System and method for predicting overall insufficiency in intensive care patients

Abstract

A system for determining a global perfusion insufficiency index (GHI) includes an arterial blood pressure sensor, a ventricular blood pressure sensor, an oximetry module, and an integrated hardware unit including a system processor and a system memory. The system memory includes instructions that cause the system to receive arterial hemodynamic data, ventricular hemodynamic data, and oxyhemoglobin saturation data. One or more right ventricular pressure characteristics, one or more pulmonary arterial pressure characteristics, one or more cardiac output parameters, and one or more venous blood oxygen saturation parameters are derived from arterial hemodynamic data, ventricular hemodynamic data, and blood oxygen saturation data. GHI is derived using a predictive decision model based on one or more right ventricular pressure characteristics, one or more pulmonary artery characteristics, one or more cardiac output parameters, and one or more venous oxygen saturation parameters.

Description

[0001] Cross-references to related applications This application claims the benefit of U.S. Provisional Application No. 63 / 515,808, filed July 26, 2023, entitled “System and method for predicting global perfusion in critical care patients”, and U.S. Provisional Application No. 63 / 623,048, filed January 19, 2024, entitled “System and method for predicting global perfusion in critical care patients”, the disclosure of which is incorporated herein by reference in its entirety. Background Technology

[0002] This disclosure relates to hemodynamic monitoring, and more specifically, to predicting overall perfusion inadequacy in patients.

[0003] Global hypoperfusion describes a condition where oxygen delivery is insufficient to meet metabolic demands. Hypoperfusion events can be triggered by a variety of physiological responses in the body, including lung problems that reduce oxygen supply, problems delivering oxygen to body cells (e.g., insufficient cardiac output (CO), low hemoglobin count, and / or bleeding events), or a sudden increase in oxygen demand. Global hypoperfusion events can cause serious harm to patients; therefore, a method for predicting when global hypoperfusion events will occur is needed. Summary of the Invention

[0004] A system for determining the Global Insufficiency Index (GHI), which represents a prediction of future global insufficiency events in a patient. The system includes an arterial blood pressure sensor comprising a housing, a fluid inlet port connected via conduit to a fluid source, a catheter-side fluid port connected to a catheter inserted into the patient's arterial system, a pressure sensor in communication with the fluid source through the fluid port, and an I / O cable electrically communicating with the pressure sensor. The system also includes a ventricular blood pressure sensor comprising a housing, a fluid inlet port connected via conduit to a fluid source, a catheter-side fluid port connected to a catheter inserted into the patient's ventricular system, a pressure sensor in communication with the fluid source through the fluid port, and an I / O cable electrically communicating with the pressure sensor. The system further includes a blood oxygenation module comprising a light emitter, a light receiver, and an I / O cable electrically communicating with the light emitter and the light receiver. The system also includes an integrated hardware unit comprising a system processor, system memory, a display including a user interface, and an analog-to-digital converter (ADC). The system memory includes instructions that, when executed by the system processor, cause the system to receive arterial hemodynamic data from an arterial blood pressure sensor, ventricular hemodynamic data from a ventricular blood pressure sensor, and oxygen saturation data from a blood oxygen saturation module. A first algorithm is used to derive one or more right ventricular pressure features from the ventricular hemodynamic data. A second algorithm is used to derive one or more pulmonary artery pressure features from the arterial hemodynamic data. A third algorithm is used to derive one or more cardiac output parameters from the ventricular hemodynamic data and / or arterial hemodynamic data. A fourth algorithm is used to derive one or more venous oxygen saturation parameters from the blood oxygen saturation data. The GHI is derived using a predictive decision model based on one or more right ventricular pressure features, one or more pulmonary artery features, one or more cardiac output parameters, and one or more venous oxygen saturation parameters. The GHI is displayed on a monitor.

[0005] A method for determining a Global Insufficiency Index (GHI) representing a prediction of future global insufficiency events in a patient, the method comprising receiving multiple hemodynamic data from arterial and ventricular blood pressure sensors, receiving oxygen saturation data from an oxygenation module, deriving one or more right ventricular pressure features from multiple right ventricular hemodynamic data using a first algorithm, deriving one or more pulmonary artery pressure features from multiple pulmonary artery hemodynamic data using a second algorithm, deriving one or more cardiac output parameters from multiple hemodynamic data using a third algorithm, deriving one or more venous oxygen saturation parameters from oxygen saturation data using a fourth algorithm, deriving the GHI using a predictive decision model based on one or more right ventricular pressure features, one or more pulmonary artery features, one or more cardiac output parameters, and one or more venous oxygen saturation parameters, and displaying the GHI on a hemodynamic display. Attached Figure Description

[0006] Figure 1 This is a schematic block diagram of a hemodynamic monitoring system used to generate the Global Insufficiency Index (GHI).

[0007] Figure 2 This is a perspective view of an example hemodynamic monitor.

[0008] Figure 3 This is a perspective view of an example catheter that can be inserted into a patient and connected to one or more hemodynamic sensors used to provide hemodynamic data to a hemodynamic monitor.

[0009] Figure 4 This is a perspective view of an example minimally invasive pressure sensor that can be attached to a patient to sense hemodynamic data representing the patient's right ventricular pressure or pulmonary artery pressure.

[0010] Figure 5 This is a perspective view of an example pulse oximetry module used to receive pulse oximetry data from a catheter inserted into a patient's body.

[0011] Figure 6 This is a block diagram of the GHI algorithm.

[0012] Figure 7 This is a graph illustrating an example right ventricular pressure (RVP) waveform trace, which includes example indices indicating insufficient blood flow, cardiac output, and overall perfusion.

[0013] Figure 8 This is a graph illustrating an example pulmonary artery pressure (PAP) waveform trace, which includes example markers indicating insufficient blood flow, cardiac output, and overall perfusion.

[0014] Figure 9 This is a schematic diagram of an example system for implementing the right ventricular output (RVCO) algorithm.

[0015] Figure 10 This is a schematic diagram of an alternative example of a system for implementing the (RVCO) algorithm.

[0016] Figure 11 This is a table showing an example of the output of the system used to generate GHI.

[0017] Figure 12 This is a flowchart illustrating the method used to generate GHI. Detailed Implementation

[0018] As described herein, a system for determining the Global Hypoperfusion Index (GHI) is used to predict future global hypoperfusion events in patients. The system can determine a real-time, continuous GHI that predicts the likelihood of a hypoperfusion event. The system for determining the GHI includes a lung catheter. The lung catheter includes multiple hemodynamic sensors configured to measure blood oxygenation data, cardiac output data, pulmonary artery pressure data, and right ventricular pressure data. A processor derives features and values ​​from the blood oxygenation data, pulmonary artery pressure data, and right ventricular pressure data using various algorithms described in more detail herein. The processor then executes a machine learning algorithm based on the features and values ​​derived from the multiple algorithms to generate the GHI. The GHI is then transmitted to an output system where it can be viewed, for example, by a clinician.

[0019] Figure 1 This is a schematic block diagram of a hemodynamic monitoring system 10 used to generate the Global Insufficiency Index (GHI). The hemodynamic monitoring system 10 includes a hemodynamic monitor 12 and hemodynamic sensors 14 (including hemodynamic sensors 14A, 14B, 14C, and 14D). The hemodynamic monitor 12 includes a system processor 20, a system memory 22, a display 24, an analog-to-digital converter (ADC) 26, and a digital-to-analog converter (DAC) 28. The system memory 22 includes GHI software code 30, which includes a blood oxygenation measurement module 32, a pulmonary artery pressure (PAP) feature module 34, a right ventricular pressure (RVP) feature module 36, a right ventricular cardiac output (RVCO) module 38, and a GHI algorithm module 40. The display 24 includes a user interface 46, which includes control elements 48 and a sensory alarm 50. Figure 1 The image also shows patient 16, healthcare worker 18, and catheter 54.

[0020] like Figure 1As shown, the hemodynamic monitoring system 10 includes a hemodynamic monitor 12 and hemodynamic sensors 14 (including hemodynamic sensors 14A, 14B, 14C, and 14D). The hemodynamic monitoring system 10 can be implemented in patient care environments, such as ICUs, ORs, or other patient care settings, to monitor the hemodynamic status of patients. Figure 1 As shown, the patient care environment may include a patient 16 and healthcare personnel 18 trained to utilize the hemodynamic monitoring system 10.

[0021] The following text is about Figure 2 The hemodynamic monitor 12 can be an integrated hardware unit including a system processor 20, a system memory 22, a display 24, an ADC 26, and a DAC 28. In other examples, any one or more components of the hemodynamic monitor 12 and / or the described functionality can be distributed across multiple hardware units. For example, in some examples, the display 24 can be a separate display device located remotely from and operatively coupled to the hemodynamic monitor 12. Similarly, at least a portion of the data processing within the hemodynamic monitoring system 10 can be performed via a smart cable connecting a catheter (e.g., catheter 54) or sensor to the hemodynamic monitor 12. Generally, although in Figure 1 The example is illustrated and described as an integrated hardware unit, but it should be understood that the hemodynamic monitor 12 may include any combination of devices and components that are electrically connected, communicatively connected, or otherwise operatively connected to perform the functions of the hemodynamic monitor 12 herein.

[0022] like Figure 1 As shown, system memory 22 stores GHI software code 30. GHI software code 30 includes a pulse oximetry module 32, a PAP feature module 34, an RVP feature module 36, an RVCO module 38, and a GHI algorithm module 40. Display 24 provides a user interface 46, which includes control elements 48 that enable the user to interact with the hemodynamic monitor 12 and / or other components of the hemodynamic monitoring system 10. Figure 1 As shown, the user interface 46 also provides a sensory alarm 50 to provide alerts to medical personnel based on the hemodynamic status of the patient 16, as further described below.

[0023] Hemodynamic sensor 14 can be attached to patient 16 to sense RVP waveform, PAP waveform, and blood oxygen saturation (in Figure 1The hemodynamic data of patient 16 (labeled "SvO2") or cardiac output, or any combination thereof, is provided. Hemodynamic sensor 14 is operatively connected to hemodynamic monitor 12 (e.g., via a wired or wireless connection, or both electrically and / or communicatively) to provide sensed hemodynamic data to hemodynamic monitor 12. In some examples, hemodynamic sensor 14 provides patient 16's hemodynamic data as an analog signal to hemodynamic monitor 12, which is converted by ADC 26 into digital hemodynamic data representing RVP and / or PAP waveforms. In other examples, hemodynamic sensor 14 may provide sensed hemodynamic data to hemodynamic monitor 12 in digital form, in which case hemodynamic monitor 12 may not include or utilize ADC 26. In still other examples, hemodynamic sensor 14 may provide patient 16's hemodynamic data as an analog signal to hemodynamic monitor 12, which is analyzed by hemodynamic monitor 12 in its analog form.

[0024] Hemodynamic sensor 14 may include one or more non-invasive, minimally invasive, or invasive sensors attached to patient 16. For example, hemodynamic sensor 14 may take the form of an invasive hemodynamic sensor 14A, such as a second pressure sensor 14A, which provides RVP waveform data sensed at the right ventricular port 68C located in the right ventricle of the patient's heart. Figure 4 (As shown). The hemodynamic sensor 14 can take the form of an invasive hemodynamic sensor 14B, such as a blood oxygenation module 14B, which is based on an optical connector 62 that is emitted from the module 14B into the pulmonary artery and via the catheter 54 (as shown). Figure 5 (As shown) The pulmonary artery oxygen saturation data is provided by light pulses reflected, returned, and received by module 14B. In other examples, the hemodynamic sensor 14 may take the form of a non-invasive hemodynamic sensor. In some examples, the hemodynamic sensor 14 may be non-invasively attached to a limb of patient 16, such as the forehead, wrist, arm, fingers, ankle, toes, or other limbs. The hemodynamic sensor 14 may also take the form of other invasive, minimally invasive, or non-invasive hemodynamic sensors.

[0025] In some examples, hemodynamic sensor 14 can be configured to sense RVP, PAP, or right ventricular and pulmonary artery pressure in patient 16. In some cases, in addition to right ventricular and pulmonary artery pressure, hemodynamic sensor 14 can also be used to sense cardiac output, pulmonary artery oxygen saturation, or both cardiac output and oxygen saturation. For example, one or more hemodynamic sensors 14 can be attached to patient 16 via a radial artery catheter inserted into patient 16's arm. In other examples, one or more hemodynamic sensors 14 can be attached to patient 16 via a femoral artery catheter inserted into patient 16's leg. Such techniques can similarly enable multiple hemodynamic sensors 14 to provide substantially continuous beat-by-beat monitoring of RVP and PAP, and monitoring of cardiac output and patient 16's oxygen saturation, or any combination of these hemodynamic data, over extended time periods (such as minutes or hours).

[0026] The system processor 20 executes GHI software code 30, which implements the blood oxygenation measurement module 32, the PAP feature module 34, the RVP feature module 36, the RVCO module 38, and the GHI algorithm module 40. These modules use RVP waveforms, PAP waveforms, and blood oxygen saturation data to determine the overall perfusion insufficiency of patient 16.

[0027] In some examples, processor 20 is configured to perform functionality and / or process instructions for execution within system 10. For example, processor 20 is capable of processing instructions stored in system memory 22. Examples of processor 20 may include any one or more of a microprocessor, controller, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other equivalent discrete or integrated logic circuit device.

[0028] System memory 22 can be configured to store information within hemodynamic monitor 12 during operation. In some examples, system memory 22 is described as a computer-readable storage medium. In some examples, computer-readable storage media includes non-transient media. The term "non-transient" indicates that the storage medium is not embodied in a carrier wave or propagating signal. In some examples, non-transient storage media stores data that changes over time (e.g., in RAM or cache). In some examples, system memory 22 is temporary memory, meaning that the primary purpose of system memory 22 is not long-term storage. In some examples, system memory 22 is described as volatile memory, meaning that system memory 22 does not maintain its stored contents when power to system memory 22 is removed. 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. In some examples, system memory 22 is used to store program instructions executed by processor 20. In one example, system memory 22 is used by software or an application to temporarily store information during program execution.

[0029] In some examples, system memory 22 also includes one or more computer-readable storage media. System memory 22 is configured to store a larger amount of information than volatile memory. System memory 22 is also configured for long-term storage of information. In some examples, system memory 22 includes non-volatile storage elements. Examples of such non-volatile storage elements include, but are not limited to, magnetic hard disks, optical disks, flash memory, or electrically programmable memory (EPROM) or electrically erasable programmable memory (EEPROM).

[0030] Display 24 may 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. User interface 46 may include graphical and / or physical control elements that enable user input to interact with hemodynamic monitor 12 and / or other components of hemodynamic monitoring system 10. In some examples, user interface 46 may take the form of a graphical user interface (GUI) that presents graphical control elements on, for example, a touch-sensitive and / or presence-sensitive display screen of display 24. In such examples, user input may be received in the form of gesture input, such as touch gestures, scroll gestures, zoom gestures, or other gesture inputs. In some examples, user interface 46 may take the form of physical control elements 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 hemodynamic monitoring system 10.

[0031] In operation, one or more hemodynamic sensors 14 are connected to the hemodynamic monitor 12 and catheter 54. Hemodynamic sensor 14A senses hemodynamic data representing the right ventricular pressure (RVP), pulmonary artery pressure (PAP), and / or other blood pressure waveforms of patient 16. Hemodynamic sensor 14A provides the hemodynamic data (e.g., as analog sensor data) to the hemodynamic monitor 12. ADC 26 converts the analog hemodynamic data into digital hemodynamic data representing the RVP, PAP, and / or other blood pressure waveforms of patient 16. Hemodynamic sensor 14B senses hemodynamic data representing mixed venous oxygen saturation (SvO2) values.

[0032] In operation, system memory 22 is encoded with instructions that are executed by processor 20. System memory 22 includes a pulse oximetry module 32. Pulse oximetry module 32 includes one or more programs containing instructions for applying the SvO2 algorithm to pulse oximetry data received from catheter 54, and more specifically from, for example, hemodynamic sensor 14B. When pulse oximetry module 32 is executed, the pulse oximetry data (i.e., transmitted from catheter 54) is processed via the SvO2 algorithm to produce one or more SvO2 parameters. In some examples, SvO2 parameters may include a measured SvO2 value and a signal quality index (SQI).

[0033] The measured SvO2 parameter is a measure of the oxygen content of blood returning to the heart after systemic perfusion. Abnormal SvO2 can indicate inadequate systemic oxygenation. SvO2 can be sampled from the hemodynamic sensor 14B, allowing new SvO2 values ​​to be measured at defined time intervals (e.g., SvO2 is sampled every 2 seconds). SQI can indicate the overall reliability and readability of the received blood oxygenation data. Therefore, a noisier signal will produce a lower SQI, indicating lower signal reliability, while a quieter signal will produce a higher SQI, indicating higher signal reliability. In some examples, SQI is represented via a digital scale (e.g., 0 to 5, where 0 is the lowest quality and 5 is the highest quality). In some examples, if the SQI is above a defined threshold (e.g., SQI is greater than 1 and therefore between 2 and 5), the GHI software code 30 only accepts the signal for further processing.

[0034] System memory 22 also includes a PAP feature module 34. The PAP feature module 34 includes one or more programs containing instructions to apply a PAP algorithm to PAP waveforms received from catheter 54, more specifically from hemodynamic sensor 14A. When the PAP feature module 34 is executed, the PAP waveforms (i.e., those transmitted from catheter 54) are processed via the PAP algorithm to generate one or more PAP features. In some examples, PAP features may include an average PAP value. The average PAP value may be the average value of the PAP waveform over a defined time interval. For example, the average PAP may be determined for a 10-second window of the PAP waveform. In other examples, the average PAP is determined for an individual heartbeat, wherein the start and end of the individual heartbeat within the PAP waveform are determined by a heartbeat detection algorithm. Other PAP features may also be determined by the PAP feature module 118, and... Figure 8 This is discussed in more detail in the description.

[0035] System memory 22 also includes an RVP feature module 36. The RVP feature module 36 includes one or more programs containing instructions to apply an RVP algorithm to RVP waveforms received from catheter 54, more specifically from hemodynamic sensor 14A. When the RVP feature module 36 is executed, the RVP waveforms (transmitted from catheter 54) are processed via the RVP algorithm to generate one or more RVP features. In some examples, RVP features may include one or more of the following: pulse rate, maximum rate of change of pressure relative to time during the systolic rise phase (“dP / dt”), minimum dP / dt during the relaxation phase after end-systole, systolic time, systolic pressure, end-systolic pressure, end-diastolic pressure, pulse pressure, and mean right ventricular pressure. Figure 7 The description discusses the RVP characteristics and their derivation from the RVP waveform in more detail.

[0036] System memory 22 also includes an RVCO module 38. RVCO module 38 includes one or more programs containing instructions to apply the RVCO algorithm to data received from catheter 54. The RVCO algorithm can be applied using an RVP waveform and the aforementioned RVP characteristics, such as those derived from the RVP waveform. In addition to RVP characteristics, the RVCO algorithm can also be applied using a PAP waveform and the aforementioned PAP characteristics derived from the PAP waveform. When RVCO module 38 is executed, the RVP waveform or the RVP and PAP waveforms are processed via the RVCO algorithm to generate one or more cardiac output parameters. In some examples, the one or more cardiac output parameters may include continuous cardiac output. Figures 9 to 10 The description provides a more detailed discussion of various examples of RVCO algorithm implementations.

[0037] In some additional or alternative examples, one or more cardiac output parameters are derived using a Swan-Ganz catheter. In other additional or alternative examples, system memory 22 includes instructions encoded in one or more programs instructing system processor 20 to use the Arterial Pressure Cardiac Output (APCO) algorithm to derive one or more cardiac output parameters. In such examples, the APCO algorithm can be used instead of the RVCO algorithm.

[0038] System memory 22 also includes a GHI algorithm module 40. The GHI algorithm module 40 includes one or more programs that contain the GHI algorithm (i.e., ... Figure 6 The GHI algorithm 200 is applied to instructions generated by the execution of the pulse oximetry module 32, PAP feature module 34, RVP feature module 36, and RVCO module 38. During the execution of the GHI algorithm module 40, SvO2 parameters, PAP features, RVP features, and cardiac output parameters are processed via the GHI algorithm. The GHI algorithm may include feature creation models, model heuristics, and machine learning models, which contribute to the creation of an overall perfusion insufficiency index. (See also...) Figure 6 The GHI algorithm is described using the GHI algorithm 200.

[0039] Figure 2 The hemodynamic monitor 12 is shown in the figure. Figure 3 The catheter 54 is shown in the image. Figure 4 An example of a minimally invasive pressure sensor is shown. Figure 5 An example of a blood oxygen measurement module is shown in the image.

[0040] Figure 2 This is a perspective view of the hemodynamic monitor 12. (See image.) Figure 2 As shown, the hemodynamic monitor 12 includes a display 24, in Figure 1 In the example, display 24 presents a graphical user interface 46, which includes control elements 48 (e.g., graphical control elements) that enable a user to interact with the hemodynamic monitor 12. The hemodynamic monitor 12 may also include multiple input and / or output (I / O) connectors 52 configured for wired connections (e.g., electrical and / or communication connections) to one or more peripheral components, such as one or more hemodynamic sensors 14. Although Figure 2 The example illustration shows five separate I / O connectors 52; however, it should be understood that in other examples, the hemodynamic monitor 12 may include fewer than five or more I / O connectors 52. In still other examples, the hemodynamic monitor 12 may not include I / O connectors 52 and may instead communicate wirelessly with various peripheral devices.

[0041] For reference Figure 1 The hemodynamic monitor 12 includes one or more system processors 20 and a system memory 22 storing GHI software code 30, which is executable to determine overall perfusion insufficiency in patient 16. The hemodynamic monitor 12 can receive sensed hemodynamic data, representing blood oxygenation data, RVP waveforms, and PAP waveforms, such as via one or more hemodynamic sensors 14 connected to the hemodynamic monitor 12 via I / O connectors 52. The hemodynamic monitor 12 executes the GHI software code 30 to determine overall perfusion insufficiency in patient 16, as further described below.

[0042] like Figure 1 As shown, the hemodynamic monitor 12 can display a graphical user interface on the display 24. The display 24 can be an LCD display, an LED display, an OLED display, or other display devices suitable for providing information to the user in graphical form. In some examples, such as Figure 2 For example, display 24 may be a touch-sensitive and / or presence-sensitive display device that is configured to receive user input in the form of gestures, such as touch gestures, scroll gestures, zoom gestures, swipe gestures, or other gesture inputs.

[0043] Hemodynamic monitor 12 receives hemodynamic data from patient 16 via one or more hemodynamic sensors 14A, 14B, 14C, and 14D (collectively referred to as hemodynamic sensors 14). In response to receiving hemodynamic data from patient 16, hemodynamic monitor 12 executes GHI software code 30 to determine global perfusion insufficiency in patient 16 and displays this global perfusion insufficiency information or other information on display 24. In some examples, in response to determining that patient 16 is at risk of experiencing a global perfusion insufficiency event, hemodynamic monitor 12 may invoke sensory alarms, such as auditory alarms, tactile alarms, or other sensory alarms (e.g., sensory alarm 50, such as...). Figure 1 (As shown). Therefore, the hemodynamic monitor 12 can alert medical personnel to potential global hypoperfusion events in patient 16.

[0044] Figure 3This is a perspective view of catheter 54, which can be inserted into patient 16 and connected to one or more hemodynamic sensors 14 for providing hemodynamic data to hemodynamic monitor 12. For example, catheter 54 can be connected to one or more pressure-sensing hemodynamic sensors 14A for detecting RVP, PAP, or right ventricular and pulmonary artery pressures in patient 16. Additionally, catheter 54 can interface with oxygenation module 14B for sensing mixed venous oxygen saturation in patient 16. Catheter 54, protected by sheath 56, includes multiple lumens 58 that communicate fluid connector 60, optical connector 62, thermistor connector 64, and hotwire connector 66 with one of the ports 68, an embedded hemodynamic sensor 14C (e.g., a thermistor), or an embedded hemodynamic sensor 14D (e.g., a hotwire). To facilitate insertion of catheter 54 into patient 16 or for certain hemodynamic measurements, catheter 54 includes a balloon 70 located at the tip 72 of catheter 54.

[0045] like Figure 3 As shown, catheter 54 includes a distal port connector 60A communicating with port 68A at tip 72. A proximal injectable connector 60B communicates with the proximal port 68B located approximately 30 cm from tip 72 and can be used to dispense fluids and medications into the patient's heart. A right ventricular pacing connector 60C communicates with the right ventricular port 68C, which may be spaced approximately 19 cm from tip 72 or approximately 12 to 13 cm from tip 72. Connector 60C can be used to detect RVP. A thermistor connector 64 is electrically connected to a hemodynamic sensor 14C (e.g., a thermistor) mounted near tip 72 of catheter 54 for measuring core blood temperature within the pulmonary artery. In some examples of catheter 54, a hot wire connector 66 is electrically connected to a hemodynamic sensor 14D (e.g., a hot wire) embedded within catheter 54 located within the patient's right ventricle. In some examples, catheter 54 does not include a hot wire or a corresponding hot wire connector 66. The balloon connector 60D communicates with the balloon 70 and can be used to inflate and deflate the balloon 70 by using the syringe 74.

[0046] After insertion into patient 16, for example, via an intubator, the distal port connector 60A and the right ventricular pacing connector 60C can be connected to a separate pressure transducer sensor 14A. The first pressure transducer 14A provides hemodynamic monitor 12 with PAP waveform data sensed at the distal port 68A located within the pulmonary artery of the patient's heart, while the second pressure transducer 14A provides hemodynamic monitor 12 with RVP waveform data sensed at the right ventricular port 68C located within the right ventricle of the patient's heart. Pulmonary artery oxygen saturation data can be provided by the oxygenation module 14B based on light pulses emitted from the oxygenation module 14B into the pulmonary artery and reflected light received by the oxygenation module 14B via the optical connector 62 of catheter 54. Furthermore, using the hot wire connector 66 and the thermistor connector 64, and associated cables, hemodynamic monitor 12 can receive cardiac output data from patient 16 using, for example, thermal dilution techniques. Cardiac output measured via the hot wire and the corresponding hot wire connector 66 can be considered as continuous cardiac output (in Figure 1 The winning designation is "CCO"). If catheter 54 does not include a heating wire, cardiac output can be determined using a thermistor after injecting a fluid bolus (or a set of boluses) of known volume and temperature via the proximal injection port 68B using a thermodilution technique. Cardiac output measured via the thermistor and the corresponding thermistor connector 64 after the injection of the fluid bolus can be considered as intermittent cardiac output (in...). Figure 1 (Illustrated as "ICO" in Chinese). Intermittent cardiac output measurements can be obtained at frequencies on the order of minutes, hours, hours, or even longer intervals, depending on the level of monitoring required by the patient. For example, a clinician may administer a set of 3 to 4 fluid boluses, with one bolus in the set administered approximately once per minute, making the complete bolus set last approximately three minutes. In one example, fluid boluses may be administered very frequently, such as once per minute or every few minutes, when a clinician is assessing a patient's responsiveness to medication or other medical interventions. In another example, fluid boluses may be administered less frequently, such as once per hour, once every six hours, if the patient is relatively stable in the ICU. Therefore, catheter 54 can be used to provide continuous cardiac output and / or intermittent cardiac output.

[0047] Catheter 54 is an example of a catheter that can be used to measure SvO2, RVP, PAP, continuous cardiac output, and / or intermittent cardiac output. In other examples, any catheter configured to measure SvO2, RVP, PAP, continuous cardiac output, and / or intermittent cardiac output can be used. For example, any right heart / pulmonary artery catheter, such as the Swan Ganz catheter, can be used.

[0048] Figure 4This is a perspective view of hemodynamic sensor 14A, which can be attached to patient 16 to sense hemodynamic data representing patient 16's RVP or PAP. Figure 4 As shown, the hemodynamic sensor 14A includes a housing 76, a fluid inlet port 78, a catheter-side fluid port 80, and an I / O cable 82. The fluid inlet port 78 is configured to be connected to a fluid source, such as a saline bag or other fluid input source, via tubing or other hydraulic connection. The catheter-side fluid port 80 is configured to be connected to a catheter (e.g., a radial artery catheter or a femoral artery catheter) via tubing or other hydraulic connection, which is inserted into the patient's arm (i.e., a radial artery catheter) or the patient's leg (i.e., a femoral artery catheter). The catheter may also be inserted into the patient's ventricular system. The I / O cable 82 is configured to be connected via, for example, one or more I / O connectors 52 (… Figure 2 (As shown) is connected to the hemodynamic monitor 12. The housing 76 of the hemodynamic sensor 14A encapsulates one or more pressure transducers, communication circuitry, processing circuitry, and corresponding electronic components to sense fluid pressure corresponding to the RVP or PAP of the patient 16, which is transmitted to the hemodynamic monitor 12 via the I / O cable 82. Figure 2 (As shown).

[0049] In operation, a fluid column (e.g., saline solution) is introduced from a fluid source (e.g., a saline bag) via a hemodynamic sensor 14A through a fluid inlet port 78 into a catheter-side fluid port 80, toward the catheter inserted into the patient 16's arterial and / or ventricular systems. RVP or PAP is transmitted via the fluid column to a pressure sensor located within the housing 76, which detects the pressure of the fluid column. The hemodynamic sensor 14A converts the detected fluid column pressure into an electrical signal via the pressure sensor and outputs the corresponding electrical signal to the hemodynamic monitor 12 via an I / O cable 82. Figure 1 (As shown). Therefore, hemodynamic sensor 14 transmits analog sensor data (or a digital representation of analog sensor data) representing substantially continuous beat-by-beat monitoring of RVP or PAP for patient 16 to hemodynamic monitor 12 (as shown). Figure 1 (As shown).

[0050] Figure 5 This is a perspective view of the pulse oximetry module 14B, which receives pulse oximetry data from a catheter inserted into the patient 16. (See diagram below.) Figure 5 As shown, the hemodynamic sensor 14B includes a light emitter and a light receiver, which are arranged to communicate electrically with the catheter via an I / O connector 84 mounted within the housing 86 and accessible through a protective door 88. Within the housing 86, as... Figure 5As shown, the hemodynamic sensor 14B includes a communication circuit, a processing circuit, and corresponding electronic components to sense blood oxygen saturation data derived from light emission transmitted through a catheter into the patient and corresponding light return received from the patient 16 via the catheter. An electrical signal indicating the patient's blood oxygen saturation level is transmitted to the hemodynamic monitor 12 via a cable 90 and a connector 92, which mates with one of the I / O connectors 52. Figure 2 (As shown).

[0051] Figure 6 This is a block diagram of the GHI algorithm 200. The GHI algorithm 200 includes a feature creation module 202, a model heuristic module 204, and a machine learning model 206. The output of the GHI algorithm 200 is the overall inflation indices 208. The GHI algorithm 200 is... Figure 1 An example of the GHI algorithm module 40 shown.

[0052] The feature creation module 202 in the GHI algorithm 200 can be a model that calculates one or more intermediate features based on RVP features, cardiac output parameters, PAP features, and SvO2 parameters. Such intermediate features may include, for example, arterial elasticity calculated by dividing the average PAP (i.e., from the PAP feature) by the stroke volume (i.e., from the cardiac output parameter). Such intermediate features may also include pulmonary vascular resistance, which is calculated by dividing the average PAP (i.e., from the PAP feature) by the continuous cardiac output (i.e., from the cardiac output parameter). The listed intermediate features are merely examples; multiple additional or alternative features can be calculated by the feature creation module 202 within the GHI algorithm 200.

[0053] The model heuristic module 204 in the GHI algorithm 200 can be used as a validation check for RVP characteristics, cardiac output parameters, PAP characteristics, and SvO2 parameters. Such validation checks can be performed to determine if the data is valid for use in the GHI algorithm 200. Data showing significant anomalies (e.g., SvO2 parameters with low SQI) can be discarded so that it is not used to calculate the overall underperfusion index 208. Similar SQIs can be generated for PAP and RVP waveforms to determine the integrity of the corresponding data. Other methods for assessing data integrity can also be used in the model heuristic module 204 to ensure that the GHI algorithm 200 is not based on erroneous data.

[0054] The machine learning model 206 within the GHI algorithm 200 can be a predictive risk model based on a linearly weighted set of predictive features identified as predictors of global perfusion insufficiency events. In some examples, a regression model minimizing loss is used to identify the features predicting global perfusion insufficiency. Predictive features may include SvO2 parameters, PAP features, RVP features, and cardiac output parameters, which are processed by the GHI algorithm 200. In some examples, the GHI algorithm 200 is configured to predict when a patient's SvO2 will drop below 60%, indicating a global perfusion insufficiency event. Such predictions can be made, for example, 30 minutes to 1 hour before the occurrence of a global perfusion insufficiency event. In other examples, the predicted time may be greater than or less than the indicated range. The machine learning model can be a deep learning model using a neural network architecture.

[0055] The global hypoperfusion index 208 generated by the GHI algorithm 200 can be a numerical value on a defined scale, where the value corresponds to the probability of a global hypoperfusion event occurring. In some examples, the value is divided into ranges, where each range indicates a risk level based on a defined threshold. For example, the global hypoperfusion index 208 can be a numerical score ranging from 0 to 100. A score of 0 to 30 may indicate a stable patient condition, a score of 31 to 60 may indicate a patient who should be observed for global hypoperfusion, and a score of 61 to 100 may indicate a recommendation for patient evaluation. Figure 11 The description elaborates in more detail on the overall underperfusion index 208 and various implementation methods with digital thresholds.

[0056] After determining the overall underperfusion index 208 and the corresponding patient risk level, this information is transmitted via a digital-to-analog converter 28 ( Figure 1 (As shown) Data is transmitted from processor 20 to display 24. Display 24 may be, for example, a patient monitor that can be viewed by a clinician. Display 24 may additionally or alternatively 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. Processor 20 may also be configured to trigger a sensory alarm via display 24 if the overall inadequacy index indicates a recommendation for patient evaluation.

[0057] The hemodynamic monitoring system 10 and the GHI algorithm 200 (an example of the GHI algorithm module 40 that can be used in the GHI software code 30) offer various advantages. System 10 allows for the prediction of global hypoperfusion events in patients based on parameters received from catheter 54. Furthermore, System 10 does this with high accuracy and sufficiently early to allow clinicians to take action. System 10 also provides the advantage of continuously updating the global hypoperfusion index on display 24, allowing clinicians or other observers to determine the patient's real-time health data. Sensory alarms and display 24 allow clinicians to be notified of potential future global hypoperfusion events and to respond accordingly. In some examples, display 24 can be used to display a graph of venous oxygen saturation values ​​changing over time.

[0058] Figure 7 A graph illustrating a right ventricular pressure (RVP) waveform trace 300 is shown, which includes example markers indicating blood flow, cardiac output, and overall perfusion insufficiency. The RVP waveform trace 300 includes markers 306, 308, 310, 312, 314, 316, 318, and 320. The RVP waveform trace 300 corresponds to hemodynamic data sensed by catheter 54, and more specifically, hemodynamic data sensed by hemodynamic sensor 14A. Figure 1 (As shown). The RVP waveform trace 300, represented by digital hemodynamic data, may include various markers indicating blood flow, cardiac output, and overall perfusion inadequacy in patient 16. This is achieved via the execution of the RVP feature module 36 ( Figure 1 As shown, right ventricular features are extracted from the RVP waveform trace 300 (i.e., the RVP waveform). In some examples, the heartbeat detector algorithm identifies the start and end of individual heartbeats within the RVP waveform before extracting markers from the RVP waveform trace 300. The heartbeat detection algorithm can identify the start of a heartbeat based on the maximum RVP, minimum RVP, maximum or minimum rate of change in the RVP, and / or the second derivative of the RVP with respect to time. Following the heartbeat identification within the RVP waveform, various markers for blood flow, cardiac output, and overall perfusion insufficiency can be extracted from the RVP waveform on a continuous, beat-by-beat basis.

[0059] Marker 306 of the RVP waveform trace 300 corresponds to the minimum diastolic pressure. Marker 308 of the RVP waveform trace 300 corresponds to the end-diastolic pressure. Marker 310 of the RVP waveform trace 300 corresponds to the maximum systolic pressure. Marker 312 of the RVP waveform trace 300 corresponds to the end-systolic pressure. The slope S1 is the slope of the RVP waveform trace 300, and it can also be marked. The slope S1 is depicted at one location, but represents multiple slopes that can be determined at multiple locations along the RVP waveform trace 300. For example, marker 314 corresponding to the maximum rate of change of pressure (dP / dt) with respect to time during the systolic rise and marker 316 corresponding to the minimum rate of change of pressure (dP / dt) with respect to time during the relaxation period after the end of systole are other example markers. Similarly, the second time derivative of the RVP waveform trace 300 can be determined at any location along the waveform and used as a marker. Other example markers include the RVP gradient, or the pressure difference at different times during diastole or systole. For example, label 318 corresponds to the diastolic gradient, or the difference between the minimum diastolic pressure (label 306) and the end-diastolic pressure (label 308). Label 320 corresponds to the right ventricular pulse pressure, or the pressure gradient equal to the difference between the end-diastolic pressure (label 308) and the maximum systolic pressure (label 310).

[0060] By executing the system memory 22 ( Figure 1 The RVP feature module 36 (shown) can extract additional markers from the RVP waveform trace 300 during various intervals. For example, the RVP feature module 36 can be used to determine systolic rise (markers 308 to 310), systolic decay (markers 310 to 312), isovolumetric relaxation (markers 312 to 306), diastole (markers 306 to 308), and heart rate intervals (between marks 306). These markers can include the average RVP over one or more time intervals.

[0061] Figure 8 A graph depicting a pulmonary artery pressure (PAP) waveform trace 400 is shown, which includes example markers indicating blood flow, cardiac output, and overall perfusion insufficiency. PAP waveform trace 400 includes markers 424, 426, 428, 430, and 432. PAP waveform trace 400 corresponds to the hemodynamic sensor 14A (contained by catheter 54, more specifically by hemodynamic sensor 14A). Figure 1 The hemodynamic data sensed (shown) is PAP waveform trace 400 (represented via digital hemodynamic data). It may include various markers indicating insufficient blood flow, cardiac output, and overall perfusion in patient 16. This is achieved via the execution of the PAP feature module 34 ( Figure 1As shown, PAP features are extracted from the PAP waveform trace 400 (i.e., the PAP waveform). In some examples, the heartbeat detector algorithm identifies the start and end of each heartbeat in the PAP waveform before extracting the markers from the PAP waveform trace 400. The heartbeat detection algorithm can identify the start of a heartbeat based on the maximum PAP, minimum PAP, maximum or minimum rate of change of the PAP, and / or the second derivative of the PAP with respect to time. After heartbeat identification within the PAP waveform, various indicators of blood flow, cardiac output, and overall perfusion insufficiency can be extracted from the PAP waveform on a continuous, beat-by-beat basis.

[0062] Marker 424 of the PAP waveform trace 400 corresponds to the start of a heartbeat. Marker 426 of the PAP waveform trace 400 corresponds to the maximum cardiac systolic pressure marking the end of the systolic rise. Marker 428 of the PAP waveform trace 400 corresponds to the presence and pressure of the dicrotic notch marking the end of the cardiac systolic decay. Marker 430 of the PAP waveform trace 400 corresponds to the minimum diastolic pressure of patient 16's heartbeat. The mean PAP can also be a marker. The PAP gradient or the pressure difference between points on the PAP waveform trace 400 can be a marker. For example, marker 432 corresponds to pulmonary artery pressure, or the difference between the minimum diastolic pressure (marker 430) and the maximum systolic pressure (marker 426). S2 is the slope of the PAP waveform trace 400, which can also be provided as a marker. The slope S2 is depicted at one location, but represents multiple slopes that can be determined at multiple locations along the PAP waveform trace 400. For example, the marker can include the maximum and / or minimum time derivative of the PAP waveform trace 400.

[0063] By executing system memory 22 ( Figure 1 The PAP feature module 34 (shown) can extract additional markers from the PAP waveform trace 400 during various intervals. For example, the interval from the maximum systolic pressure at marker 426 to the diastolic phase at marker 428, and the interval from the onset of heartbeat at marker 424 to the diastolic phase at marker 430, can be extracted from the PAP waveform trace 400. The PAP feature module 34 can identify additional markers from the PAP waveform trace 400 during various intervals. For example, the PAP feature module 34 can be used to determine the systolic rise (markers 424 to 426), systolic decay (markers 426 to 428), systolic phase (markers 424 to 428), diastolic phase (markers 428 to 430), and heartbeat interval (between markers 424). These markers may include the average PAP during one or more time intervals. The area under the curve of the PAP waveform trace 400 and the standard deviation of the PAP waveform trace 400 determined for the aforementioned intervals can also be used as additional indicators for the patient 16.

[0064] Figure 9This is a schematic diagram of an example of a system 500 for implementing the right ventricular output (RVCO) algorithm. System 500 may be included in... Figure 1 Within system 100, for example, within system memory 22. System 500 is described herein as a standalone system, but components of system 500 may also be integrated with... Figure 1 The components of the system 100 shown are shared. The system 500 can be used with any suitable conduit, such as... Figure 1 The catheter 54 is shown. System 500 includes an RVP feature module 532, a PAP feature module 534, a verification module 536, a flow module 538, and a CO... AE Module 540 (Module for estimating cardiac output based on autoencoder model), CO LR Module 542 (Module for estimating cardiac output using a linear regression model), CO filtered (CO) 经滤波 Module 544 (a module for filtering one or more heart rate output estimates), and output device 102. RVP feature module 532 may be RVP feature module 36, and PAP feature module 534 may be Figure 1 The PAP feature module 34 of system 100 is shown, but for clarity, it is described herein as part of system 500. Verification module 536, flow module 538, CO AE Module 540, CO LR Module 542 and CO filtered Each of modules 544 can be included Figure 1 The RVCO module 38 of system 100 is shown. As a result of software code organization, the number and organization of modules within system 100 may be more or fewer than described herein. The modules of system 500 will be described sequentially; however, these modules may also include overlapping or distributed functionality.

[0065] RVP feature module 532 includes a coded method for extracting RVP features from RVP waveform 530. RVP waveform 530 is similar to... Figure 7 The RVF waveform trace 300 is used. The RVP feature module 532 receives the RVP waveform 530 as input. The RVP waveform 530 corresponds to the hemodynamic data sensed by the catheter 54, and more specifically, by the hemodynamic data sensed by the hemodynamic sensor 14A. The sensed hemodynamic data corresponding to the RVP waveform 530 is transmitted to the RVP feature module 532. The RVP feature module 532 extracts RVP features from the RVP waveform 530. The RVP feature module 532 outputs the RVP features to the verification module 536. The RVP feature module 532 also outputs the RVP features to the CO. LR Module 542 outputs RVP features.

[0066] PAP feature module 534 includes a coded method for extracting PAP features from PAP waveform 528. PAP waveform 528 is similar to... Figure 8 PAP waveform trace 400. PAP feature module 534 receives PAP waveform 528 as input. PAP waveform 528 corresponds to hemodynamic data sensed by catheter 54, more specifically, by hemodynamic data sensed by hemodynamic sensor 14A. The sensed hemodynamic data corresponding to PAP waveform 528 is transmitted to PAP feature module 534. PAP feature module 534 extracts PAP features from PAP waveform 528. PAP feature module 534 outputs PAP features to verification module 536. PAP feature module 534 also outputs PAP features to CO. LR Module 542 outputs RVP features.

[0067] Verification module 536 includes methods in the code for clearing data and ensuring that the RVP waveform 530 and PAP waveform 528 are valid and reliable. Verification module 536 receives the RVP waveform 530, PAP waveform 528, RVP features, and PAP features as input. Verification module 536 can analyze the RVP waveform 530 and / or PAP waveform 528 within a ten-second time period. The ten-second time period is merely an example, and it should be understood that the verification module can use any other suitable time window to evaluate the RVP waveform 530 and PAP waveform 528. Within the applicable time window, the signal quality detector within verification module 536 can analyze the RVP waveform 530 and PAP waveform 528 and assign a signal quality index (SQI) to each waveform based on a signal quality algorithm. The signal quality algorithm can analyze data such as negative pressure, abnormally high pressure, or other physiologically impossible data by comparing the RVP waveform 530 with the PAP waveform 528 and / or by identifying artifacts between the RVP waveform 530 and the PAP waveform 528. Values ​​that are outside the physiologically possible range can be discarded, so the RVP waveform 530 and PAP waveform 528 can be smoothed through this process.

[0068] Verification module 536 Figure 9 The modules contained within the dashed box shown (i.e., flow module 538, CO) AE Module 540, CO LR Module 542 and CO filtered Module 544) outputs instructions indicating whether valid RVP (“RVP_valid”) and valid PAP (“PAP_valid”) are true or false, and can also output instructions to displays such as 24 ( Figure 1The output device 502 (shown) outputs an indication of whether the RVP waveform 530 and PAP waveform 528 are valid. Validity can be determined based on the SQI of each waveform derived from a signal quality algorithm. Instructions indicating that RVP_valid and PAP_valid are true signify that the hemodynamic data corresponding to RVP waveform 530 and PAP waveform 528 are valid for further processing by the module enclosed in the dashed box. Instructions indicating that RVP_valid and PAP_valid are false signify that the hemodynamic data corresponding to RVP waveform 530 and PAP waveform 528 are invalid for further processing. The verification module 536 also outputs a smoothed RVP waveform to the flow module 538 and to the CO... LR Module 542 outputs RVP and PAP features.

[0069] The flow module 538 includes an encoding method for estimating the blood flow waveform from the RVP waveform 530. The flow module 538 receives the RVP waveform 530 as input. The flow module 538 can also receive a smoothed RVP waveform from the verification module 536. The RVP waveform 530 can be transformed and processed via an autoencoder model and a filter. The autoencoder model can derive an estimated waveform of the raw blood flow, and the filter can further process the estimated waveform based on physiological expectations (e.g., removing negative flow, excessively high flow values, flow with very dissimilar stroke volume, etc.) to generate the flow. processed (flow 经处理 The filter can also generate a flow corresponding to the filter. processed SQI. Based on SQI, the flow module 538 can generate flow. processed Indicator of validity.

[0070] Flow module 538 to CO AE Module 540 outputs an instruction indicating whether the valid flow (“flow_valid”) is true or false, and can send this instruction to output device 502 (such as display 24). Figure 1 The output indicates the processed blood flow (as shown). processed The result determines whether the estimated blood flow waveform is valid. A true `flow_valid` command indicates that the estimated blood flow waveform is valid. processed For CO AE Further processing by module 540 is valid. The instruction `flow_valid` being false indicates that the estimated blood flow waveform is valid. processed Further processing was ineffective. Flow module 538 further directed to CO. AE Module 540 output flow processed The flow module 538 can also output flow to the output device 502. processed .

[0071] CO AE Module 540 includes an encoding method for deriving cardiac output from estimated blood flow waveforms. AE Module 540 receives flow processed As input. flow processed Feeding from flow module 538 to CO AE Module 540. CO AE Module 540 also receives an instruction from flow module 538 indicating whether flow_valid is true or false, causing CO to... AE Module 540 can continue or not continue accordingly. If instructed to continue, CO AE Module 540 calculates flow processed The average value of the waveform is used to generate an estimate of the cardiac output. For example, this could be a ten-second flow. processed Partially calculated estimates. CO AE Module 540 to CO LR Module 542 and CO filtered Module 544 outputs the auto encoder core output ("CO"). AE ”). CO AE Module 540 can also output CO to output device 502 AE .

[0072] CO LR Module 542 includes a coding method for estimating cardiac output and cardiac output variation based on RVP and PAP features. LR Module 542 receives RVP characteristics, PAP characteristics, and CO. AE CCO and iCO are used as inputs. RVP features are fed into CO from RVP feature module 532 or verification module 536. LR Module 542. Similarly, PAP features are fed from PAP feature module 534 or verification module 536 to CO. LR Module 542. CO AE From CO AE Module 540 is fed to CO LR Module 542. CCO and iCO correspond to the patient's cardiac output data received from catheter 54. CCO and iCO are passed to CO. LR Module 542.

[0073] CO LRModule 542 may include a regression model configured to estimate the change in cardiac output over time. The regression model may be a machine learning model trained with a training dataset, where the changes in cardiac output and the corresponding changes in RVP and PAP features are known to the patient. Therefore, when RVP and PAP features for a defined time window are provided, the regression model can determine the linear regression change in cardiac output (“ΔCO”) based on a set of reference RVP and PAP features corresponding to a reference time window. LR In some examples, in addition to RVP and PAP features, demographic information and SvO2 are also fed into the regression model.

[0074] CO LR Module 542 may also include a cardiac output estimator, which is then based on ΔCO LR Calculate the linear regression core output ("CO"). LR In some examples, CO AE CCO and iCO are also fed into the cardiac output estimator. In this type of example, CO corresponds to the reference time window. AE The values ​​of CO, CCO, and iCO are used to calculate CO. LR The starting point. CO LR Module 542 to CO filtered Module 544 outputs the linear regression center output ("CO"). LR ") and linear regression cardiac output change ("ΔCO") LR ”). CO LR Module 542 can also output CO to output device 502 LR and ΔCO LR .

[0075] CO filtered Module 544 includes a coded method for filtering cardiac output estimates or cardiac output change estimates via, for example, a Kalman filter algorithm. filtered Module 544 receives CO AE CO LR CCO, iCO and ΔCO LR As input. CO AE From CO AE Module 540 is fed to CO filtered Module 544. CO LR and ΔCO LR From CO LR Module 542 is fed to CO filtered Module 544. (In conjunction with the aforementioned CO) LR In the same manner as module 542, CCO and iCO are also passed to CO. filteredModule 544. CO filtered Module 44 outputs filtered cardiac output ("CO") to output device 102. filtered ") and filtered cardiac output change ("ΔCO") filtered (”).

[0076] Output device 502 is a device used to receive output from system 500. For example... Figure 1 As shown, output device 502 may include display 24. For example, output device 502 may receive a final estimate of flow rate, cardiac output, and / or cardiac output changes for display via display 24. Output device 502 may receive data from flow module 538, CO2, etc. AE Module 540, CO LR Module 542 and CO filtered Module 544 receives the output. More specifically, output device 502 receives the flow. processed CO AE CO LR ΔCO LR CO filtered and ΔCO filtered Each of these outputs can be displayed on monitor 24 as a corresponding graph showing how the value changes over time.

[0077] Although several modules are in Figure 9 The diagram is illustrated as having multiple inputs and outputs, but some inputs and outputs are optional, and many configurations of the System 500 are possible. In some examples, the PAP waveform, CCO, and / or iCO may not be used. In some examples, the patient's cardiac output can be estimated from the CO. AE Module 540, CO LR Module 542 and CO filtered Any one or more outputs of module 544. These configurations may depend on, for example, the conduit 52 used ( Figure 1 The combination or desired output of the hemodynamic sensors within (as shown). Figure 10 One such alternative is described, in which via and Figure 9 The examples depicted use different sets of inputs to calculate the cardiac output.

[0078] Figure 10 This is a schematic diagram of System 600, an alternative example to System 500 for implementing the RVCO algorithm. System 600 can be included in... Figure 1 Within system 100, for example, within system memory 22. System 600 is described herein as a standalone system, but components of system 600 may also be integrated with... Figure 1 The components of the system 100 shown are shared. The system 600 can be used with any suitable conduit, such as... Figure 1 The catheter 54 is shown. System 600 includes an RVP waveform 630, an RVP feature module 632, a verification module 636, a flow module 638, and a CO... AE Module 640, CO LR Module 642, CO filtered Module 644 and output device 602. RVP feature module 632 may be Figure 1 The RVP feature module 36 of system 100 is shown, but for clarity, it is described herein as part of system 600. RVP waveform 630, RVP feature module 632, verification module 636, flow module 638, CO AE Module 640, CO LR Module 642, CO filtered Each of module 644 and output device 602 is generally similar to a component or module having the same name and reference number minus 100, as referenced above. Figure 9 The present paper describes one possible configuration of these components and modules.

[0079] like Figure 10 As shown, the RVP feature module 632 receives the RVP waveform 620 as input. The RVP feature module 632 extracts RVP features from the RVP waveform 630. The RVP feature module 632 outputs the RVP features to the verification module 636. The RVP feature module 632 also outputs the RVP features to the CO. LR Module 642 outputs RVP features.

[0080] The verification module 636 receives the RVP waveform 630 and RVP features as input. The RVP features are fed from the RVP feature module 632 to the verification module 636. The verification module 636 outputs a command to the flow module 638 indicating whether RVP_valid is true or false. A command indicating that RVP_valid is true means that the hemodynamic data corresponding to the RVP waveform 630 is valid for further processing by the flow module 638. A command indicating that RVP_valid is false means that the hemodynamic data corresponding to the RVP waveform 630 is invalid for further processing. The verification module 636 also outputs a smoothed RVP waveform to the flow module 638.

[0081] The flow module 638 receives a smoothed RVP waveform as input from the verification module 636. The flow module 638 then directs the CO... AE Module 640 outputs an instruction indicating whether flow_valid is true or false. A true flow_valid instruction indicates that the estimated blood flow waveform is valid. processed For CO AEFurther processing by module 640 is valid. The instruction `flow_valid` being false indicates that the estimated blood flow waveform is valid. processed Further processing was ineffective. Flow module 638 further directed the CO... AE Module 640 output flow processed The flow module 638 also outputs flow to the output device 602. processed .

[0082] CO AE Module 640 receives flow processed As input. flow processed Feeding from flow module 638 to CO AE Module 640. CO AE Module 640 also receives an instruction from flow module 638 indicating whether flow_valid is true or false, causing CO to... AE Module 640 can continue or not, depending on the situation. AE Module 640 to CO LR Module 642 and CO filtered Module 644 outputs CO AE .

[0083] CO LR Module 642 receives RVP characteristics and CO AE As input, RVP features are fed from RVP feature module 632 to CO. LR Module 642. CO AE From CO AE Module 640 is fed to CO LR Module 642. CO LR Module 642 to CO filtered Module 644 outputs CO LR and ΔCO LR .

[0084] CO filtered Module 644 receives CO AE CO LR and ΔCO LR As input. CO AE From CO AE Module 640 is fed to CO filtered Module 644. CO LR and ΔCO LR From CO LR Module 642 is fed to CO filtered Module 644. CO filtered Module 644 will CO filtered Output to output device 602.

[0085] like Figure 6 As shown, output device 602 receives data from flow module 638 and CO. filtered Module 644 receives the output. More specifically, output device 602 receives the flow. processed and CO filtered Each of these outputs can be displayed (e.g., via display 24, such as...). Figure 1 The graph shown is a curve representing how the value changes over time.

[0086] Systems 500 and 600 are systems that implement right ventricular cardiac output (RVCO) algorithms. Implementing such algorithms within the environment of System 100, used to generate the GHI, allows for the use of reliable cardiac output in GHI algorithm 200. Furthermore, Systems 500 and 600 also generate intermediate data that can be displayed via display 24. In addition to the GHI index, this data can also inform clinicians of key parameters such as flow rate. processed and CO filtered Therefore, systems 500 and 600 are advantageous for providing parameters in GHI calculations and for outputting other key parameters for clinicians.

[0087] Figure 11 This is a table illustrating an example of the output of system 100 used to generate GHI. Figure 11 This includes Table A, which contains various thresholds for risk levels of patient conditions based on the derived GHI (Gross Hourly Index). In the examples in Table A, a GHI of 0 to 30 indicates a stable patient condition. A GHI of 31 to 60 indicates a “close watch” status, suggesting that clinicians should observe the patient in case of worsening condition. A GHI of 61 to 100 suggests that the patient should be evaluated and that clinicians should take further action. In these examples, a GHI of 61 to 100 could indicate that the predicted venous oxygen saturation (SvO2) value will be below 60.

[0088] Table A is merely one example of the output implementation of system 100. In other examples, the threshold of GHI corresponding to a given risk level can be adjusted. In other examples, there may be two, three, or more than three different risk levels, where a predetermined GHI range corresponds to each risk level.

[0089] In some examples, the output of system 100 may include sensory alarms. Therefore, in the example in Table A, a sensory alarm could be output once the patient reaches a GHI of 61 to 100, indicating a recommendation for patient evaluation. In other examples, various sensory alarms may be used to indicate different risk levels (e.g., different sensory alarms for "close observation" and "recommend patient evaluation" situations). In some examples, display 24 may be used to display a graph of venous oxygen saturation values ​​changing over time.

[0090] In some examples, in addition to GHI and sensory alarms, display 24 may also show secondary screening information. When the risk level indication requires patient assessment, secondary screening information can indicate one or more possible causes of the patient's condition. Secondary screening information may indicate whether cardiac output or oxygen uptake is relevant to the patient's condition. If neither cardiac output nor oxygen uptake is a problem, secondary screening information can be omitted.

[0091] Figure 12 This is a flowchart illustrating method 800 for generating GHI. For clarity, method 800 will be described with reference to the reference numerals in the system 100. Method 800 includes steps 802 to 814.

[0092] Method 800 begins at step 802, wherein the hemodynamic monitor 12 receives multiple hemodynamic parameters from catheter 54. Catheter 54 includes multiple hemodynamic sensors, such as hemodynamic sensors 14A, 14B, 14C, and 14D, which are configured to output SvO2 values, RVP waveforms, and PAP waveforms.

[0093] At step 804, the system processor 20 of the hemodynamic monitor 12 uses a first algorithm to derive one or more RVP features from multiple hemodynamic parameters. The first algorithm can be executed when the processor 20 executes the RVP feature module 36. The first algorithm can be executed on the RVP waveform received from the catheter 54.

[0094] At step 806, the system processor 20 of the hemodynamic monitor 12 uses a second algorithm to derive one or more PAP features from multiple hemodynamic parameters. The second algorithm can be executed when the processor 20 executes the PAP feature module 34. The second algorithm can be executed on the PAP waveform received from the catheter 54.

[0095] At step 808, the system processor 20 of the hemodynamic monitor 12 uses a second algorithm to derive one or more cardiac output parameters from a plurality of hemodynamic parameters. The second algorithm can be executed when the processor 20 executes the RVCO module 38. The second algorithm can be executed on RVP waveforms, PAP waveforms, and / or SvO2 data (or any combination thereof) received from the catheter 54.

[0096] At step 810, the processor 20 of the hemodynamic monitor 12 uses a fourth algorithm to derive one or more SvO2 parameters from a plurality of hemodynamic parameters. The fourth algorithm can be executed when the processor 20 executes the oxygenation measurement module 32. The fourth algorithm can be executed based on the SvO2 parameters received from the catheter 54.

[0097] Steps 804, 806, 808, and 810 can be completed in any order. Furthermore, any one of steps 804, 806, 808, and 810 can be completed simultaneously or at different times.

[0098] At step 812, the processor 20 of the hemodynamic monitor 12 derives the GHI. The processor 20 derives the GHI using a predictive decision model based on one or more RVP features, one or more PAP features, one or more cardiac output parameters, and one or more venous oxygen saturation parameters. The GHI derive can be completed when the processor 20 executes the GHI algorithm module 40.

[0099] At step 814, the hemodynamic monitor 12 transmits the GHI to the display 24, where the GHI is displayed. The GHI may be displayed along with a risk level based on, for example, one or more predetermined risk level thresholds, such as regarding... Figure 11 Table A describes those.

[0100] This disclosure describes a system for determining the Global Insufficiency Index (GHI). The GHI is used to predict future global insufficiency events in patients. This system is advantageous because it uses multiple hemodynamic parameters combined with a predictive machine learning model to accurately determine the likelihood of future global insufficiency events. Because of this, clinicians can be alerted to such events in advance and take action before they occur. The system also generates various useful hemodynamic parameters, which clinicians can then view on a display device. The system includes clinician-friendly and easily interpretable outputs. The outputs conform to clinical hemodynamic parameter thresholds used to identify hemodynamically unstable patients.

[0101] Any of the various systems, devices, apparatuses, etc. disclosed herein may be sterilized (e.g., with heat, radiation, ethylene oxide, hydrogen peroxide, etc.) to ensure their safety for patient use, and the methods herein may include sterilization of the relevant systems, devices, apparatuses, etc. (e.g., with heat, radiation, ethylene oxide, hydrogen peroxide, etc.).

[0102] The treatment techniques, methods, procedures, etc. described or suggested in this article or in references incorporated herein by reference may be performed on live animals or on non-living simulations, such as on cadavers, cadaver hearts, anthropomorphic models, simulators (e.g., body parts, tissues, etc. being simulated).

[0103] Detailed Description of Implementation Examples The following is a non-exclusive description of possible embodiments of the present invention.

[0104] A system for determining the Global Insufficiency Index (GHI), representing a prediction of future global insufficiency events in a patient, includes an arterial blood pressure sensor, a ventricular blood pressure sensor, a blood oxygenation module, and an integrated hardware unit. The arterial blood pressure sensor includes a first housing, a first fluid input port connected via conduit to a first fluid source, a first catheter-side fluid port connected to a catheter inserted into the patient's arterial system, a first pressure transducer in communication with the first fluid source via the first catheter-side fluid port, and a first I / O cable in electrical communication with the first pressure transducer. The ventricular blood pressure sensor includes a second housing, a second fluid input port connected via conduit to a second fluid source, a second catheter-side fluid port connected to a catheter inserted into the patient's ventricular system, a second pressure transducer in communication with the second fluid source via the second catheter-side fluid port, and a second I / O cable in electrical communication with the second pressure transducer. The blood oxygenation module includes a light emitter, a light receiver, and an I / O cable in electrical communication with the light emitter and the light receiver. The integrated hardware unit includes a system processor, system memory, a display including a user interface, and an analog-to-digital converter (ADC). The system memory includes instructions that, when executed by the system processor, cause the system to perform the following steps: receiving arterial hemodynamic data from an arterial blood pressure sensor; receiving ventricular hemodynamic data from a ventricular blood pressure sensor; receiving oxygen saturation data from an oxygenation module; deriving one or more right ventricular pressure features from the ventricular hemodynamic data using a first algorithm; deriving one or more pulmonary artery pressure features from the arterial hemodynamic data using a second algorithm; deriving one or more cardiac output parameters from the ventricular hemodynamic data and / or arterial hemodynamic data using a third algorithm; deriving one or more venous oxygen saturation parameters from the oxygen saturation data using a fourth algorithm; deriving the GHI using a predictive decision model based on one or more right ventricular pressure features, one or more pulmonary artery features, one or more cardiac output parameters, and one or more venous oxygen saturation parameters; and displaying the GHI on a hemodynamic display.

[0105] The system described in the preceding paragraph may optionally include, additionally and / or alternatively, any one or more of the following features, configurations and / or additional components: The first algorithm is the right ventricular pressure algorithm.

[0106] The right ventricular pressure algorithm is applied to the right ventricular pressure waveform from ventricular hemodynamic data to derive one or more right ventricular pressure features.

[0107] One or more right ventricular pressure characteristics include one or more of the following: pulse rate, maximum rate of change of pressure relative to time during the rise of systole (“dP / dt”), minimum dP / dt during the relaxation period after end of systole, systolic time, systolic pressure, end-systolic pressure, end-diastolic pressure, pulse pressure, and mean pressure.

[0108] The second algorithm is the pulmonary artery pressure (PAP) algorithm.

[0109] The PAP algorithm is applied to pulmonary artery pressure waveforms from arterial hemodynamic data to derive one or more pulmonary artery pressure features.

[0110] One or more pulmonary artery characteristics include mean pulmonary artery pressure.

[0111] The third algorithm is the right ventricular output (RVCO) algorithm.

[0112] The RVCO algorithm is applied to right ventricular pressure (RVP) waveforms from ventricular hemodynamic data and / or arterial hemodynamic data to derive one or more cardiac output parameters.

[0113] Cardiac output parameters include continuous cardiac output.

[0114] The RVCO algorithm includes applying a verification module to the RVP waveform to determine whether the RVP waveform is valid.

[0115] The RVCO algorithm involves converting the patient's right ventricular pressure waveform into the patient's blood flow waveform using a machine learning model.

[0116] Machine learning models are deep learning models that use neural network architectures.

[0117] The machine learning model is the autoencoder model.

[0118] The RVCO algorithm involves filtering the blood flow waveform to remove artifacts or physiological inaccuracies, thereby generating a processed blood flow waveform.

[0119] The blood flow waveform is processed by removing negative flow, flow values ​​in the thousands, square flow, excessive increase in blood flow, or excessive dissimilar flow per stroke.

[0120] The RVCO algorithm includes generating a signal quality index for the processed blood flow waveform, which indicates signal quality based on the amount of artifacts or physiological inaccuracies removed from the blood flow waveform.

[0121] The signal quality index is generated based on the analysis of 10-second intervals of the patient's blood flow waveform.

[0122] The signal quality index indicates whether the processed blood flow waveform is a valid or invalid processed blood flow waveform.

[0123] Effective processed blood flow waveforms are used to measure one or more cardiac output parameters.

[0124] The RVCO algorithm is applied to right ventricular pressure (RVP) waveforms, pulmonary artery pressure (PAP) waveforms, and intermittent cardiac output from arterial hemodynamic data and / or ventricular hemodynamic data to derive one or more cardiac output parameters.

[0125] The RVCO algorithm includes applying a verification module to the RVP and PAP waveforms to determine whether the RVP and PAP waveforms are valid.

[0126] The fourth algorithm is the venous blood oxygen saturation algorithm.

[0127] The venous oxygen saturation algorithm is used to derive venous oxygen saturation values ​​and signal quality indices from oxygen saturation data.

[0128] The system memory is also encoded with instructions that, when executed by the system processor, cause the system to display a graph of venous oxygen saturation over time on a hemodynamic display.

[0129] The predictive decision model includes a machine learning model, a feature creation module, and a model heuristic module.

[0130] The machine learning model is a predictive risk model based on a linearly weighted predictive feature set that has been identified as a predictor of overall inadequate perfusion events.

[0131] A regression model that minimizes the loss is used to identify the predictive feature set for predicting overall underperfusion events.

[0132] The feature creation module calculates one or more intermediate features based on one or more right ventricular pressure features, one or more cardiac output parameters, one or more pulmonary artery pressure features, and one or more venous oxygen saturation parameters.

[0133] One or more intermediate characteristics include arterial elasticity and pulmonary vascular resistance.

[0134] The model heuristic module performs validation checks on one or more right ventricular pressure features, one or more cardiac output parameters, one or more pulmonary artery pressure features, and one or more venous oxygen saturation parameters to determine whether the data is effective for use in a machine learning model.

[0135] The system memory is also encoded with instructions that, when executed by the system processor, cause the system to assign a risk level to the overall hypoperfusion index based on one or more predetermined thresholds, wherein the risk level indicates the patient’s condition based on the overall hypoperfusion index.

[0136] The system memory is also encoded with instructions that, when executed by the system processor, cause the system to output a sensory alarm when the risk level indicates that patient assessment is required.

[0137] When the predicted venous oxygen saturation value is below 60, the output indicates the risk level to be assessed for the patient.

[0138] One or more predetermined thresholds indicate stable status, careful observation status, and patient assessment recommendation status.

[0139] The system memory is also encoded with instructions that, when executed by the system processor, cause the system to provide secondary screening information indicating one or more possible causes of the patient's condition when the risk level indicates that patient assessment is required.

[0140] Secondary screening information includes information indicating whether cardiac output is related to the patient's condition.

[0141] Secondary screening information includes information indicating whether oxygen uptake is related to the patient's condition.

[0142] The catheter is a pulmonary artery catheter coupled to an arterial blood pressure sensor, a ventricular blood pressure sensor, and a blood oxygen measurement module.

[0143] One or more cardiac output parameters are derived from data generated by the thermistor or hot wire of the catheter.

[0144] The third algorithm is the Arterial Pressure and Cardiac Output (APCO) algorithm.

[0145] A method for determining a Global Insufficiency Index (GHI) representing a prediction of future global insufficiency events in a patient, the method comprising: receiving arterial hemodynamic data from an arterial blood pressure sensor; receiving ventricular hemodynamic data from a ventricular blood pressure sensor; receiving oxygen saturation data from an oxygenation module; deriving one or more right ventricular pressure features from the ventricular hemodynamic data using a first algorithm; deriving one or more pulmonary artery pressure features from the arterial hemodynamic data using a second algorithm; deriving one or more cardiac output parameters from the ventricular hemodynamic data and / or arterial hemodynamic data using a third algorithm; deriving one or more venous oxygen saturation parameters from the oxygen saturation data using a fourth algorithm; deriving the GHI using a predictive decision model based on one or more right ventricular pressure features, one or more pulmonary artery features, one or more cardiac output parameters, and one or more venous oxygen saturation parameters; and displaying the GHI on a hemodynamic display.

[0146] The method in the preceding paragraph may optionally include, additionally and / or alternatively, any one or more of the following features, configurations and / or additional components: The first algorithm is the right ventricular pressure algorithm.

[0147] The right ventricular pressure algorithm is applied to the right ventricular pressure waveform from ventricular hemodynamic data to derive one or more right ventricular pressure features.

[0148] One or more right ventricular pressure characteristics include one or more of the following: pulse rate, maximum rate of change of pressure relative to time during the rise of systole (“dP / dt”), minimum dP / dt during the relaxation period after end of systole, systolic time, systolic pressure, end-systolic pressure, end-diastolic pressure, pulse pressure, and mean pressure.

[0149] The second algorithm is the pulmonary artery pressure (PAP) algorithm.

[0150] The PAP algorithm is applied to pulmonary artery pressure waveforms from arterial hemodynamic data to derive one or more pulmonary artery pressure features.

[0151] One or more pulmonary artery characteristics include mean pulmonary artery pressure.

[0152] The third algorithm is the right ventricular output (RVCO) algorithm.

[0153] Cardiac output parameters include continuous cardiac output.

[0154] The fourth algorithm is the venous blood oxygen saturation algorithm.

[0155] The venous oxygen saturation algorithm is used to derive venous oxygen saturation values ​​and signal quality indices from arterial hemodynamic data and / or ventricular hemodynamic data.

[0156] The method also includes assigning a risk level to the overall hypoperfusion index based on one or more predetermined thresholds, wherein the risk level indicates the patient's condition based on the overall hypoperfusion index.

[0157] The method also includes outputting a sensory alarm when the risk level indication requires patient assessment.

[0158] When the predicted venous oxygen saturation value is below 60, the output indicates the risk level to be assessed for the patient.

[0159] Although the invention has been described with reference to exemplary embodiments, those skilled in the art will understand that various changes can be made without departing from the scope of the invention, and equivalents can be substituted for its elements. Furthermore, many modifications can be made to adapt particular situations or materials to the teachings of the invention without departing from the basic scope of the invention. Therefore, it is intended that the invention be limited to the specific embodiments disclosed, but rather that the invention encompass all embodiments falling within the scope of the appended claims.

Claims

1. A system for determining the Global Infiltration Index (GHI), which represents a prediction of future global infiltration events in a patient, the system comprising: An arterial blood pressure sensor, comprising a first housing, a first fluid input port connected to a first fluid source via a conduit, a first catheter-side fluid port connected to a catheter inserted into a patient's arterial system, a first pressure transducer communicating with the first fluid source through the first catheter-side fluid port, and a first I / O cable electrically communicating with the first pressure transducer. A ventricular blood pressure sensor, comprising a second housing, a second fluid input port connected to a second fluid source via a conduit, a second catheter-side fluid port connected to the catheter inserted into the patient's ventricular system, a second pressure transducer communicating with the second fluid source via the second catheter-side fluid port, and a second I / O cable electrically communicating with the second pressure transducer; A blood oxygen measurement module, comprising a light emitter, a light receiver, and an I / O cable for electrical communication with the light emitter and the light receiver; The integrated hardware unit includes: System processor; System memory; Including the display of the user interface; and Analog-to-digital converter (ADC); The system memory includes instructions that, when executed by the system processor, cause the system to perform the following steps: Receive arterial hemodynamic data from the arterial blood pressure sensor; Receive ventricular hemodynamic data from the ventricular blood pressure sensor; Receive blood oxygen saturation data from the blood oxygen measurement module; One or more right ventricular pressure features are derived from the ventricular hemodynamic data using the first algorithm; One or more pulmonary artery pressure features are derived from the arterial hemodynamic data using a second algorithm; One or more cardiac output parameters are derived from the ventricular hemodynamic data and / or the arterial hemodynamic data using a third algorithm; One or more venous oxygen saturation parameters are derived from the oxygen saturation data using a fourth algorithm; The GHI is derived using a predictive decision model based on one or more right ventricular pressure characteristics, one or more pulmonary artery characteristics, one or more cardiac output parameters, and one or more venous oxygen saturation parameters; and The GHI is displayed on the hemodynamic monitor.

2. The system of claim 1, wherein the first algorithm is a right ventricular pressure algorithm, the right ventricular pressure algorithm being applied to the right ventricular pressure waveform from the ventricular hemodynamic data to derive the one or more right ventricular pressure features, and wherein the one or more right ventricular pressure features include one or more of the following: pulse rate, the maximum rate of change of pressure relative to time during the systolic rise phase, i.e., "dP / dt", the minimum dP / dt during the relaxation phase after end-systole, systolic time, systolic pressure, end-systolic pressure, end-diastolic pressure, pulse pressure, and mean pressure.

3. The system according to claim 1, wherein the second algorithm is a pulmonary artery pressure algorithm, i.e., the PAP algorithm, wherein the PAP algorithm is applied to the pulmonary artery pressure waveform from the arterial hemodynamic data to derive the one or more pulmonary artery pressure features, and wherein the one or more pulmonary artery pressure features include mean pulmonary artery pressure.

4. The system according to claim 1, wherein the third algorithm is a right ventricular cardiac output algorithm, i.e., the RVCO algorithm, wherein the RVCO algorithm is applied to the right ventricular pressure waveform, i.e., the RVP waveform, from the ventricular hemodynamic data and / or the arterial hemodynamic data to derive the one or more cardiac output parameters, and wherein the cardiac output parameters include continuous cardiac output.

5. The system of claim 4, wherein the RVCO algorithm includes applying a verification module to the RVP waveform to determine whether the RVP waveform is valid.

6. The system of claim 4, wherein the RVCO algorithm includes converting the patient's right ventricular pressure waveform into the patient's blood flow waveform via a machine learning model, and wherein the RVCO algorithm includes filtering the blood flow waveform to remove artifacts or physiological inaccuracies, thereby obtaining a processed blood flow waveform.

7. The system of claim 1, wherein the RVCO algorithm is applied to the right ventricular pressure waveform (RVP waveform), pulmonary artery pressure waveform (PAP waveform), and intermittent cardiac output from the arterial hemodynamic data and / or the ventricular hemodynamic data to derive the one or more cardiac output parameters.

8. The system of claim 7, wherein the RVCO algorithm includes applying a verification module to the RVP waveform and the PAP waveform to determine whether the RVP waveform and the PAP waveform are valid.

9. The system according to claim 1, wherein the fourth algorithm is a venous oxygen saturation algorithm, wherein the venous oxygen saturation algorithm is used to derive venous oxygen saturation values ​​and signal quality indices from the oxygen saturation data.

10. The system of claim 1, wherein the system memory is further encoded with instructions that, when executed by the system processor, cause the system to: The graph showing the change of venous blood oxygen saturation value over time is displayed on the hemodynamic monitor.

11. The system according to claim 1, wherein: The predictive decision model includes a machine learning model, a feature creation module, and a model heuristic module; The machine learning model is a risk prediction model based on a linearly weighted set of predictive features, which has been identified as predicting overall infusion insufficiency events. The predictive feature set for predicting these events is identified using a regression model that minimizes the loss. The feature creation module calculates one or more intermediate features based on one or more right ventricular pressure features, one or more cardiac output parameters, one or more pulmonary artery pressure features, and one or more venous oxygen saturation parameters, wherein the one or more intermediate features include arterial elasticity and pulmonary vascular resistance.

12. The system of claim 1, wherein the system memory is further encoded with instructions that, when executed by the system processor, cause the system to: A risk level is assigned to the overall hypoperfusion index based on one or more predetermined thresholds, wherein the risk level indicates the patient's condition based on the overall hypoperfusion index; and When the risk level indication requires patient assessment, a sensory alarm is output, wherein when the predicted venous oxygen saturation value is below 60, an indication is output recommending the risk level for patient assessment.

13. The system of claim 12, wherein the system memory is further encoded with instructions that, when executed by the system processor, cause the system to: When the risk level indication requires patient assessment, secondary screening information indicating one or more possible causes of the patient's condition is provided.

14. The system according to claim 1, wherein the third algorithm is the arterial pressure cardiac output algorithm, i.e., the APCO algorithm.

15. A method for determining the Global Infiltration Index (GHI), which represents a prediction of future global infiltration events in a patient, the method comprising: Receive arterial hemodynamic data from an arterial blood pressure sensor; Receive ventricular hemodynamic data from the ventricular blood pressure sensor; Receives blood oxygen saturation data from the blood oxygen measurement module; One or more right ventricular pressure features are derived from the ventricular hemodynamic data using a right ventricular pressure algorithm; One or more pulmonary artery pressure features are derived from the arterial hemodynamic data using the pulmonary artery pressure algorithm, namely the PAP algorithm. One or more cardiac output parameters are derived from the ventricular hemodynamic data and / or the arterial hemodynamic data using the right ventricular cardiac output algorithm, i.e., the RVCO algorithm. One or more venous oxygen saturation parameters are derived from the oxygen saturation data using a venous oxygen saturation algorithm. The GHI is derived using a predictive decision model based on one or more right ventricular pressure characteristics, one or more pulmonary artery characteristics, one or more cardiac output parameters, and one or more venous oxygen saturation parameters. as well as The GHI is displayed on a hemodynamic monitor.

16. The method of claim 15, wherein the right ventricular pressure algorithm is applied to the right ventricular pressure waveform from the ventricular hemodynamic data to derive the one or more right ventricular pressure features, and wherein the one or more right ventricular pressure features include one or more of the following: pulse rate, the maximum rate of change of pressure relative to time during the systolic rise phase, i.e., "dP / dt", the minimum dP / dt during the relaxation phase after end-systole, systolic time, systolic pressure, end-systolic pressure, end-diastolic pressure, pulse pressure, and mean pressure.

17. The method of claim 15, wherein the PAP algorithm is applied to pulmonary artery pressure waveforms from the arterial hemodynamic data to derive the one or more pulmonary artery pressure features, and wherein the one or more pulmonary artery pressure features include mean pulmonary artery pressure.

18. The method of claim 15, wherein the cardiac output parameter includes continuous cardiac output.

19. The method of claim 15, wherein the venous oxygen saturation algorithm is used to derive venous oxygen saturation values ​​and signal quality indices from the arterial hemodynamic data and / or the ventricular hemodynamic data.

20. The method of claim 15, further comprising: A risk level is assigned to the overall infiltration index based on one or more predetermined thresholds, wherein the risk level indicates the patient's condition based on the overall infiltration index. as well as When the risk level indication requires patient assessment, a sensory alarm is output, wherein when the predicted venous oxygen saturation value is below 60, an indication is output recommending the risk level for patient assessment.

Images