Hemodynamic monitoring with nociception prediction and detection.

Abstract

A hemodynamic monitoring system monitors a patient's arterial pressure and provides an alert to a medical professional of the patient's nociception. The system includes a hemodynamic sensor that generates hemodynamic data representative of the patient's arterial pressure waveform. A hardware processor of the system is configured to execute nociception detection software code to perform waveform analysis of the hemodynamic data to determine a plurality of signal measurements. Detection input features indicative of a nociceptive event in the patient are extracted by the processor from the plurality of signal measurements. A nociceptive score representative of a probability of a nociceptive event in the patient is determined from the detection input features. A sensory alarm is activated in response to the nociceptive score meeting a predetermined detection criterion.

Description

Technical Field

[0004]

[0001] Related Applications This application claims priority based on U.S. Provisional Patent Application No. 63 / 165,702, filed on March 24, 2021, entitled "HEMODYNAMIC MONITOR WITH NOCICEPTION PREDICTION AND DETECTION", the entire disclosure of which is hereby incorporated herein by reference in its entirety.

[0002] This disclosure generally relates to hemodynamic monitoring, and more particularly to using monitored hemodynamic data to detect and predict nociception in a patient.

Background Art

[0003] Nociception is the process by which nerve endings called nociceptors detect a noxious stimulus and transmit a signal interpreted as pain to the central nervous system. Nociception can trigger an involuntary response without or before reaching consciousness, and thus an unconscious patient during surgery may experience pain. To prevent the patient from waking up in pain from surgery, healthcare providers administer analgesics to the patient before and / or during surgery. However, pain thresholds and tolerances vary among patients, and since patients cannot communicate verbally or provide feedback while unconscious, it can be difficult to know the amount of analgesic to administer. If too little analgesic is administered to the patient during surgery, the patient may wake up in pain after surgery. If too much analgesic is administered to the patient during surgery, the patient may experience nausea, drowsiness, impairment of thinking ability, and impairment of function.

[0004] Given the negative consequences of both under-administering and over-administering analgesics to patients, a solution is needed that empowers healthcare professionals to detect or predict unconscious patient nociception during surgery. Accurately detecting or predicting patient nociception during surgery can help healthcare professionals know the appropriate amount of analgesics to administer to patients, preventing them from waking up from surgery due to severe pain and avoiding over-administering analgesics. [Overview of the project] [Means for solving the problem]

[0005] For example, a method for monitoring a patient's arterial pressure and providing alerts to healthcare professionals about the patient's current or predicted future nociceptiveness involves receiving hemodynamic data sensed by a hemodynamic monitor, representing the patient's arterial pressure waveform. The method further involves the hemodynamic monitor performing waveform analysis of the sensed hemodynamic data to calculate multiple signal measurements of the sensed hemodynamic data. The hemodynamic monitor extracts input features from the multiple signal measurements that indicate the patient's current nociceptive events and predict the patient's future nociceptive events. A nociceptive score is determined by the hemodynamic monitor based on the input features. The nociceptive score represents the probability of the patient's current nociceptive events and / or the probability of the patient's future nociceptive events. In response to the nociceptive score meeting a predetermined level criterion, the hemodynamic monitor triggers a sensory alarm and generates a sensory signal.

[0006] In another embodiment, a system for monitoring a patient's arterial pressure and providing alerts to healthcare professionals about patient nociception includes a hemodynamic sensor that generates hemodynamic data representing the patient's arterial pressure waveform. The system also includes a system memory for storing nociception detection software code and a user interface with sensory alarms that provide sensory signals to alert healthcare professionals about nociceptive events. A hardware processor within the system is configured to execute the nociception detection software code to perform waveform analysis of the hemodynamic data and determine a set of signal measurements. The hardware processor is also configured to execute the nociception software code to extract detection input features from the set of signal measurements that indicate a patient nociceptive event. The hardware processor is also configured to execute the nociception software code to determine a nociception score representing the probability of a patient nociceptive event based on the detection input features. The processor is configured to trigger sensory alarms in the user interface in response to the nociception score meeting predetermined detection criteria. [Brief explanation of the drawing]

[0007] [Figure 1] Figure 1 is a perspective view of an exemplary hemodynamic monitor that analyzes a patient's arterial pressure and provides healthcare professionals with risk scores and warnings regarding the patient's nociceptive events. [Figure 2] Figure 2 is a perspective view of an example of a minimally invasive pressure sensor for sensing hemodynamic data representing a patient's arterial pressure. [Figure 3] Figure 3 is a perspective view of an example of a non-invasive sensor for sensing hemodynamic data representing a patient's arterial pressure. [Figure 4] Figure 4 is a block diagram illustrating an exemplary hemodynamic monitoring system that determines a risk score representing the probability of current nociceptive events, future nociceptive events, current hemodynamic drug administration events, future hemodynamic drug administration events, and / or periods of stability for a patient, based on a set of input features derived from signal measurements of the patient's arterial pressure waveform. [Figure 5]Figure 5 shows a clinical dataset containing clinical annotations used for data mining and machine training of a hemodynamic monitoring system. [Figure 6] Figure 6 shows systolic blood pressure and heart rate over time from the clinical dataset in Figure 5, and is a graph showing nociceptive events and analgesic administration. [Figure 7] Figure 7 shows the systolic blood pressure and heart rate over time from the clinical dataset in Figure 5, and is a graph that illustrates a stable episode. [Figure 8] Figure 8 shows systolic blood pressure and heart rate over time from the clinical dataset in Figure 5, and is a graph showing hemodynamic drug administration events and vasopressor administration. [Figure 9] Figure 9 is a flowchart for extracting a set of input features derived from the waveform features of a patient's arterial pressure waveform, for training a machine learning model of a hemodynamic monitoring system. [Figure 10] Figure 10 is a graph showing an example of an arterial pressure waveform trace, including an example of a sign corresponding to a signal measurement used to extract input features for determining a patient's risk score. [Modes for carrying out the invention]

[0008] As described herein, the hemodynamic monitoring system implements a predictive model that generates risk scores representing the probability of a patient experiencing a current nociceptive event, the probability of a patient experiencing a future nociceptive event, and the probability that the patient is experiencing a stable episode. The predictive model of the hemodynamic monitoring system may also optionally generate a risk score representing the probability that the patient has experienced the effects of a previously administered hemodynamic drug (hereinafter referred to as a "hemodynamic drug administration event") and is not experiencing a current nociceptive event. The predictive model of the hemodynamic monitoring system may also optionally generate a risk score representing the probability that the patient will experience the onset of a future hemodynamic drug administration event and is not experiencing the onset of a future nociceptive event.

[0009] The hemodynamic monitoring system's predictive model uses machine learning to extract a set of input features from the patient's arterial pressure. This set of input features is used by the hemodynamic monitoring system to generate the aforementioned risk score for the patient during surgery, for example, in an operating room (OR), intensive care unit (ICU), or other patient care environment. Depending on the risk score level, the hemodynamic monitoring system may signal or alarm healthcare workers to warn them that the patient is experiencing or will soon experience a nociceptive event. Upon receiving the signal, healthcare workers can administer analgesics to the patient to mitigate or prevent the nociceptive event. If the risk score indicates that the patient is experiencing or will soon experience a hemodynamic drug event, the hemodynamic monitoring system may signal healthcare workers to prevent them from confusing the patient's hemodynamic drug event with a nociceptive event.

[0010] The machine learning of the predictive model for the hemodynamic monitoring system is trained using a clinical dataset including arterial pressure waveforms, labeled with clinical annotations for the administration of analgesics, vasopressors, inotropes, fluids, and other drugs that alter cardiovascular hemodynamics. The hemodynamic monitoring system is described in detail below with reference to Figures 1–10.

[0011] Figure 1 is a perspective view of a hemodynamic monitor 10 that determines a score representing the probability of a patient's current nociceptive event and / or a score representing the probability of a patient's future nociceptive event. As illustrated in Figure 1, the hemodynamic monitor 10 includes a display device 12 that presents a graphical user interface including control elements (e.g., graphical control elements) that enable user interaction with the hemodynamic monitor 10, in the embodiment of Figure 1. The hemodynamic monitor 10 may also include a plurality of input and / or output (I / O) connectors configured for wired connections (e.g., electrical and / or communicative connections) to one or more peripheral components, such as one or more hemodynamic sensors, as further described below. For example, as shown in Figure 1, the hemodynamic monitor 10 may include I / O connectors 14. While the embodiment of Figure 1 shows five distinct I / O connectors 14, it should be understood that in other embodiments, the hemodynamic monitor 10 may include fewer than five I / O connectors or more than five I / O connectors. In further embodiments, the hemodynamic monitor 10 may not include the I / O connector 14 and may instead communicate wirelessly with various peripheral devices.

[0012] As further described below, the hemodynamic monitor 10 includes one or more processors and computer-readable memory that stores executable nociceptive detection and prediction software code to generate scores representing the probability of the patient's current (i.e., present) nociceptive events and / or scores representing the probability of the patient's future nociceptive events. The hemodynamic monitor 10 can receive sensed hemodynamic data representing the patient's arterial pressure waveform via one or more hemodynamic sensors connected to the hemodynamic monitor 10, for example, via an I / O connector 14. As further described below, the hemodynamic monitor 10 executes nociceptive prediction software code to obtain a number of nociceptive profiling parameters (e.g., input features) using the received hemodynamic data, which may include one or more vital sign parameters characterizing the patient's vital sign data, as well as differential and combined parameters derived from one or more vital sign parameters.

[0013] As shown in Figure 1, the hemodynamic monitor 10 can present a graphical user interface to the display device 12. The display device 12 can be a liquid crystal display (LCD), a light-emitting diode (LED) display, an organic light-emitting diode (OLED) display, or another display device suitable for providing information to the user in a graphical format. In some embodiments, such as the embodiment in Figure 1, the display device 12 may be a touch-sensitive and / or presence-sensitive display device configured to receive user input in the form of gestures, such as touch gestures, scroll gestures, zoom gestures, swipe gestures, or other gesture inputs.

[0014] Figure 2 is a perspective view of a hemodynamic sensor 16 that can be attached to a patient to sense hemodynamic data representing the patient's arterial pressure. The hemodynamic sensor 16 illustrated in Figure 2 is an example of a minimally invasive hemodynamic sensor that can be attached to a patient, for example, via a radial artery catheter inserted in the patient's arm. In other embodiments, the hemodynamic sensor 16 may be attached to the patient via a femoral artery catheter inserted in the patient's leg.

[0015] As shown in Figure 2, the hemodynamic sensor 16 includes a housing 18, a fluid input port 20, a catheter-side fluid port 22, and an I / O cable 24. The fluid input port 20 is configured to connect via a tube or other hydraulic connection to a fluid source, such as a saline bag or other fluid input source. The catheter-side fluid port 22 is configured to connect via a tube or other hydraulic connection to a catheter (e.g., a radial artery catheter or a femoral artery catheter) inserted into the patient's arm (i.e., a radial artery catheter) or leg (i.e., a femoral artery catheter). The I / O cable 24 is configured to connect to the hemodynamic monitor 10, for example, via one or more of the I / O connectors 14 (Figure 1). The housing 18 of the hemodynamic sensor 16 encloses one or more pressure transducers, communication circuits, processing circuits, and corresponding electronic components to sense the fluid pressure corresponding to the patient's arterial pressure transmitted to the hemodynamic monitor 10 (Figure 1) via the I / O cable 24.

[0016] During operation, a fluid column (e.g., saline solution) is introduced from a fluid source (e.g., a saline bag) through a hemodynamic sensor 16 to a catheter-side fluid port 22 via a fluid input port 20, towards a catheter to be inserted into the patient. Arterial pressure is transmitted through the fluid column to a pressure sensor located in a housing 16 that senses the pressure in the fluid column. The hemodynamic sensor 16 converts the sensed pressure in the fluid column into an electrical signal via a pressure transducer and outputs the corresponding electrical signal to the hemodynamic monitor 10 (Figure 1) via an I / O cable 24. Thus, the hemodynamic sensor 16 transmits analog sensor data (or a digital representation of analog sensor data) to the hemodynamic monitor 10 (Figure 1), which represents substantially continuous beat-to-beat monitoring of the patient's arterial pressure.

[0017] Figure 3 is a perspective view of a hemodynamic sensor 26 for sensing hemodynamic data representing a patient's arterial pressure. The hemodynamic sensor 26 illustrated in Figure 3 is an example of a non-invasive hemodynamic sensor that can be attached to a patient via one or more finger cuffs to sense data representing a patient's arterial pressure. As shown in Figure 3, the hemodynamic sensor 26 includes an inflatable finger cuff 28 and a cardiac reference sensor 30. The inflatable finger cuff 28 includes an inflatable blood pressure bladder configured to inflate and deflate as controlled by a pressure controller (not shown) pneumatically connected to the inflatable finger cuff 28. The inflatable finger cuff 28 also includes an optical (e.g., infrared) transmitter and an optical receiver electrically connected to the pressure controller (not shown) to measure the changing volume of the artery beneath the finger cuff.

[0018] During operation, the pressure controller continuously adjusts the pressure within the finger cuff to maintain a constant volume of the finger artery (i.e., the unloaded volume of the artery) as measured via the optical transmitter and optical receiver of the inflatable finger cuff 28. The pressure applied by the pressure controller to continuously maintain the unloaded volume represents the blood pressure in the finger and is communicated by the pressure controller to the hemodynamic monitor 10 shown in Figure 1. The cardiac reference sensor 30 measures the difference in hydrostatic height between the level at which the finger is held and the reference level for pressure measurement, which is typically the cardiac level. Thus, the hemodynamic sensor 26 transmits sensor data representing a substantially continuous beat-to-beat monitoring of the patient's arterial pressure waveform.

[0019] FIG. 4 is a block diagram of a hemodynamic monitoring system 32 that determines an insult tolerance score representing the probability of a current or future insult tolerance event for patient 36 based on a set of insult tolerance profiling parameters (also referred to as input features) derived from the patient's arterial pressure. The hemodynamic monitoring system 32 monitors the arterial pressure of patient 36 and provides a warning to healthcare provider 38 when the insult tolerance score of patient 36 exceeds a predetermined threshold. The healthcare provider 38 can respond to the warning by administering an appropriate analgesic to patient 36 to reduce a current or future insult tolerance event.

[0020] As shown in FIG. 4, the hemodynamic monitoring system 32 includes a hemodynamic monitor 10 and a hemodynamic sensor 34. The hemodynamic monitoring system 32 can be implemented within a patient care environment, such as an ICU, an OR, or other patient care environment. As shown in FIG. 4, the patient care environment can include patient 36 and a healthcare provider 38 trained to utilize the hemodynamic monitoring system 32.

[0021] As described above with respect to FIG. 1, the hemodynamic monitor 10 can be an integrated hardware unit that includes, for example, a system processor 40, a system memory 42, a display device 12, an analog-to-digital (ADC) converter 44, and a digital-to-analog (DAC) converter 46. In other embodiments, any one or more components and / or the described functionality of the hemodynamic monitor 10 can be distributed among multiple hardware units. For example, in some embodiments, the display device 12 can be a separate display device that is remote from the hemodynamic monitor 10 and operably coupled to the hemodynamic monitor 10. In general, although illustrated and described as an integrated hardware unit in the embodiment of FIG, 4, it should be understood that the hemodynamic monitor 10 can include any combination of devices and components that are operably connected electrically, communicatively, or otherwise to implement the functionality attributed to the hemodynamic monitor 10 herein.

[0022] As shown in Figure 4, the system memory 42 stores nociceptive software code 48 that forms a predictive model for the hemodynamic monitor 10. The nociceptive software code 48 includes a first module 50 for extracting and calculating waveform features from the patient's 36 arterial pressure, a second module 51 for extracting input features from the waveform features, and a third module 52 for calculating the probability of nociceptiveness for the patient 36 based on the input features. The display device 12 provides a user interface 54 that includes control elements 56 that enable user interaction with the hemodynamic monitor 10 and / or other components of the hemodynamic monitoring system 32. As illustrated in Figure 4, the user interface 54 also provides sensory alarms 58 to alert healthcare professionals about current or predicted future nociceptive events for the patient 36, as will be further described below. The sensory alarms 58 may be implemented as one or more of visual, audible, tactile, or other types of sensory alarms. For example, the sensory alarm 58 may be triggered as any combination of flashing graphics and / or colored graphics indicated by the user interface 54 on the display device 12, a display of a nociceptivity score via the user interface 54 on the display device 12, a warning sound such as a siren or repetitive sound, and a tactile alarm configured to cause the hemodynamic monitor 10 to vibrate or otherwise deliver a physical impulse perceptible to a healthcare worker 38 or other user.

[0023] The hemodynamic sensor 34 can be attached to patient 36 to sense hemodynamic data representing the patient's arterial pressure waveform. The hemodynamic sensor 34 is operably connected to the hemodynamic monitor 10 (e.g., electrically and / or communicatively via wired, wireless, or both) to provide the sensed hemodynamic data to the hemodynamic monitor 10. In some embodiments, the hemodynamic sensor 34 provides the hemodynamic data representing the patient's arterial pressure waveform to the hemodynamic monitor 10 as an analog signal, which is converted by the ADC 44 into digital hemodynamic data representing the arterial pressure waveform. In other embodiments, the hemodynamic sensor 34 can provide the sensed hemodynamic data to the hemodynamic monitor 10 in digital format, in which case the hemodynamic monitor 10 does not have to include or utilize the ADC 44. In yet another embodiment, the hemodynamic sensor 34 can provide hemodynamic data representing the arterial pressure waveform of the patient 36 to the hemodynamic monitor 10 as an analog signal, which is then analyzed by the hemodynamic monitor 10 in its analog form.

[0024] The hemodynamic sensor 34 may be a non-invasive or minimally invasive sensor attached to the patient 36. For example, the hemodynamic sensor 34 may take the form of a minimally invasive hemodynamic sensor 16 (Figure 2), a non-invasive hemodynamic sensor 26 (Figure 3), or other minimally invasive or non-invasive hemodynamic sensors. In some embodiments, the hemodynamic sensor 34 can be non-invasively attached to an extremity of the patient 36, such as the wrist, arm, fingers, ankle, toes, or other extremities of the patient 36. Thus, the hemodynamic sensor 34 can take the form of a small, lightweight, and comfortable hemodynamic sensor suitable for prolonged wear by the patient 36, and can provide substantially continuous beat-to-beat monitoring of the patient 36's arterial pressure over a long period, such as several minutes or several hours.

[0025] In certain embodiments, the hemodynamic sensor 34 may be configured to sense the arterial pressure of patient 36 in a minimally invasive manner. For example, the hemodynamic sensor 34 can be attached to patient 36 via a radial artery catheter inserted into the patient's arm. In other embodiments, the hemodynamic sensor 34 can be attached to patient 36 via a femoral artery catheter inserted into the patient's leg. Such minimally invasive techniques can also enable the hemodynamic sensor 34 to provide substantially continuous beat-to-beat monitoring of the patient's arterial pressure over a long period, such as several minutes or several hours.

[0026] The system processor 40 is a hardware processor configured to execute nociceptive software code 48, which implements a first module 50, a second module 51, and a third module 52 to generate a nociceptive score representing the probability of a patient 36's current nociceptive event or the probability of a future nociceptive event. An example of the system processor 40 may include any one or more of the following: a microprocessor, a controller, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other equivalent discrete logic circuits or integrated logic circuits.

[0027] The system memory 42 may be configured to store information within the hemodynamic monitor 10 during operation. In some embodiments, the system memory 42 is described as a computer-readable storage medium. In some embodiments, the computer-readable storage medium may include a non-temporary medium. The term “non-temporary” may indicate that the storage medium is not embodied in a carrier wave or propagating signal. In certain embodiments, the non-temporary storage medium may store data that may change over time (e.g., in RAM or a cache). The system memory 42 may include volatile and non-volatile computer-readable memory. Examples of volatile memory include random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), and other forms of volatile memory. Examples of non-volatile memory include, for example, magnetic hard disks, optical disks, flash memory, or electrically programmable memory (EPROM) or electrically erasable programmable memory (EEPROM).

[0028] The display device 12 can be a liquid crystal display device (LCD), a light-emitting diode (LED) display device, an organic light-emitting diode (OLED) display device, or other display device suitable for providing information to the user in a graphical format. The user interface 54 may include graphical and / or physical control elements that enable user input to interact with the hemodynamic monitor 10 and / or other components of the hemodynamic monitoring system 32. In some embodiments, the user interface 54 may take the form of a graphical user interface (GUI) that presents graphical control elements presented on, for example, a touch-sensitive and / or presence-sensitive display screen of the display device 12. In such embodiments, user input may be received in the form of gesture input, such as touch gestures, scroll gestures, zoom gestures, or other gesture inputs. In certain embodiments, the user interface 54 may take the form of physical control elements, such as physical buttons, keys, knobs, or other physical control elements configured to receive user input that interacts with components of the hemodynamic monitoring system 32, and / or include them.

[0029] During operation, the hemodynamic sensor 34 senses hemodynamic data representing the arterial pressure waveform of the patient 36. The hemodynamic sensor 34 provides the hemodynamic data (for example, as analog sensor data) to the hemodynamic monitor 10. The ADC 44 converts the analog hemodynamic data into digital hemodynamic data representing the patient's arterial pressure waveform.

[0030] The nociceptive software code 48 may include nociceptive detection software code. The system processor 40 executes the nociceptive detection software code of the nociceptive software code 48 to determine a nociceptive detection score representing the probability of the patient 36's current nociceptive event, using the received hemodynamic data. For example, the system processor 40 may execute a first module 50 to perform waveform analysis of the hemodynamic data and determine several signal measurements. The system processor 40 executes a second module 51 to extract nociceptive detection input features from the several signal measurements to detect the patient 36's nociceptive event. The system processor 40 executes a third module 52 to determine a nociceptive detection score representing the probability of the patient 36's nociceptive event, based on the nociceptive detection input features. If the nociceptive detection score meets a predetermined detection criterion, the system processor 40 activates a sensory alarm 58 on the user interface 54 and transmits a first sensory signal to warn the healthcare worker 38 that the patient 36 is currently experiencing the current nociceptive event. A healthcare worker 38 may respond to a warning by administering an analgesic to the patient 36 or by administering any other form of treatment to the patient 36.

[0031] The nociceptive software code 48 may also include nociceptive prediction software code. The system processor 40 executes the nociceptive prediction software code of the nociceptive software code 48 to determine a nociceptive prediction score representing the probability of a future nociceptive event for patient 36, using the received hemodynamic data. For example, the system processor 40 may execute a first module 50 to perform waveform analysis of the hemodynamic data to determine several signal measurements. The system processor 40 executes a second module 51 to extract nociceptive prediction input features from the several signal measurements that predict a future nociceptive event for patient 36. The system processor 40 executes a third module 52 to determine a nociceptive prediction score representing the probability of a future nociceptive event for patient 36, based on the nociceptive prediction input features. If the nociceptive prediction score meets a predetermined prediction criterion, the system processor 40 activates a sensory alarm 58 on the user interface 54 and transmits a second sensory signal to warn the healthcare worker 38 that patient 36 will soon experience a future nociceptive event. A healthcare professional 38 may respond to this warning by administering an analgesic to the patient 36 or by administering any other form of treatment to the patient 36, thereby mitigating or preventing the onset of the anticipated future nociceptive event.

[0032] In addition to detecting current nociceptive events in patient 36 and predicting future nociceptive events, the hemodynamic monitoring system 32 can identify when patient 36 is experiencing a current nociceptive event and when patient 36 is merely reacting to a hemodynamic drug previously administered to patient 36 by a healthcare professional 38 (hereinafter referred to as a hemodynamic drug administration event). A hemodynamic drug administration event is defined as an event in which patient 36 experiences an increase in heart rate and blood pressure due to the administration of a compound that alters cardiovascular hemodynamics (e.g., analgesics, vasopressors, inotropes, fluids, and / or other drugs), and is not a nociceptive event of patient 36. The nociceptive software code 48 includes hemodynamic drug detection software code for detecting the presence of a hemodynamic drug administration event in patient 36. The system processor 40 executes the hemodynamic drug detection software code of the nociceptive software code 48 to determine a hemodynamic drug detection score, which represents the probability that a hemodynamic drug administration event is the cause of the increase in patient 36's heart rate and blood pressure, using the received hemodynamic data. For example, the system processor 40 may execute a first module 50 to perform waveform analysis of the hemodynamic data and determine multiple signal measurements. The system processor 40 executes a second module 51 to extract hemodynamic drug detection input features from the multiple signal measurements to detect the current effect of the hemodynamic drug administration event in patient 36. The system processor 40 executes a third module 52 to determine the hemodynamic drug detection score for patient 36 based on the hemodynamic drug detection input features. If the hemodynamic drug detection score meets a predetermined hemodynamic detection criterion, the system processor 40 activates a sensory alarm 58 on the user interface 54 and transmits a third sensory signal to warn the healthcare worker 38 that patient 36 is experiencing a hemodynamic drug administration event rather than a current nociceptive event. The hemodynamic drug detection score and the third sensory signal help prevent healthcare professionals 38 from confusing hemodynamic drug administration events with nociceptive events and from unnecessarily administering analgesics to patients 36.

[0033] The nociceptive software code 48 also includes hemodynamic drug prediction software code for detecting the onset of a future hemodynamic drug administration event in patient 36. The system processor 40 executes the hemodynamic drug prediction software code of the nociceptive software code 48 to determine a hemodynamic drug prediction score, which represents the probability that a hemodynamic drug administration event is the cause of an increase in heart rate and blood pressure in patient 36, using the received hemodynamic data. For example, the system processor 40 may execute a first module 50 to perform waveform analysis of the hemodynamic data to determine several signal measurements. The system processor 40 executes a second module 51 to extract hemodynamic drug prediction input features from the several signal measurements that will detect the onset of a hemodynamic drug administration event in patient 36. The system processor 40 executes a third module 52 to determine the hemodynamic drug prediction score for patient 36 based on the hemodynamic drug prediction input features. If the hemodynamic drug prediction score meets the predetermined hemodynamic prediction criteria, the system processor 40 activates a sensory alarm 58 on the user interface 54 and transmits a fourth sensory signal to warn the healthcare worker 38 that the patient 36 will soon experience a hemodynamic drug administration event. The hemodynamic drug prediction score and the fourth sensory signal help prevent the healthcare worker 38 from confusing a future hemodynamic drug administration event with a future nociceptive event, and thus prevent the healthcare worker 38 from administering unnecessary analgesics to the patient 36.

[0034] The system memory 42 of the hemodynamic monitor 10 may also include stability detection software code for detecting stable episodes in patient 36. A stable episode is defined as a period in which patient 36 does not experience a nociceptive event or a hemodynamic drug administration event. The stability detection software code may be a subpart of the nociceptive software code 48. The system processor 40 executes the stability detection software code to extract stability detection input features from multiple signal measurements. The stability detection software code may use a second module 51 to extract stability detection input features from multiple signal measurements. The stability detection input features detect stable episodes in patient 36. The system processor 40 executes a third module 52 to determine patient 36's stability score based on the stability detection input features. The system processor 40 outputs patient 36's stability score to the user interface 54 of the display device 12.

[0035] The system processor 40 can execute a first module 50 to extract a single batch of multiple signal measurements for a given unit time, and this single batch of signal measurements can be used by a second module 51 to extract all of the nociceptive detection input features, nociceptive prediction input features, hemodynamic drug detection input features, hemodynamic drug prediction input features, and stable detection input features for that unit time. The second module 51 can simultaneously extract all of the nociceptive detection input features, nociceptive prediction input features, hemodynamic drug detection input features, hemodynamic drug prediction input features, and stable detection input features from the multiple signal measurements. The system processor 40 can execute a third module 52 to simultaneously determine the nociceptive detection score, nociceptive prediction score, hemodynamic drug detection score, hemodynamic drug prediction score, and stable score. In some embodiments, the nociceptive software code 48 of the hemodynamic monitor 10 can utilize a classification machine learning model with binary positive vs. negative labels. In certain embodiments, the processor 40 can output the nociceptive detection score and the hemodynamic drug detection score together to the display device 12, allowing the two probabilities to be compared and contrasted, which can help healthcare professionals 38 better understand whether a nociceptive event or a hemodynamic drug administration event is causing an increase in blood pressure and heart rate in the patient 36.

[0036] Alternatively, the nociceptive software code 48 of the hemodynamic monitor 10 can utilize a multiclass machine learning model with three labels: nociceptive events, hemodynamic drug events, and stable episodes. For example, the processor 40 can output a nociceptive detection score along with both a stable score and a hemodynamic drug detection score to the display device 12 so as to compare all three probabilities with each other: the probability that the patient is experiencing a current nociceptive event, the probability that the patient is experiencing a current hemodynamic drug administration event, and the probability that the patient is stable. As will be discussed below with reference to Figures 5-8, the machine learning model of the hemodynamic monitor 10 can be trained to recognize and / or predict these types of events and episodes in the arterial pressure waveform of patient 36 using a clinical dataset that includes arterial pressure waveforms and clinical annotations of the administration of compounds that alter cardiovascular hemodynamics (e.g., analgesics, vasopressors, inotropes, fluids, and / or other drugs).

[0037] Figure 5 is a diagram of a clinical dataset 60 used for data mining and machine training of the hemodynamic monitor 10. The clinical dataset 60 includes a first dataset 61 containing a collection of arterial pressure waveforms recorded from previous patients. The first dataset 61 may be collected by an invasive hemodynamic sensor, such as the hemodynamic sensor 16 shown in Figure 2, or by a non-invasive hemodynamic sensor, such as the hemodynamic sensor 26 shown in Figure 3. The clinical dataset 60 also includes a second dataset 62 containing a log of instances in which compounds that alter cardiovascular hemodynamics (e.g., analgesics, vasopressors, inotropes, fluids, and / or other drugs) were administered to previous patients in the first dataset 61 while their arterial pressure waveforms were being recorded. Healthcare professionals can directly input administration information into the same hemodynamic monitor collecting the first dataset 61 so that the first dataset 61 and the second dataset 62 are collected together simultaneously. As shown in Figures 6-8, the information from the second dataset 62 is annotated and labeled with the arterial pressure waveform collection from the first dataset 61.

[0038] Figure 6 is a graph showing a plot of systolic blood pressure over time (hereinafter referred to as the "SBP plot") and a plot of heart rate over time (hereinafter referred to as the "HR plot"). Before the clinical dataset 60 can be used to machine-train the hemodynamic monitor 10, the SBP plot and HR plot are determined for each of the arterial pressure waveforms collected in the clinical dataset 60. The SBP plot and HR plot shown in Figure 6 are examples from one of the arterial pressure waveforms (not shown) in the clinical dataset 60. After the SBP plot and HR plot have been determined for each of the arterial pressure waveforms collected in the clinical dataset 60, both the SBP plot and HR plot are annotated to indicate when a compound that alters cardiovascular hemodynamics was administered to a clinical patient. For example, the SBP plot and HR plot shown in Figure 6 include an analgesic label 64, which is a vertical bar extending across the SBP plot and HR plot at the same position in time. The analgesic label 64 in Figure 6 indicates that the clinical patient was administered an analgesic during the time shown by the SBP and HR plots in Figure 6. After the SBP and HR plots are annotated and labeled to indicate drug administration to the clinical patient, the nociception data segment 66 is identified and labeled on the SBP and HR plots.

[0039] As shown in Figure 6, the nociceptive data segment 66 is identified on the SBP plot and HR plot by finding a time segment in both the SBP plot and HR plot where the clinical patient's systolic blood pressure increased by at least a threshold amount (e.g., 20% or other threshold amount) compared to the previous period, the clinical patient's heart rate also increased by at least a threshold amount (e.g., 20% or other threshold amount) compared to the previous period, and the infusion of a cardiovascular hemodynamic compound (e.g., analgesic, vasopressor, inotropic agent, fluid, and / or other drug) was not initiated before the increase in blood pressure and heart rate. In Figure 6, both the SBP plot and HR plot increase by more than 20% at the start point 68, which occurs before the analgesic label 64, thus indicating the start of the nociceptive data segment 66 in Figure 6. The nociceptive data segment 66 in Figure 6 continues until both the SBP plot and HR plot begin to decrease as a result of the analgesic administered to the clinical patient at just the right time with the analgesic label 64. The decrease in the SBP plot and HR plot is indicated by the end point 70. Both the start point 68 and the end point 70 are labeled on the HR plot and SBP plot, and the time segment between the start point 68 and the end point 70 is designated as a single nociceptive data segment 66. Once the analgesic label 64 and the nociceptive data segment 66 are identified on the SBP plot and HR plot, the arterial pressure waveforms used to generate the SBP plot and HR plot in Figure 6 may also be annotated and labeled to indicate when the analgesic label 64 and the nociceptive data segment 66 occurred on the arterial pressure waveform. Once labeled with the analgesic label 64 and the nociceptive data segment 66, the arterial pressure waveforms are ready to be used for data mining and machine training of the hemodynamic monitor 10 to detect nociceptive events. Waveform analysis is performed on the clinical dataset 60 containing the nociceptive data segment 66 to compute multiple signal measurements that will then be used to compute nociceptive detection input features that best detect the probability of the current nociceptive event, as will be further discussed below with reference to Figures 9-10.

[0040] The predictive data segment 71 in Figure 6 may also be used for machine training of the hemodynamic monitor 10 to predict future nociceptive events. The predictive data segment 71 may be identified within the clinical dataset 60 by identifying the preceding period before the start of increases in the SBP and HR plots. In the example in Figure 6, the preceding period occurs before the start point 68. The preceding period before the start point 68 is labeled as the predictive data segment 71. In some embodiments, the predictive data segment 71 includes a period that starts 15 minutes before the nociceptive data segment 66 and ends immediately before the nociceptive data segment 66. In other embodiments, the predictive data segment 71 may include a larger or smaller period before the nociceptive data segment 66. Once the predictive data segment 71 is identified and labeled on the SBP and HR plots, the arterial pressure waveforms used to generate the SBP and HR plots in Figure 6 may also be annotated and labeled to indicate when the predictive data segment 71 occurred on the arterial pressure waveforms. Once labeled with the predictive data segment 71, the arterial pressure waveforms are ready for use in data mining and machine training of the hemodynamic monitor 10 to predict nociceptive events. Waveform analysis is performed on the clinical dataset 60, including the predictive data segment 71, to compute multiple signal measurements that will then be used to compute nociceptive predictive input features that best detect the probability of the onset of a future nociceptive event, as will be further discussed below with reference to Figures 9-10.

[0041] Figure 7 is a graph showing another SBP plot and HR plot derived from an arterial pressure waveform segment (not shown) from a clinical dataset 60. The arterial pressure waveform segment that generated the SBP and HR plots in Figure 7 is identified as a stable data segment 72 and can be used for data mining and machine training of the hemodynamic monitor 10 to detect when a patient is experiencing a stable episode without nociception. The arterial pressure waveform segment of the clinical dataset 60 is identified as a stable data segment 72 if there is no increase greater than a threshold amount (e.g., 20% or other threshold amount) in the SBP plot, no increase greater than a threshold amount (e.g., 20% or other threshold amount) in the HR plot, and no infusion of a compound that alters cardiovascular hemodynamics is performed. As shown in the example in Figure 7, the SBP plot does not contain an increase greater than 20% between the start point 74 and the end point 76. The HR plot in the example in Figure 7 also does not contain an increase greater than 20% between the start point 74 and the end point 76. The HR and SBP plots in Figure 7 also do not include any annotations or labels indicating the infusion of compounds that alter cardiovascular hemodynamics in clinical patients between the start point 74 and the end point 76. Given the aforementioned characteristics of the HR and SBP plots in the example of Figure 7, the HR and SBP plots in Figure 7 are labeled as stable data segments 72 between the start point 74 and the end point 76. The arterial pressure waveform segments (not shown) that generated the HR and SBP plots in Figure 7 are also labeled as stable data segments 72 between the start point 74 and the end point 76. Once labeled as stable data segments 72, the arterial pressure waveform segments are ready for use in stable data mining and stable machine training of the hemodynamic monitor 10. Waveform analysis is performed on the clinical dataset 60 containing the stable data segments 72 to compute multiple signal measurements that are subsequently used to compute stable detection input features that best detect the probability of a stable episode, as will be further discussed below with reference to Figures 9-10.

[0042] Figure 8 is a graph showing another SBP plot and HR plot derived from an arterial pressure waveform segment (not shown) from a clinical dataset 60. The arterial pressure waveform segment that generated the SBP and HR plots in Figure 8 is identified as a hemodynamic drug administration data segment 78 (hereinafter referred to as "HDA data segment 78") and can be used for data mining and machine training of the hemodynamic monitor 10 to detect when a patient is experiencing a current hemodynamic drug administration event. An arterial pressure waveform segment from the clinical dataset 60 is identified as an HDA data segment 78 if the arterial pressure waveform segment includes an infusion of a compound that alters cardiovascular hemodynamics to a clinical patient, and there is at least a threshold amount increase (e.g., 20% or another threshold amount) in both the SBP plot and HR plot after the infusion. In the example in Figure 8, the vasopressor infusion label 80 on the SBP plot and HR plot indicates that the clinical patient was administered a vasopressor. Immediately after the vasopressor infusion label 80, the SBP plot increased by at least 20% between the start point 82 and the end point 84. Between the start point 82 and the end point 84, the HR plot also increased by at least 20%, thus indicating that the HDA data segment 78 occurred between the start point 82 and the end point 84. The HR plot and SBP plot in Figure 8 are labeled as the HDA data segment 78 between the start point 82 and the end point 84. The arterial pressure waveform segment (not shown) that generated the HR plot and SBP plot in Figure 8 is also labeled as the HDA data segment 78 between the start point 82 and the end point 84. Once labeled as the HDA data segment 78, the arterial pressure waveform segment is ready for use in hemodynamic drug detection data mining and machine training of the hemodynamic monitor 10. Waveform analysis is performed on the clinical dataset 60, including the HDA data segment 78, to compute multiple signal measurements that will then be used to compute hemodynamic drug detection input features that best detect the probability of the current hemodynamic drug administration event, as will be further discussed below with reference to Figures 9-10.

[0043] The hemodynamic drug prediction data segment 85 (hereinafter referred to as "HDP data segment 85") in Figure 8 may also be used for machine training of the hemodynamic monitor 10 to predict future hemodynamic drug administration events. The HDP data segment 85 may be identified within the clinical dataset 60 by identifying the prior period before the start of the increase in the SBP and HR plots in Figure 8. In the example in Figure 8, the prior period occurs before the start point 82. The prior period before the start point 82 is labeled as the HDP data segment 85. In some embodiments, the HDP data segment 85 includes a period that starts 15 minutes before the HDA data segment 78 and ends immediately before the HDA data segment 78. In other embodiments, the HDP data segment 85 may include a larger or smaller period before the HDA data segment 78. Once the HDP data segment 85 is identified and labeled on the SBP plot and HR plot, the arterial pressure waveforms used to generate the SBP plot and HR plot in Figure 8 may also be annotated and labeled to indicate when the HDP data segment 85 occurred on the arterial pressure waveform. Once labeled with the HDP data segment 85, the arterial pressure waveforms are ready to be used for data mining and machine training of the hemodynamic monitor 10 to predict the onset of future hemodynamic drug administration events. Waveform analysis is performed on the clinical dataset 60, including the HDP data segment 85, to compute multiple signal measurements that will then be used to compute hemodynamic drug prediction input features that best detect the probability of the onset of future hemodynamic drug administration events, as will be further discussed below with reference to Figures 9-10.

[0044] Figure 9 is a flowchart of Method 86 for data mining of the clinical dataset 60 from Figures 5-8 for machine training of a machine learning model of the hemodynamic monitor 10. Method 86 in Figure 9 will be discussed with reference to Figure 10 as well. Method 86 is applied to each of the nociceptive data segment 66, predictive data segment 71, stable data segment 72, HDA data segment 78, and HDP data segment 85 of the clinical dataset 60 to train the hemodynamic monitor and find the input features previously described with reference to Figure 4. Method 86 will be described as being applied to the nociceptive data segment 66 (shown in Figure 6).

[0045] To machine train the hemodynamic monitor 10 to identify the nociceptive detection input features described in Figure 4, the nociceptive detection input features are first determined by applying Method 86 to the nociceptive data segment 66 of the clinical dataset 60. The first step 88 of Method 86 is to perform waveform analysis of the nociceptive data segment 66 of the arterial waveforms collected in the dataset 60 to calculate multiple signal measurements of the nociceptive data segment. Performing waveform analysis of the nociceptive data segment 66 may include identifying individual cardiac cycles in each of the arterial pressure waveforms of the nociceptive data segment 66. Figure 10 provides an exemplary graph showing an example of arterial pressure waveform tracing with individual cardiac cycles identified and magnified. Next, performing waveform analysis of the nociceptive data segment 66 may include identifying overlapping notches in each of the individual cardiac cycles of each of the arterial pressure waveforms of the nociceptive data segment 66, similar to the example shown in Figure 10. Next, waveform analysis of the nociceptive data segment 66 involves identifying the systolic rise phase, systolic decay phase, and diastolic phase for each arterial pressure waveform of the nociceptive data segment 66, for each individual cardiac cycle, similar to the example shown in Figure 10.

[0046] Signal measurements are extracted from each of the systolic rise phase, systolic decay phase, and diastolic phases of each arterial pressure waveform of the nociceptive data segment 66, from each of the individual cardiac cycles. The signal measurements may correspond to hemodynamic effects from each of the systolic rise phase, systolic decay phase, and diastolic phases of each of the individual cardiac cycles. These hemodynamic effects may include contractility, aortic compliance, stroke volume, vascular tone, afterload, and the entire cardiac cycle. The signal measurements calculated or extracted by waveform analysis in the first step 88 of Method 86 include mean, maximum, minimum, duration, area, standard deviation, derivative, and / or morphological measurements from each of the systolic rise phase, systolic decay phase, and diastolic phases of each of the individual cardiac cycles. The signal measurements may also include heart rate, respiratory rate, stroke volume, pulse pressure, pulse pressure variability, stroke volume variability, mean arterial pressure (MAP), systolic pressure (SYS), diastolic pressure (DIA), heart rate variability, cardiac output, peripheral resistance, vascular compliance, and / or left ventricular contractility, extracted from each of the arterial pressure waveforms of each of the nociceptive data segments 66, and each of the individual cardiac cycles.

[0047] After the signal measurements for the nociceptive data segment 66 have been determined, step 90 of method 86 is performed on the signal measurements of the nociceptive data segment 66. Step 90 of method 86 calculates the combined measurement between the signal measurements of the nociceptive data segment 66. Calculating the combined measurement between the signal measurements of the nociceptive data segment 66 may involve performing steps 92, 94, 96, and 98 shown in Figure 9 for all the signal measurements of the nociceptive data segment 66. Step 92 is performed by arbitrarily selecting three signal measurements from the signal measurements of the nociceptive data segment. Next, as shown in step 94 of Figure 9, powers of different orders are calculated for each of the three signal measurements to generate a power of the three signal measurements. In step 96 of Figure 9, the powers of the three signal measurements are then multiplied together to generate the product of the powers of the three signal measurements. Step 98 involves performing a receiver operating characteristic (ROC) analysis of the product to arrive at the combined measurement for the three signal measurements. Steps 92, 94, 96, and 98 are repeated until all combined measurements have been calculated among all signal measurements of the nociceptive data segment 66. Signal measurements with the most predictable top combined measurements (i.e., combined measurements that satisfy the threshold prediction criterion) are selected as top signal measurements for the nociceptive data segment 66 and labeled as nociceptive detection input features. Once the nociceptive detection input features are determined, the hemodynamic monitor 10 is trained or programmed to perform waveform analysis on the patient 36's arterial pressure waveform (shown in Figure 4) to extract nociceptive detection input features from the patient 36's arterial pressure waveform and to use these nociceptive detection input features to determine the probability that the patient 36 is currently experiencing a current nociceptive event.

[0048] Similar to how Method 86 was applied to the nociceptive data segment 66, Method 86 is applied to the predictive data segment 71, stable data segment 72, HDA data segment 78, and HDP data segment 85 of the clinical dataset 60 to determine the nociceptive predictive input features, stable detection input features, hemodynamic drug detection input features, and hemodynamic drug predictive input features, respectively.

[0049] While the present invention has been described with reference to exemplary embodiments, it will be understood by those skilled in the art that various modifications may be made, and equivalents may be substituted for their elements without departing from the scope of the invention. Furthermore, many modifications may be made to adapt specific situations or materials to the teachings of the invention without departing from their essential scope. Thus, the present invention is not limited to the specific embodiments disclosed, and is intended to encompass all embodiments included in the appended claims.

Claims

1. A method for monitoring a patient's arterial pressure and providing a warning to a healthcare professional about the patient's current or anticipated future nociceptiveness, The hemodynamic monitor receives sensed hemodynamic data representing the arterial pressure waveform of the patient, The hemodynamic monitor performs waveform analysis of the sensed hemodynamic data and calculates multiple signal measurements of the sensed hemodynamic data. Extracting input features for the hemodynamic monitor from the plurality of signal measurements that indicate the patient's current nociceptive events and predict the patient's future nociceptive events, The hemodynamic monitor determines a nociceptivity score based on the input characteristics, which represents the probability of the patient's current nociceptive event and / or the probability of the patient's future nociceptive event. The hemodynamic monitor, in response to the nociceptivity score meeting a predetermined level criterion, activates a sensory alarm and generates a sensory signal. The hemodynamic monitor determines a hemodynamic drug score representing the probability of a hemodynamic drug administration event and / or the probability of a future hemodynamic drug administration event for the patient, based on the input characteristics, wherein the hemodynamic drug administration event is defined as the patient experiencing an increase in heart rate and blood pressure due to the administration of a compound that alters cardiovascular hemodynamics, and is not a nociceptive event for the patient. A method comprising outputting the hemodynamic drug score to the display device of the hemodynamic monitor.

2. The hemodynamic monitor determines a stability score based on the input characteristics, which represents the probability of a stable episode in which the patient has not experienced either a nociceptive event or a hemodynamic drug administration event. The method according to claim 1, further comprising outputting the stability score to a display device of the hemodynamic monitor.

3. The further includes training the hemodynamic monitor to determine the probability of the current nociceptive event in the patient, and training the hemodynamic monitor To collect clinical datasets, including clinical annotations of arterial pressure waveforms and the administration of compounds that alter cardiovascular hemodynamics, Identifying nociceptive data segments within the clinical dataset, wherein each nociceptive data segment is An increase in blood pressure, at least above the first threshold, compared to the previous period, Compared to the previous period, an increase in heart rate of at least the second threshold, Identifying that the infusion of the compound that alters cardiovascular hemodynamics is not initiated before the aforementioned increase in blood pressure and the aforementioned increase in heart rate, Identifying the start and end of the increase in blood pressure and the increase in heart rate, Labeling the nociceptive data segment after the aforementioned start, and during the aforementioned increase in blood pressure and the aforementioned increase in heart rate, Waveform analysis of the labeled nociceptive data segment is performed to calculate multiple signal measurements of the nociceptive data segment, The method according to claim 2, comprising calculating a combination of signal measurement values ​​between the plurality of signal measurement values, and determining at least a portion of the input features by selecting the signal measurement value having the most predictable combination of signal measurement values ​​from the plurality of signal measurement values ​​as belonging to the input features.

4. In order to determine the probability of the predicted future nociceptive event for the patient, Identifying the preceding period in each of the nociceptive data segments prior to the onset of the increase in blood pressure and the increase in heart rate, Labeling each of the preceding periods of the aforementioned infringement data segments as a predictive data segment, The waveform analysis of the predicted data segment is performed to calculate multiple signal measurements of the predicted data segment, The method according to claim 3, further comprising training the hemodynamic monitor by determining at least a portion of the input features by calculating from the plurality of signal measurements of the prediction data segment as belonging to the input features a combination of signal measurements between the plurality of signal measurements of the prediction data segment, and a signal measurement having the most predictable combination of signal measurements.

5. The process further includes training the hemodynamic monitor to determine the probability of the hemodynamic drug administration event in the patient, Identifying hemodynamic drug administration data segments within the clinical dataset, wherein each hemodynamic drug administration data segment is: Injection of compounds that alter cardiovascular hemodynamics, The increase in blood pressure by at least a third threshold after the aforementioned injection, Identifying, including an increase in heart rate of at least a fourth threshold after the injection, In each of the hemodynamic drug administration data segments, the start and end of the increase in blood pressure and the increase in heart rate are identified. Labeling the hemodynamic drug administration data segment after the aforementioned start, and during the aforementioned increase in blood pressure and the aforementioned increase in heart rate, Waveform analysis of the labeled hemodynamic drug administration data segment is performed to calculate multiple signal measurements of the hemodynamic drug administration data segment, The method according to claim 4, comprising: calculating a combined value between the plurality of signal values ​​of the hemodynamic drug administration data segment; and determining at least a portion of the input features by selecting the signal value having the most predictable combined value from the plurality of signal values ​​of the hemodynamic drug administration data segment as belonging to the input features.

6. The process further includes training the hemodynamic monitor to determine the probability of the future hemodynamic drug administration event for the patient, Identifying the prior period in each of the hemodynamic drug administration data segments prior to the onset of the increase in blood pressure and the increase in heart rate, Each of the preceding periods in the hemodynamic drug administration data segments is labeled as a hemodynamic drug prediction data segment. Waveform analysis of the hemodynamic drug prediction data segment is performed to calculate multiple signal measurements of the hemodynamic drug prediction data segment, The method according to claim 5, comprising calculating a combination of signal measurements between the plurality of signal measurements of the hemodynamic drug prediction data segment, and determining at least a portion of the input features by selecting the signal measurement having the most predictable combination of signal measurements from the plurality of signal measurements of the hemodynamic drug prediction data segment as belonging to the input features.

7. The further includes training the hemodynamic monitor to determine the probability of the stable episode in the patient, and training the hemodynamic monitor to determine the probability of the stable episode Identifying stable data segments within the clinical dataset, wherein each of the stable data segments is A stable blood pressure that does not rise above the first threshold over a set period of time, A stable heart rate that does not increase above the second threshold over the set period, Identifying that no infusion of compounds that alter cardiovascular hemodynamics is performed, Identifying the start and end of the stable blood pressure and the stable heart rate, Labeling the stable data segment from the start and end of the stable blood pressure and stable heart rate, Waveform analysis of the labeled stable data segment is performed to calculate multiple stable signal measurements of the stable data segment, The method according to claim 6, comprising calculating a combination of stable signal measurements among the plurality of stable signal measurements, and determining at least a portion of the input features by selecting from the plurality of stable signal measurements the stable signal measurement having the most predictable combination of measurements as belonging to the input features.

8. A system for monitoring a patient's arterial pressure and providing warnings to healthcare professionals regarding the patient's nociceptiveness, A hemodynamic sensor that generates hemodynamic data representing the arterial pressure waveform of the patient, System memory for storing the noxious perception detection software code, A user interface including a sensory alarm that provides a sensory signal to warn the healthcare worker about the nociceptive event of the patient, A hardware processor that executes the intrusion detection software code, Waveform analysis of the hemodynamic data is performed to determine multiple signal measurements, The detection input features indicating the nociceptive event of the patient are extracted from the plurality of signal measurements. Based on the detection input features, a nociceptivity score representing the probability of the nociceptive event for the patient is determined. In response to the noxious perception score meeting predetermined detection criteria, the sensory alarm of the user interface is activated. Based on the detection input characteristics, a hemodynamic drug score is determined that represents the probability of a hemodynamic drug administration event for the patient and / or the probability of a future hemodynamic drug administration event for the patient. The system comprises a hardware processor configured to output the hemodynamic drug score to a display device of the system, A system in which the hemodynamic drug administration event is defined as the patient experiencing an increase in heart rate and blood pressure due to the administration of a compound that alters cardiovascular hemodynamics, and which is not a nociceptive event for the patient.

9. The detection input features of the aforementioned noxious perception detection software code are determined by detection machine training, and the detection machine training is To collect clinical datasets, including clinical annotations of arterial pressure waveforms and the administration of compounds that alter cardiovascular hemodynamics, Identifying nociceptive data segments within the clinical dataset, wherein each nociceptive data segment is An increase in blood pressure, at least above the first threshold, compared to the previous period, Compared to the previous period, an increase in heart rate of at least the second threshold, Identifying that the infusion of the compound that alters cardiovascular hemodynamics is not initiated before the aforementioned increase in blood pressure and the aforementioned increase in heart rate, Identifying the start and end of the increase in blood pressure and the increase in heart rate, Labeling the nociceptive data segment after the aforementioned start, and during the aforementioned increase in blood pressure and the aforementioned increase in heart rate, Waveform analysis of the labeled nociceptive data segment is performed to calculate multiple signal measurements of the nociceptive data segment, The system according to claim 8, comprising: calculating a combination of signal measurements between the plurality of signal measurements of the nociceptive data segment; selecting the top signal measurement having the most predictable combination of signal measurements from the plurality of signal measurements of the nociceptive data segment; and determining the detection input feature by labeling the top signal measurement as the detection input feature.

10. The system memory stores nociceptive prediction software code for determining the probability of a predicted future nociceptive event in the patient, the sensory alarm provides a second sensory signal to warn the healthcare worker about the predicted future nociceptive event, and the hardware processor executes the nociceptive prediction software code. Predictive input features for predicting the future nociceptive events of the patient are extracted from the plurality of signal measurements. Based on the predictive input features, a nociceptive prediction score is determined that represents the probability of the patient's future nociceptive event. The system according to claim 9, configured to activate the sensory alarm of the user interface in response to the nociceptibility prediction score meeting a predetermined prediction criterion.

11. The prediction input features of the nociceptibility prediction software code are determined by prediction machine training, and the prediction machine training is Identifying the preceding period in each of the nociceptive data segments prior to the onset of the increase in blood pressure and the increase in heart rate, Labeling each of the preceding periods of the aforementioned infringement data segments as a predictive data segment, The waveform analysis of the predicted data segment is performed to calculate multiple signal measurements of the predicted data segment, The system according to claim 10, comprising: calculating a combination of signal measurement values ​​between the plurality of signal measurement values ​​of the prediction data segment; and determining the prediction input feature by selecting the signal measurement value having the most predictable combination of signal measurement values ​​from the plurality of signal measurement values ​​of the prediction data segment as the prediction input feature.

12. The system memory stores hemodynamic drug detection software code for detecting hemodynamic drug administration events in the patient, the sensory alarm provides a third sensory signal to warn the healthcare worker about the hemodynamic drug administration event, and the hardware processor executes the hemodynamic drug detection software code. The hemodynamic drug detection input features indicating the hemodynamic drug administration event of the patient are extracted from the plurality of signal measurement values. Based on the hemodynamic drug detection input characteristics, a hemodynamic drug detection score representing the probability of the hemodynamic drug administration event is determined. The system according to claim 11, configured to activate the sensory alarm of the user interface in response to the hemodynamic drug detection score meeting predetermined prediction criteria.

13. The hemodynamic drug detection input features of the hemodynamic drug detection software code are determined by hemodynamic drug detection machine training, and the hemodynamic drug detection machine training is Identifying hemodynamic drug administration data segments within the clinical dataset, wherein each hemodynamic drug administration data segment is: Injection of compounds that alter cardiovascular hemodynamics, The increase in blood pressure by at least a third threshold after the aforementioned injection, Identifying, including an increase in heart rate of at least a fourth threshold after the injection, In each of the hemodynamic drug administration data segments, the start and end of the increase in blood pressure and the increase in heart rate are identified. Labeling the hemodynamic drug administration data segment after the aforementioned start, and during the aforementioned increase in blood pressure and the aforementioned increase in heart rate, Waveform analysis of the labeled hemodynamic drug administration data segment is performed to calculate multiple signal measurements of the hemodynamic drug administration data segment, The system according to claim 12, comprising: calculating a combination of signal measurements between a plurality of signal measurements in the hemodynamic drug administration data segment; and determining the hemodynamic drug detection input feature by selecting the signal measurement having the most predictable combination of signal measurements from the plurality of signal measurements in the hemodynamic drug administration data segment as the hemodynamic drug detection input feature.

14. The system memory stores hemodynamic drug prediction software code for determining the probability of future hemodynamic drug administration events for the patient, the sensory alarm provides a fourth sensory signal to warn the healthcare worker about the future hemodynamic drug administration event, and the hardware processor executes the hemodynamic drug prediction software code. Hemodynamic drug prediction input features that predict the future hemodynamic drug administration events of the patient are extracted from the plurality of signal measurements. Based on the hemodynamic drug prediction input features, a hemodynamic drug prediction score is determined that represents the probability of the patient's future hemodynamic drug administration event. The system according to claim 13, configured to activate the sensory alarm of the user interface in response to the hemodynamic drug prediction score meeting predetermined hemodynamic drug prediction criteria.

15. The hemodynamic drug prediction input features of the hemodynamic drug prediction software code are determined by hemodynamic drug prediction machine training, and the hemodynamic drug prediction machine training is Identifying the prior period in each of the hemodynamic drug administration data segments prior to the onset of the increase in blood pressure and the increase in heart rate, Each of the preceding periods in the hemodynamic drug administration data segments is labeled as a hemodynamic drug prediction data segment. Waveform analysis of the hemodynamic drug prediction data segment is performed to calculate multiple signal measurements of the hemodynamic drug prediction data segment, The system according to claim 14, comprising: calculating a combined value among the plurality of signal values ​​of the hemodynamic drug prediction data segment; and determining the hemodynamic drug prediction input feature by selecting the signal value having the most predictable combined value from the plurality of signal values ​​of the hemodynamic drug prediction data segment as the hemodynamic drug prediction input feature.

16. The system memory stores stability detection software code for determining the probability of a stable episode in the patient, and the hardware processor executes the stability detection software code. Stable detection input features indicating the stable episode of the patient are extracted from the plurality of signal measurements. Based on the stable detection input features, a stability score is determined that represents the probability of a stable episode in which the patient has not experienced either a nociceptive event or a hemodynamic drug administration event. The system according to claim 15, configured to output the stability score to a display device.

17. The stability detection input features of the stability detection software code are determined by stability detection machine training, and the stability detection machine training is Identifying stable data segments within the clinical dataset, wherein each of the stable data segments is A stable blood pressure that does not rise above the first threshold over a set period of time, A stable heart rate that does not increase above the second threshold over the set period, Identifying that no infusion of compounds that alter cardiovascular hemodynamics is performed, Identifying the start and end of the stable blood pressure and the stable heart rate, Labeling the stable data segment from the start and end of the stable blood pressure and stable heart rate, Waveform analysis of the labeled stable data segment is performed to calculate multiple stable signal measurements of the stable data segment, The system according to claim 16, comprising: calculating a combination of stable signal measurement values ​​among the plurality of stable signal measurement values; and determining the stable detection input feature by selecting the stable signal measurement value having the most predictable combination of stable signal measurement values ​​from the plurality of stable signal measurement values ​​as the stable detection input feature.

18. Performing waveform analysis on the labeled nociceptive data segment and calculating multiple signal measurements of the nociceptive data segment is, To identify individual cardiac cycles in the arterial pressure waveform of the clinical dataset, Identifying overlapping notches in each of the aforementioned individual cardiac cycles, In each of the aforementioned cardiac cycles, the systolic rise phase, the systolic decay phase, and the diastolic phase are identified. The system according to claim 17, comprising extracting signal measurements from each of the systolic rise phase, the systolic decay phase, and the diastolic phase from each of the individual cardiac cycles.

19. The system according to claim 18, wherein the signal measurement values ​​correspond to hemodynamic effects from each of the systolic rise phase, the systolic decay phase, and the diastolic phase, respectively, of each of the individual cardiac cycles, and the hemodynamic effects include contractility, aortic compliance, stroke volume, vascular tone, afterload, and the entire cardiac cycle.

20. The system according to claim 19, wherein the signal measurement includes mean, maximum, minimum, duration, area, standard deviation, derivative, and / or morphological measurement from each of the individual cardiac cycles, from each of the systolic rise phase, the systolic decay phase, and the diastolic phase.

21. The system according to claim 20, wherein the signal measurements include heart rate, respiratory rate, stroke volume, pulse pressure, pulse pressure variability, stroke volume variability, mean arterial pressure (MAP), systolic pressure (SYS), diastolic pressure (DIA), heart rate variability, cardiac output, peripheral resistance, vascular compliance, and / or left ventricular contractility, extracted from each of the individual cardiac cycles.

22. Calculating the combined measurement value between the plurality of signal measurement values ​​of the noxious reception data segment, Step 1 is performed by arbitrarily selecting three signal measurements from the plurality of signal measurements of the nociceptive data segment. Step 2 is performed by calculating powers of different orders for each of the three signal measurements and generating powers of the three signal measurements. Step 3 is performed by multiplying the powers of the three signal measurements by each other to generate the product of the powers of the three signal measurements. Step 4 is performed by performing a receiver operating characteristic (ROC) analysis of the product to obtain a combined measurement for the three signal measurements, The system according to claim 21, comprising repeating steps 1, 2, 3, and 4 until all of the combined measurements are calculated between all of the plurality of signal measurements of the nociceptive data segment.

23. The system according to any one of claims 8 to 22, wherein the hemodynamic sensor is a non-invasive hemodynamic sensor that can be attached to the patient's extremities.

24. The system according to any one of claims 8 to 22, wherein the hemodynamic sensor is a minimally invasive arterial catheter-based hemodynamic sensor.

25. The system according to any one of claims 8 to 24, wherein the hemodynamic sensor generates the hemodynamic data as an analog hemodynamic sensor signal representing the arterial pressure waveform of the patient.

26. The system according to any one of claims 8 to 25, further comprising an analog-to-digital converter that converts an analog hemodynamic sensor signal into digital hemodynamic data representing the arterial pressure waveform of the patient.

Images