Hemodynamic monitor for triage of low ejection fraction patients

Abstract

A hemodynamic monitor comprising: a non-invasive blood pressure sensor; and an integrated hardware unit having a system processor, a system memory, and a display having a user interface. The system memory includes instructions configured to: adjust, via the pressure controller, a pressure within the inflatable blood pressure bag to maintain a constant volume of a patient's artery for a period of time; generating arterial pressure waveform data of the patient based on the adjusted pressure within the inflatable blood pressure bag for the period of time; extracting a plurality of signal measurements from the arterial pressure waveform data of the patient; extracting an input feature from the plurality of signal measurements indicative of the ejection score score of the patient; and determining the ejection score score for the patient based on the extracted input features.

Description

[0001] Cross - Reference to Related Applications

[0002] This application claims the benefit of U.S. Provisional Application No. 63 / 375,843, filed on September 15, 2022, entitled "HEMODYNAMIC MONITOR FOR TRIAGING PATIENTS WITH LOW EJECTION FRACTION OR AORTIC STENOSIS", the disclosure of which is hereby incorporated by reference in its entirety. Technical Field

[0003] The present disclosure generally relates to ejection fraction and, in particular, to measuring a patient's ejection fraction and triaging the patient for treatment. Background Art

[0004] Ejection fraction is a measurement of the amount of blood pumped out of a heart chamber during each contraction. Ejection fraction is essentially a comparison of the amount of blood in a heart chamber to the amount of blood pumped out of the heart chamber. Left ventricular ejection fraction is the ejection fraction of the left heart and indicates the efficiency of the heart in pumping blood into the systemic circulation. Traditionally, a patient's ejection fraction has been measured by image tests such as echocardiogram, multigated acquisition (MUGA) scan, or computed tomography (CT) scan. Other tests used to determine ejection fraction include cardiac catheterization and nuclear stress testing. Each of these tests requires a trained expert to perform the test and interpret the test results. Thus, a patient must travel to a cardiologist or other cardiovascular specialist for an initial cardiac screening. These tests can be expensive and may take days or weeks to inform the patient of their ejection fraction. There is a need for a solution that will provide more opportunities for patients to have their ejection fraction screened and that is closer to home. Preferably, the solution will also reduce the amount of time a patient must wait to receive the results from an ejection fraction screening so that the patient can seek further testing and / or treatment with less delay. Summary of the Invention

[0005] In one example, a hemodynamic monitor for detecting heart failure is disclosed. The hemodynamic monitor includes a non-invasive blood pressure sensor that includes an inflatable blood pressure cuff, a pressure controller pneumatically connected to the inflatable blood pressure cuff, and an optical transmitter and an optical receiver electrically connected to the pressure controller. The hemodynamic monitor further includes an integrated hardware unit having a system processor, a system memory, and a display having a user interface. The system memory includes instructions that, when executed by the system processor, are configured to: adjust the pressure within the inflatable blood pressure cuff via the pressure controller to maintain a constant volume of the patient's artery for a period of time based on feedback signals generated by the optical transmitter and the optical receiver; generate arterial pressure waveform data of the patient based on the adjusted pressure within the inflatable blood pressure cuff over the period of time; extract a plurality of signal measures from the arterial pressure waveform data of the patient; extract input features from the plurality of signal measures indicative of an ejection fraction score of the patient; determine the ejection fraction score of the patient based on the extracted input features; generate a first sensory alert signal configured to generate a first sensory alert indicating that the patient has a low ejection fraction when the ejection fraction score exceeds a threshold score, or generate a second sensory alert signal configured to generate a second sensory alert indicating that the patient does not have a low ejection fraction when the ejection fraction score is below the threshold score; transmit the first sensory alert signal or the second sensory alert signal to the user interface; and output the first sensory alert or the second sensory alert via the user interface.

[0006] In another example, a hemodynamic monitor for detecting heart failure is disclosed. The hemodynamic monitor includes an arterial blood pressure sensor having: a housing; a fluid input port connected via tubing to a fluid source; a catheter-side fluid port connected to a catheter inserted into a patient's arterial system; 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. The hemodynamic monitor further includes an integrated hardware unit having a system processor, a system memory, a display including a user interface, and an analog-to-digital (ADC) converter. The system memory includes instructions that, when executed by the system processor, are configured to: receive, over a period of time, an electrical signal from the pressure transducer, the electrical signal being based on the pressure of the patient's arterial system transmitted through the fluid source; convert the electrical signal into a digital signal; generate arterial pressure waveform data for the patient based on the digital signal; extract a plurality of signal measurements from the arterial pressure waveform data; extract input features from the plurality of signal measurements indicative of an ejection fraction score of the patient; determine the ejection fraction score of the patient based on the extracted input features; generate a first sensory alert signal configured to generate a first sensory alert indicating that the patient has a low ejection fraction when the ejection fraction score exceeds a threshold score, or generate a second sensory alert signal configured to generate a second sensory alert indicating that the patient does not have a low ejection fraction when the ejection fraction score is below the threshold score; transmit the first sensory alert signal or the second sensory alert signal to the user interface; and output the first sensory alert or the second sensory alert through the user interface.

[0007] In a further example, a method for risk triage of heart failure in a patient is disclosed. The method includes receiving, by a hemodynamic monitor, sensed hemodynamic data representative of an arterial pressure waveform of the patient. The hemodynamic monitor performs waveform analysis of the sensed hemodynamic data to calculate a plurality of signal measurements of the sensed hemodynamic data and to extract input features from the plurality of signal measurements indicative of an ejection fraction of the patient. The hemodynamic monitor further determines the ejection fraction of the patient based on the input features and outputs the ejection fraction of the patient to a display. When the ejection fraction is less than or equal to forty percent, the hemodynamic monitor alerts the patient or medical staff that the ejection fraction is low. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1Perspective view of an exemplary hemodynamic monitor that analyzes a patient's arterial pressure and provides the patient's ejection fraction and heart failure risk score to medical personnel.

[0009] Figure 2 Perspective view of an exemplary minimally invasive pressure sensor for sensing hemodynamic data representative of a patient's arterial pressure.

[0010] Figure 3 Perspective view of an exemplary non-invasive sensor for sensing hemodynamic data representative of a patient's arterial pressure.

[0011] Figure 4 Block diagram of an exemplary hemodynamic monitoring system that determines a patient's ejection fraction based on an input feature set derived from signal measurements of the patient's arterial pressure waveform.

[0012] Figure 5 Schematic diagram of a method for triaging a patient's ejection fraction.

[0013] Figure 6 Diagram of a first clinical data set, a second clinical data set, and a third clinical data set for data mining and machine training of a hemodynamic monitoring system.

[0014] Figure 7 Flowchart for extracting an input feature set derived from signal measurements of a patient's arterial pressure waveform for training a machine learning model of a hemodynamic monitoring system.

[0015] Figure 8 Diagram showing an exemplary arterial pressure waveform trace including example markers corresponding to signal measurements for extracting input features for determining a patient's ejection fraction. Specific embodiments

[0016] As described herein, a hemodynamic monitoring system uses a patient's arterial waveform to detect the patient's ejection fraction. The hemodynamic monitoring system uses machine learning to extract an input feature set from the patient's arterial pressure. The hemodynamic monitoring system uses the input feature set to determine the patient's ejection fraction when the patient visits a primary care physician's office, is in an urgent care facility, or in any other patient care environment.

[0017] Based on the ejection fraction measured by the hemodynamic monitoring system, the hemodynamic monitoring system is capable of signaling or alerting medical staff and / or the patient to alert the medical staff and / or the patient that the patient has a low ejection fraction and is at high risk of heart failure. The following is a detailed description of the hemodynamic monitoring system with reference to Figures 1-8 in detail.

[0018] Figure 1is a perspective view of a hemodynamic monitor 10 capable of determining a patient's ejection fraction. As Figure 1 shown, the hemodynamic monitor 10 includes a display 12, and in Figure 1 the example, the display 12 presents a graphical user interface including control elements (e.g., graphical control elements) that enable a user to interact with the hemodynamic monitor 10. The hemodynamic monitor 10 can also include a plurality of input and / or output (I / O) connectors configured for wired connection (e.g., electrical connection and / or communication connection) with one or more peripheral components, such as one or more hemodynamic sensors, as further described below. For example, as Figure 1 shown, the hemodynamic monitor 10 can include an I / O connector 14. Although Figure 1 the example shows five separate input / output connectors 14, it should be understood that in other examples, the hemodynamic monitor 10 can include fewer than five I / O connectors or more than five I / O connectors. In still other examples, the hemodynamic monitor 10 may not include the I / O connector 14 but may instead communicate wirelessly with various peripheral devices.

[0019] As further described below, the hemodynamic monitor 10 includes one or more processors and a computer-readable memory storing ejection fraction software code that can be executed to determine an ejection fraction measurement of a patient based on sensed hemodynamic data of the patient. The hemodynamic monitor 10 can receive sensed hemodynamic data representing a patient's arterial pressure waveform, for example, via one or more hemodynamic sensors connected to the hemodynamic monitor 10 through the I / O connector 14. The hemodynamic monitor 10 executes the ejection fraction software code and uses the sensed hemodynamic data to obtain a plurality of ejection fraction profiling parameters (e.g., input features), which can include one or more vital sign parameters characterizing the patient's vital sign data, as well as differential parameters and combined parameters derived from the one or more vital sign parameters, as further described below.

[0020] As Figure 1 shown, the hemodynamic monitor 10 can present a graphical user interface at the display 12. The display 12 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 a user in graphical form. In some examples, such as Figure 1In the example, the display 12 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, pinch gestures, swipe gestures, or other gesture inputs.

[0021] Figure 2 is a perspective view of a hemodynamic sensor 16 that can be attached to a patient for sensing hemodynamic data representative of the patient's arterial pressure. Figure 2 The hemodynamic sensor 16 shown in FIG. is an example of a minimally invasive hemodynamic sensor that can be attached to a patient via, for example, a radial artery catheter inserted into the patient's arm. In other examples, the hemodynamic sensor 16 can be attached to the patient via a femoral artery catheter inserted into the patient's leg.

[0022] As Figure 2 shown, the hemodynamic sensor 16 includes a housing 18, a fluid input port 20, a catheter-side fluid port 22, and an I / O cable 24. The fluid input port 20 is configured to be connected to a fluid source, such as a saline bag or other fluid input source, via tubing or other hydraulic connections. The catheter-side fluid port 22 is configured to be connected to a catheter (e.g., a radial artery catheter or a femoral artery catheter) inserted into the patient's arm (i.e., the radial artery catheter) or the patient's leg (i.e., the femoral artery catheter) via tubing or other hydraulic connections. The I / O cable 24 is configured to be connected to the hemodynamic monitor 10 via one or more of, for example, the I / O connectors 14 ( Figure 1 ). The housing 18 of the hemodynamic sensor 16 encloses one or more pressure transducers, communication circuits, processing circuits, and corresponding electronic components to sense a fluid pressure corresponding to the patient's arterial pressure, and the fluid pressure is transmitted to the hemodynamic monitor 10 via the I / O cable 24 ( Figure 1 ).

[0023] In operation, a column of fluid (e.g., a saline solution) is introduced from a fluid source (e.g., a saline bag) through the fluid input port 20 through the hemodynamic sensor 16 towards the catheter inserted into the patient to the catheter-side fluid port 22. The arterial pressure is transmitted through the fluid column to a pressure sensor located within the housing 16 that senses the pressure of the fluid column. The hemodynamic sensor 16 converts the sensed pressure of the fluid column into an electrical signal via a pressure transducer and outputs the corresponding electrical signal to the hemodynamic monitor 10 via the I / O cable 24 ( Figure 1 ). The hemodynamic sensor 16 thus transmits analog sensor data (or a digital representation of the analog sensor data) representative of a substantially continuous beat-to-beat monitoring of the patient's arterial pressure to the hemodynamic monitor 10 ( Figure 1 ).

[0024] Figure 3 is a perspective view of a hemodynamic sensor 26 for sensing hemodynamic data representative of a patient's arterial pressure. Figure 3 The hemodynamic sensor 26 shown in is an example of a non-invasive hemodynamic sensor that can be attached to a patient via one or more finger cuffs to sense data representative of the patient's arterial pressure. As Figure 3 shown, the hemodynamic sensor 26 includes an inflatable finger cuff 28 and a cardiac reference sensor 30. The inflatable finger cuff 28 also includes an optical (e.g., infrared) transmitter and an optical receiver electrically connected to a pressure controller (not shown). The optical transmitter and the optical receiver are capable of measuring the changing volume of the artery under the finger cuff. The optical transmitter and the optical receiver can be positioned to transmit and receive light therebetween through an inflatable blood pressure bladder.

[0025] In operation, the pressure controller continuously adjusts the pressure within the finger cuff to maintain a constant volume (i.e., the unloaded volume) of the artery in the finger as measured by the optical transmitter and the optical receiver of the inflatable finger cuff 28. The pressure applied by the pressure controller to continuously maintain the unloaded volume represents the blood pressure in the finger and is transmitted by the pressure controller to Figure 1 the hemodynamic monitor 10 shown. The cardiac reference sensor 30 measures the hydrostatic height difference between the level at which the finger is held and a reference level for pressure measurement, which is generally the cardiac level. Accordingly, the hemodynamic sensor 26 transmits sensor data representative of a substantially continuous beat-to-beat monitoring of the patient's arterial pressure waveform.

[0026] Figure 4 is a block diagram of a hemodynamic monitoring system 32 that determines an ejection fraction measurement for a patient 36 based on a set of ejection fraction profiling parameters (also referred to as input features) derived from the patient 36's arterial pressure. The hemodynamic monitoring system 32 monitors the arterial pressure of the patient 36 and provides the ejection fraction measurement to a healthcare provider 38. If the ejection fraction measurement for the patient 36 is low or critical, the healthcare provider 38 can respond to the ejection fraction measurement by recommending treatment for heart failure or cardiomyopathy to the patient 36.

[0027] As Figure 4 shown, the hemodynamic monitoring system 32 includes a hemodynamic monitor 10 and a hemodynamic sensor 34. The hemodynamic monitoring system 32 can be performed in a primary care physician's office during a routine physical examination or check-up, when in a patient care environment (such as an ICU, OR) or any other patient care environment. The hemodynamic monitoring system 32 can even be used and operated by the patient 36 at home. As Figure 4 shown, the patient care environment can include the patient 36 and a healthcare worker 38 trained to use the hemodynamic monitoring system 32.

[0028] As described above regarding Figure 1 the hemodynamic monitor 10 can be, for example, an integrated hardware unit that includes a system processor 40, a system memory 42, a display 12, an analog-to-digital (ADC) converter 44, and a digital-to-analog (DAC) converter 46. In other examples, any one or more components and / or the described functionality of the hemodynamic monitor 10 can be distributed among multiple hardware units. For example, in some examples, the display 12 can be a separate display device that is remote from and operatively coupled to the hemodynamic monitor 10. Generally, although shown and described as an integrated hardware unit in the Figure 4 examples, it should be understood that the hemodynamic monitor 10 can include any combination of devices and components that are electrically connected, communicatively connected, or otherwise operatively connected to perform the functions attributed to the hemodynamic monitor 10 herein.

[0029] As Figure 4 shown, the system memory 42 stores ejection fraction software code 48. The ejection fraction software code 48 includes a first module 50 for extracting and calculating waveform features from the arterial pressure of the patient 36, a second module 51 for extracting input features from the waveform features, and a third module 52 for determining an ejection fraction measurement of the patient 36 based on the input features. The display 12 provides a user interface 54 that includes control elements 56 that enable a user to interact with the hemodynamic monitor 10 and / or other components of the hemodynamic monitoring system 32. As Figure 4 shown, the user interface 54 also provides a sensory alert 58 to provide a warning to medical personnel when the ejection fraction of the patient 36 is low or critical. The sensory alert 58 can be implemented as one or more of a visual alert, an audible alert, a tactile alert, or other types of sensory alerts. For example, the sensory alert 58 can be invoked as any combination of a flashing and / or colored graphic shown by the user interface 54 on the display 12, a display of the ejection fraction measurement along with a heart failure risk score via the user interface 54 on the display 12, a warning sound such as a siren or repeating tone, and a tactile alert configured to cause the hemodynamic monitor 10 to vibrate or otherwise transmit a perceptible physical impulse to the medical worker 38 or other user.

[0030] The hemodynamic sensor 34 can be attached to a patient 36 to sense hemodynamic data representative of the arterial pressure waveform of the patient 36. The hemodynamic sensor 34 is operatively connected to a hemodynamic monitor 10 (e.g., electrically connected and / or communicatively connected via a wired or wireless connection, or both) to provide the sensed hemodynamic data to the hemodynamic monitor 10. In some examples, the hemodynamic sensor 34 provides hemodynamic data representative of the arterial pressure waveform of the patient 36 to the hemodynamic monitor 10 as an analog signal, and the analog signal is converted by an ADC 44 into digital hemodynamic data representative of the arterial pressure waveform. In other examples, the hemodynamic sensor 34 can provide the sensed hemodynamic data to the hemodynamic monitor 10 in digital form, in which case the hemodynamic monitor 10 may not include or use an ADC 44. In still other examples, the hemodynamic sensor 34 can provide hemodynamic data representative of the arterial pressure waveform of the patient 36 to the hemodynamic monitor 10 as an analog signal, and the analog signal is analyzed by the hemodynamic monitor 10 in its analog form.

[0031] The hemodynamic sensor 34 can be a non-invasive or minimally invasive sensor attached to the patient 36. For example, the hemodynamic sensor 34 can take the form of a minimally invasive hemodynamic sensor 16( Figure 2 ), a non-invasive hemodynamic sensor 26( Figure 3 ) or other minimally invasive or non-invasive hemodynamic sensors. In some examples, the hemodynamic sensor 34 can be non-invasively attached to a limb of the patient 36, such as the patient 36's wrist, arm, finger, ankle, toe or other limb. Thus, the hemodynamic sensor 34 can take the form of a small, lightweight and comfortable hemodynamic sensor suitable for long-term wear by the patient 36 to provide substantially continuous beat-to-beat monitoring of the arterial pressure of the patient 36 over an extended period of time (such as several minutes or possibly several hours). Although the hemodynamic sensor 34 can monitor the arterial pressure of the patient 36 over an extended period of time, the hemodynamic sensor 34 will only need to monitor the arterial pressure of the patient 36 for a few minutes (such as 5 minutes) to provide sufficient data to the hemodynamic monitor 10 to determine an ejection fraction measurement of the patient 36.

[0032] In some examples, the hemodynamic sensor 34 can be configured to sense the arterial pressure of the patient 36 in a minimally invasive manner. For example, the hemodynamic sensor 34 can be attached to the patient 36 via a radial artery catheter inserted into the arm of the patient 36. In other examples, the hemodynamic sensor 34 can be attached to the patient 36 via a femoral artery catheter inserted into the leg of the patient 36. Such minimally invasive techniques can similarly enable the hemodynamic sensor 34 to provide substantially continuous beat-to-beat monitoring of the arterial pressure of the patient 36 over an extended period of time (such as several minutes or hours). Although the hemodynamic sensor 34 can monitor the arterial pressure of the patient 36 over an extended period of time, the hemodynamic sensor 34 will only need to monitor the arterial pressure of the patient 36 for a few minutes (such as 5 minutes) to provide sufficient data to the hemodynamic monitor 10 to determine an ejection fraction measurement of the patient 36.

[0033] The system processor 40 is a hardware processor configured to execute the ejection fraction software code 48, which executes a first module 50, a second module 51, and a third module 52 to generate an ejection fraction measurement of the patient 36. Examples of the system processor 40 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 circuits.

[0034] The system memory 42 can be configured to store information within the hemodynamic monitor 10 during operation. The system memory 42 is described in some examples as a computer-readable storage medium. In some examples, the 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, the non-transitory storage medium can store data that can change over time (e.g., stored in RAM or a cache). The system memory 42 can include volatile and non-volatile computer-readable memory. Examples of volatile memory can include random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), and other forms of volatile memory. Examples of non-volatile memory can include, for example, magnetic hard disks, optical disks, flash memory, or various forms of electrically programmable memory (EPROM) or electrically erasable programmable (EEPROM) memory.

[0035] The display 12 can be a liquid crystal display (LCD), a light emitting diode (LED) display, an organic light emitting diode (OLED) display, or other display devices suitable for providing information to a user in graphical form. The user interface 54 can include graphical and / or physical control elements that enable user input to interact with the hemodynamic monitor 10 and / or other components of the hemodynamic monitoring system 32. In some examples, the user interface 54 can take the form of a graphical user interface (GUI) that presents graphical control elements on a touch-sensitive and / or presence-sensitive display screen such as, for example, the display 12. In such examples, user input can be received in the form of gesture input, such as touch gestures, scroll gestures, pinch gestures, or other gesture input. In certain examples, the user interface 54 can take the form of and / or include physical control elements, such as physical buttons, keys, knobs, or other physical control elements configured to receive user input to interact with components of the hemodynamic monitoring system 32.

[0036] In operation, the hemodynamic sensor 34 senses hemodynamic data representative of the arterial pressure waveform of the patient 36. The hemodynamic sensor 34 provides the hemodynamic data to the hemodynamic monitor 10 (e.g., provided as analog sensor data). The ADC 44 converts the analog hemodynamic data into digital hemodynamic data representative of the patient's arterial pressure waveform.

[0037] The system processor 40 executes the ejection fraction software code 48 to determine an ejection fraction measurement of the patient 36 using the received hemodynamic data. For example, the system processor 40 can execute a first module 50 to perform waveform analysis of the hemodynamic data to determine a plurality of signal measurements. The plurality of signal measurements includes waveform features and hemodynamic effects characterizing individual cardiac cycles of the patient's arterial pressure waveform. The plurality of signal measurements is discussed in more detail below in the discussion of Figure 8 The system processor 40 executes a second module 51 to extract input features for determining an ejection fraction measurement of the patient 36 from the plurality of signal measurements. The system processor 40 executes a third module 52 to determine an ejection fraction measurement of the patient 36 based on the input features. The third module 52 can also convert the ejection fraction measurement of the patient 36 into a heart failure score representing the probability of heart failure of the patient 36.

[0038] If the measured ejection fraction value of patient 36 is equal to or less than forty percent, the system processor 40 invokes the sensory alert 58 of the user interface 54 to send a first sensory signal to alert the medical worker 38 that patient 36 has a low measured ejection fraction value and that patient 36 is at high risk of heart failure. The medical worker 38 can respond to the low ejection measurement of patient 36 by advising patient 36 to undergo further tests and examinations to verify the heart health of patient 36. In this way, the hemodynamic monitor 10 serves as a screening tool that can be used in the office of a primary care physician to detect and identify heart failure in patient 36 during a routine physical examination. Similarly, the hemodynamic monitor 10 can be used by patient 36 at home for self-screening to self-determine whether patient 36 needs to see a doctor or a specialist.

[0039] If the system processor 40 and the third module 52 determine that the measured ejection fraction value of patient 36 is between forty-one and forty-nine percent, the system processor 40 invokes the sensory alert 58 of the user interface 54 to send a second sensory signal to alert the medical worker 38 that patient 36 has a borderline ejection fraction value and that patient 36 may be at risk of heart failure in the near future. The medical worker 38 can respond to the borderline ejection measurement of patient 36 by advising patient 36 to undergo further tests and examinations to verify the heart health of patient 36. In this way, the hemodynamic monitor 10 serves as a tool that can be used in the office of a primary care physician to detect the future possibility of heart failure or the early onset of heart failure in patient 36 during a routine physical examination. Similarly, the hemodynamic monitor 10 can be used by patient 36 at home for self-screening to self-determine whether patient 36 needs to see a doctor or a specialist.

[0040] If the system processor 40 and the third module 52 determine that the measured ejection fraction value of patient 36 is above fifty percent, the system processor 40 invokes the sensory alert 58 of the user interface 54 to send a third sensory signal to alert the medical worker 38 that patient 36 has a normal ejection fraction value and that patient 36 has a low risk of heart failure in the near future. When the hemodynamic monitor 10 determines that patient 36 has a normal ejection fraction value, it is less likely that additional ejection fraction screening or examinations will be performed on patient 36. Since the amount of blood pumped out by a healthy heart in one heartbeat does not exceed half to two-thirds of the amount of blood in one chamber, the measured ejection fraction value of patient 36 should not exceed seventy percent.

[0041] In some embodiments, the system processor 40 is capable of determining multiple subsets of input features, where each subset of the input features is associated with a different level or range of an ejection fraction measurement. For example, the system processor 40 is capable of executing a first module 50 to perform waveform analysis of hemodynamic data to determine multiple signal measurements. The system processor 40 executes a second module 51 to extract a first subset, a second subset, and a third subset of the input features from the multiple signal measurements of the patient 36. The first subset of the input features is those input features that a third module 52 will use to determine whether the patient 36 has a normal ejection fraction measurement. The second subset of the input features is those input features that the third module 52 will use to determine whether the patient 36 has a low ejection fraction measurement. The third subset of the input features is those input features that the third module 52 will use to determine whether the patient 36 has a borderline ejection fraction measurement. The system processor 40 is capable of executing the first module 50 to extract a single batch of the multiple signal measurements for a given unit of time, and the single batch of signal measurements can be used by the second module 51 to extract all of the first subset, the second subset, and the third subset of the input features for that unit of time. The second module 51 is capable of extracting all of the first subset, the second subset, and the third subset of the input features from the multiple signal measurements simultaneously. The system processor 40 is capable of executing the third module 52 to calculate the probabilities of a normal ejection fraction score, a low ejection fraction score, and a borderline ejection fraction score for the patient 36 simultaneously.

[0042] In some examples, the ejection fraction software code 48 of the hemodynamic monitor 10 can utilize a multi-class type machine learning model with three labels (i.e., normal ejection fraction vs low ejection fraction vs borderline ejection fraction). For example, the processor 40 can output to the display 12 (and / or the display of the patient 36's mobile device) both the normal ejection fraction score of the patient 36 and both the low ejection fraction score and the borderline ejection fraction score of the patient 36 such that the entire subset of probabilities can be compared together: the probability that the patient 36 has a normal ejection fraction measurement, the probability that the patient 36 has a low ejection fraction measurement, and the probability that the patient 36 has a borderline ejection fraction measurement. In the case where the normal ejection fraction score, the low ejection fraction score, and the borderline ejection fraction score of the patient 36 are together on the display 12 of the hemodynamic monitor 10, the healthcare worker 38 can better understand and cross-check whether the patient 36 has a normal ejection fraction measurement relative to a low ejection fraction measurement or a borderline ejection fraction measurement. As discussed below with reference to Figure 5 the hemodynamic monitor 10 is a fast and effective tool for screening and triaging the patient 36 before referring the patient 36 for more lengthy and expensive examinations.

[0043] Figure 5Shows a perspective view of a hemodynamic monitoring system 32 and a schematic diagram of a method for triaging a patient 36 based on an ejection fraction measurement of the patient 36. As Figure 5 shown, the hemodynamic monitoring system 32 includes a hemodynamic monitor 10 and a hemodynamic sensor 34. In Figure 5 an embodiment, the hemodynamic sensor 34 is a non-invasive hemodynamic sensor 26 (described in detail above with reference to Figure 3 ), which can be attached to the patient 36 via one or more finger cots to sense data representing the arterial pressure of the patient 36. In Figure 5 an embodiment, the hemodynamic monitor 10 is a compact wearable unit that can be strapped to the arm of the patient 36 and connected to the hemodynamic sensor 34 to receive sensed data representing the arterial pressure of the patient 36. Figure 5 An embodiment of the hemodynamic monitoring system 32 can operate and function as described above with reference to Figure 4 to determine an ejection fraction measurement of the patient 36. During a routine physical examination in a primary care physician's office, the patient 36 can be quickly tested and triaged for heart failure risk by connecting the hemodynamic monitoring system 32 to the hand and arm of the patient 36 and feeding the sensed hemodynamic data of the patient 36 into the hemodynamic monitor 10. After a few minutes (such as five minutes) of feeding the sensed hemodynamic data of the patient 36 into the hemodynamic monitor 10, the hemodynamic monitor 10 will output an ejection fraction measurement of the patient 36 to the display 12. In some embodiments, the hemodynamic monitor 10 can also output the ejection fraction measurement of the patient 36 to a display on the mobile device of the patient 36.

[0044] The hemodynamic monitor 10 can color-code and / or score the ejection fraction measurement of the patient 36 on the display 12 based on whether the ejection fraction measurement is normal, borderline, or low. As described above with reference to Figure 4 , a normal ejection fraction measurement is above fifty percent, a borderline ejection fraction measurement is between forty-one and forty-nine percent, and a low ejection fraction measurement is forty percent or lower. If the hemodynamic monitor 10 determines that the patient 36 has a normal ejection fraction measurement, the hemodynamic monitor 10 can output a green score with a positive value to the display 12. If the hemodynamic monitor 10 determines that the patient 36 has a borderline ejection fraction measurement, the hemodynamic monitor can output a yellow score with a neutral or zero value to the display 12. If the hemodynamic monitor 10 determines that the patient 36 has a low ejection fraction measurement, the hemodynamic monitor 10 can output a red score with a negative value to the display 12.

[0045] A healthcare worker 38 in this scenario ( Figure 4 as shown) can be a primary care physician or nurse performing a routine physical examination of patient 36. Once the hemodynamic monitor 10 outputs the ejection fraction measurement of patient 36 to the display 12 after monitoring and processing the sensed hemodynamic data of patient 36 for a few minutes, the healthcare worker 38 can triage patient 36 based on the ejection fraction measurement of patient 36. If the ejection fraction measurement of patient 36 is indicated as low on the display 12, the healthcare worker 38 can inform patient 36 that patient 36 may be experiencing heart failure and that patient 36 should immediately seek further testing, examination, and treatment by a cardiovascular specialist. Then the healthcare worker 38 can refer patient 36 to a cardiovascular specialist for more intensive examinations such as echocardiogram, multiple gated acquisition (MUGA) scan, computed tomography (CT) scan, cardiac catheterization, and / or nuclear stress test. If the ejection fraction measurement of patient 36 in the display 12 is borderline, the healthcare worker 38 can inform patient 36 that patient 36 may be at risk of heart failure and that patient 36 should seek further testing, examination, and treatment by a cardiovascular specialist within a reasonable amount of time. If the ejection fraction measurement of patient 36 in the display 12 is normal, the healthcare worker 38 can inform patient 36 that patient 36 has a low risk of developing heart failure and does not require additional testing. As discussed below with reference to Figures 6-8 a clinical dataset can be used to train the machine learning model of the hemodynamic monitor 10 to identify input features in the arterial pressure waveform of patient 36 and use those input features to determine the ejection fraction measurement of patient 36.

[0046] Figure 6 is a diagram of clinical data 60 for data mining and machine training of the hemodynamic monitor 10 of the hemodynamic monitoring system 32. The clinical data 60 includes a first clinical dataset 61, a second clinical dataset 62, and a third clinical dataset 63.

[0047] The first clinical dataset 61 contains a set of arterial pressure waveforms recorded from a first group of individuals, each of whom has a confirmed ejection fraction measurement of over fifty percent normal. The first clinical dataset 61 can be collected from the first group of individuals by an invasive hemodynamic sensor (such as Figure 2 the hemodynamic sensor 16 shown), and can also be collected by a non-invasive hemodynamic sensor (such as Figure 3Collected by the hemodynamic sensor 26) shown. When each individual in the first clinical dataset 61 is connected to the hemodynamic sensor, the hemodynamic sensor records the arterial pressure waveform of that individual, and the arterial pressure waveform of that individual is labeled with a first label such that the arterial pressure waveform can ultimately be added to the first clinical dataset 61. Adding the first label to the arterial pressure waveforms of the individuals in the first group also allows the first clinical dataset 61 to be collected and stored at a common location together with the second clinical dataset 62 and the third clinical dataset 63 without the arterial pressure waveforms of the first clinical dataset 61 being lost or confused among the arterial pressure waveforms of the second clinical dataset 62 and the third clinical dataset 63.

[0048] After the arterial pressure waveforms of the first clinical dataset 61 have been collected and labeled with the first label, the arterial pressure waveforms of the first clinical dataset 61 are ready for data mining and machine training of the hemodynamic monitor 10. The arterial pressure waveforms of the first clinical dataset 61 are mined data and are used to machine train the hemodynamic monitor 10 to determine a first subset of input features. As referred to above Figure 4 discussed, the first subset of input features is those input features that the third module 52 will use to determine whether the patient 36 has a normal ejection fraction measurement. As will be referred to below Figures 7-8 further discussed, waveform analysis is performed on the first clinical dataset 61 to calculate a plurality of signal measurements, and then these signal measurements are used to calculate a first subset of input features that optimally detect and measure the normal ejection fraction from the arterial pressure waveform.

[0049] The second clinical dataset 61 contains a collection of arterial pressure waveforms recorded from a second group of individuals, each of whom has a confirmed low ejection fraction measurement of less than or equal to forty percent. The second clinical dataset 61 can be collected from the second group of individuals by an invasive hemodynamic sensor (such as Figure 2 the hemodynamic sensor 16) shown, and can also be collected by a non-invasive hemodynamic sensor (such as Figure 3 the hemodynamic sensor 26) shown. When each individual in the second clinical dataset 62 is connected to the hemodynamic sensor, the hemodynamic sensor records the arterial pressure waveform of that individual, and the arterial pressure waveform of that individual is labeled with a second label such that the arterial pressure waveform can ultimately be added to the second clinical dataset 62. Adding the second label to the arterial pressure waveforms of the individuals in the second group also allows the second clinical dataset 62 to be collected and stored at a common location together with the first clinical dataset 61 and the third clinical dataset 63 without the arterial pressure waveforms of the second clinical dataset 62 being lost or confused among the arterial pressure waveforms of the first clinical dataset 61 and the third clinical dataset 63.

[0050] After the arterial pressure waveforms of the second clinical dataset 62 have been collected and labeled with the second label, the arterial pressure waveforms of the second clinical dataset 62 are ready for data mining and machine training of the hemodynamic monitor 10. The arterial pressure waveforms of the second clinical dataset 62 are mined data and are used for machine training of the hemodynamic monitor 10 to determine a second subset of input features. As discussed above with reference to Figure 4 the second subset of input features are those input features that the third module 52 will use to determine whether the patient 36 has a low ejection fraction measurement. As will be discussed below with reference to Figures 7-8 the waveform analysis is performed on the second clinical dataset 62 to calculate a plurality of signal measurements, and then these signal measurements are used to calculate a second subset of input features that optimally detect and measure low ejection fraction from the arterial pressure waveform.

[0051] The third clinical dataset 63 contains a set of arterial pressure waveforms recorded from a third group of individuals, each of whom has a confirmed critical ejection fraction measurement between forty-one and forty-nine percent. The third clinical dataset 61 can be collected from the third group of individuals by an invasive hemodynamic sensor (such as Figure 2 the hemodynamic sensor 16 shown), and can also be collected by a non-invasive hemodynamic sensor (such as Figure 3 the hemodynamic sensor 26 shown). When each individual in the third clinical dataset 62 is connected to the hemodynamic sensor, the hemodynamic sensor records the individual's arterial pressure waveform, and the individual's arterial pressure waveform is labeled with the third label so that the arterial pressure waveform can ultimately be added to the third clinical dataset 62. Adding the third label to the arterial pressure waveforms of the individuals in the third group also allows the third clinical dataset 63 to be collected and stored in a common location with the first clinical dataset 61 and the second clinical dataset 62 without losing or confusing the arterial pressure waveforms of the third clinical dataset 63 among the arterial pressure waveforms of the first clinical dataset 61 and the second clinical dataset 62.

[0052] After the arterial pressure waveforms of the third clinical dataset 62 have been collected and labeled with the third label, the arterial pressure waveforms of the third clinical dataset 62 are ready for data mining and machine training of the hemodynamic monitor 10. The arterial pressure waveforms of the third clinical dataset 63 are mined data and are used for machine training of the hemodynamic monitor 10 to determine a third subset of input features. As discussed above with reference to Figure 4 the third subset of input features are those input features that the third module 52 will use to determine whether the patient 36 has a critical ejection fraction measurement. As will be discussed below with reference to Figures 7-8For further discussion, waveform analysis is performed on the third clinical dataset 62 to calculate a plurality of signal measurements, and then these signal measurements are used to calculate a third subset of input features that optimally detect and measure the critical ejection fraction from the arterial pressure waveform.

[0053] Figure 7 is a flowchart of a method 70 for data mining clinical data 60 from Figure 6 to machine train a machine learning model of the hemodynamic monitor 10. The method 70 will be discussed Figure 7 in the context of the method 70, also with reference to Figure 8 . The method 70 is applied to each of the first clinical dataset 61, the second clinical dataset 62, and the third clinical dataset 63 to train the hemodynamic monitor to find the input features (including the first subset, the second subset, and the third subset of the input features) previously referenced in Figure 4 and Figure 6 . The method 70 will be described as applied to the arterial pressure waveform of the first clinical dataset 61.

[0054] To machine train the hemodynamic monitor 10 to identify Figure 4 the first subset of the input features described in, the first subset of the input features is first determined by applying the method 70 to the arterial pressure waveform of the first clinical dataset 61 of the clinical data 60. The first step 72 of the method 70 is to perform waveform analysis on the arterial pressure waveforms collected in the first clinical dataset 61 to calculate a plurality of signal measurements of the first clinical dataset 61. Performing waveform analysis on the arterial pressure waveforms of the first clinical dataset 61 can include identifying individual cardiac cycles in each arterial pressure waveform of the first clinical dataset 61. Figure 8 An example graph is provided showing an example trace of an arterial pressure waveform with individual cardiac cycles identified and magnified. Next, performing waveform analysis on the arterial pressure waveforms of the first clinical dataset 61 can include identifying dicrotic notches in each individual cardiac cycle of each arterial pressure waveform of the first clinical dataset 61, similar to the example shown in Figure 8 . Next, waveform analysis of the arterial pressure waveforms of the first clinical dataset 61 includes identifying the systolic upstroke, systolic decay, and diastolic phases in each individual cardiac cycle of each arterial pressure waveform of the first clinical dataset 61, similar to the example shown in Figure 8 .

[0055] Signal measurements are extracted from each of the systolic upstroke, systolic decay, and diastolic phases of each individual cardiac cycle of each arterial pressure waveform of the first clinical dataset 61. The signal measurements can correspond to hemodynamic effects from each of the systolic upstroke, systolic decay, and diastolic phases of each individual cardiac cycle. These hemodynamic effects can include contractility, aortic compliance, stroke volume, vascular tone, afterload, and the entire cardiac cycle. The signal measurements calculated or extracted by the waveform analysis of the first step 72 of method 70 include the mean, maximum, minimum, duration, area, standard deviation, derivative, and / or morphological measurements from each of the systolic upstroke, systolic decay, and diastolic phases of each individual cardiac cycle. The signal measurements can also include heart rate, respiratory rate, stroke volume, pulse pressure, pulse pressure variability, stroke volume variability, mean arterial pressure (MAP), systolic blood pressure (SYS), diastolic blood pressure (DIA), heart rate variability, cardiac output, peripheral resistance, vascular compliance, and / or left ventricular contractility extracted from each individual cardiac cycle of each arterial pressure waveform of the first clinical dataset 61.

[0056] After determining the signal measurements of the first clinical dataset 61, step 74 of method 70 is performed on the signal measurements of the first clinical dataset 61. Step 74 of method 70 calculates combined measurements between the signal measurements of the first clinical dataset 61. Calculating the combined measurements between the signal measurements of the first clinical dataset 61 can include performing Figure 7 the steps 76, 78, 80, and 82 shown. Step 76 is performed by arbitrarily selecting a subset of the signal measurements (such as a subset of the signal measurements) from the signal measurements of the first clinical dataset 61. Next, different orders of power of each signal measurement in this subset of signal measurements are calculated to generate the powers of this subset of signal measurements, as Figure 7 shown in step 78. In Figure 7In step 80, the powers of this subset of signal measurements are then multiplied to generate a product of the powers of this subset of signal measurements. Step 82 includes performing a receiver operating characteristic (ROC) analysis of the product to obtain a combined measurement of this subset of signal measurements. Steps 76, 78, 80, and 82 are repeated until all combined measurements are calculated between all signal measurements of the first clinical dataset 61. The final step 84 includes selecting the signal measurements with the most predictive top combined measurements (i.e., the combined measurements that meet the threshold prediction criteria) as the top signal measurements of the first clinical dataset 61 and labeling them as the first subset of input features. In the case where the first subset of input features is determined, the hemodynamic monitor 10 is trained or programmed to perform waveform analysis on the arterial pressure waveform of the patient 36 ( Figure 4 as shown) and extract the first subset of input features from the arterial pressure waveform of the patient 36, and use the first subset of input features to determine whether the patient 36 has a normal ejection fraction measurement.

[0057] Similar to how method 70 is applied to the arterial pressure waveform of the first clinical dataset 61 to determine the first subset of input features, method 70 is applied to the second clinical dataset 62 to determine the second subset of input features. Similarly, method 70 is applied to the third clinical dataset 63 to determine the third subset of input features.

[0058] Possible embodiments discussion

[0059] The following is a non-exclusive description of possible embodiments of the present invention.

[0060] In one example, a method for risk triage of heart failure in a patient includes receiving sensed hemodynamic data representing the arterial pressure waveform of the patient through a hemodynamic monitor. The hemodynamic monitor performs waveform analysis of the sensed hemodynamic data to calculate a plurality of signal measurements of the sensed hemodynamic data. The hemodynamic monitor extracts input features from the plurality of signal measurements indicating the ejection fraction of the patient. The hemodynamic monitor determines the ejection fraction of the patient based on the input features and outputs the ejection fraction of the patient to a display. When the ejection fraction is less than or equal to forty percent, the hemodynamic monitor alerts the patient of a low ejection fraction. When the ejection fraction is between forty-one and forty-nine percent, the hemodynamic monitor alerts the patient of a borderline ejection fraction. When the ejection fraction is above fifty percent, the hemodynamic monitor alerts the patient of a normal ejection fraction.

[0061] The method of the preceding paragraph can optionally include, additionally and / or alternatively, any one or more of the following features, configurations, and / or additional components listed below.

[0062] A further embodiment of the foregoing method further includes: training a hemodynamic monitor to determine a patient's ejection fraction, wherein training the hemodynamic monitor includes: collecting a first clinical data set containing arterial pressure waveforms from a first group of individuals having normal ejection fraction measurements as described above; collecting a second clinical data set containing arterial pressure waveforms from a second group of individuals having low ejection fraction measurements; collecting a third clinical data set containing arterial pressure waveforms from a third group of individuals having critical ejection fraction measurements between forty-one and forty-nine percent; performing waveform analysis of the arterial pressure waveforms of the first clinical data set, the second clinical data set, and the third clinical data set to calculate a plurality of waveform signal measurements; and determining an input feature by calculating a combined measurement between the plurality of waveform signal measurements, and selecting a leading signal measurement from the plurality of waveform signal measurements having the most predictive combined measurement and labeling the leading signal measurement as the input feature.

[0063] In another example, a system for risk triage of heart failure in a patient includes a hemodynamic sensor that generates hemodynamic data representing the patient's arterial pressure waveform. The system further includes a user interface having a display for displaying to a medical staff the patient's ejection fraction measurement. Ejection fraction software code is stored in the system memory of the system. The system includes a processor configured to execute the ejection fraction software code to perform: waveform analysis of the hemodynamic data to determine a plurality of signal measurements; extracting an input feature indicative of the patient's ejection fraction measurement from the plurality of signal measurements; determining the patient's ejection fraction measurement based on the input feature; and outputting the ejection fraction measurement to the display of the user interface.

[0064] 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 listed below.

[0065] A further embodiment of the foregoing system, wherein input features of the ejection fraction software code are determined by machine learning, and wherein the machine learning includes: collecting a first clinical data set containing arterial pressure waveforms from a first group of individuals having normal ejection fraction measurements of more than fifty percent; collecting a second clinical data set containing arterial pressure waveforms from a second group of individuals having low ejection fraction measurements of less than or equal to forty percent; collecting a third clinical data set containing arterial pressure waveforms from a third group of individuals having borderline ejection fraction measurements between forty-one and forty-nine percent; performing waveform analysis of the arterial pressure waveforms of the first clinical data set, the second clinical data set, and the third clinical data set to calculate a plurality of waveform signal measurements; and determining the input features by calculating a combined measurement between the plurality of waveform signal measurements, and selecting and labeling as the input feature the leading signal measurement from among the plurality of waveform signal measurements having the most predictive combined measurement.

[0066] A further embodiment of the foregoing system, wherein performing waveform analysis of the labeled arterial pressure waveforms of the first clinical data set, the second clinical data set, and the third clinical data set to calculate a plurality of waveform signal measurements includes: identifying independent cardiac cycles in each arterial pressure waveform of the first clinical data set, the second clinical data set, and the third clinical data set; identifying dicrotic notches in each independent cardiac cycle; identifying systolic upstrokes, systolic decays, and diastolic phases in each independent cardiac cycle; and extracting a plurality of waveform signal measurements from each of the systolic upstrokes, systolic decays, and diastolic phases of each independent cardiac cycle.

[0067] A further embodiment of the foregoing system, wherein the plurality of waveform signal measurements correspond to hemodynamic effects from each of the systolic upstrokes, systolic decays, and diastolic phases of each independent cardiac cycle, and wherein the hemodynamic effects include contractility, aortic compliance, stroke volume, vascular tone, afterload, and total cardiac cycle.

[0068] A further embodiment of the foregoing system, wherein the plurality of waveform signal measurements include mean values, maximum values, minimum values, durations, areas, standard deviations, derivatives, and / or morphological measurements from each of the systolic upstrokes, systolic decays, and diastolic phases of each independent cardiac cycle.

[0069] A further embodiment of the foregoing system, wherein the plurality of waveform signal measurements include heart rate, respiratory rate, stroke volume, pulse pressure, pulse pressure variability, stroke volume variability, mean arterial pressure (MAP), systolic blood pressure (SYS), diastolic blood pressure (DIA), heart rate variability, cardiac output, peripheral resistance, vascular compliance, and / or left ventricular contractility extracted from each independent cardiac cycle.

[0070] A further embodiment of the foregoing system, wherein calculating a combined measurement between a plurality of waveform signal measurements of a first clinical data set, a second clinical data set, and a third clinical data set includes: performing step one by arbitrarily selecting a subset of signal measurements from the plurality of waveform signal measurements; performing step two by calculating different powers of each of the signal measurements in this subset to generate powers of the subset of signal measurements; performing step three by multiplying the powers of the subset of signal measurements to generate a product of the powers of the subset of signal measurements; performing step four by performing a receiver operating characteristic (ROC) analysis of the product to obtain a combined measurement of the subset of signal measurements; and repeating steps one, two, three, and four until all combined measurements are calculated between all of the plurality of waveform signal measurements.

[0071] A further embodiment of the foregoing system, wherein the hemodynamic sensor is a non-invasive hemodynamic sensor capable of being attached to a patient's limb.

[0072] A further embodiment of the foregoing system, wherein the hemodynamic sensor is a hemodynamic sensor based on a minimally invasive arterial catheter.

[0073] A further embodiment of the foregoing system, wherein the hemodynamic sensor generates hemodynamic data as an analog hemodynamic sensor signal representing the patient's arterial pressure waveform.

[0074] A further embodiment of the foregoing system further includes: an analog-to-digital converter that converts the analog hemodynamic sensor signal into digital hemodynamic data representing the patient's arterial pressure waveform.

[0075] In another example, a method for risk triage of heart failure in a patient is disclosed. The method includes receiving sensed hemodynamic data representing the patient's arterial pressure waveform through a hemodynamic monitor. The hemodynamic monitor performs waveform analysis of the sensed hemodynamic data to calculate a plurality of signal measurements of the sensed hemodynamic data. The hemodynamic monitor extracts input features from the plurality of signal measurements indicating the patient's ejection fraction. The hemodynamic monitor determines the patient's ejection fraction based on the input features and outputs the patient's ejection fraction to a display and / or a mobile device. When the ejection fraction is less than or equal to forty percent, the hemodynamic monitor alerts the patient or medical staff of a low ejection fraction.

[0076] The method of the previous paragraph can optionally include, additionally and / or alternatively, any one or more of the following features, configurations, and / or additional components listed below.

[0077] A further embodiment of the foregoing method further includes: when the ejection fraction is between forty-one and forty-nine percent, alerting the patient or medical staff that the ejection fraction is critical.

[0078] A further embodiment of the foregoing method further includes: when the ejection fraction is above fifty percent, alerting the patient or medical staff that the ejection fraction is normal.

[0079] A further embodiment of the foregoing method, wherein training the hemodynamic monitor to determine the ejection fraction of a patient further includes: collecting a first clinical data set containing arterial pressure waveforms from a first group of individuals having normal ejection fraction measurements above fifty percent; labeling each arterial pressure waveform of the first clinical data set with a first label; performing waveform analysis of the labeled arterial pressure waveforms of the first clinical data set to calculate a plurality of waveform signal measurements of the first clinical data set; and determining a first subset of input features by calculating a combined measurement between the plurality of waveform signal measurements of the first clinical data set, and selecting the leading signal measurement from the plurality of waveform signal measurements of the first clinical data set having the most predictive combined measurement and labeling the leading signal measurement of the first clinical data set as the first subset of input features.

[0080] A further embodiment of the foregoing method, wherein training the hemodynamic monitor to determine the ejection fraction of a patient further includes: collecting a second clinical data set containing arterial pressure waveforms from a second group of individuals having low ejection fraction measurements less than or equal to forty percent; labeling each arterial pressure waveform of the second clinical data set with a second label; performing waveform analysis of the labeled arterial pressure waveforms of the second clinical data set to calculate a plurality of waveform signal measurements of the second clinical data set; and determining a second subset of input features by calculating a combined measurement between the plurality of waveform signal measurements of the second clinical data set, and selecting the leading signal measurement from the plurality of waveform signal measurements of the second clinical data set having the most predictive combined measurement and labeling the leading signal measurement of the second clinical data set as the second subset of input features.

[0081] A further embodiment of the foregoing method, wherein training a hemodynamic monitor to determine a patient's ejection fraction further comprises: collecting a third clinical data set comprising arterial pressure waveforms from a third group of individuals having critical ejection fraction measurements between forty-one and forty-nine percent; labeling each arterial pressure waveform of the third clinical data set with a third label; performing waveform analysis of the labeled arterial pressure waveforms of the third clinical data set to calculate a plurality of waveform signal measurements of the third clinical data set; and determining a third subset of input features by calculating a combined measurement between the plurality of waveform signal measurements of the third clinical data set, and selecting a leading signal measurement from among the plurality of waveform signal measurements of the third clinical data set having the most predictive combined measurement and labeling the leading signal measurement of the third clinical data set as the third subset of input features.

[0082] A further embodiment of the foregoing method, wherein performing waveform analysis of the labeled arterial pressure waveforms of the first clinical data set to calculate a plurality of waveform signal measurements of the first clinical data set comprises: identifying individual cardiac cycles in each arterial pressure waveform of the first clinical data set; identifying dicrotic notches in each individual cardiac cycle in each arterial pressure waveform of the first clinical data set; identifying systolic upstrokes, systolic decays, and diastolic phases in each individual cardiac cycle in each arterial pressure waveform of the first clinical data set; and extracting a plurality of waveform signal measurements of the first clinical data set from each of the systolic upstrokes, systolic decays, and diastolic phases in each individual cardiac cycle in each arterial pressure waveform of the first clinical data set.

[0083] A further embodiment of the foregoing method, wherein the plurality of waveform signal measurements of the first clinical data set correspond to hemodynamic effects from each of the systolic upstrokes, systolic decays, and diastolic phases in each individual cardiac cycle in each arterial pressure waveform from the first clinical data set, and wherein the hemodynamic effects include contractility, aortic compliance, stroke volume, vascular tone, afterload, and entire cardiac cycle.

[0084] A further embodiment of the foregoing method, wherein the plurality of waveform signal measurements of the first clinical data set include means, maxima, minima, durations, areas, standard deviations, derivatives, and / or morphological measurements from each of the systolic upstrokes, systolic decays, and diastolic phases in each individual cardiac cycle in each arterial pressure waveform from the first clinical data set.

[0085] A further embodiment of the foregoing method, wherein the plurality of waveform signal measurements of the first clinical dataset include heart rate, respiratory rate, stroke volume, pulse pressure, pulse pressure variability, stroke volume variability, mean arterial pressure (MAP), systolic blood pressure (SYS), diastolic blood pressure (DIA), heart rate variability, cardiac output, peripheral resistance, vascular compliance, and / or left ventricular contractility extracted from each independent cardiac cycle in each arterial pressure waveform of the first clinical dataset.

[0086] A further embodiment of the foregoing method, wherein calculating a combined measurement between the plurality of waveform signal measurements of the first clinical dataset includes: performing step one by arbitrarily selecting a subset of signal measurements from the plurality of waveform signal measurements of the first clinical dataset; performing step two by calculating different powers of each of the signal measurements in this subset of signal measurements from the plurality of waveform signal measurements of the first clinical dataset to generate powers of the signal measurements in this subset of signal measurements from the plurality of waveform signal measurements of the first clinical dataset; performing step three by multiplying the powers of the signal measurements in this subset of signal measurements from the plurality of waveform signal measurements of the first clinical dataset to generate a product of the powers of the signal measurements in this subset of signal measurements from the plurality of waveform signal measurements of the first clinical dataset; performing step four by performing a receiver operating characteristic (ROC) analysis on the product of the powers of the signal measurements in this subset of signal measurements from the plurality of waveform signal measurements of the first clinical dataset to obtain a combined measurement of the product of the powers of the signal measurements in this subset of signal measurements from the plurality of waveform signal measurements of the first clinical dataset; and repeating steps one, two, three, and four until all combined measurements are calculated between all of the plurality of waveform signal measurements of the first clinical dataset.

[0087] A further embodiment of the foregoing method, wherein performing waveform analysis on the labeled arterial pressure waveforms of the second clinical dataset to calculate the plurality of waveform signal measurements of the second clinical dataset includes: identifying independent cardiac cycles in each arterial pressure waveform of the second clinical dataset; identifying dicrotic notches in each independent cardiac cycle in each arterial pressure waveform of the second clinical dataset; identifying systolic upstrokes, systolic decays, and diastolic phases in each independent cardiac cycle in each arterial pressure waveform of the second clinical dataset; and extracting the plurality of waveform signal measurements of the second clinical dataset from each of the systolic upstrokes, systolic decays, and diastolic phases in each independent cardiac cycle in each arterial pressure waveform of the second clinical dataset.

[0088] A further embodiment of the foregoing method, wherein the plurality of waveform signal measurements of the second clinical dataset correspond to the hemodynamic effects of each of the systolic upstroke, systolic decay, and diastole of each independent cardiac cycle in each arterial pressure waveform from the second clinical dataset, and wherein the hemodynamic effects include contractility, aortic compliance, stroke volume, vascular tone, afterload, and the entire cardiac cycle.

[0089] A further embodiment of the foregoing method, wherein the plurality of waveform signal measurements of the second clinical dataset include the mean, maximum, minimum, duration, area, standard deviation, derivative, and / or morphological measurements of each of the systolic upstroke, systolic decay, and diastole of each independent cardiac cycle in each arterial pressure waveform from the second clinical dataset.

[0090] A further embodiment of the foregoing method, wherein the plurality of waveform signal measurements of the second clinical dataset include heart rate, respiratory rate, stroke volume, pulse pressure, pulse pressure variability, stroke volume variability, mean arterial pressure (MAP), systolic blood pressure (SYS), diastolic blood pressure (DIA), heart rate variability, cardiac output, peripheral resistance, vascular compliance, and / or left ventricular contractility extracted from each independent cardiac cycle in each arterial pressure waveform from the second clinical dataset.

[0091] A further embodiment of the foregoing method, wherein calculating the combined measurements between the plurality of waveform signal measurements of the second clinical dataset includes: performing step one by arbitrarily selecting a subset of signal measurements from the plurality of waveform signal measurements of the second clinical dataset; performing step two by calculating different powers of each of the signal measurements in this subset of signal measurements from the plurality of waveform signal measurements of the second clinical dataset to generate the powers of the signal measurements in this subset of signal measurements from the plurality of waveform signal measurements of the second clinical dataset; performing step three by multiplying the powers of the signal measurements in this subset of signal measurements from the plurality of waveform signal measurements of the second clinical dataset to generate the product of the powers of the signal measurements in this subset of signal measurements from the plurality of waveform signal measurements of the second clinical dataset; performing step four by performing a receiver operating characteristic (ROC) analysis on the product of the powers of the signal measurements in this subset of signal measurements from the plurality of waveform signal measurements of the second clinical dataset to obtain the combined measurement of the product of the powers of the signal measurements in this subset of signal measurements from the plurality of waveform signal measurements of the second clinical dataset; and repeating steps one, two, three, and four until all of the combined measurements have been calculated between all of the plurality of waveform signal measurements of the second clinical dataset.

[0092] A further embodiment of the foregoing method, wherein performing waveform analysis of the labeled arterial pressure waveforms of the third clinical dataset to calculate a plurality of waveform signal measurements of the third clinical dataset includes: identifying individual cardiac cycles in each arterial pressure waveform of the third clinical dataset; identifying dicrotic notches in each individual cardiac cycle in each arterial pressure waveform of the third clinical dataset; identifying systolic upstrokes, systolic decays, and diastolic phases in each individual cardiac cycle in each arterial pressure waveform of the third clinical dataset; and extracting a plurality of waveform signal measurements of the third clinical dataset from each of the systolic upstrokes, systolic decays, and diastolic phases in each individual cardiac cycle in each arterial pressure waveform of the third clinical dataset.

[0093] A further embodiment of the foregoing method, wherein the plurality of waveform signal measurements of the third clinical dataset correspond to the hemodynamic effects from each of the systolic upstrokes, systolic decays, and diastolic phases in each individual cardiac cycle from each arterial pressure waveform of the third clinical dataset, and wherein the hemodynamic effects include contractility, aortic compliance, stroke volume, vascular tone, afterload, and total cardiac cycle.

[0094] A further embodiment of the foregoing method, wherein the plurality of waveform signal measurements of the third clinical dataset include the mean, maximum, minimum, duration, area, standard deviation, derivative, and / or morphological measurements from each of the systolic upstrokes, systolic decays, and diastolic phases in each individual cardiac cycle from each arterial pressure waveform of the third clinical dataset.

[0095] A further embodiment of the foregoing method, wherein the plurality of waveform signal measurements of the third clinical dataset include heart rate, respiratory rate, stroke volume, pulse pressure, pulse pressure variability, stroke volume variability, mean arterial pressure (MAP), systolic blood pressure (SYS), diastolic blood pressure (DIA), heart rate variability, cardiac output, peripheral resistance, vascular compliance, and / or left ventricular contractility extracted from each individual cardiac cycle in each arterial pressure waveform of the third clinical dataset.

[0096] A further embodiment of the foregoing method, wherein calculating a combined measurement between multiple waveform signal measurements of a third clinical dataset includes: performing step one by arbitrarily selecting a subset of signal measurements from the multiple waveform signal measurements of the third clinical dataset; performing step two by calculating different powers of each signal measurement among this subset of signal measurements from the multiple waveform signal measurements of the third clinical dataset to generate powers of this subset of signal measurements from the multiple waveform signal measurements of the third clinical dataset; performing step three by multiplying the powers of this subset of signal measurements from the multiple waveform signal measurements of the third clinical dataset to generate a product of the powers of this subset of signal measurements from the multiple waveform signal measurements of the third clinical dataset; performing step four by performing a receiver operating characteristic (ROC) analysis on the product of the powers of this subset of signal measurements from the multiple waveform signal measurements of the third clinical dataset to obtain a combined measurement of the product of the powers of this subset of signal measurements from the multiple waveform signal measurements of the third clinical dataset; and repeating steps one, two, three, and four until all combined measurements are calculated between all of the multiple waveform signal measurements of the third clinical dataset.

[0097] In another example, a method of training a hemodynamic monitor for determining a patient's ejection fraction is disclosed. The method of training a hemodynamic monitor includes collecting a first clinical dataset containing arterial pressure waveforms from a first group of individuals having normal ejection fraction measurements of more than fifty percent. A second clinical dataset is collected, the second clinical dataset containing arterial pressure waveforms from a second group of individuals having low ejection fraction measurements of less than or equal to forty percent. The method further includes collecting a third clinical dataset, the third clinical dataset containing arterial pressure waveforms from a third group of individuals having critical ejection fraction measurements between forty-one and forty-nine percent. Performing waveform analysis on the arterial pressure waveforms of the first clinical dataset, the second clinical dataset, and the third clinical dataset to calculate multiple waveform signal measurements. Determining input features by calculating combined measurements between the multiple waveform signal measurements and selecting the top signal measurement from among the multiple waveform signal measurements having the most predictive combined measurement and labeling the top signal measurement as an input feature. The input features are stored in the memory of the hemodynamic monitor.

[0098] The method of the previous paragraph can optionally include, additionally and / or alternatively, any one or more of the following features, configurations, and / or additional components listed below.

[0099] A further embodiment of the foregoing method further includes: connecting a hemodynamic sensor to a hemodynamic monitor and a patient to input a sensed arterial pressure waveform of the patient into the hemodynamic monitor; extracting, by a processor of the hemodynamic monitoring, values of input features of the sensed arterial pressure waveform of the patient; determining, by the processor of the hemodynamic monitor, an ejection fraction of the patient based on the values of the input features of the sensed arterial pressure waveform; and outputting the ejection fraction of the patient to a display and / or a mobile device.

[0100] A further embodiment of the foregoing method further includes: alerting the patient and / or medical staff of a low ejection fraction when the ejection fraction is less than or equal to forty percent.

[0101] A further embodiment of the foregoing method further includes: alerting the patient and / or medical staff of a borderline ejection fraction when the ejection fraction is between forty-one and forty-nine percent.

[0102] A further embodiment of the foregoing method further includes: alerting the patient and / or medical staff of a normal ejection fraction when the ejection fraction is above fifty percent.

[0103] In another example, a hemodynamic monitor for detecting heart failure is disclosed. The hemodynamic monitor includes a non-invasive blood pressure sensor, the non-invasive blood pressure sensor including: an inflatable blood pressure cuff; a pressure controller pneumatically connected to the inflatable blood pressure cuff; and an optical transmitter and an optical receiver electrically connected to the pressure controller. The hemodynamic monitor further includes an integrated hardware unit having a system processor, a system memory, and a display with a user interface. The system memory includes instructions that, when executed by the system processor, are configured to: adjust the pressure within the inflatable blood pressure cuff by the pressure controller to maintain a constant volume of the patient's artery for a period of time based on a feedback signal generated by the optical transmitter and the optical receiver; generate arterial pressure waveform data of the patient based on the adjusted pressure within the inflatable blood pressure cuff over a period of time; extract a plurality of signal measurements from the arterial pressure waveform data of the patient; extract input features from the plurality of signal measurements indicative of an ejection fraction score of the patient; determine the ejection fraction score of the patient based on the extracted input features; generate a first sensory alert signal configured to generate a first sensory alert indicating that the patient has a low ejection fraction when the ejection fraction score exceeds a threshold score, or generate a second sensory alert signal configured to generate a second sensory alert indicating that the patient does not have a low ejection fraction when the ejection fraction score is below the threshold score; transmit the first sensory alert signal or the second sensory alert signal to the user interface; and output the first sensory alert or the second sensory alert through the user interface.

[0104] The hemodynamic monitor of the previous paragraph can optionally include, additionally and / or alternatively, any one or more of the following features, configurations, and / or additional components listed below.

[0105] A further embodiment of the foregoing hemodynamic monitor, wherein the input feature is determined by machine learning, and the machine learning includes: collecting a first clinical data set containing arterial pressure waveforms from a first group of individuals having normal ejection fraction measurements of more than fifty percent; collecting a second clinical data set containing arterial pressure waveforms from a second group of individuals having low ejection fraction measurements of less than or equal to forty percent; collecting a third clinical data set containing arterial pressure waveforms from a third group of individuals having critical ejection fraction measurements between forty-one and forty-nine percent; performing waveform analysis of the arterial pressure waveforms of the first clinical data set, the second clinical data set, and the third clinical data set to calculate a plurality of waveform signal measurements; and determining the input feature by calculating a combined measurement between the plurality of waveform signal measurements, and selecting the leading signal measurement from the plurality of waveform signal measurements having the most predictive combined measurement and marking the leading signal measurement as the input feature.

[0106] A further embodiment of the foregoing hemodynamic monitor, wherein performing waveform analysis of the arterial pressure waveforms of the first clinical data set, the second clinical data set, and the third clinical data set to calculate a plurality of waveform signal measurements includes: identifying independent cardiac cycles in each arterial pressure waveform of the first clinical data set, the second clinical data set, and the third clinical data set; identifying dicrotic notches in each independent cardiac cycle; identifying systolic upstrokes, systolic decays, and diastolic phases in each independent cardiac cycle; and extracting a plurality of waveform signal measurements from each of the systolic upstrokes, systolic decays, and diastolic phases of each independent cardiac cycle.

[0107] A further embodiment of the foregoing hemodynamic monitor, wherein the plurality of waveform signal measurements correspond to hemodynamic effects from each of the systolic upstrokes, systolic decays, and diastolic phases of each independent cardiac cycle, and wherein the hemodynamic effects include contractility, aortic compliance, stroke volume, vascular tone, afterload, and the entire cardiac cycle.

[0108] A further embodiment of the hemodynamic monitor, wherein: the plurality of waveform signal measurements include the mean, maximum, minimum, duration, area, standard deviation, derivative, and / or morphological measurements of each of the systolic upstroke, systolic decay, and diastolic phases from each independent cardiac cycle; and / or the plurality of waveform signal measurements include the heart rate, respiratory rate, stroke volume, pulse pressure, pulse pressure variability, stroke volume variability, mean arterial pressure (MAP), systolic blood pressure (SYS), diastolic blood pressure (DIA), heart rate variability, cardiac output, peripheral resistance, vascular compliance, and / or left ventricular contractility extracted from each independent cardiac cycle.

[0109] A further embodiment of the hemodynamic monitor, wherein calculating a combined measurement between the plurality of waveform signal measurements of the first clinical data set, the second clinical data set, and the third clinical data set includes: performing step one by arbitrarily selecting a subset of signal measurements from the plurality of waveform signal measurements; performing step two by calculating different powers of each of the signal measurements in this subset to generate the powers of the subset of signal measurements; performing step three by multiplying the powers of the subset of signal measurements to generate the product of the powers of the subset of signal measurements; performing step four by performing a receiver operating characteristic (ROC) analysis of the product to obtain the combined measurement of the subset of signal measurements; and repeating steps one, two, three, and four until all combined measurements are calculated between all of the plurality of waveform signal measurements.

[0110] A further embodiment of the hemodynamic monitor, wherein the input features include a first subset and a second subset, and wherein the instructions, when executed by the system processor, are further configured to: simultaneously extract the first subset and the second subset of the input features from the plurality of signal measurements; simultaneously determine a normal ejection fraction score of the patient from the first subset of the input features and a low ejection fraction score of the patient from the second subset of the input features; output the normal ejection fraction score of the patient and the low ejection fraction score of the patient to a display of the user interface.

[0111] A further embodiment of the hemodynamic monitor, wherein the input features include a third subset, and wherein when executed by the system processor, the instructions are further configured to: simultaneously extract the first subset, the second subset, and the third subset of the input features from the plurality of signal measurements; simultaneously determine a normal ejection fraction score of the patient from the first subset of the input features, a low ejection fraction score of the patient from the second subset of the input features, and a critical ejection fraction score of the patient from the third subset of the input features; output the normal ejection fraction score of the patient, the low ejection fraction score of the patient, and the critical ejection fraction score of the patient to a display of the user interface.

[0112] In another example, a hemodynamic monitor for detecting heart failure is disclosed. The hemodynamic monitor includes an arterial blood pressure sensor having: a housing; a fluid input port connected via tubing to a fluid source; a catheter-side fluid port connected to a catheter inserted into a patient's arterial system; a pressure transducer in fluid communication with the fluid source via the fluid ports; and an I / O cable in electrical communication with the pressure transducer. The hemodynamic monitor further includes an integrated hardware unit having a system processor, a system memory, a display including a user interface, and an analog-to-digital (ADC) converter. The system memory includes instructions that, when executed by the system processor, are configured to: receive an electrical signal from the pressure transducer over a period of time, the electrical signal based on the pressure of the patient's arterial system transmitted through the fluid source; convert the electrical signal into a digital signal; generate arterial pressure waveform data for the patient based on the digital signal; extract a plurality of signal measurements from the arterial pressure waveform data; extract input features from the plurality of signal measurements indicative of the patient's ejection fraction score; determine the patient's ejection fraction score based on the extracted input features; generate a first sensory alert signal configured to generate a first sensory alert indicating that the patient has a low ejection fraction when the ejection fraction score exceeds a threshold score, or generate a second sensory alert signal configured to generate a second sensory alert indicating that the patient does not have a low ejection fraction when the ejection fraction score is below the threshold score; transmit the first sensory alert signal or the second sensory alert signal to the user interface; and output the first sensory alert or the second sensory alert via the user interface.

[0113] The hemodynamic monitor of the previous paragraph can optionally include, additionally and / or alternatively, any one or more of the following features, configurations, and / or additional components listed below.

[0114] A further embodiment of the aforementioned hemodynamic monitor, wherein the input features are determined by machine training, and the machine training includes: collecting a first clinical data set containing arterial pressure waveforms from a first group of individuals having normal ejection fraction measurements of more than fifty percent; collecting a second clinical data set containing arterial pressure waveforms from a second group of individuals having low ejection fraction measurements of less than or equal to forty percent; collecting a third clinical data set containing arterial pressure waveforms from a third group of individuals having critical ejection fraction measurements between forty-one and forty-nine percent; performing waveform analysis of the arterial pressure waveforms of the first clinical data set, the second clinical data set, and the third clinical data set to calculate a plurality of waveform signal measurements; and determining the input features by calculating combined measurements between the plurality of waveform signal measurements and selecting and labeling as the input features the leading signal measurements from among the plurality of waveform signal measurements having the most predictive combined measurements.

[0115] A further embodiment of the foregoing hemodynamic monitor, wherein waveform analysis of arterial pressure waveforms of a first clinical data set, a second clinical data set, and a third clinical data set is performed to calculate a plurality of waveform signal measurements, including: identifying independent cardiac cycles in each of the arterial pressure waveforms of the first clinical data set, the second clinical data set, and the third clinical data set; identifying dicrotic notches in each independent cardiac cycle; identifying systolic upstrokes, systolic decays, and diastolic phases in each independent cardiac cycle; and extracting a plurality of waveform signal measurements from each of the systolic upstrokes, systolic decays, and diastolic phases of each independent cardiac cycle.

[0116] A further embodiment of the foregoing hemodynamic monitor, wherein the plurality of waveform signal measurements correspond to hemodynamic effects from each of the systolic upstrokes, systolic decays, and diastolic phases of each independent cardiac cycle, and wherein the hemodynamic effects include contractility, aortic compliance, stroke volume, vascular tone, afterload, and total cardiac cycle.

[0117] A further embodiment of the foregoing hemodynamic monitor, wherein: the plurality of waveform signal measurements include mean values, maximum values, minimum values, durations, areas, standard deviations, derivatives, and / or morphological measurements from each of the systolic upstrokes, systolic decays, and diastolic phases of each independent cardiac cycle; and / or the plurality of waveform signal measurements include heart rate, respiratory rate, stroke volume, pulse pressure, pulse pressure variability, stroke volume variability, mean arterial pressure (MAP), systolic blood pressure (SYS), diastolic blood pressure (DIA), heart rate variability, cardiac output, peripheral resistance, vascular compliance, and / or left ventricular contractility extracted from each independent cardiac cycle.

[0118] A further embodiment of the foregoing hemodynamic monitor, wherein calculating a combined measurement between the plurality of waveform signal measurements of the first clinical data set, the second clinical data set, and the third clinical data set includes: performing step one by arbitrarily selecting a subset of signal measurements from the plurality of waveform signal measurements; performing step two by calculating different powers of each of the signal measurements in this subset to generate powers of this subset of signal measurements; performing step three by multiplying the powers of this subset of signal measurements to generate a product of the powers of this subset of signal measurements; performing step four by performing a receiver operating characteristic (ROC) analysis of the product to obtain a combined measurement of this subset of signal measurements; and repeating steps one, two, three, and four until all combined measurements between all of the plurality of waveform signal measurements are calculated.

[0119] A further embodiment of the foregoing hemodynamic monitor, wherein the input features include a first subset and a second subset, and wherein when executed by the system processor, the instructions are further configured to: extract the first subset and the second subset of the input features from a plurality of signal measurements simultaneously; determine a normal ejection fraction score of the patient from the first subset of the input features and a low ejection fraction score of the patient from the second subset of the input features simultaneously; determine an ejection fraction measurement of the patient based on the normal ejection fraction score of the patient and the low ejection fraction score of the patient; and output the ejection fraction measurement to a display of the user interface.

[0120] A further embodiment of the foregoing hemodynamic monitor, wherein the input features include a third subset, and wherein when executed by the system processor, the instructions are further configured to: extract the first subset, the second subset, and the third subset of the input features from a plurality of signal measurements simultaneously; determine a normal ejection fraction score of the patient from the first subset of the input features, a low ejection fraction score of the patient from the second subset of the input features, and a critical ejection fraction score of the patient from the third subset of the input features simultaneously; and output the normal ejection fraction score of the patient, the low ejection fraction score of the patient, and the critical ejection fraction score of the patient to a display of the user interface.

[0121] In another example, a method for risk triage of heart failure in a patient is disclosed. The method includes receiving sensed hemodynamic data representing an arterial pressure waveform of the patient via a hemodynamic monitor. The hemodynamic monitor performs waveform analysis of the sensed hemodynamic data to calculate a plurality of signal measurements of the sensed hemodynamic data. The method further includes extracting input features from the plurality of signal measurements indicative of the ejection fraction of the patient via the hemodynamic monitor. Extracting the input features includes extracting a first subset of the input features and simultaneously extracting a second subset of the input features together with the first subset of the input features. The method further includes, via the hemodynamic monitor, determining a normal ejection fraction score of the patient from the first subset of the input features and a low ejection fraction score of the patient from the second subset of the input features simultaneously. The hemodynamic monitor outputs the normal ejection fraction score and the low ejection fraction score of the patient to a display and / or a mobile device.

[0122] The method of the preceding paragraph can optionally include, additionally and / or alternatively, any one or more of the following features, configurations, and / or additional components listed below.

[0123] A further embodiment of the foregoing method, wherein extracting the input features further comprises: extracting a third subset of the input features simultaneously with a first subset and a second subset of the input features; and wherein the hemodynamic monitor determines a normal ejection fraction score of the patient from the first subset of the input features, a low ejection fraction score of the patient from the second subset of the input features, and a critical ejection fraction score of the patient from the third subset of the input features; and wherein the hemodynamic monitor outputs the normal ejection fraction score of the patient, the low ejection fraction score of the patient, and the critical ejection fraction score of the patient to a display and / or a mobile device.

[0124] A further embodiment of the foregoing method further comprises: training a hemodynamic monitor for determining an ejection fraction of a patient, wherein training the hemodynamic monitor comprises: collecting a first clinical data set including arterial pressure waveforms from a first group of individuals having normal ejection fraction measurements of more than fifty percent; labeling each arterial pressure waveform of the first clinical data set with a first label; performing waveform analysis of the labeled arterial pressure waveforms of the first clinical data set to calculate a plurality of waveform signal measurements of the first clinical data set; determining a first subset of the input features by calculating combined measurements between the plurality of waveform signal measurements of the first clinical data set, and selecting a leading signal measurement from the plurality of waveform signal measurements of the first clinical data set having the most predictive combined measurement and labeling the leading signal measurement of the first clinical data set as the first subset of the input features; collecting a second clinical data set including arterial pressure waveforms from a second group of individuals having low ejection fraction measurements of less than or equal to forty percent; labeling each arterial pressure waveform of the second clinical data set with a second label; performing waveform analysis of the labeled arterial pressure waveforms of the second clinical data set to calculate a plurality of waveform signal measurements of the second clinical data set; determining a second subset of the input features by calculating combined measurements between the plurality of waveform signal measurements of the second clinical data set, and selecting a leading signal measurement from the plurality of waveform signal measurements of the second clinical data set having the most predictive combined measurement and labeling the leading signal measurement of the second clinical data set as the second subset of the input features; collecting a third clinical data set including arterial pressure waveforms from a third group of individuals having critical ejection fraction measurements between forty-one and forty-nine percent; labeling each arterial pressure waveform of the third clinical data set with a third label; performing waveform analysis of the labeled arterial pressure waveforms of the third clinical data set to calculate a plurality of waveform signal measurements of the third clinical data set; and determining a third subset of the input features by calculating combined measurements between the plurality of waveform signal measurements of the third clinical data set, and selecting a leading signal measurement from the plurality of waveform signal measurements of the third clinical data set having the most predictive combined measurement and labeling the leading signal measurement of the third clinical data set as the third subset of the input features.

[0125] A further embodiment of the foregoing method, wherein performing waveform analysis of the labeled arterial pressure waveforms of the first clinical dataset to calculate a plurality of waveform signal measurements of the first clinical dataset includes: identifying independent cardiac cycles in each arterial pressure waveform of the first clinical dataset; identifying dicrotic notches in each independent cardiac cycle in each arterial pressure waveform of the first clinical dataset; identifying a systolic upstroke, a systolic decay, and a diastolic phase in each independent cardiac cycle in each arterial pressure waveform of the first clinical dataset; and extracting a plurality of waveform signal measurements of the first clinical dataset from each of the systolic upstroke, the systolic decay, and the diastolic phase in each independent cardiac cycle in each arterial pressure waveform of the first clinical dataset.

[0126] A further embodiment of the foregoing method, wherein performing waveform analysis of the labeled arterial pressure waveforms of the second clinical dataset to calculate a plurality of waveform signal measurements of the second clinical dataset includes: identifying independent cardiac cycles in each arterial pressure waveform of the second clinical dataset; identifying dicrotic notches in each independent cardiac cycle in each arterial pressure waveform of the second clinical dataset; identifying a systolic upstroke, a systolic decay, and a diastolic phase in each independent cardiac cycle in each arterial pressure waveform of the second clinical dataset; and extracting a plurality of waveform signal measurements of the second clinical dataset from each of the systolic upstroke, the systolic decay, and the diastolic phase in each independent cardiac cycle in each arterial pressure waveform of the second clinical dataset.

[0127] A further embodiment of the foregoing method, wherein performing waveform analysis of the labeled arterial pressure waveforms of the third clinical dataset to calculate a plurality of waveform signal measurements of the third clinical dataset includes: identifying independent cardiac cycles in each arterial pressure waveform of the third clinical dataset; identifying dicrotic notches in each independent cardiac cycle in each arterial pressure waveform of the third clinical dataset; identifying a systolic upstroke, a systolic decay, and a diastolic phase in each independent cardiac cycle in each arterial pressure waveform of the third clinical dataset; and extracting a plurality of waveform signal measurements of the third clinical dataset from each of the systolic upstroke, the systolic decay, and the diastolic phase in each independent cardiac cycle in each arterial pressure waveform of the third clinical dataset.

[0128] A further embodiment of the foregoing method, wherein: the plurality of waveform signal measurements of the first clinical dataset correspond to the hemodynamic effects of each of the systolic upstroke, systolic decay, and diastole of each independent cardiac cycle in each arterial pressure waveform from the first clinical dataset, and wherein the hemodynamic effects include contractility, aortic compliance, stroke volume, vascular tone, afterload, and the entire cardiac cycle; the plurality of waveform signal measurements of the second clinical dataset correspond to the hemodynamic effects of each of the systolic upstroke, systolic decay, and diastole of each independent cardiac cycle in each arterial pressure waveform from the second clinical dataset, and wherein the hemodynamic effects include contractility, aortic compliance, stroke volume, vascular tone, afterload, and the entire cardiac cycle; and the plurality of waveform signal measurements of the third clinical dataset correspond to the hemodynamic effects of each of the systolic upstroke, systolic decay, and diastole of each independent cardiac cycle in each arterial pressure waveform from the third clinical dataset, and wherein the hemodynamic effects include contractility, aortic compliance, stroke volume, vascular tone, afterload, and the entire cardiac cycle.

[0129] A further embodiment of the foregoing method, wherein: the plurality of waveform signal measurements of the first clinical dataset include the mean, maximum, minimum, duration, area, standard deviation, derivative, and / or morphological measurements of each of the systolic upstroke, systolic decay, and diastole of each independent cardiac cycle in each arterial pressure waveform from the first clinical dataset; the plurality of waveform signal measurements of the second clinical dataset include the mean, maximum, minimum, duration, area, standard deviation, derivative, and / or morphological measurements of each of the systolic upstroke, systolic decay, and diastole of each independent cardiac cycle in each arterial pressure waveform from the second clinical dataset; and the plurality of waveform signal measurements of the third clinical dataset include the mean, maximum, minimum, duration, area, standard deviation, derivative, and / or morphological measurements of each of the systolic upstroke, systolic decay, and diastole of each independent cardiac cycle in each arterial pressure waveform from the third clinical dataset.

[0130] Further embodiments of the foregoing method, wherein: the plurality of waveform signal measurements of the first clinical dataset include heart rate, respiratory rate, stroke volume, pulse pressure, pulse pressure variability, stroke volume variability, mean arterial pressure (MAP), systolic blood pressure (SYS), diastolic blood pressure (DIA), heart rate variability, cardiac output, peripheral resistance, vascular compliance, and / or left ventricular contractility extracted from each independent cardiac cycle in each arterial pressure waveform of the first clinical dataset; the plurality of waveform signal measurements of the second clinical dataset include heart rate, respiratory rate, stroke volume, pulse pressure, pulse pressure variability, stroke volume variability, mean arterial pressure (MAP), systolic blood pressure (SYS), diastolic blood pressure (DIA), heart rate variability, cardiac output, peripheral resistance, vascular compliance, and / or left ventricular contractility extracted from each independent cardiac cycle in each arterial pressure waveform of the second clinical dataset; and wherein the plurality of waveform signal measurements of the third clinical dataset include heart rate, respiratory rate, stroke volume, pulse pressure, pulse pressure variability, stroke volume variability, mean arterial pressure (MAP), systolic blood pressure (SYS), diastolic blood pressure (DIA), heart rate variability, cardiac output, peripheral resistance, vascular compliance, and / or left ventricular contractility extracted from each independent cardiac cycle in each arterial pressure waveform of the third clinical dataset.

[0131] Further embodiments of the foregoing method, wherein calculating a combined measurement between the plurality of waveform signal measurements of the first clinical dataset includes: performing step one by arbitrarily selecting a subset of signal measurements from the plurality of waveform signal measurements of the first clinical dataset; performing step two by calculating different powers of each of the signal measurements in this subset of signal measurements from the plurality of waveform signal measurements of the first clinical dataset to generate powers of the signal measurements in this subset of signal measurements from the plurality of waveform signal measurements of the first clinical dataset; performing step three by multiplying the powers of the signal measurements in this subset of signal measurements from the plurality of waveform signal measurements of the first clinical dataset to generate a product of the powers of the signal measurements in this subset of signal measurements from the plurality of waveform signal measurements of the first clinical dataset; performing step four by performing a receiver operating characteristic (ROC) analysis on the product of the powers of the signal measurements in this subset of signal measurements from the plurality of waveform signal measurements of the first clinical dataset to obtain a combined measurement of the product of the powers of the signal measurements in this subset of signal measurements from the plurality of waveform signal measurements of the first clinical dataset; and repeating steps one, two, three, and four until all combined measurements have been calculated between all of the plurality of waveform signal measurements of the first clinical dataset.

[0132] A further embodiment of the foregoing method, wherein calculating a combined measurement between a plurality of waveform signal measurements of a second clinical dataset includes: performing step one by arbitrarily selecting a subset of signal measurements from the plurality of waveform signal measurements of the second clinical dataset; performing step two by calculating different powers of each of the signal measurements in this subset of signal measurements from the plurality of waveform signal measurements of the second clinical dataset to generate powers of this subset of signal measurements from the plurality of waveform signal measurements of the second clinical dataset; performing step three by multiplying the powers of this subset of signal measurements from the plurality of waveform signal measurements of the second clinical dataset to generate a product of the powers of this subset of signal measurements from the plurality of waveform signal measurements of the second clinical dataset; performing step four by performing a receiver operating characteristic (ROC) analysis on the product of the powers of this subset of signal measurements from the plurality of waveform signal measurements of the second clinical dataset to obtain a combined measurement of the product of this subset of signal measurements of the powers of this subset of signal measurements from the plurality of waveform signal measurements of the second clinical dataset; and repeating steps one, two, three, and four until all combined measurements are calculated between all of the plurality of waveform signal measurements of the second clinical dataset; wherein calculating a combined measurement between a plurality of waveform signal measurements of a third clinical dataset includes: performing step one by arbitrarily selecting a subset of signal measurements from the plurality of waveform signal measurements of the third clinical dataset; performing step two by calculating different powers of each of the signal measurements in this subset of signal measurements from the plurality of waveform signal measurements of the third clinical dataset to generate powers of this subset of signal measurements from the plurality of waveform signal measurements of the third clinical dataset; performing step three by multiplying the powers of this subset of signal measurements from the plurality of waveform signal measurements of the third clinical dataset to generate a product of the powers of this subset of signal measurements from the plurality of waveform signal measurements of the third clinical dataset; performing step four by performing a receiver operating characteristic (ROC) analysis on the product of the powers of this subset of signal measurements from the plurality of waveform signal measurements of the third clinical dataset to obtain a combined measurement of the product of this subset of signal measurements of the powers of this subset of signal measurements from the plurality of waveform signal measurements of the third clinical dataset; and repeating steps one, two, three, and four until all combined measurements are calculated between all of the plurality of waveform signal measurements of the third clinical dataset.

[0133] Although the invention has been described with reference to one or more exemplary embodiments, those skilled in the art will understand that various changes can be made and elements thereof can be replaced with equivalents without departing from the scope of the invention. Additionally, various modifications can be made to adapt a particular situation or material to the teachings of the invention without departing from the essential scope of the invention. Therefore, it is intended that the invention not be limited to the specific embodiments disclosed, but that the invention will include all embodiments falling within the scope of the appended claims.

Claims

1. A hemodynamic monitor for detecting heart failure, the hemodynamic monitor comprising: A non-invasive blood pressure sensor, comprising: an inflatable blood pressure cuff, a pressure controller pneumatically connected to the inflatable blood pressure cuff, and an optical transmitter and an optical receiver electrically connected to the pressure controller; An integrated hardware unit, comprising: A system processor; A system memory; and A display, comprising a user interface; and Wherein the system memory includes instructions that, when executed by the system processor, are configured to: Adjust the pressure within the inflatable blood pressure cuff by the pressure controller to maintain a constant volume of the patient's artery for a period of time based on feedback signals generated by the optical transmitter and the optical receiver; Generate arterial pressure waveform data of the patient based on the adjusted pressure within the inflatable blood pressure cuff during the period of time; Extract a plurality of signal measurements from the arterial pressure waveform data of the patient; Extract input features from the plurality of signal measurements indicating the patient's ejection fraction score; Determine the ejection fraction score of the patient based on the extracted input features; Generate a first sensory alert signal configured to generate a first sensory alert indicating that the patient has a low ejection fraction when the ejection fraction score exceeds a threshold score, or generate a second sensory alert signal configured to generate a second sensory alert indicating that the patient does not have a low ejection fraction when the ejection fraction score is below the threshold score; Transmit the first sensory alert signal or the second sensory alert signal to the user interface; and Output the first sensory alert or the second sensory alert through the user interface.

2. The hemodynamic monitor according to claim 1, wherein the input features are determined by machine training, and wherein the machine training comprises: Collect a first clinical dataset containing arterial pressure waveforms from a first group of individuals with normal ejection fraction measurements of more than fifty percent; Collect a second clinical dataset containing arterial pressure waveforms from a second group of individuals with low ejection fraction measurements of less than or equal to forty percent; Collect a third clinical dataset containing arterial pressure waveforms from a third group of individuals with critical ejection fraction measurements between forty-one and forty-nine percent; Perform waveform analysis of the arterial pressure waveforms of the first clinical dataset, the second clinical dataset, and the third clinical dataset to calculate a plurality of waveform signal measurements; And Determine the input features by calculating a combined measurement between the plurality of waveform signal measurements, and selecting the leading signal measurement from the plurality of waveform signal measurements with the most predictive combined measurement and labeling the leading signal measurement as the input feature.

3. The hemodynamic monitor according to claim 2, wherein performing waveform analysis of the arterial pressure waveforms of the first clinical data set, the second clinical data set, and the third clinical data set to calculate the plurality of waveform signal measurements comprises: Identify independent cardiac cycles in each of the arterial pressure waveforms of the first clinical dataset, the second clinical dataset, and the third clinical dataset; Identify dicrotic notches in each of the independent cardiac cycles; Identify the systolic upstroke, systolic decay, and diastolic phases in each of the independent cardiac cycles; and Extract the plurality of waveform signal measurements from each of the systolic upstroke, systolic decay, and diastolic phases of each of the independent cardiac cycles.

4. The hemodynamic monitor according to claim 3, wherein the plurality of waveform signal measurements correspond to hemodynamic effects of each of the systolic upstroke, the systolic decay, and the diastolic phase from each of the independent cardiac cycles, and wherein the hemodynamic effects include contractility, aortic compliance, stroke volume, vascular tone, afterload, and the entire cardiac cycle.

5. The hemodynamic monitor according to claim 4, wherein: The plurality of waveform signal measurements includes mean, maximum, minimum, duration, area, standard deviation, derivative, and / or morphological measurements from each of the systolic upstroke, systolic decay, and diastole of each of the individual cardiac cycles; and / or The plurality of waveform signal measurements includes heart rate, respiratory rate, stroke volume, pulse pressure, pulse pressure variability, stroke volume variability, mean arterial pressure (MAP), systolic blood pressure (SYS), diastolic blood pressure (DIA), heart rate variability, cardiac output, peripheral resistance, vascular compliance, and / or left ventricular contractility extracted from each of the individual cardiac cycles.

6. The hemodynamic monitor according to claim 5, wherein calculating the combined measurement between the plurality of waveform signal measurements of the first clinical data set, the second clinical data set, and the third clinical data set comprises: Step one is performed by arbitrarily selecting a subset of signal measurements from the plurality of waveform signal measurements; Step two is performed by calculating different powers of each of the signal measurements in the subset to generate powers of the subset of signal measurements; Step three is performed by multiplying the powers of the subset of signal measurements to generate a product of the powers of the subset of signal measurements; Step four is performed by performing a receiver operating characteristic (ROC) analysis of the product to obtain a combined measurement of the subset of signal measurements; And Steps one, two, three, and four are repeated until all of the combined measurements have been calculated between all of the plurality of waveform signal measurements.

7. The hemodynamic monitor according to claim 6, wherein the input features include a first subset and a second subset, and wherein the instructions, when executed by the system processor, are further configured to: Simultaneously extract the first subset and the second subset of the input features from the plurality of signal measurements; Simultaneously determine a normal ejection fraction score of the patient from the first subset of the input features and a low ejection fraction score of the patient from the second subset of the input features; Output the normal ejection fraction score of the patient and the low ejection fraction score of the patient to the display of the user interface.

8. The hemodynamic monitor according to claim 7, wherein the input features include a third subset, and wherein the instructions, when executed by the system processor, are further configured to: Simultaneously extract the first subset, the second subset, and the third subset of the input features from the plurality of signal measurements; Simultaneously determine the normal ejection fraction score of the patient from the first subset of the input features, the low ejection fraction score of the patient from the second subset of the input features, and a critical ejection fraction score of the patient from the third subset of the input features; Output the normal ejection fraction score of the patient, the low ejection fraction score of the patient, and the critical ejection fraction score of the patient to the display of the user interface.

9. A hemodynamic monitor for detecting heart failure, the hemodynamic monitor comprising: An arterial blood pressure sensor, comprising: a housing; a fluid input port connected via tubing to a fluid source; a catheter-side fluid port connected to a catheter inserted into a patient's arterial system; 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; An integrated hardware unit, comprising: A system processor; A system memory; A display including a user interface; and An analog-to-digital (ADC) converter; Wherein the system memory includes instructions that, when executed by the system processor, are configured to: Receive an electrical signal from the pressure transducer over a period of time, the electrical signal being based on the pressure of the patient's arterial system transmitted through the fluid source; Convert the electrical signal into a digital signal; Generate arterial pressure waveform data of the patient based on the digital signal; Extract a plurality of signal measurements from the arterial pressure waveform data; Extract input features from the plurality of signal measurements indicative of the patient's ejection fraction score; Determine the patient's ejection fraction score based on the extracted input features; Generate a first sensory alert signal configured to generate a first sensory alert indicating that the patient has a low ejection fraction when the ejection fraction score exceeds a threshold score, or generate a second sensory alert signal configured to generate a second sensory alert indicating that the patient does not have a low ejection fraction when the ejection fraction score is below the threshold score; Transmit the first sensory alert signal or the second sensory alert signal to the user interface; and Output the first sensory alert or the second sensory alert through the user interface.

10. The hemodynamic monitor according to claim 9, wherein the input features of the ejection fraction software code are determined by machine training, and wherein the machine training comprises: Collect a first clinical data set containing arterial pressure waveforms from a first group of individuals having normal ejection fraction measurements of greater than fifty percent; Collect a second clinical data set containing arterial pressure waveforms from a second group of individuals having low ejection fraction measurements of less than or equal to forty percent; Collect a third clinical data set containing arterial pressure waveforms from a third group of individuals having critical ejection fraction measurements between forty - one and forty - nine percent; Perform waveform analysis of the arterial pressure waveforms of the first clinical data set, the second clinical data set, and the third clinical data set to calculate a plurality of waveform signal measurements; And Determine the input feature by calculating a combined measurement between the plurality of waveform signal measurements, and selecting the top - ranked signal measurement from the plurality of waveform signal measurements having the most predictive combined measurement and labeling the top - ranked signal measurement as the input feature.

11. The hemodynamic monitor according to claim 10, wherein performing waveform analysis of the labeled arterial pressure waveforms of the first clinical data set, the second clinical data set, and the third clinical data set to calculate the plurality of waveform signal measurements comprises: Identify independent cardiac cycles in each of the arterial pressure waveforms of the first clinical data set, the second clinical data set, and the third clinical data set; Identify dicrotic notches in each of the independent cardiac cycles; Identify systolic upstrokes, systolic decays, and diastolic phases in each of the independent cardiac cycles; and Extract the plurality of waveform signal measurements from each of the systolic upstrokes, systolic decays, and diastolic phases of each of the independent cardiac cycles.

12. The hemodynamic monitor according to claim 11, wherein the plurality of waveform signal measurements correspond to hemodynamic effects during each of the systolic upstroke, the systolic decay, and the diastolic phase from each of the individual cardiac cycles, and wherein the hemodynamic effects include contractility, aortic compliance, stroke volume, vascular tone, afterload, and the entire cardiac cycle.

13. The hemodynamic monitor according to claim 12, wherein: The plurality of waveform signal measurements includes mean values, maximum values, minimum values, durations, areas, standard deviations, derivatives, and / or morphological measurements from each of the systolic upstrokes, systolic decays, and diastolic phases of each of the independent cardiac cycles; and / or The plurality of waveform signal measurements includes heart rate, respiratory rate, stroke volume, pulse pressure, pulse pressure variability, stroke volume variability, mean arterial pressure (MAP), systolic blood pressure (SYS), diastolic blood pressure (DIA), heart rate variability, cardiac output, peripheral resistance, vascular compliance, and / or left ventricular contractility extracted from each of the independent cardiac cycles.

14. The hemodynamic monitor according to claim 13, wherein calculating the combined measurement between the plurality of waveform signal measurements of the first clinical data set, the second clinical data set, and the third clinical data set comprises: Perform step one by arbitrarily selecting a subset of signal measurements from the plurality of waveform signal measurements; Perform step two by calculating different powers of each of the signal measurements in the subset to generate powers of the subset of signal measurements; Perform step three by multiplying the powers of the subset of signal measurements to generate a product of the powers of the subset of signal measurements; Perform step four by performing receiver operating characteristic (ROC) analysis of the product to obtain a combined measurement of the subset of signal measurements; And Repeat steps one, two, three, and four until all of the combined measurements have been calculated between all of the plurality of waveform signal measurements.

15. The hemodynamic monitor according to claim 14, wherein the input features include a first subset and a second subset, and wherein the instructions, when executed by the system processor, are further configured to: simultaneously extract the first subset and the second subset of the input features from the plurality of signal measurements; simultaneously determine a normal ejection fraction score of the patient from the first subset of the input features and a low ejection fraction score of the patient from the second subset of the input features; output the normal ejection fraction score of the patient and the low ejection fraction score of the patient to the display of the user interface.

16. The hemodynamic monitor according to claim 15, wherein the input features include a third subset, and wherein the instructions, when executed by the system processor, are further configured to: simultaneously extract the first subset, the second subset, and the third subset of the input features from the plurality of signal measurements; simultaneously determine the normal ejection fraction score of the patient from the first subset of the input features, the low ejection fraction score of the patient from the second subset of the input features, and a critical ejection fraction score of the patient from the third subset of the input features; output the normal ejection fraction score of the patient, the low ejection fraction score of the patient, and the critical ejection fraction score of the patient to the display of the user interface.

17. A method for risk triage of heart failure in a patient, the method comprising: Receive sensed hemodynamic data representing the arterial pressure waveform of the patient through a hemodynamic monitor; Perform waveform analysis of the sensed hemodynamic data through the hemodynamic monitor to calculate a plurality of signal measurements of the sensed hemodynamic data; Extract an input feature from the plurality of signal measurements indicating the ejection fraction score of the patient through the hemodynamic monitor; Wherein extracting the input features includes: extracting a first subset of the input features; and simultaneously extracting a second subset of the input features together with the first subset of the input features; simultaneously determining, by the hemodynamic monitor, a normal ejection fraction score of the patient from the first subset of the input features and a low ejection fraction score of the patient from the second subset of the input features; and outputting the normal ejection fraction score of the patient and the low ejection fraction score of the patient to a display and / or a mobile device.

18. The method according to claim 17, wherein extracting the input feature further comprises: simultaneously extracting a third subset of the input features together with the first subset and the second subset of the input features; and wherein the hemodynamic monitor simultaneously determines the normal ejection fraction score of the patient from the first subset of the input features, the low ejection fraction score of the patient from the second subset of the input features, and a critical ejection fraction score of the patient from the third subset of the input features; and wherein the hemodynamic monitor outputs the normal ejection fraction score of the patient, the low ejection fraction score of the patient, and the critical ejection fraction score of the patient to the display and / or the mobile device.

19. The method according to claim 18, further comprising: Training the hemodynamic monitor to determine the ejection fraction of the patient, wherein training the hemodynamic monitor includes: collecting a first clinical data set containing arterial pressure waveforms from a first group of individuals having normal ejection fraction measurements of more than fifty percent; labeling each of the arterial pressure waveforms of the first clinical data set with a first label; performing waveform analysis of the labeled arterial pressure waveforms of the first clinical data set to calculate a plurality of waveform signal measurements of the first clinical data set; determining the first subset of the input features by calculating combined measurements between the plurality of waveform signal measurements of the first clinical data set, and selecting a leading signal measurement from the plurality of waveform signal measurements of the first clinical data set having the most predictive combined measurement and labeling the leading signal measurement of the first clinical data set as the first subset of the input features; collecting a second clinical data set containing arterial pressure waveforms from a second group of individuals having low ejection fraction measurements less than or equal to forty percent; labeling each of the arterial pressure waveforms of the second clinical data set with a second label; performing waveform analysis of the labeled arterial pressure waveforms of the second clinical data set to calculate a plurality of waveform signal measurements of the second clinical data set; determining the second subset of the input features by calculating combined measurements between the plurality of waveform signal measurements of the second clinical data set, and selecting a leading signal measurement from the plurality of waveform signal measurements of the second clinical data set having the most predictive combined measurement and labeling the leading signal measurement of the second clinical data set as the second subset of the input features; Collect a third clinical dataset containing arterial pressure waveforms from a third group of individuals having critical ejection fraction measurements between forty-one and forty-nine percent; Label each of the arterial pressure waveforms of the third clinical dataset with a third label; Perform waveform analysis of the labeled arterial pressure waveforms of the third clinical dataset to compute a plurality of waveform signal measurements of the third clinical dataset; and Determine the third subset of the input features by computing a combined measurement between the plurality of waveform signal measurements of the third clinical dataset, and selecting a top signal measurement from the plurality of waveform signal measurements of the third clinical dataset having the most predictive combined measurement and labeling the top signal measurement of the third clinical dataset as the third subset of the input features.

20. The method according to claim 19, wherein performing waveform analysis of the labeled arterial pressure waveforms of the first clinical dataset to calculate the plurality of waveform signal measurements of the first clinical dataset comprises: Identify individual cardiac cycles in each of the arterial pressure waveforms of the first clinical dataset; Identify dicrotic notches in each of the individual cardiac cycles in each of the arterial pressure waveforms of the first clinical dataset; Identify systolic upstrokes, systolic decays, and diastolic phases in each of the individual cardiac cycles in each of the arterial pressure waveforms of the first clinical dataset; and Extract the plurality of waveform signal measurements of the first clinical dataset from each of the systolic upstrokes, systolic decays, and diastolic phases in each of the individual cardiac cycles in each of the arterial pressure waveforms of the first clinical dataset. Identify individual cardiac cycles in each of the arterial pressure waveforms of the second clinical dataset; 21. The method according to claim 20, wherein performing waveform analysis of the labeled arterial pressure waveforms of the second clinical dataset to calculate the plurality of waveform signal measurements of the second clinical dataset comprises: Identify dicrotic notches in each of the individual cardiac cycles in each of the arterial pressure waveforms of the second clinical dataset; Identify systolic upstrokes, systolic decays, and diastolic phases in each of the individual cardiac cycles in each of the arterial pressure waveforms of the second clinical dataset; and Extract the plurality of waveform signal measurements of the second clinical dataset from each of the systolic upstrokes, systolic decays, and diastolic phases in each of the individual cardiac cycles in each of the arterial pressure waveforms of the second clinical dataset. Identify individual cardiac cycles in each of the arterial pressure waveforms of the third clinical dataset; 22. The method according to claim 21, wherein performing waveform analysis of the labeled arterial pressure waveforms of the third clinical dataset to calculate the plurality of waveform signal measurements of the third clinical dataset includes: Identify dicrotic notches in each of the individual cardiac cycles in each of the arterial pressure waveforms of the third clinical dataset; Identify systolic upstrokes, systolic decays, and diastolic phases in each of the individual cardiac cycles in each of the arterial pressure waveforms of the third clinical dataset; and Extract the plurality of waveform signal measurements of the third clinical dataset from each of the systolic upstrokes, systolic decays, and diastolic phases in each of the individual cardiac cycles in each of the arterial pressure waveforms of the third clinical dataset. The plurality of waveform signal measurements of the first clinical dataset correspond to each from the first clinical dataset 23. The method according to claim 22, wherein: ​ the hemodynamic effects of each of the systolic upstroke, the systolic decay, and the diastole of each of the individual cardiac cycles in the arterial pressure waveform, and wherein the hemodynamic effects include contractility, aortic compliance, stroke volume, vascular tone, afterload, and the entire cardiac cycle; the plurality of waveform signal measurements of the second clinical dataset correspond to each of those from the second clinical dataset the hemodynamic effects of each of the systolic upstroke, the systolic decay, and the diastole of each of the individual cardiac cycles in the arterial pressure waveform, and wherein the hemodynamic effects include contractility, aortic compliance, stroke volume, vascular tone, afterload, and the entire cardiac cycle; and the plurality of waveform signal measurements of the third clinical dataset correspond to each of those from the third clinical dataset the hemodynamic effects of each of the systolic upstroke, the systolic decay, and the diastole of each of the individual cardiac cycles in the arterial pressure waveform, and wherein the hemodynamic effects include contractility, aortic compliance, stroke volume, vascular tone, afterload, and the entire cardiac cycle.

24. The method according to claim 23, wherein: the plurality of waveform signal measurements of the first clinical dataset include the mean, maximum, minimum, duration, area, standard deviation, derivative, and / or morphological measurement of each of the systolic upstroke, the systolic decay, and the diastole of each of the individual cardiac cycles in each of the arterial pressure waveforms from the first clinical dataset; the plurality of waveform signal measurements of the second clinical dataset include the mean, maximum, minimum, duration, area, standard deviation, derivative, and / or morphological measurement of each of the systolic upstroke, the systolic decay, and the diastole of each of the individual cardiac cycles in each of the arterial pressure waveforms from the second clinical dataset; and the plurality of waveform signal measurements of the third clinical dataset include the mean, maximum, minimum, duration, area, standard deviation, derivative, and / or morphological measurement of each of the systolic upstroke, the systolic decay, and the diastole of each of the individual cardiac cycles in each of the arterial pressure waveforms from the third clinical dataset.

25. The method according to claim 24, wherein: the plurality of waveform signal measurements of the first clinical dataset include heart rate, respiratory rate, stroke volume, pulse pressure, pulse pressure variability, stroke volume variability, mean arterial pressure (MAP), systolic blood pressure (SYS), diastolic blood pressure (DIA), heart rate variability, cardiac output, peripheral resistance, vascular compliance, and / or left ventricular contractility extracted from each of the individual cardiac cycles in each of the arterial pressure waveforms from the first clinical dataset; The multiple waveform signal measurements of the second clinical dataset include heart rate, respiratory rate, stroke volume, pulse pressure, pulse pressure variability, stroke volume variability, mean arterial pressure (MAP), systolic blood pressure (SYS), diastolic blood pressure (DIA), heart rate variability, cardiac output, peripheral resistance, vascular compliance, and / or left ventricular contractility extracted from each independent cardiac cycle in each of the arterial pressure waveforms of the second clinical dataset; and wherein the multiple waveform signal measurements of the third clinical dataset include heart rate, respiratory rate, stroke volume, pulse pressure, pulse pressure variability, stroke volume variability, mean arterial pressure (MAP), systolic blood pressure (SYS), diastolic blood pressure (DIA), heart rate variability, cardiac output, peripheral resistance, vascular compliance, and / or left ventricular contractility extracted from each independent cardiac cycle in each of the arterial pressure waveforms of the third clinical dataset.

26. The method according to claim 25, wherein calculating the combined measurement between the plurality of waveform signal measurements of the first clinical dataset includes: Step one is performed by arbitrarily selecting a subset of signal measurements from the multiple waveform signal measurements of the first clinical dataset; Step two is performed by calculating different powers of each of the signal measurements in the subset of signal measurements from the multiple waveform signal measurements of the first clinical dataset to generate the powers of the subset of signal measurements from the multiple waveform signal measurements of the first clinical dataset; Step three is performed by multiplying the powers of the subset of signal measurements from the multiple waveform signal measurements of the first clinical dataset to generate the product of the powers of the subset of signal measurements from the multiple waveform signal measurements of the first clinical dataset; Step four is performed by performing a receiver operating characteristic (ROC) analysis on the product of the powers of the subset of signal measurements from the multiple waveform signal measurements of the first clinical dataset to obtain a combined measurement of the product of the subset of signal measurements of the powers of the subset of signal measurements from the multiple waveform signal measurements of the first clinical dataset; and Steps one, two, three, and four are repeated until all the combined measurements are calculated among all the multiple waveform signal measurements of the first clinical dataset.

27. The method according to claim 26, wherein calculating the combined measurement between the plurality of waveform signal measurements of the second clinical dataset includes: Step one is performed by arbitrarily selecting a subset of signal measurements from the multiple waveform signal measurements of the second clinical dataset; Step two is performed by calculating different powers of each of the signal measurements in the subset of signal measurements from the multiple waveform signal measurements of the second clinical dataset to generate the powers of the subset of signal measurements from the multiple waveform signal measurements of the second clinical dataset; Step three is performed by multiplying the powers of the subset of signal measurements from the multiple waveform signal measurements of the second clinical dataset to generate the product of the powers of the subset of signal measurements from the multiple waveform signal measurements of the second clinical dataset; Perform step four by performing a receiver operating characteristic (ROC) analysis on the product of the powers of the subset of the signal measurements of the plurality of waveform signal measurements from the second clinical dataset to obtain a combined measurement of the product of the powers of the subset of the signal measurements of the plurality of waveform signal measurements from the second clinical dataset; and Repeat steps one, two, three, and four until all the combined measurements are calculated among all the plurality of waveform signal measurements of the second clinical dataset; wherein calculating the combined measurements among the plurality of waveform signal measurements of the third clinical dataset includes: Performing step one by arbitrarily selecting a subset of signal measurements from the plurality of waveform signal measurements of the third clinical dataset; Performing step two by calculating different powers of each of the signal measurements of the subset of the signal measurements of the plurality of waveform signal measurements from the third clinical dataset to generate the powers of the subset of the signal measurements of the plurality of waveform signal measurements from the third clinical dataset; Performing step three by multiplying the powers of the subset of the signal measurements of the plurality of waveform signal measurements from the third clinical dataset to generate the product of the powers of the subset of the signal measurements of the plurality of waveform signal measurements from the third clinical dataset; Performing step four by performing a receiver operating characteristic (ROC) analysis on the product of the powers of the subset of the signal measurements of the plurality of waveform signal measurements from the third clinical dataset to obtain a combined measurement of the product of the powers of the subset of the signal measurements of the plurality of waveform signal measurements from the third clinical dataset; and Repeat steps one, two, three, and four until all the combined measurements are calculated among all the plurality of waveform signal measurements of the third clinical dataset.

Images