding Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 uncertainty epand uncertainty em. Predicted value p and measured value m are weighted based on their associated uncertainties epand em, respectively. The one of predicted value p and measured value m that has a greater uncertainty will be given less weight, and the one of predicted value p and measured value m that has a lower uncertainty will be given more weight. Each of uncertainty epand uncertainty emcan be fixed or modulated over time. For example, uncertainty em could be scaled based on SQIRVP or SQIPAP, as described above with reference to FIG.9. To illustrate, if the value of SQIRVPis zero to one (0 to 1, indicating a signal quality within the designated range), then fluid responsiveness software code 30 (shown in FIG. 1) can proceed to estimate SVVAEand SVVLRusing the corresponding RVP waveform data. However, there may be a different uncertainty for SVVAE and SVVLR associated with a signal quality index of zero versus a signal quality index of one (SQIRVP=0 vs. SQIRVP=1), even though both are valid. For example, uncertainty in measurements might be lower when SQIRVP=0, so uncertainty em associated with measured value m could be multiplied by one (or unchanged). In the same example, uncertainty in measurements might be higher when SQIRVP=1, so uncertainty em associated with measured value m could be multiplied by some factor, such as two or more, to increase the uncertainty. In other examples, uncertainty ep and / or uncertainty em could be scaled based on factors other than SQIRVPand SQIPAP. FIG.25C is a graph that corresponds to the functioning of filter sub-module 184 using information from prediction block 186 and update block 188, as shown in FIG. 24 and described with reference to FIGS. 25A-25B above. In FIG. 25C, an SVV value is shown for each of time steps n, n-1, n-2, n-3, and n-4. Filtered value f is the SVV value corresponding to current time step n. Filtered value f is an example value of SVVfiltered that is output by filter sub-module 184 for current time step n. Filtered value f is also used by prediction block 186 in the prediction for the next time step. The SVV values corresponding to time steps n-1, n-2, n-3, and n-4 are previous SVVfiltered values that were output by filter sub-module 184 in previous time steps. Filtered value f, and its associated uncertainty ef, are computed according to the following general forms using predicted value p, measured value m, and associated uncertainties ep and em: ]̂8 = ^ ^\]× & + ^ ^× / & (Equation 5) Attorney Docket No.: P-31209.WO01-B0968-P14934WO01^[ ≤ ^^;^[ ≤ ^a; and1c ^[: = ^1c ^a: & + d1c ^^: e. (Equation 6)and re-written to clearly show the update of value m (i.e., the measured inputs in the Kalman filter algorithm): ^^ ]8 = _ + ^(^^]^^\]0 × ( / − _)& (Equation 7)as: =_ − (Equation 8)Where, ^]K is the Kalman Gain =^(^^]^^\]0;^[ ≤ ^^; and^5 to show two simultaneous measured values m from two different sources of measured inputs at a time (e.g., SVVLR and SVVAE), Equation 5 can be re-written as: 9) ofSVVAE, SVVLR, or SVVadd; / _2 is a second measured value from a second source of the measured inputs, such as adifferent one of SVVAE, SVVLR, or SVVadd;^[ ≤ ^^_6;&. (Equation 10) Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 As shown in Equation 5, predicted value p is weighted by the respective contribution of measured value m to the overall noise, and measured value m is weighted by the respective contribution of predicted value p to the overall noise. In other words, whichever value of predicted value p and measured value m has a greater uncertainty will cause the other value to be weighted more. To illustrate, if predicted value p had uncertainty ep=0 (no uncertainty), then Equation 5 simplifies so that predicted value p is weighted by one (em / em) and measured value m is weighted by zero (0 / em). Generally, filtered value f is different than both predicted value p and measured value m. However, if measured value same as predicted value p, then filtered value f will also be the same regardless of the weighting in Equation 5. Equation 9 shows how filtered value f is calculated when there are two simultaneous measured values m, such as from two different sources of measured inputs.Equation 7 can be further expanded to include any number of measured values m (e.g., / _1, / _2, . . . / _N). For example, filtered value f could be computed using a measuredvalue m from each of the sources of measured inputs that is available in the system, including SVVAE, SVVLR, and SVVadd. As shown in FIG. 25C, filtered value f has corresponding uncertainty ef. Uncertainty efrepresents the uncertainty in filtered value f. The arrows extending from filtered value f are proportional to the amount of uncertainty in filtered value f. In an example that includes a single measured value m, uncertainty efcan be determined using Equation 4 above. In an example that includes multiple measured values m, uncertainty ef can be determined using Equation 8 above. As described above, uncertainty ef is ideally less than both uncertainty ep and uncertainty em individually. Accordingly, the arrows indicating uncertainty ef are shorter than the arrows indicating uncertainty ep and uncertainty em. Because uncertainty efis less than uncertainty epand uncertainty em, filtered value f is more accurate than predicted value p or measured value m alone. Thus, filter sub- module 184 of SVVcompmodule 44 is able to output SVVfiltered, which can be more accurate than either of the computed SVVAE or SVVLR alone for current time step n. Fluid Responsiveness Index Module (FIGS.26-28) FIG.26 is a schematic block diagram illustrating fluid responsiveness index module 45. FIG. 27 is a graph illustrating right ventricular end diastolic pressure values over time for an animal model. FIG. 28 is a flow diagram illustrating process 200 associated with fluid responsiveness index module 45. FIGS. 26-28 will be discussed together. As illustrated in FIG. 26, one or more RVP features (including right ventricular Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 end diastolic pressure (“RVEDP”) and / or other preload parameters), SVVAE, SVVLR, and SVVcompare input into fluid responsiveness index module 45. Fluid responsiveness index module 45 outputs IFR. In FIG. 27, values of RVEDP in units of millimeters of mercury (mmHg) are shown over time. The graph in FIG. 27 is separated into three portions, including first portion 190, second portion 192, and third portion 194. FIG.27 also shows low pressure portion 196, upper threshold T1, and lower threshold T2. FIG.28 shows steps 210-216 of process 200. Fluid responsiveness index module 45 estimates a preload status of patient 16 (shown in FIG.1) using parameters derived from the RVP waveform. RVEDP and other RVP parameters provide important information regarding cases where a patient has extremely high or extremely low preload. Using this information in conjunction with SVV can result in a better index of fluid responsiveness. RVEDP is one of the RVP features derived from the RVP waveform by RVP features module 32 (or validation module 36) and passed to fluid responsiveness index module 45. RVEDP represents the filling pressure of the right ventricle immediately before contraction and, thus, provides important insight into a patient’s preload status. Patients with extremely high RVEDP (e.g., greater than 15 mmHg or above upper threshold T1 in FIG.27) are usually volume overloaded due to any of a wide range of diseases, including pulmonary hypertension and heart failure. In these cases, patients’ SVV values may also be very high, which would normally indicate fluid responsiveness. However, these patients have too much fluid, so administering any additional fluid will not increase cardiac output and instead can have detrimental effects to the patients’ health. These patients are more correctly categorized as not fluid responsive. Thus, RVEDP values can be used to identify situations when SVV is high but not indicative of fluid responsiveness. On the other hand, patients with very low RVEDP (e.g., less than 5 mmHg or below lower threshold T2 in FIG.27) have low preload, and these patients’ SVV values may also be very low. However, these patients are normally fluid responsive regardless of their SVV value. These patients are more correctly categorized as fluid responsive. Thus, RVEDP values can be used to identify situations when SVV is low but not indicative of non-fluid responsiveness. In animal studies, RVEDP can be used as a simple assessment of fluid status of the subject. This is typically limited to the extremes of the pressure range, as described above. RVEDP alone is less indicative of fluid responsiveness at moderate pressures. Generally, if fluid is administered, RVEDP increases, which indicates more fluid is Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 returning to the heart. Similarly, if there is bleeding, RVEDP decreases, which indicates less fluid is returning to the heart. As illustrated in FIG.27, the graph of RVEDP values is separated into three portions, including first portion 190, second portion 192, and third portion 194. First, second, and third portions 190, 192, and 194 each represent some arbitrary amount of time in the dashed-line boxed areas along the x-axis. First portion 190 corresponds to a fluid administration period for the animal model. First portion 190 includes example RVEDP values measured or obtained during fluid administration. RVEDP generally increases slightly in first portion 190. Second portion 192 corresponds to a bleeding period. Second portion 192 includes example RVEDP values measured or obtained during bleeding. RVEDP decreases in second portion 192. Third portion 194 corresponds to a blood transfusion period. Third portion 194 includes example RVEDP values measured or obtained during a blood transfusion. RVEDP increases in third portion 194. The example illustrated in FIG. 27 includes RVEDP values for a healthy animal model. Because the animal model is healthy, abnormally high RVEDP values are not achieved. As a result, SVV calculated during fluid administration (first portion 190) would be an accurate assessment of fluid responsiveness. Very low RVEDP values appear in low pressure portion 196 after bleeding. In low pressure portion 196, the animal model would be fluid responsive regardless of SVV values. Fluid responsiveness index module 45 generates IFR based on the preload status of patient 16 as estimated by values of RVEDP (or other suitable RVP parameters) that correspond to an estimate of SVV, such as any one of SVVAE, SVVLR, and SVVcomp. Fluid responsiveness index module 45 uses RVEDP to produce a corrected (or adjusted) determination of fluid responsiveness for patient 16 that can be conveyed as IFR. More specifically, IFRcan take the form of a binary indicator of fluid responsiveness of patient 16 (e.g., “FLUID RESPONSIVE” or “NOT FLUID RESPONSIVE” or other binary systems). For example, IFR can indicate “NOT FLUID RESPONSIVE” when RVEDP values are extremely high (e.g., greater than 15 mmHg) and can indicate “FLUID RESPONSIVE” when RVEDP values are very low (e.g., less than 5 mmHg). In some examples, IFRmay only be used when RVEDP falls within certain ranges—either very high or very low pressures as described above—to effectively override the fluid responsiveness determination that would otherwise be made based solely on SVV. In other examples, IFRmay be used supplementarily to an estimate of SVV. Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 Using the example RVEDP values from the graph in FIG. 27 to illustrate, IFRcould have the binary indicator for “FLUID RESPONSIVE” in the time period associated with low pressure portion 196, which includes RVEDP values below lower threshold T2, regardless of the corresponding estimate of SVV. In the other portions of the graph, IFR may not be needed or used because there are no other RVEDP values above upper threshold T1 or below lower threshold T2. More generally, fluid responsiveness index module 45 can carry out the steps illustrated in FIG.28. FIG.28 shows process 200, including steps 210-216. Process 200 uses RVEDP; however, other variations of process 200 can use other RVP parameters relating to preload instead of RVEDP to determine preload status in a similar manner. As illustrated in FIG.28, a first step of process 200 is receiving a value of RVEDP or another RVP parameter relating to preload that corresponds to an estimate of SVV (step 210). The estimate of SVV can be any one of SVVAE, SVVLR, and SVVcomp. At decision 212, fluid responsiveness index module 45 determines whether the RVEDP value is above an upper threshold (e.g., greater than 15 mmHg) or below a lower threshold (e.g., less than 5 mmHg). Decision 212 represents determining preload status based on RVEDP. In response to determining the RVEDP value is above the upper threshold or below the lower threshold (“Yes” in FIG. 28), fluid responsiveness index module 45 proceeds to use IFR(step 214), e.g., to adjust an SVV-based fluid responsiveness determination. In response to determining the RVEDP value is not above the upper threshold or below the lower threshold (“No” in FIG. 28) fluid responsiveness index module 45 does not use IFR and indicates that the estimate of SVV is reliable for determining fluid responsiveness (step 216). Either step 214 or step 216 can be a final step of process 200. Although illustrated as single steps, it should be understood that each of steps 210-216 can, in other examples, be repeated any number of times in process 200. The final output produced by fluid responsiveness index module 45 is IFR. IFRis an adjusted or supplementary representation of fluid responsiveness of patient 16 (shown in FIG.1). In some examples, fluid responsiveness index module 45 can output IFR to output device 102, as shown in FIG. 6. For example, output device 102 can display an indication of “FLUID RESPONSIVE” or “NOT FLUID RESPONSIVE.” In some examples, output device 102 can display a color or other visual or audio indicator associated with IFR. In some examples, fluid responsiveness index module 45 continuously outputs IFRto output device 102 for monitoring the hemodynamic condition of patient 16. Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 RVEDP is normally an “unseen” variable in considering a patient’s fluid responsiveness, but here, RVEDP is obtainable as one of the RVP features (e.g., from RVP features module 32 or validation module 36). Combining preload information from RVEDP (or another RVP parameter relating to preload) with an estimate of SVV (e.g., one of SVVAE, SVVLR, and SVVcomp) helps adjust for edge cases where SVV alone may not be accurate for assessing fluid responsiveness. Thus, fluid responsiveness index module 45 is able to use IFR together with SVVAE, SVVLR, and SVVcomp to produce or enable a more accurate determination of fluid responsiveness for patient 16. Any of the various systems, devices, apparatuses, etc. in this disclosure can be sterilized (e.g., with heat, radiation, ethylene oxide, hydrogen peroxide, etc.) to ensure they are safe for use with patients, and the methods herein can comprise sterilization of the associated system, device, apparatus, etc. (e.g., with heat, radiation, ethylene oxide, hydrogen peroxide, etc.). The treatment techniques, methods, steps, etc. described or suggested herein or in references incorporated herein can be performed on a living animal or on a non-living simulation, such as on a cadaver, cadaver heart, anthropomorphic ghost, simulator (e.g., with the body parts, tissue, etc. being simulated), etc. DISCUSSION OF DETAILED EMBODIMENTS The following are non-exclusive descriptions of possible embodiments of the present invention. A system for determining fluid responsiveness of a patient includes a hemodynamic sensor that produces, on an ongoing basis, a hemodynamic sensor signal representative of a right ventricular pressure (RVP) waveform of the patient and an integrated hardware unit. The integrated hardware unit includes a system processor, a system memory, and a display including a user interface. The system memory includes instructions that, when executed by the system processor, cause the system to receive the hemodynamic sensor signal representative of the RVP waveform of the patient, convert the RVP waveform of the patient into an estimate of a blood flow waveform of the patient, determine a stroke volume variation (SVV) of the patient based on the estimate of the blood flow waveform of the patient to generate a determined SVV of the patient, and output, to the display, an indication of a fluid responsiveness status of the patient that is based on the determined SVV of the patient. Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 The system of the preceding paragraph can optionally include, additionally and / or alternatively, any one or more of the following features, configurations and / or additional components: Wherein the hemodynamic sensor includes a right ventricular blood pressure sensor including a housing, a fluid input port connected via tubing to a fluid source, a catheter-side fluid port connected to a catheter inserted within a right ventricle of the patient, a pressure transducer in communication with the fluid source through the fluid port, and an I / O cable in electrical communication with the pressure transducer. Wherein the system memory is further configured to: receive an electrical signal from the pressure transducer over a period of time, the electrical signal based on a pressure of the right ventricle transmitted through the fluid source; convert the electrical signal to a digital signal; and generate an RVP waveform of the patient based on the digital signal. Wherein the instructions that cause the system to determine the SVV of the patient based on the estimate of the blood flow waveform of the patient further cause the system to determine a stroke volume (SV) for each beat within a sample of the estimate of the blood flow waveform. Wherein the determined SVV of the patient is calculated for the sample ofthe estimate of the blood flow waveform according to the following equation:^^^ = (^^^^^ − ^^^^^)⁄ ^^^^^^wherein ^^^^^is a maximum SV for the sample; wherein ^^^^^is a minimum SV for the sample; and wherein ^^^^^^is a mean SV for the sample. Wherein the sample of the estimate of the blood flow waveform is a ten- second sample. Wherein the determined SVV of the patient is calculated from a beat-to-beat estimate of stroke volume (SV) of the patient. Wherein samples of the RVP waveform of the patient are converted into corresponding samples of the estimate of the blood flow waveform on a rolling basis such that the system is configured to continuously calculate the determined SVV of the patient. Wherein the samples of the RVP waveform of the patient and the corresponding samples of the estimate of the blood flow waveform are each ten-second samples. Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 Wherein the fluid responsiveness status is determined based on a value of the determined SVV of the patient. Wherein the fluid responsiveness status is determined based on a trend of the determined SVV of the patient. Wherein the instructions further cause the system to: estimate a preload status of the patient using the RVP waveform; generate a fluid responsiveness index based on the preload status and the determined SVV of the patient; and output an indication of the fluid responsiveness index to the display. Wherein the fluid responsiveness index is a binary indicator of fluid responsiveness for the patient indicating either the patient is fluid responsive or the patient is not fluid responsive, and wherein the fluid responsiveness index is adjusts an SVV-based fluid responsiveness status of the patient. Wherein the instructions further cause the system to: extract one or more features from the RVP waveform of the patient; and estimate the preload status of the patient using a right ventricular end diastolic pressure (RVEDP) extracted from the RVP waveform. Wherein the fluid responsiveness index indicates the patient is fluid responsive when the RVEDP is below a lower threshold. Wherein the fluid responsiveness index indicates the patient is not fluid responsive when the RVEDP is above an upper threshold. Wherein the hemodynamic sensor is connected to the integrated hardware unit. Wherein the RVP waveform of the patient is converted into the estimate of the blood flow waveform using a machine learning model. Wherein the machine learning model is a deep-learning-based model that uses a neural network architecture. Wherein the machine learning model is an autoencoder model, and wherein using the autoencoder model includes: inputting the RVP waveform of the patient; encoding the RVP waveform into condensed data via a first set of filters; storing the condensed data in a latent space; decoding the condensed data via a second set of filters; and outputting the blood flow waveform of the patient. Wherein samples of the RVP waveform of the patient are input into the autoencoder model on a rolling basis. Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 Wherein the samples of the RVP waveform of the patient are ten-second samples. Wherein the machine learning model is an autoencoder model. Wherein the autoencoder model is trained using animal data. Wherein the instructions further cause the system to train the autoencoder model. Wherein training the autoencoder model includes: training the autoencoder model with a measured animal RVP waveform and a measured animal blood flow to get an animal trained autoencoder model; inputting the measured animal RVP waveform into the animal trained autoencoder model to generate a predicted animal blood flow; comparing the measured animal blood flow to the predicted animal blood flow to validate the animal trained autoencoder model; determining whether the predicted animal blood flow from the animal trained autoencoder model is valid or invalid; inputting a human RVP waveform into the animal trained autoencoder model to generate a human raw blood flow; scaling the human raw blood flow using an intermittent cardiac output to generate a human scaled blood flow; and retraining the animal trained autoencoder model using the human RVP waveform and the human scaled blood flow to get a human trained autoencoder model. Wherein the autoencoder model estimates a raw blood flow waveform of the patient, and wherein the estimate of the blood flow waveform is an estimate of a processed blood flow waveform of the patient. Wherein the raw blood flow waveform of the patient is filtered to remove artifacts or physiological inaccuracies from the raw blood flow waveform to yield the processed blood flow waveform of the patient. Wherein negative flow, flow values in the thousands, square-shaped flow, an inordinate increase in blood flow, or inordinately dissimilar flow per beat is removed from the raw blood flow waveform to yield the processed blood flow waveform of the patient. Wherein the estimate of the blood flow waveform is an estimate of a processed blood flow waveform, the processed blood flow waveform having been filtered via a flow filter to reflect physiological expectations of blood flow. Wherein the instructions further cause the system to smooth the blood flow waveform of the patient. Wherein the instructions further cause the system to assign a signal quality index to the blood flow waveform of the patient based on an amount of erroneous data Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 detected in the blood flow waveform of the patient, the signal quality index indicating a quality of the blood flow waveform of the patient. Wherein the signal quality index is assigned to the blood flow waveform of the patient based on analysis of a sample of the blood flow waveform of the patient. Wherein the sample of the blood flow waveform of the patient is a ten- second sample. Wherein the instructions further cause the system to determine whether the blood flow waveform of the patient is valid based on the signal quality index of the blood flow waveform of the patient, a valid blood flow waveform of the patient indicating that the blood flow waveform of the patient is of high quality and usable for further analysis, and an invalid blood flow waveform of the patient indicating that the blood flow waveform of the patient is of low quality and not usable for further analysis. Wherein the instructions further cause the system to: extract features from the RVP waveform of the patient; and determine a second SVV of the patient based on the features extracted from the RVP waveform of the patient using a regression model to generate a second determined SVV of the patient. Wherein the determined SVV and the second determined SVV are combined to generate a composite SVV. Wherein the determined SVV and the second determined SVV are averaged and the composite SVV is an average SVV. Wherein the second determined SVV is used to validate the determined SVV. Wherein the determined SVV is valid when the determined SVV is within a predetermined range of the second determined SVV, and wherein the determined SVV is not valid when the determined SVV is outside the predetermined range of the second determined SVV. Wherein the features extracted from the RVP waveform include one or more of: a pulse rate, a maximum pressure rate of change with respect to time (“dP / dt”) during systolic rise, a minimum dP / dt during a relaxation period after end systole, a systole time, a systolic pressure, an end systolic pressure, an end diastolic pressure, a pulse pressure, and a mean pressure. Wherein the features extracted from the RVP waveform of the patient include reference features corresponding to a reference time window and current features corresponding to a current time window. Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 Wherein each of the reference time window and the current time window is a time interval that corresponds to an individual beat portion of the RVP waveform of the patient such that the reference features and the current features are features for a respective individual beat. Wherein the reference time window corresponds to a beat at peak inspiration of a respiratory cycle of the patient, and wherein the current time window corresponds to a beat at peak expiration of the respiratory cycle of the patient. Wherein the beat at peak inspiration and the beat at peak expiration are identified by determining the maximum change in cardiac output calculable from a combination of a first window corresponding to an individual beat from a sample of the RVP waveform of the patient and a second window corresponding to a relatively later beat from the sample of the RVP waveform of the patient. Wherein the sample of the RVP waveform of the patient is an at least ten- second sample. Wherein the regression model uses a change between individual features of the reference features and corresponding individual features of the current features to determine a change in cardiac output from the reference time window to the current time window, and wherein the change in cardiac output determined using the regression model is used to calculate the second determined SVV of the patient. Wherein the regression model includes one or more variables, the one or more variables including: one or more first variables, each first variable of the one or more first variables representing a measured value of the reference features or the current features; one or more second differential variables, each second differential variable of the one or more second differential variables representing a difference between an individual feature of the reference features and a corresponding individual feature of the current features; one or more third combinatorial variables, each third combinatorial variable of the one or more third combinatorial variables representing a combination of multiple of the one or more first variables and / or the one or more second differential variables; or any combination of the one or more first variables, the one or more second differential variables, and / or the one or more third combinatorial variables. Wherein the regression model includes one or more terms, each of the one or more terms being formed of one of the one or more variables multiplied by a predetermined coefficient; wherein a change in cardiac output is computed using the regression model as a sum of all the one or more terms; and wherein the change in cardiac Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 output computed using the regression model is used to calculate the second determined SVV of the patient. Wherein the regression model is a machine learning model. Wherein the regression model is a linear regression model. Wherein the determined SVV that is calculated based on the estimate of the blood flow waveform and the second determined SVV that is calculated using the regression model are filtered using a Kalman filter algorithm to produce a filtered SVV. Wherein the Kalman filter algorithm is configured such that each iteration of the Kalman filter algorithm can include a prediction phase and one or more update phases, and wherein the prediction phase alternates with the one or more update phases. Wherein the prediction phase predicts a predicted estimate of SVV that corresponds to a current time step, wherein each of the one or more update phases consumes a measured input that corresponds to the current time step, such that one or more measured inputs are consumed, and wherein the predicted estimate of SVV is updated using a weighted average of the predicted estimate of SVV and each of the one or more measured inputs. Wherein the one or more measured inputs include one or more of the determined SVV that is calculated based on the estimate of the blood flow waveform and the second determined SVV that is calculated using the regression model. Wherein the prediction phase predicts the predicted estimate of SVV based on one or more previous filtered estimates of SVV corresponding to previous time steps of the Kalman filter algorithm. Wherein the predicted estimate of SVV includes a corresponding prediction uncertainty; wherein each of the one or more measured inputs includes a corresponding measurement uncertainty; wherein the corresponding prediction uncertainty and the corresponding measurement uncertainties are predetermined; and wherein the predicted estimate of SVV and each of the one or more measured inputs are weighted by the corresponding prediction uncertainty and the corresponding measurement uncertainties, respectively, such that greater uncertainty is given less weight and lower uncertainty is given more weight. Wherein the corresponding prediction uncertainty and the corresponding measurement uncertainties are fixed over time. Wherein the corresponding prediction uncertainty and the corresponding measurement uncertainties are modulated over time. Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 Wherein the corresponding measurement uncertainties are scaled based on a signal quality index of the RVP waveform of the patient. Wherein a corresponding uncertainty of the filtered SVV is less than the corresponding prediction uncertainty and the corresponding measurement uncertainties. Wherein the Kalman filter algorithm is configured such that a number of update phases per iteration of the Kalman filter algorithm depends on which of the one or more measured inputs are available for a corresponding iteration, and wherein the Kalman filter algorithm is configured to tolerate asynchronous receipt of the one or more measured inputs and / or additional sources of measured inputs. Wherein the Kalman filter algorithm is recursive and uses one or more previous filtered estimates of SVV corresponding to previous time steps of the Kalman filter algorithm and one or more measured inputs that correspond to a current time step to produce the filtered SVV for the current time step. A system for determining fluid responsiveness of a patient includes a hemodynamic sensor that produces, on an ongoing basis, a hemodynamic sensor signal representative of a right ventricular pressure (RVP) waveform of the patient and an integrated hardware unit. The integrated hardware unit includes a system processor, a system memory, and a display including a user interface. The system memory includes instructions that, when executed by the system processor, cause the system to receive the hemodynamic sensor signal representative of the RVP waveform of the patient, convert the RVP waveform of the patient into an estimate of a blood flow waveform of the patient, and determine a stroke volume variation (SVV) of the patient based on the estimate of the blood flow waveform of the patient to generate a determined SVV of the patient. The instructions further cause the system to extract one or more features from the RVP waveform of the patient and estimate a preload status of the patient using a right ventricular end diastolic pressure (RVEDP) extracted from the RVP waveform. The instructions further cause the system to generate a fluid responsiveness index based on the preload status and the determined SVV of the patient, the fluid responsiveness index indicating that the patient is fluid responsive when the RVEDP is below a lower threshold and indicating the patient is not fluid responsive when the RVEDP is above an upper threshold, and output an indication of the fluid responsiveness index to the display. A system for determining fluid responsiveness of a patient includes a hemodynamic sensor that produces, on an ongoing basis, a hemodynamic sensor signal representative of a right ventricular pressure (RVP) waveform of the patient and an Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 integrated hardware unit. The integrated hardware unit includes a system processor, a system memory, and a display including a user interface. The system memory includes instructions that, when executed by the system processor, cause the system to receive the hemodynamic sensor signal representative of the RVP waveform of the patient, convert the RVP waveform of the patient into an estimate of a blood flow waveform of the patient, and determine a stroke volume variation (SVV) of the patient based on the estimate of the blood flow waveform of the patient to generate a determined SVV of the patient. The instructions further cause the system to extract features from the RVP waveform of the patient, determine a second SVV of the patient based on the features extracted from the RVP waveform of the patient using a regression model to generate a second determined SVV of the patient, combine the determined SVV and the second determined SVV to generate a composite SVV, and estimate a preload status of the patient using a right ventricular end diastolic pressure (RVEDP) extracted from the RVP waveform. The instructions further cause the system to generate a fluid responsiveness index based on the preload status and the composite SVV, the fluid responsiveness index indicating that the patient is fluid responsive when the RVEDP is below a lower threshold and indicating the patient is not fluid responsive when the RVEDP is above an upper threshold, and output an indication of the fluid responsiveness index to the display. While the invention has been described with reference to an exemplary example(s), it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the scope of the invention. In addition, many modifications may be made to adapt a particular situation or material to the teachings of the invention without departing from the essential scope thereof. Therefore, it is intended that the invention not be limited to the particular example(s) disclosed, but that the invention will include all examples falling within the scope of the appended claims.

Claims

Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 CLAIMS:

1. A system for determining fluid responsiveness of a patient, the system comprising: a hemodynamic sensor that produces, on an ongoing basis, a hemodynamic sensor signal representative of a right ventricular pressure (RVP) waveform of the patient; and an integrated hardware unit comprising: a system processor; a system memory; and a display including a user interface; wherein the system memory includes instructions that, when executed by the system processor, cause the system to: receive the hemodynamic sensor signal representative of the RVP waveform of the patient; convert the RVP waveform of the patient into an estimate of a blood flow waveform of the patient; determine a stroke volume variation (SVV) of the patient based on the estimate of the blood flow waveform of the patient to generate a determined SVV of the patient; and output, to the display, an indication of a fluid responsiveness status of the patient that is based on the determined SVV of the patient.

2. The system of claim 1, wherein the hemodynamic sensor comprises: a right ventricular blood pressure sensor including a housing, a fluid input port connected via tubing to a fluid source, a catheter-side fluid port connected to a catheter inserted within a right ventricle of the patient, a pressure transducer in communication with the fluid source through the fluid port, and an I / O cable in electrical communication with the pressure transducer; wherein the system memory is further configured to: receive an electrical signal from the pressure transducer over a period of time, the electrical signal based on a pressure of the right ventricle transmitted through the fluid source; convert the electrical signal to a digital signal; and generate an RVP waveform of the patient based on the digital signal.Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 3. The system of claim 1, wherein: the instructions that cause the system to determine the SVV of the patient based on the estimate of the blood flow waveform of the patient further cause the system to determine a stroke volume (SV) for each beat within a sample of the estimate of the blood flow waveform; and the determined SVV of the patient is calculated for the sample of the estimate of the blood flow waveform according to the following equation:^^^ = (^^^^^ − ^^^^^)⁄ ^^^^^^wherein ^^^^^is a maximum SV for the sample; wherein ^^^^^is a minimum SV for the sample; and wherein ^^^^^^is a mean SV for the sample.

4. The system of claim 1, wherein the determined SVV of the patient is calculated from a beat-to-beat estimate of stroke volume (SV) of the patient.

5. The system of claim 1, wherein samples of the RVP waveform of the patient are converted into corresponding samples of the estimate of the blood flow waveform on a rolling basis such that the system is configured to continuously calculate the determined SVV of the patient.

6. The system of claim 1, wherein: the fluid responsiveness status is determined based on a value of the determined SVV of the patient; or wherein the fluid responsiveness status is determined based on a trend of the determined SVV of the patient.

7. The system of claim 1, wherein the instructions further cause the system to: estimate a preload status of the patient using the RVP waveform; generate a fluid responsiveness index based on the preload status and the determined SVV of the patient; and output an indication of the fluid responsiveness index to the display.

8. The system of claim 7, wherein the fluid responsiveness index is a binary indicator of fluid responsiveness for the patient indicating either the patient is fluid responsive or the patient is not fluid responsive, and wherein the fluid responsiveness index an SVV-based fluid responsiveness status of the patient.Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 9. The system of claim 7, wherein the instructions further cause the system to: extract one or more features from the RVP waveform of the patient; and estimate the preload status of the patient using a right ventricular end diastolic pressure (RVEDP) extracted from the RVP waveform; wherein the fluid responsiveness index indicates the patient is fluid responsive when the RVEDP is below a lower threshold; and Wherein the fluid responsiveness index indicates the patient is not fluid responsive when the RVEDP is above an upper threshold.

10. The system of claim 1, wherein the RVP waveform of the patient is converted into the estimate of the blood flow waveform using an autoencoder model, and wherein using the autoencoder model includes: inputting the RVP waveform of the patient; encoding the RVP waveform into condensed data via a first set of filters; storing the condensed data in a latent space; decoding the condensed data via a second set of filters; and outputting the blood flow waveform of the patient.

11. The system of claim 10, wherein samples of the RVP waveform of the patient are input into the autoencoder model on a rolling basis.

12. The system of claim 10, wherein: the autoencoder model estimates a raw blood flow waveform of the patient, and wherein the estimate of the blood flow waveform is an estimate of a processed blood flow waveform of the patient; the raw blood flow waveform of the patient is filtered to remove artifacts or physiological inaccuracies from the raw blood flow waveform to yield the processed blood flow waveform of the patient; and negative flow, flow values in the thousands, square-shaped flow, an inordinate increase in blood flow, or inordinately dissimilar flow per beat is removed from the raw blood flow waveform to yield the processed blood flow waveform of the patient.

13. The system of claim 1, wherein the estimate of the blood flow waveform is an estimate of a processed blood flow waveform, the processed blood flow waveform having been filtered via a flow filter to reflect physiological expectations of blood flow.

14. The system of claim 1, wherein the instructions further cause the system to smooth the blood flow waveform of the patient.Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 15. The system of claim 1, wherein the instructions further cause the system to: assign a signal quality index to the blood flow waveform of the patient based on an amount of erroneous data detected in the blood flow waveform of the patient, the signal quality index indicating a quality of the blood flow waveform of the patient; and determine whether the blood flow waveform of the patient is valid based on the signal quality index of the blood flow waveform of the patient, a valid blood flow waveform of the patient indicating that the blood flow waveform of the patient is of high quality and usable for further analysis, and an invalid blood flow waveform of the patient indicating that the blood flow waveform of the patient is of low quality and not usable for further analysis.

16. The system of claim 1, wherein the instructions further cause the system to: extract features from the RVP waveform of the patient; and determine a second SVV of the patient based on the features extracted from the RVP waveform of the patient using a regression model to generate a second determined SVV of the patient; wherein the determined SVV and the second determined SVV are combined to generate a composite SVV.

17. The system of claim 16, wherein the determined SVV and the second determined SVV are averaged and the composite SVV is an average SVV.

18. The system of claim 16, wherein the second determined SVV is used to validate the determined SVV, and wherein: the determined SVV is valid when the determined SVV is within a predetermined range of the second determined SVV; and the determined SVV is not valid when the determined SVV is outside the predetermined range of the second determined SVV.

19. The system of claim 16, wherein the features extracted from the RVP waveform include one or more of: a pulse rate, a maximum pressure rate of change with respect to time (“dP / dt”) during systolic rise, a minimum dP / dt during a relaxation period after end systole, a systole time, a systolic pressure, an end systolic pressure, an end diastolic pressure, a pulse pressure, and a mean pressure.

20. The system of claim 16, wherein:Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 the features extracted from the RVP waveform of the patient include reference features corresponding to a reference time window and current features corresponding to a current time window; each of the reference time window and the current time window is a time interval that corresponds to an individual beat portion of the RVP waveform of the patient such that the reference features and the current features are features for a respective individual beat; the reference time window corresponds to a beat at peak inspiration of a respiratory cycle of the patient, and wherein the current time window corresponds to a beat at peak expiration of the respiratory cycle of the patient; and the beat at peak inspiration and the beat at peak expiration are identified by determining the maximum change in cardiac output calculable from a combination of a first window corresponding to an individual beat from a sample of the RVP waveform of the patient and a second window corresponding to a relatively later beat from the sample of the RVP waveform of the patient.

21. The system of claim 20, wherein the regression model uses a change between individual features of the reference features and corresponding individual features of the current features to determine a change in cardiac output from the reference time window to the current time window, and wherein the change in cardiac output determined using the regression model is used to calculate the second determined SVV of the patient.

22. The system of claim 20, wherein the regression model includes one or more variables, the one or more variables including: one or more first variables, each first variable of the one or more first variables representing a measured value of the reference features or the current features; one or more second differential variables, each second differential variable of the one or more second differential variables representing a difference between an individual feature of the reference features and a corresponding individual feature of the current features; one or more third combinatorial variables, each third combinatorial variable of the one or more third combinatorial variables representing a combination ofAttorney Docket No.: P-31209.WO01-B0968-P14934WO01 multiple of the one or more first variables and / or the one or more second differential variables; or any combination of the one or more first variables, the one or more second differential variables, and / or the one or more third combinatorial variables.

23. The system of claim 22, wherein the regression model includes one or more terms, each of the one or more terms being formed of one of the one or more variables multiplied by a predetermined coefficient; wherein a change in cardiac output is computed using the regression model as a sum of all the one or more terms; and wherein the change in cardiac output computed using the regression model is used to calculate the second determined SVV of the patient.

24. The system of claim 16, wherein: the determined SVV that is calculated based on the estimate of the blood flow waveform and the second determined SVV that is calculated using the regression model are filtered using a Kalman filter algorithm to produce a filtered SVV; 25. The system of claim 24, wherein: the Kalman filter algorithm is configured such that each iteration of the Kalman filter algorithm can include a prediction phase and one or more update phases, wherein the prediction phase alternates with the one or more update phases, and wherein the prediction phase predicts a predicted estimate of SVV that corresponds to a current time step; each of the one or more update phases consumes a measured input that corresponds to the current time step, such that one or more measured inputs are consumed; and the predicted estimate of SVV is updated using a weighted average of the predicted estimate of SVV and each of the one or more measured inputs.

26. The system of claim 25, wherein the one or more measured inputs include one or more of the determined SVV that is calculated based on the estimate of the blood flow waveform and the second determined SVV that is calculated using the regression model.Attorney Docket No.: P-31209.WO01-B0968-P14934WO01 27. The system of claim 25, wherein the prediction phase predicts the predicted estimate of SVV based on one or more previous filtered estimates of SVV corresponding to previous time steps of the Kalman filter algorithm.

28. The system of claim 25, wherein the Kalman filter algorithm is configured such that a number of update phases per iteration of the Kalman filter algorithm depends on which of the one or more measured inputs are available for a corresponding iteration, and wherein the Kalman filter algorithm is configured to tolerate asynchronous receipt of the one or more measured inputs and / or additional sources of measured inputs.

29. A system for determining fluid responsiveness of a patient, the system comprising: a hemodynamic sensor that produces, on an ongoing basis, a hemodynamic sensor signal representative of a right ventricular pressure (RVP) waveform of the patient; and an integrated hardware unit comprising: a system processor; a system memory; and a display including a user interface; wherein the system memory includes instructions that, when executed by the system processor, cause the system to: receive the hemodynamic sensor signal representative of the RVP waveform of the patient; convert the RVP waveform of the patient into an estimate of a blood flow waveform of the patient; determine a stroke volume variation (SVV) of the patient based on the estimate of the blood flow waveform of the patient to generate a determined SVV of the patient; extract one or more features from the RVP waveform of the patient; estimate a preload status of the patient using a right ventricular end diastolic pressure (RVEDP) extracted from the RVP waveform; generate a fluid responsiveness index based on the preload status and the determined SVV of the patient, the fluid responsiveness index indicating that the patient is fluid responsive when the RVEDP is below a lower threshold and indicating the patient is not fluid responsive when the RVEDP is above an upper threshold; andAttorney Docket No.: P-31209.WO01-B0968-P14934WO01 output an indication of the fluid responsiveness index to the display.

30. A system for determining fluid responsiveness of a patient, the system comprising: a hemodynamic sensor that produces, on an ongoing basis, a hemodynamic sensor signal representative of a right ventricular pressure (RVP) waveform of the patient; and an integrated hardware unit comprising: a system processor; a system memory; and a display including a user interface; wherein the system memory includes instructions that, when executed by the system processor, cause the system to: receive the hemodynamic sensor signal representative of the RVP waveform of the patient; convert the RVP waveform of the patient into an estimate of a blood flow waveform of the patient; determine a stroke volume variation (SVV) of the patient based on the estimate of the blood flow waveform of the patient to generate a determined SVV of the patient; extract features from the RVP waveform of the patient; determine a second SVV of the patient based on the features extracted from the RVP waveform of the patient using a regression model to generate a second determined SVV of the patient; combine the determined SVV and the second determined SVV to generate a composite SVV; estimate a preload status of the patient using a right ventricular end diastolic pressure (RVEDP) extracted from the RVP waveform; generate a fluid responsiveness index based on the preload status and the composite SVV, the fluid responsiveness index indicating that the patient is fluid responsive when the RVEDP is below a lower threshold and indicating the patient is not fluid responsive when the RVEDP is above an upper threshold; and output an indication of the fluid responsiveness index to the display.

Images