Systems and methods for computer-assisted measurement of pulmonary capillary wedge pressure

Abstract

Systems and methods are provided for computer-assisted analysis of an individual's pulmonary capillary wedge pressure (PCWP) measurement acquisition. Various systems and methods measure wedge pressure via a pulmonary artery catheter and determine the quality of the wedge pressure measurement. In some cases, the systems and methods utilize trained computational models to assess the quality of PCWP. The systems and methods are also directed to determining transitions between wedged and non-wedged positions, which may utilize fuzzy logic to identify such transitions based on one or more hemodynamic features.

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. Provisional Patent Application No. 63 / 389,331, filed July 14, 2022, to Al Hatib et al., entitled "Systems and Methods for Machine Learning Enabled Measurement of Pulmonary Capillary Wedge Pressure," and U.S. Provisional Patent Application No. 63 / 486,914, filed February 24, 2023, to Angel et al., entitled "Systems and Methods for Computer Enabled Measurement of Pulmonary Capillary Wedge Pressure," the entire disclosures of which are incorporated herein by reference.

[0002] The present invention relates generally to systems and methods for computer-assisted acquisition and analysis of pulmonary capillary wedge pressure (PCWP). [Background technology]

[0003] Left atrial pressure is an important measurement in individuals with left ventricular dysfunction and / or valvular heart disease. While direct methods for determining left atrial pressure are available, such methods (e.g., transseptal approach) have inherent risks. As such, indirect methods are typically used, including determining pulmonary capillary wedge pressure (PCWP), also known as pulmonary artery occlusion pressure (PAOP), using a pulmonary artery catheter (PA catheter), also known as a Swan-Ganz catheter. Summary of the Invention [Problem to be solved by the invention]

[0004] Although PCWP measurement is considered a low-risk procedure, an expert is often required for accurate interpretation of the pulmonary artery pressure (PAP) and PCWP waveforms. Thus, there is a need for methods and systems that can help ensure accurate acquisition and analysis of PAP and PCWP measurements. [Means for solving the problem]

[0005] In some implementations, a computational method is for performing a pulmonary capillary wedge pressure (PCWP) measurement on an individual and assessing the quality of the PCWP measurement. The method includes acquiring a blood pressure waveform on the individual, the waveform including a blood pressure measurement obtained from a pulmonary artery location and a blood pressure measurement obtained from a wedge location. The blood pressure waveform is acquired using a pulmonary artery catheter. The method includes determining, using a computational system, the PCWP measurement from the blood pressure measurements from the wedge location. The method includes determining, using the computational system, a quality assessment for the PCWP measurement using a machine learning model configured to provide a quality assessment for the PCWP measurement based on the blood pressure measurements obtained from the pulmonary artery location and the blood pressure measurements obtained from the wedge location.

[0006] In some implementations, a hemodynamic monitoring system is for performing pulmonary capillary wedge pressure (PCWP) measurements and assessing the quality of the PCWP measurements. The system includes a pulmonary artery catheter configured to acquire blood pressure measurements obtained from a pulmonary artery location and a wedge location. The pulmonary artery catheter includes an inflatable balloon. The system includes a computing system in communication with the pulmonary artery catheter. The computing system includes a processor system, a display screen digitally connected to the processor system, and memory housing one or more applications. The one or more applications can direct the processor to acquire blood pressure measurements at the pulmonary artery location. The one or more applications can direct the processor to inflate the balloon. Inflating the balloon allows the catheter to move to the wedge location. The one or more applications can direct the processor to acquire blood pressure measurements at the wedge location. The one or more applications can direct the processor to generate a blood pressure waveform from the blood pressure measurements obtained from the pulmonary artery location and the blood pressure measurements obtained from the wedge location. The one or more applications can direct the processor to determine a PCWP measurement from the blood pressure measurements from the wedge position. The one or more applications can direct the processor to determine a quality assessment for the PCWP measurement using a machine learning model configured to provide a quality assessment for the PCWP measurement based on the blood pressure measurements obtained from the pulmonary artery position and the blood pressure measurements obtained from the wedge position. The one or more applications can direct the processor to display one or more of the blood pressure waveform, the PCWP measurement, or the quality assessment for the PCWP measurement on a display screen.

[0007] In some implementations, a blood pressure waveform is generated and displayed in real time on a display screen.

[0008] In some implementations, PCWP measurements are determined and displayed in real time on a display screen.

[0009] In some implementations, a quality assessment for the PCWP measurement is determined and displayed on a display screen in real time.

[0010] In some implementations, a computational method for performing a pulmonary capillary wedge pressure (PCWP) measurement on an individual is provided. The method includes acquiring a blood pressure waveform on the individual using a pulmonary artery catheter. The waveform includes blood pressure measurements obtained from a pulmonary artery location. The pulmonary artery catheter is connected to a hemodynamic monitoring system. The method includes evaluating the blood pressure measurements obtained from the pulmonary artery location for artifacts while the blood pressure measurements are being obtained from the pulmonary artery location using the hemodynamic monitoring system. After determining that the blood pressure measurements obtained from the pulmonary artery location are free of artifacts, the method includes inflating a balloon at or near a distal end of the pulmonary artery catheter using the hemodynamic monitoring system to enable the pulmonary artery catheter to move to a wedging position. The method further includes acquiring a blood pressure waveform on the individual using the pulmonary artery catheter, the waveform including blood pressure measurements obtained from the wedging position. The method includes determining a PCWP measurement from the blood pressure measurements from the wedging position using the hemodynamic monitoring system.

[0011] In some implementations, a hemodynamic monitoring system is for performing pulmonary capillary wedge pressure (PCWP) measurements. The system includes a pulmonary artery catheter configured to acquire blood pressure measurements obtained from a pulmonary artery location and blood pressure measurements obtained from a wedge location. The pulmonary artery catheter includes an inflatable balloon. The system includes a computing system in communication with the pulmonary artery catheter. The computing system includes a processor system, a display screen digitally connected to the processor system, and a memory system housing one or more applications. One or more applications are provided that can direct the processor system to acquire blood pressure measurements at the pulmonary artery location. One or more applications are provided that can direct the processor system to evaluate the blood pressure measurements obtained from the pulmonary artery location for artifacts. One or more applications are provided that can direct the processor system to inflate a balloon after determining that the blood pressure measurements obtained from the pulmonary artery location are free of artifacts, where inflating the balloon enables the catheter to move to the wedge location. One or more applications are provided that can direct the processor system to acquire blood pressure measurements at the wedge location. One or more applications are provided that can direct the processor system to generate a blood pressure waveform from blood pressure measurements taken from the pulmonary artery location and blood pressure measurements taken from the wedge location. One or more applications are provided that can direct the processor system to determine PCWP measurements from the blood pressure measurements from the wedge location. One or more applications are provided that can direct the processor system to display the PCWP measurements on a display screen.

[0012] In some implementations, a computational method for detecting a transition between a pulmonary artery position and a wedge position is provided. The method includes acquiring a blood pressure waveform of an individual using a pulmonary artery catheter. The waveform includes blood pressure measurements obtained from the pulmonary artery position. The pulmonary artery catheter is connected to a hemodynamic monitoring system. The method includes using the hemodynamic monitoring system to inflate a balloon at or near a distal end of the pulmonary artery catheter to allow the pulmonary artery catheter to move to the wedge position. The method includes detecting a transition from the pulmonary artery position to the wedge position using the hemodynamic monitoring system. The method further includes acquiring a blood pressure waveform of the individual using the pulmonary artery catheter. The waveform includes blood pressure measurements obtained from the wedge position. The method includes using the hemodynamic monitoring system to deflate a balloon at or near the distal end of the pulmonary artery catheter to allow the pulmonary artery catheter to move back to the pulmonary artery position. The method includes detecting a transition from the wedge position to the pulmonary artery position using the hemodynamic monitoring system.

[0013] In some implementations, a hemodynamic monitoring system is for detecting a transition between a pulmonary artery position and a wedge position. The system includes a pulmonary artery catheter configured to acquire a blood pressure measurement obtained from the pulmonary artery position and a blood pressure measurement obtained from the wedge position. The pulmonary artery catheter includes an inflatable balloon. The system includes a computing system in communication with the pulmonary artery catheter. The computing system includes a processor system, a display screen digitally connected to the processor system, and a memory system housing one or more applications. The one or more applications can instruct the processor system to acquire a blood pressure measurement at the pulmonary artery position. The one or more applications can instruct the processor system to inflate the balloon. Inflating the balloon allows the catheter to move to the wedge position. The one or more applications can instruct the processor system to detect a transition from the pulmonary artery position to the wedge position. The one or more applications can instruct the processor system to acquire a blood pressure measurement at the wedge position. The one or more applications can direct the processor system to deflate a balloon at or near the distal end of the pulmonary artery catheter to allow the pulmonary artery catheter to move back to the pulmonary artery position. The one or more applications can direct the processor system to detect a transition from the wedge position to the pulmonary artery position.

[0014] In some implementations, the PCWP measurement and the quality assessment are each determined in real time.

[0015] In some implementations, the computing system and the pulmonary artery catheter are part of a hemodynamic monitoring system.

[0016] In some implementations, acquiring a blood pressure waveform includes inserting a pulmonary artery catheter into a central vein of the individual, navigating the pulmonary artery catheter into the pulmonary artery, and inflating a balloon at or near a distal end of the pulmonary artery catheter to allow the pulmonary artery catheter to move into a wedging position.

[0017] In some implementations, the method includes using a computing system to evaluate blood pressure measurements obtained from the pulmonary artery location in real time for artifacts before inflating the balloon.

[0018] In some implementations, the artifacts include one or more of measurements taken during patient movement, measurements taken during catheter flushing, and measurements showing flat lines, measurements showing underattenuation, and measurements showing overattenuation.

[0019] In some implementations, detection of artifacts based on flashing, improper zero, or patient movement is based on the PAP maximum (PAP max ) is greater than the threshold, the minimum PAP (PAP min ) is less than the threshold, and / or the maximum PAP minus the minimum PAP (PAP max -PAP min ) is greater than a threshold, and PAP is the blood pressure measurement taken from the pulmonary artery location.

[0020] In some implementations, flat line or overattenuation based artifact detection is performed using the PAP maximum minus the PAP minimum (PAP max -PAP min ) is less than a threshold, and PAP is the blood pressure measurement taken from the pulmonary artery location.

[0021] In some implementations, the pulmonary artery catheter includes a lumen configured to measure blood pressure.

[0022] In some implementations, the pulmonary artery catheter is a Swan-Ganz catheter.

[0023] In some implementations, the machine learning model is based on at least one feature selected from the group consisting of waveform phase features, determinable features, and morphological features. The waveform phase features are selected from contractility, pulmonary artery compliance, stroke volume, vascular tone, afterload, and the entire cardiac cycle. The determinable features are determined based on the waveform phase features and are selected from phase mean, maximum, minimum, duration, area, standard deviation, slope, derivative, trend, deviation from trend, variance, and variance. The morphological features are based on the waveform features and are selected from frequency content, skewness, and kurtosis.

[0024] In some implementations, the machine learning model is based on one or more of approximate entropy, sample entropy, baroreflex sensitivity, variability, and change.

[0025] In some implementations, obtaining the PCWP measurement includes determining a respiratory cycle of the individual. Determining the PCWP measurement is based on the respiratory cycle of the individual.

[0026] In some implementations, determining the PCWP measurement includes determining a blood pressure measurement from a wedge position at the end of expiration of the respiratory cycle.

[0027] In some implementations, determining the PCWP measurement includes averaging blood pressure measurements from the wedge positions over one or more respiratory cycles.

[0028] In some implementations, the method includes using a computing system to detect in real time a transition from a pulmonary artery location to a wedge location or from the wedge location to a pulmonary artery location by extracting one or more hemodynamic features from the blood pressure measurements at the pulmonary artery location and the blood pressure measurements at the wedge location, and using fuzzy logic membership functions to determine a fuzzy logic value for each hemodynamic feature of the one or more hemodynamic features based on a change in value between the blood pressure measurements at the pulmonary artery location and the blood pressure measurements at the wedge location.

[0029] In some implementations, the one or more features include at least one of a statistical moment, a percentile value of the data, a histogram of the data, a diastolic pressure, a median pressure, a mean pressure, a systolic pressure, a pulse pressure, Shannon's entropy, a number of peaks above a percentile, a number of valleys below a percentile, a number of mean crossings, an area under the curve, a singular vector coefficient after principal component analysis, a subsampled signal, a determinable feature, a waveform phase feature, and a morphological feature.

[0030] In some implementations, the morphological features are selected from frequency content, skewness, and kurtosis, the waveform phase features are selected from contractility, pulmonary artery compliance, stroke volume, vascular tone, afterload, and the entire cardiac cycle, and the determinable features are selected from mean, maximum, minimum, duration, area, standard deviation, slope, derivative, trend, deviation from trend, variance, and variance of the phase.

[0031] In some implementations, the one or more features include mean pressure and pulse pressure.

[0032] In some implementations, the method further includes dividing the blood pressure measurements obtained from the pulmonary artery location and the wedge location into time windows. The method further includes extracting features from the time windows of the blood pressure measurements obtained from the pulmonary artery location and the wedge location. The machine learning model is trained to detect whether the extracted features for the time windows are derived from blood pressure measurements obtained from the pulmonary artery location or from blood pressure measurements obtained from the wedge location. Using the computing system to determine a quality assessment for the PCWP measurements using the machine learning model includes inputting the extracted features from the time windows into the machine learning model to generate a quality assessment for each time window. The quality assessment is based on whether the extracted features for each time window can be distinguished as being derived from the pulmonary artery location or from the wedge location.

[0033] In some implementations, the quality assessment is categorical.

[0034] In some implementations, the categories are qualitative rankings.

[0035] In some implementations, using a computing system to determine a quality assessment for the PCWP measurement using a machine learning model includes determining whether one or more extracted features for a time window are above or below a threshold.

[0036] In some implementations, the one or more extracted features are Mean , PAP Diastolic , and PCWP PulsePress Including PCWP Mean is the average pressure measurement taken at the wedge position, and PAP Diastolic is the diastolic pressure at the pulmonary artery, and PCWP PulsePress is the pulse pressure at the wedge position.

[0037] In some implementations, high quality isMean <PAP Diastolic AND a×PCWP PulsePress +b×PCWP Mean ≦c, where a, b, and c are determinant values.

[0038] In some implementations, medium quality is Mean <PAP Diastolic AND a×PCWP PulsePress +b×PCWP Mean >c, where a, b, and c are determinant values.

[0039] In some implementations, the low quality is Mean ≧PAP Diastolic This is shown when

[0040] In some implementations, the method further includes using a computing system to assign each time window its quality rating.

[0041] In some implementations, the method further includes digitally communicating with a computing system to display the quality assessments for the one or more time windows on a display screen.

[0042] In some implementations, using a computing system, determining the PCWP measurement includes averaging blood pressure measurements obtained from wedge positions in the time window determined to have a quality above a threshold.

[0043] In some implementations, using a computing system, determining the PCWP measurements includes excluding blood pressure measurements obtained from wedge positions in the time window determined to have a quality below a threshold, and averaging the non-excluded blood pressure measurements obtained from wedge positions in the time window.

[0044] In some implementations, the method further includes digitally communicating with a computing system to display the quality assessments for the one or more time windows on a display screen.

[0045] Additional implementations and features are set forth in part in the description which follows, and in part will become apparent to those skilled in the art after examination of the specification or may be learned by practice of the present disclosure. The nature and advantages of the present disclosure may be better understood by reference to the remaining portions of the specification and the drawings, which form a part of this disclosure.

[0046] The description will be more fully understood with reference to the following figures, which are presented as exemplary implementations of the invention and should not be construed as an exhaustive recitation of the scope of the invention: [Brief explanation of the drawings]

[0047] [Figure 1] FIG. 10 provides an example of a catheter positioned in a wedging position. [Figure 2A] FIG. 1 provides an example of a PA catheter position within the heart and the pressure obtainable by a PA catheter in such a position. [Figure 2B] FIG. 1 provides an example of a PA catheter position within the heart and the pressure obtainable by a PA catheter in such a position. [Figure 2C] FIG. 1 provides an example of a PA catheter position within the heart and the pressure obtainable by a PA catheter in such a position. [Figure 2D] FIG. 1 provides an example of a PA catheter position within the heart and the pressure obtainable by a PA catheter in such a position. [Figure 3A] FIG. 2A provides an example of a wedge position with proper (FIG. 2A) wedge placement. [Figure 3B] FIG. 2B provides an example of a wedging position resulting in an over-inflated balloon (FIG. 2B). [Figure 3C]FIG. 10 presents an example of a waveform during PCWP measurement. [Figure 3D] FIG. 10 presents an example of a waveform during PCWP measurement. [Figure 4A] FIG. 1 presents an example of a method and calculation process for obtaining and assessing the quality of PCWP measurements. [Figure 4B] FIG. 1 presents an example of a method and calculation process for obtaining and assessing the quality of PCWP measurements. [Figure 5] FIG. 1 presents an example of a computational method for detecting artifacts in a PAP waveform. [Figure 6] FIG. 10 provides an example of a calculation method for determining the transition point of a balloon inflation or balloon deflation. [Figure 7A] FIG. 1 presents an example of utilizing plots of fuzzy logic membership functions. [Figure 7B] FIG. 1 presents an example of utilizing plots of fuzzy logic membership functions. [Figure 7C] FIG. 1 presents an example of utilizing plots of fuzzy logic membership functions. [Figure 7D] FIG. 1 presents an example of utilizing plots of fuzzy logic membership functions. [Figure 7E] FIG. 1 presents an example of utilizing plots of fuzzy logic membership functions. [Figure 8] FIG. 1 presents an example of a method for generating fuzzy logic membership functions. [Figure 9] FIG. 1 presents an example of clinical data for a cohort of patients plotting pulse pressure against mean pressure. [Figure 10] FIG. 1 presents an example of a computational method for performing PCWP measurement and quality assessment. [Figure 11A] FIG. 1 presents an example of quality metrics. [Figure 11B] FIG. 1 presents an example of quality metrics. [Figure 12]FIG. 10 provides an example of plotting quality assessment across wedge position waveforms. [Figure 13A] FIG. 1 provides an example of a pressure wave. [Figure 13B] FIG. 1 provides an example of a pressure wave. [Figure 14A] FIG. 1 provides an example of various parameters derived from a pressure wave. [Figure 14B] FIG. 1 provides an example of various parameters derived from a pressure wave. [Figure 14C] FIG. 1 provides an example of various parameters derived from a pressure wave. [Figure 14D] FIG. 1 provides an example of various parameters derived from a pressure wave. [Figure 14E] FIG. 1 provides an example of various parameters derived from a pressure wave. [Figure 14F] FIG. 1 provides an example of various parameters derived from a pressure wave. [Figure 15] FIG. 1 presents an example of a computing system. [Figure 16] FIG. 1 presents an example of a hemodynamic monitoring system. DETAILED DESCRIPTION OF THE INVENTION

[0048] Referring now to the drawings, systems and methods for computer-assisted acquisition and analysis of pulmonary capillary wedge pressure (PCWP) are described. In many cases, a hemodynamic monitoring system including a pulmonary artery catheter system (e.g., a Swan-Ganz catheter) is utilized to acquire PCWP. Computational methods may be implemented to assist in the acquisition and analysis of PCWP. In some cases, computational methods are utilized to detect when the pulmonary artery catheter is ready to acquire PCWP (e.g., when a balloon on the end of the pulmonary artery catheter is ready to be inflated). In some cases, computational methods are utilized to detect when the balloon is inflated and / or when the balloon is deflated. In some cases, computational methods are utilized to detect respiratory signals and / or perform PCWP measurements. In some cases, trained computational models are utilized to assess the quality of the PCWP acquisition. In some cases, a computational system is configured to perform one or more of the described computational methods. The computational system may be part of or used in conjunction with the hemodynamic monitoring system.

[0049] PCWP is often used to assess left ventricular filling, represent left atrial pressure, and evaluate mitral valve function. In many cases, PCWP is also an estimate of left ventricular end-diastolic pressure (LVEDP). Physiologically normal PCWP is between 4 and 12 mmHg, and elevated PCWP levels may indicate severe left ventricular failure or severe mitral stenosis.

[0050] To measure PCWP, a balloon-tipped, multi-lumen catheter (e.g., a Swan-Ganz catheter) may be inserted into a central vein (such as the femoral, subclavian, internal jugular, or other suitable vein) and advanced through the superior or inferior vena cava until it reaches the right atrium. From the right atrium, the catheter may be advanced through the tricuspid valve into the right ventricle. After entering the right ventricle, the balloon on the catheter's tip is inflated to advance the catheter into the right ventricular outflow tract, then across the pulmonary valve and into the pulmonary artery. After the catheter enters the main pulmonary artery, the balloon is deflated. The catheter tip is then placed within the main pulmonary artery, where the balloon may be re-inflated as needed, allowing the catheter to be moved downstream (e.g., through the circulatory system in the direction of blood flow) where the balloon can occlude a branch of the pulmonary artery, i.e., a "wedge" position. The catheter can then provide a measurement of PCWP, which should be equivalent to the pressure in the left atrium.

[0051] 1 provides an exemplary illustration of a pulmonary artery catheter positioned in a wedging position. An inflated balloon 102 occludes a branch of the pulmonary artery 104, allowing one or more ports positioned on the catheter 106 to acquire pressure measurements. The pressure measurements can be single measurements, sequential measurements, continuous measurements, and combinations thereof.

[0052] As the catheter advances through the ventricles and / or circulatory system, various blood pressure waveforms may be acquired and / or allow specific measurements within the ventricles, blood vessels, or other circulatory components. Figures 2A-2D present example waveforms showing the progression of the catheter through its path from the right atrium (Figure 2A) to the wedge position (Figure 2D). Figure 2A illustrates the pressure acquired in the right atrium, where physiologically normal pressure is approximately 2-6 mmHg, with an average of 4 mmHg. Waveform 202 illustrates an example ECG of an individual during a PCWP procedure, while waveform 204 presents an example right atrial pressure waveform measured by catheter 206 (e.g., a Swan-Ganz catheter). Peaks a, c, and v represent atrial systole, posterior elevation from tricuspid valve closure, and atrial filling and ventricular systole, respectively.

[0053] 2B, catheter 206 is advanced into the right ventricle, which causes a pattern change in pressure waveform 204. Once catheter 206 enters the right ventricle, right ventricular systolic pressure (RVSP) and right ventricular diastolic pressure (RVDP) can be measured, where a physiologically normal RVSP is approximately 15-25 mmHg and a physiologically normal RVDP is approximately 0-8 mmHg.

[0054] FIG. 2C illustrates an example of a pressure waveform 204 as the catheter 206 is advanced into the pulmonary artery, where the pulmonary artery systolic pressure (PASP), pulmonary artery diastolic pressure (PADP), and mean pulmonary artery pressure (MPA) can be measured, with a physiologically normal PASP being approximately 15-25 mmHg, a physiologically normal PADP being approximately 8-15 mmHg, and a physiologically normal MPA being approximately 10-20 mmHg.

[0055] FIG. 2D illustrates an example pressure waveform 204 generated at the wedge position to obtain PCWP (also referred to as pulmonary artery occlusion pressure (PAOP)). As previously mentioned, PCWP is equal to left atrial pressure, with a physiologically normal PCWP being approximately 6-12 mmHg. Additionally, pressure waveform 204 exhibits peaks a and v, representing atrial systole and atrial-filling ventricular systole, respectively.

[0056] Abnormal waveforms can occur for a variety of reasons, particularly due to incorrect catheter placement, such as placement too close to the right ventricle, placement too far from the right ventricle, and / or failure of the catheter to move from the pulmonary artery to a wedging position. Additional abnormalities can result from improper inflation of the balloon, including over-inflation and under-inflation. Non-clinicians (e.g., nurses, doctors, physicians, surgeons, and / or other medical personnel) may not recognize abnormal waveforms, which can lead to incorrect measurement interpretation or not performing the procedure at all.

[0057] Figures 3A and 3B provide examples of pressure waveforms for correct and incorrect PCWP measurements. Specifically, Figure 3A illustrates proper wedging, where the waveform shows proper a- and v-waves as illustrated in Figure 2D. Figure 3B, however, shows a waveform produced from an over-inflated balloon, resulting in an inaccurate PCWP waveform (indicated by the gradual rise of the waveform) and less pronounced a- and v-peaks.

[0058] 3C and 3D provide examples of pressure waveforms generated from a PCWP procedure. An example of an accurately acquired waveform is provided in FIG. 3C, while an inaccurately acquired waveform is illustrated in FIG. 3D.

[0059] In FIG. 3C, waveform 300 begins at time t0 and continues until time t fFIG. 3D illustrates pressure measurements taken by a healthcare provider, ending with . Region 302 represents a pressure acquisition and resulting PCWP waveform when the catheter is in the wedge position, and region 304 represents a pressure acquisition (e.g., pre- and post-PCWP) when the catheter is in the pulmonary artery position. In contrast, FIG. 3D illustrates a situation in which waveform 300 has an attenuated measurement in region 306. Such attenuation may be caused by improper catheter placement or other issues during acquisition. To overcome these complications, hemodynamic monitoring systems such as those described herein can utilize one or more computational processes to ensure proper wedge pressure readings. These systems and methods can be deployed within healthcare facilities, allowing clinicians (e.g., physicians, internists, nurses, cardiologists, etc.) to acquire PCWP readings and assess their quality in real time. In some implementations, the hemodynamic monitoring system can indicate to the clinician the quality and / or whether the catheter needs to be repositioned and measurements reacquired.

[0060] FIG. 4A illustrates an example of a method 400 for performing PCWP measurements. Generally, the method involves the use of a pulmonary artery catheter (e.g., a Swan-Ganz catheter) delivered to the pulmonary artery to perform PCWP measurements. The pulmonary artery catheter may include one or more sensors, such as (for example) a pressure sensor, a thermal sensor (e.g., for measuring cardiac output by thermodilution), or an optical fiber (e.g., photometric or other optical measurement). The pulmonary artery catheter may also include a balloon near its distal end to perform a wedging technique within the pulmonary artery. The pulmonary artery catheter may be used in conjunction with a hemodynamic monitoring system to measure blood pressure, cardiac output, and various other hemodynamic measurements in real time. The monitoring system may further include one or more computational programs to monitor hemodynamic parameters and / or assist in performing various measurements (e.g., PCWP). To perform computational tasks, the monitoring system may include a processor, memory, a display, one or more computational programs stored in the memory and executed by the processor, and one or more ports for connecting various sensors to the system.

[0061] Method 400 navigates a pulmonary artery catheter into the pulmonary artery (402). Any suitable method for reaching the pulmonary artery may be utilized. The catheter may be inserted into a central vein and navigated into the right atrium, then through the tricuspid valve and right ventricle, and then through the pulmonary valve into the pulmonary artery (see, e.g., FIGS. 2A-2D). To aid in navigation and positioning, a pressure waveform may be monitored as the catheter floats into the pulmonary artery. In some implementations, the catheter may include markings (e.g., fluoroscopy, radiography, or ultrasound) at specific distances along the proximal-distal axis, and visualization methods such as (for example) fluoroscopy, radiography, or ultrasound may be utilized.

[0062] Once the pulmonary artery catheter reaches the pulmonary artery, a pressure sensor can measure pulmonary artery blood pressure (404). In some implementations, the blood pressure sensor includes a distal lumen connected to a pressure transducer for measuring blood pressure. The blood pressure measurement can be displayed and / or recorded on a monitoring system.

[0063] The method 400 further includes obtaining a PCWP measurement (406). In many implementations, a balloon at or near the distal end of the catheter is inflated, allowing the catheter to float in the wedging position. After the catheter is placed in the wedging position, a distal lumen connected to a pressure transducer measures the blood pressure at the wedging position, which may be displayed on the monitor. When the blood pressure is measured by the pressure sensor at the wedging position, a PCWP measurement is obtained. As one skilled in the art will appreciate, the timing of the PCWP measurement is taken according to the patient's breathing and may further depend on whether the patient is breathing spontaneously or via a ventilator. Typically, the PCWP may be obtained at the end of the respiratory cycle (i.e., at the completion of exhalation). In some implementations, the PCWP measurement is displayed on a display screen of the monitoring system.

[0064] The method 400 can assess the quality of the PCWP measurement. The reliability of the PCWP measurement depends on the conditions of acquisition. For example, if the distal lumen is not in the correct position or the balloon is over-inflated, the PCWP measurement may be inaccurate. The quality can be assessed by analysis and comparison of the pressure waveforms in the pulmonary artery and at the wedge location.

[0065] In some implementations, a quality rating may be generated. In some implementations, the quality rating is generated via a computational process performed by the hemodynamic monitoring system. The quality rating can be quantitative (e.g., a score ranging from 0 to 100) or categorical (e.g., good vs. poor, adequate vs. insufficient). In some implementations, a threshold is used to determine whether the quality score is low / high or poor / good. The threshold may be based on clinical data. In some implementations, a trained computational model is used to determine the quality rating. The machine learning computational model may be trained using clinical data. In some implementations, the quality rating is displayed on a display screen of the hemodynamic monitoring system. In some implementations, the quality rating is saved in memory or transmitted to another computing device for storage or downstream analysis. In some implementations, a low or poor quality score is used to notify a clinician that a repeat PCWP measurement is recommended. In some implementations, a low or poor quality score is used to automatically repeat the PCWP measurement.

[0066] While a particular example of a method for performing PCWP measurements is described above with reference to FIG. 4A, those skilled in the art will understand that various steps of the method may be performed in different orders and that some steps may be optional according to various implementations. As such, it will be apparent that various steps of the method may be used as appropriate to the requirements of a particular application. Furthermore, any of a variety of methods for performing PCWP measurements suitable for the requirements of a given application may be utilized in various implementations.

[0067] 4B presents an example of a set of actions and processes that a hemodynamic monitoring system may perform to obtain and evaluate the quality of PCWP measurements. The hemodynamic monitoring system may perform any combination of one or more of the actions and processes in the set of actions and processes. In some implementations, the set of actions and processes performed by the hemodynamic monitoring system enables automated acquisition and / or evaluation of PCWP measurements.

[0068] The hemodynamic monitoring system can include a pulmonary artery catheter (e.g., a Swan-Ganz catheter) and a computing system. The pulmonary artery catheter can include one or more sensors, such as (for example) a pressure sensor, a thermal sensor (e.g., for measuring cardiac output by thermodilution), or an optical fiber (e.g., photometric or other optical measurement). The pulmonary artery catheter can also include a balloon near its distal end for performing a wedging technique within the pulmonary artery. Utilizing the pulmonary artery catheter, the hemodynamic monitoring system can measure blood pressure, cardiac output, and various other hemodynamic measurements in real time. The monitoring system can further include one or more computing programs to monitor hemodynamic parameters and / or assist in performing various measurements (e.g., PCWP). To perform computing tasks, the monitoring system can include a processor, memory, a display, one or more computing programs stored in the memory and executed by the processor, and one or more ports for connecting various sensors to the system.

[0069] As shown in FIG. 4B , the hemodynamic monitoring system can execute a set of actions (420) and a set of calculation processes (440). The pulmonary artery catheter can be positioned in the pulmonary artery and a pressure waveform (300) can be acquired. To measure PCWP, the monitoring system can enter PCWP mode (422) and initiate a set of actions and calculation processes. After entering PCWP mode, the monitoring system can determine whether the system and the patient are ready for PCWP (422). The determination of readiness can include a calculation process that determines whether there is a problem with the machine or the current readings. In some implementations, the calculation process analyzes the waveform data for artifacts. The calculation process can also perform a set of checks, such as verifying (for example) that the pulmonary artery catheter and machine are properly connected and that the patient's breathing is regular. After determining that the system and the patient are ready for PCWP measurement, in some implementations, the monitoring system can provide a signal to the clinician that balloon inflation can begin. In some implementations, after determining readiness, the monitoring system automatically begins the balloon inflation process.

[0070] The hemodynamic monitoring system inflates a balloon (424) at the distal end of the catheter, allowing the catheter to float to the wedging position. By evaluating hemodynamic parameters derived from the pressure waveform, the hemodynamic system can detect a balloon inflation point (444), indicating that the catheter is in the wedging position. In some implementations, a computational process detects balloon inflation through a probabilistic model. In some implementations, the computational process detects balloon inflation using fuzzy logic or Boolean logic.

[0071] After detecting balloon inflation, in some implementations, the hemodynamic monitoring system can perform one or more computational processes to determine the respiratory cycle (446). The respiratory cycle (310) is shown in FIG. 4B along with the blood pressure waveform (300). In some implementations, the respiratory cycle is extracted using the blood pressure waveform. In some implementations, the respiratory cycle is detected using a sensor or other device in conjunction with the hemodynamic monitor. Numerous techniques are known for measuring respiratory rate, including (for example) measuring airflow (e.g., a flow meter), detecting respiratory sounds (e.g., a microphone), measuring temperature (e.g., a thermistor), measuring air humidity (e.g., a capacitance sensor), measuring CO2 (e.g., an infrared sensor), measuring chest wall movement (e.g., an accelerometer), and measuring cardiac activity (e.g., an ECG sensor). In some implementations, when a ventilator is used, the respiratory rate is determined by the ventilator settings.

[0072] The hemodynamic monitoring system can measure PCWP (426) using a computational process to determine PCWP (446). In some implementations, PCWP is measured according to a respiratory cycle. In certain implementations, PCWP is the pressure measured after a respiratory cycle is completed (i.e., the end-expiratory pressure or the average of the end-expiratory pressures). In some implementations, PCWP is the average pressure measured over a number of respiratory cycles (e.g., 1, 2, 3, or 4 respiratory cycles) during wedging. In some implementations, PCWP is the average pressure measured over a period of time (e.g., between 2 and 20 seconds) during wedging.

[0073] After completing the PCWP measurement, the hemodynamic monitoring system deflates the balloon (428) at the distal end of the catheter, allowing the catheter to retract into the pulmonary artery. In a manner similar to detecting balloon inflation, the monitoring system can include a computational process for detecting the balloon deflation point (448). Thus, by evaluating hemodynamic parameters derived from the pressure waveform, the hemodynamic system can detect the balloon deflation point, indicating that the catheter has retracted from the wedging position. In some implementations, the computational process detects balloon deflation via a probabilistic model. In some implementations, the computational process detects balloon deflation using fuzzy logic or Boolean logic.

[0074] The hemodynamic monitoring system can perform quality assessment of the PCWP acquisition (450) by analyzing hemodynamic data between the balloon inflation point and the balloon deflation point. In some implementations, the quality of the PCWP acquisition can be performed by analyzing the pressure waveform. In some implementations, the quality of the PCWP acquisition can be performed by comparing the acquired PAP to the acquired PCWP. In certain implementations, a trained machine learning model is utilized to determine the quality of the PCWP acquisition by analysis. Various machine learning models can be used, including (but not limited to) regression models, logistic regression models, neural networks, support vector machines, decision trees, Adaboost, random forests, ensemble learning models (combining one or more models), and / or any other machine learning model capable of determining the quality of pressure readings based on feature data and classified measurements. The machine learning model can be trained using clinical data of the PCWP acquisition, and high-quality PCWP acquisition data is utilized to distinguish low-quality PCWP acquisition data using a set of hemodynamic data features. In some implementations, the hemodynamic data features are extracted from PAP and wedge pressure waveforms. The quality rating can be quantitative (e.g., a score ranging from 0 to 100) or categorical (e.g., "good" vs. "poor," "adequate" vs. "inadequate"). In some implementations, a threshold is utilized to determine whether the quality score is low / high or "poor / good." The threshold may be based on clinical data.

[0075] The hemodynamic monitoring system can report a quality rating of the acquired PCWP and / or PCWP measurement. In some implementations, the quality of the acquired PCWP and / or PCWP measurement is displayed on a display screen of the monitoring system. In some implementations, the quality rating is saved in memory or transmitted to another computing device for storage or downstream analysis. In some implementations, a low or "poor" quality score is used to notify a clinician that a repeat PCWP measurement is recommended. In some implementations, a low or "poor" quality score is used to automatically repeat the PCWP measurement. Once the PCWP measurement (or repeated PCWP measurement) is completed, the monitoring system can exit PCWP mode (432).

[0076] While a specific example of a set of hemodynamic monitoring system actions and computational processes for performing PCWP measurements is described above with reference to FIG. 4B , those skilled in the art will understand that the various actions and processes may be performed in different orders and that some actions and processes may be optional or omitted depending on various implementations. As such, it will be apparent that various actions and processes may be used as appropriate for the requirements of a particular application. Furthermore, any of the various actions and processes for performing PCWP measurements suitable for the requirements of a given application may be utilized in various implementations.

[0077] 5 presents an example of a computational method for evaluating a pulmonary artery pressure (PAP) waveform for artifacts and issuing an alert if detected, which may be implemented using a hemodynamic monitoring system. Prior to initiating a procedure to obtain a PCWP measurement, a determination may be made as to whether the system and patient are in an appropriate state to perform the procedure. This determination may prevent degradation of PCWP acquisition quality and ensure that a high-quality measurement is obtained. In some implementations, the computational method for evaluating a pulmonary artery pressure (PAP) waveform for artifacts is utilized as or within a computational process to determine whether the monitoring system and patient are ready for PCWP acquisition (e.g., see 442 in FIG. 4B ).

[0078] The calculation method 500 may be performed in real time while a PAP waveform is being acquired using a pulmonary artery catheter (e.g., a Swan-Ganz catheter) and before inflating the balloon to perform a PCWP measurement. The method 500 may evaluate 502 the PAP for artifacts. Artifacts may be caused by such things as patient movement, measurements acquired while flushing the catheter, measurements that show a flat line, measurements that show underattenuation, measurements that show overattenuation, and / or any other phenomenon that may result in an abnormal or unnatural reading in the blood pressure waveform.

[0079] The PAP evaluation for artifacts can be performed over a period of time. In some implementations, the PAP evaluation for artifacts is performed over a period of time ranging from 1 second to 20 seconds. In some implementations, the PAP evaluation for artifacts is performed for a period of about 1 second, about 2 seconds, about 3 seconds, about 4 seconds, about 5 seconds, about 10 seconds, about 15 seconds, or about 20 seconds. This time period can be further divided into smaller discrete or overlapping intervals for batch analysis.

[0080] In some implementations, heuristic metrics may be utilized to determine whether an artifact is present in the PAP waveform. In some implementations, artifacts due to flushing, improper zeroing, or patient movement may be detected by the PAP maximum (PAP max ) is greater than the threshold, the minimum PAP (PAP min ) is less than the threshold, and / or the maximum PAP minus the minimum PAP (PAP max -PAP min ) is greater than a threshold. In various implementations, the artifact may be detected when the PAP max is greater than 60 mmHg, greater than 80 mmHg, greater than 100 mmHg, or greater than 120 mmHg. min is detected when the PAP is less than 5 mmHg, less than 0 mmHg, less than -10 mmHg, less than -20 mmHg, or less than -30 mmHg. max -PAP min is detected when blood pressure is greater than 60mmHg, greater than 80mmHg, greater than 100mmHg, or greater than 120mmHg.

[0081] In some implementations, artifacts based on flat lines or overattenuation are reduced by the PAP maximum minus the PAP minimum (PAP max -PAP min ) is smaller than a threshold. In various implementations, the artifact may be detected when the PAP max -PAP min It is detected when blood pressure is less than 5mmHg, less than 2mmHg, less than 1mmHg, or less than 0.5mmHg.

[0082] After determining that an artifact is present, method 500 can issue a warning 504. In some implementations, the hemodynamic monitoring system displays a warning on a display screen. In some implementations, when an artifact is detected, the monitoring system prevents the PCWP procedure from being performed.

[0083] While a specific example of a computational method for evaluating a PAP waveform for artifacts is described above with reference to FIG. 5, those skilled in the art will appreciate that the various steps of the method may be performed in different orders and that some steps may be optional according to various implementations. As such, it will be apparent that the various steps of the method may be used as appropriate to the requirements of a particular application. Furthermore, any of a variety of methods for evaluating a PAP waveform for artifacts suitable for the requirements of a given application may be utilized in various implementations.

[0084] FIG. 6 presents an example of a computational method for determining a transition to and / or from a wedging position, which may be implemented using a hemodynamic monitoring system. It may be beneficial to determine that the pulmonary artery catheter is transitioning from the pulmonary artery to the wedging position (i.e., detecting the balloon inflation point) in order to obtain a PCWP measurement. Similarly, it may be beneficial to determine that the pulmonary artery catheter has returned from the wedging position to the pulmonary artery (i.e., detecting the balloon deflation point) after obtaining a PCWP measurement. This determination may help ensure that a PCWP measurement is obtained at the appropriate time when the catheter is in the appropriate wedging position. This transition determination may also be further utilized in assessing the quality of the PCWP acquisition. In some implementations, the computational method for determining a transition to and / or from a wedging position is utilized as or within a computational process for detecting the balloon inflation and / or deflation points (e.g., see 444 and 448 in FIG. 4B ).

[0085] The calculation method 600 may be performed in real time after a decision to perform a PCWP measurement acquisition and / or after completion of the PCWP measurement acquisition. The method may help determine whether the pulmonary artery catheter has properly inflated the balloon and reached the wedge position, and / or may help determine whether the pulmonary artery catheter has properly deflated the balloon and returned from the wedge position. The method 600 may extract (602) hemodynamic parameters from the PAP and wedge position waveforms. The PAP and wedge position waveforms may be acquired from a pulmonary artery catheter (e.g., a Swan-Ganz catheter).

[0086] Any hemodynamic parameter capable of distinguishing between a PAP waveform and a wedge position waveform may be utilized. Examples of hemodynamic parameters that may be utilized include (but are not limited to) blood pressure parameters, phase parameters, morphological features, determinable components, demographic features, and combinations thereof. Examples of blood pressure parameters that may be utilized include (but are not limited to) pulse pressure (systolic-diastolic), mean pressure, median pressure, diastolic pressure, systolic pressure, and / or any other obtainable blood pressure parameter. Examples of phase parameters that may be utilized include (but are not limited to) contractility, pulmonary artery compliance, stroke volume, vascular tone, afterload, total cardiac cycle, and / or any other phase parameter. Morphological features that may be utilized include (but are not limited to) frequency content (fft), skewness, kurtosis, and / or any other obtainable morphological feature. Further, determinable components include numerical analysis of the waveform, such as percentiles (e.g., 10%, 25%, 50%, 75%, 90% of systolic pressure or other hemodynamic parameter), number of peaks above the percentile, number of valleys below the percentile, statistical moments, histograms of the data, Shannon's entropy, number of average intersections, area under the curve, singular vector coefficients after principal component analysis, subsampled signals, and / or any other determinable components. Demographic characteristics that may be utilized include (but are not limited to) age, sex, gender, medical history, body mass index, any other relevant characteristics, and / or any other demographic characteristics. In certain implementations, hemodynamic parameters extracted from the PAP waveform and wedge position waveform include pulse pressure (systolic-diastolic) and mean pressure.

[0087] Using the extracted hemodynamic parameters, a fuzzy logic membership function is utilized to generate a fuzzy logic score (604) to determine the status of the current pressure measurement. To generate a fuzzy logic value, the difference between the extracted hemodynamic parameters of the current pressure measurement and the previous PAP sample is calculated. This difference is utilized within the fuzzy logic membership function to determine the current status.

[0088] Any fuzzy logic membership function suitable for assigning membership based on the difference between the extracted hemodynamic parameters of wedge pressure and PAP may be utilized. Examples of fuzzy logic membership functions that may be utilized include (but are not limited to) triangular, Gaussian, and trapezoidal functions. Furthermore, any method for generating any fuzzy logic membership function suitable for assigning membership based on the difference between the extracted hemodynamic parameters of wedge pressure and PAP may be utilized. In general, clinical data of wedge pressure and PAP waveforms may be utilized to identify hemodynamic parameters that provide robust membership classification. See FIG. 8 and related discussion for an example of generating a fuzzy logic function.

[0089] In some implementations, hemodynamic parameter thresholds are utilized in conjunction with fuzzy logic membership functions to assign membership. Thus, in addition to assigning fuzzy logic membership, the extracted hemodynamic parameters must also fall within a threshold range to be assigned to a particular state (e.g., transition to or return from the wedge position pressure). For example, a transition to the wedge position (i.e., balloon inflation point) may be detected using a fuzzy logic membership function based on pulse pressure and mean pressure in conjunction with a mean pressure threshold (e.g., mean pressure is below a threshold) and a pulse pressure threshold (e.g., pulse pressure is below a threshold). In another example, a transition back from the wedge position (i.e., balloon deflation point) may be detected using a fuzzy logic membership function based on pulse pressure and mean pressure, or a mean pressure threshold (e.g., mean pressure is above a threshold) or a pulse pressure threshold (e.g., pulse pressure is above a threshold).

[0090] Based on the results of the fuzzy logic membership functions (and hemodynamic parameter thresholds, if utilized), the method 600 determines (606) the transition points from the pulmonary artery to the wedge position (i.e., balloon inflation point) and / or from the wedge position back to the pulmonary artery (i.e., balloon deflation point).

[0091] 7A shows an example of a fuzzy logic membership plot for plotting transitions to a wedge position and transitions back to the pulmonary artery, where the hemodynamic parameters utilized to distinguish between positions are pulse pressure and mean pressure. As can be seen from the membership plot, the difference in pulse pressure is plotted against the difference in mean pressure. When the calculated fuzzy logic value falls within a particular region, membership to that state can be assigned.

[0092] 7B-7E show trapezoidal fuzzy logic membership functions plotted on a pulmonary artery pressure waveform 300 captured by a pulmonary artery catheter. The trapezoidal fuzzy logic membership functions are based on inputs of the difference between pulse pressure and mean pressure. 7B and 7C show successful transitions to and from the wedging position, marked by transitions 702, 704, 706, and 708, respectively. 7D and 7E show unsuccessful transitions to and from the wedging position, marked by transitions 710 and 712, respectively.

[0093] While a particular example of a computational method for determining transitions to and / or from a wedge position is described above with reference to FIG. 6 , those skilled in the art will understand that various steps of the method may be performed in different orders and that some steps may be optional according to various implementations. As such, it will be apparent that various steps of the method may be used as appropriate to the requirements of a particular application. Furthermore, any of a variety of methods for determining transitions to and / or from a wedge position suitable for the requirements of a given application may be utilized in various implementations.

[0094] An example of a computational method for generating fuzzy logic membership functions for determining transitions to and / or from a wedge position is presented in Figure 8. The generated fuzzy logic functions may be utilized for real-time assessment of a pulmonary artery catheter (e.g., a Swan-Ganz catheter) transition from the pulmonary artery to the wedge position (i.e., balloon inflation point) and / or back from the wedge position to the pulmonary artery (i.e., balloon deflation point).

[0095] The calculation method 800 acquires 802 clinical pulmonary artery and wedge position pressure waveform data, which may be acquired from a PCWP procedure. The waveform data should have a distinguishable transition between the pulmonary artery and wedge positions.

[0096] The method 800 identifies PAP and wedge pressure regions in the waveform data 804. Generally, the selected regions should be clearly within a PAP state or clearly within a wedge pressure state.

[0097] The method 800 extracts one or more hemodynamic parameters from the PAP and wedge pressure regions. Any hemodynamic parameter capable of distinguishing between a PAP waveform and a wedge position waveform may be utilized. Examples of hemodynamic parameters that may be utilized include (but are not limited to) blood pressure parameters, phase parameters, morphological features, determinable components, demographic features, and combinations thereof. Examples of blood pressure parameters that may be utilized include (but are not limited to) pulse pressure (systolic-diastolic), mean pressure, median pressure, diastolic pressure, systolic pressure, and / or any other obtainable blood pressure parameter. Examples of phase parameters that may be utilized include (but are not limited to) contractility, pulmonary artery compliance, stroke volume, vascular tone, afterload, total cardiac cycle, and / or any other phase parameter. Morphological features that may be utilized include (but are not limited to) frequency content (fft), skewness, kurtosis, and / or any other obtainable morphological feature. Further, determinable components include numerical analysis of the waveform, such as percentiles (e.g., 10%, 25%, 50%, 75%, 90% of systolic pressure or other hemodynamic parameter), number of peaks above the percentile, number of valleys below the percentile, statistical moments, histograms of the data, Shannon's entropy, number of average intersections, area under the curve, singular vector coefficients after principal component analysis, subsampled signals, and / or any other determinable components. Demographic characteristics that may be utilized include (but are not limited to) age, sex, gender, medical history, body mass index, any other relevant characteristics, and / or any other demographic characteristics. In certain implementations, hemodynamic parameters extracted from the PAP waveform and wedge position waveform include pulse pressure (systolic-diastolic) and mean pressure.

[0098] The parameters for membership of the generated fuzzy logic may be selected for a variety of purposes. The parameters may be selected based on computational power, ease of measurement, correlation, accuracy, any other relevant parameters and / or metrics, and combinations thereof. The correlation may be with another feature, such as with pulse pressure and / or other features.

[0099] The method 800 generates a fuzzy logic membership function using one or more extracted hemodynamic parameters. To generate the fuzzy logic membership function, the difference of the extracted hemodynamic parameters between the wedge pressure region and the PAP region is calculated. The difference is utilized within the fuzzy logic membership function to determine whether the hemodynamic parameters provide a robust differential quantification of the condition.

[0100] In some implementations, hemodynamic parameter thresholds are utilized in conjunction with fuzzy logic membership functions to assign membership. Thus, in addition to assigning fuzzy logic membership, the extracted hemodynamic parameters must also fall within a threshold range to be assigned to a particular state (e.g., transition to or return from the wedge position pressure). For example, a transition to the wedge position (i.e., balloon inflation point) may be detected using a fuzzy logic membership function based on pulse pressure and mean pressure in conjunction with a mean pressure threshold (e.g., mean pressure is below a threshold) and a pulse pressure threshold (e.g., pulse pressure is below a threshold). In another example, a transition back from the wedge position (i.e., balloon deflation point) may be detected using a fuzzy logic membership function based on pulse pressure and mean pressure, or a mean pressure threshold (e.g., mean pressure is above a threshold) or a pulse pressure threshold (e.g., pulse pressure is above a threshold).

[0101] Presented in Figure 9 are plots of pulse pressure (systolic-diastolic) and mean pressure (mean signal) derived from clinical pulmonary artery and wedge position pressure waveform data for a large cohort of patients. As can be seen from the plot, the hemodynamic parameter data derived from the wedge position waveform is primarily located in the lower left quadrant. To ensure that the hemodynamic parameter data is actually derived from the wedge position waveform, a pulse pressure threshold (e.g., 15 mmHg) and mean pressure threshold (e.g., 32 mmHg) may be applied.

[0102] While a specific example of a computational method for generating fuzzy logic membership functions is described above with reference to FIG. 6, those skilled in the art will appreciate that various steps of the method may be performed in different orders and that some steps may be optional according to various implementations. As such, it will be apparent that various steps of the method may be used as appropriate to the requirements of a particular application. Furthermore, any of a variety of methods for generating fuzzy logic membership functions suitable for the requirements of a given application may be utilized in various implementations.

[0103] Various other methods according to some implementations may be utilized to separate, classify, and / or otherwise analyze the data to identify clusters that detect transitions to and / or from the wedge position. Such methods may include algorithmic, machine learning (e.g., artificial intelligence), statistical, and / or other methods for identifying data clusters. Various machine learning models are provided, including (but not limited to) convolutional neural networks (CNNs), support vector machines (SVMs), and / or any other machine learning model sufficient to identify features that classify catheter positions.

[0104] FIG. 10 presents an example of a computational method for performing PCWP measurements and assessing the quality of PCWP acquisition, which may be performed using a hemodynamic monitoring system. Determining the quality of the PCWP acquisition may help inform a clinician whether the PCWP measurement is adequate for making a health status determination or whether the PCWP procedure should be repeated. Furthermore, the assessment of the quality of the wedge pressure acquisition may be used to improve the PCWP calculation by utilizing only portions of the wedge pressure waveform that exceed quality standards. The quality of the PCWP acquisition may be determined using one or more trained machine learning models and / or various hemodynamic thresholds. In certain implementations, the computational method for performing PCWP acquisition and assessing its quality may be combined with a set of other computational processes to perform high-quality automated PCWP measurements (e.g., see 450 in FIG. 4B ).

[0105] The calculation method 1000 may be performed in real time to improve and / or evaluate the quality of PCWP measurement acquisition. The method 1000 divides the PAP and wedge position waveforms into multiple time windows (1002). The PAP and wedge position waveforms may be acquired from a pulmonary artery catheter (e.g., a Swan-Ganz catheter).

[0106] The multiple time windows can be discrete or overlapping, contiguous, or non-contiguous. A time window can be defined by any non-zero time duration up to the full time frame of the PAP or wedge position waveform. In some implementations, the length of the time window is between 0.5 and 20 seconds. In various implementations, the length of the time window is between 0.5 and 1.5 seconds, between 1.0 and 2.0 seconds, between 1.0 and 3.0 seconds, between 2.0 and 4.0 seconds, between 3.0 and 5.0 seconds, between 4.0 and 6.0 seconds, between 5.0 and 7.0 seconds, between 6.0 and 8.0 seconds, between 7.0 and 9.0 seconds, between 8.0 and 10.0 seconds, between 9.0 and 11.0 seconds, between 10.0 and 15.0 seconds, between 12.5 and 17.5 seconds, or between 15.0 and 20.0 seconds. In some implementations, the time window is defined by a physiological event (e.g., one or more respiratory cycles). In some implementations, a user (e.g., a clinician) can select the length of the time window.

[0107] The method 1000 extracts one or more hemodynamic parameters from the PAP and wedge pressure regions. Any hemodynamic parameter capable of distinguishing between a PAP waveform and a wedge position waveform may be utilized. Examples of hemodynamic parameters that may be utilized include (but are not limited to) blood pressure parameters, phase parameters, morphological features, determinable components, demographic features, and combinations thereof. Examples of blood pressure parameters that may be utilized include (but are not limited to) pulse pressure (systolic-diastolic), mean pressure, median pressure, diastolic pressure, systolic pressure, and / or any other obtainable blood pressure parameter. Examples of phase parameters that may be utilized include (but are not limited to) contractility, pulmonary artery compliance, stroke volume, vascular tone, afterload, total cardiac cycle, and / or any other phase parameter. Morphological features that may be utilized include (but are not limited to) frequency content (fft), skewness, kurtosis, and / or any other obtainable morphological feature. Further, determinable components include numerical analysis of the waveform, such as percentiles (e.g., 10%, 25%, 50%, 75%, 90% of systolic pressure or other hemodynamic parameter), number of peaks above the percentile, number of valleys below the percentile, statistical moments, histograms of the data, Shannon's entropy, number of average intersections, area under the curve, singular vector coefficients after principal component analysis, subsampled signals, and / or any other determinable components. Demographic features that may be utilized include (but are not limited to) age, sex, gender, medical history, body mass index, any other relevant features, and / or any other demographic features. In some implementations, hemodynamic parameters extracted from the PAP waveform and wedge position waveform include pulse pressure (systolic-diastolic) and mean pressure.

[0108] Method 1000 assesses the quality of PAP and wedge pressure waveforms over multiple segmented time windows. Quality can be assessed by a variety of methods, which may be combined. In some implementations, quality is assessed using a trained machine learning model. In some implementations, quality is assessed using thresholds for various hemodynamic parameters. Quality ratings can be quantitative (e.g., a score ranging from 0 to 100) or categorical (e.g., "good" vs. "poor," "adequate" vs. "inadequate"). In some implementations, thresholds are used to determine whether the quality score is low / high or "poor / good." The thresholds may be based on clinical data.

[0109] To assess the quality of PAP and wedge pressure waveforms using a machine learning model, one or more parameters are input as features into the model to generate a quality assessment. Various machine learning models may be used, including (but not limited to) regression models, logistic regression models, neural networks, convolutional neural networks, support vector machines, decision trees, Adaboost, random forests, ensemble learning models (combining one or more models), and / or any other machine learning model capable of determining the quality of pressure readings based on feature data and classified measurements. The machine learning model may be trained using acquired clinical PAP and wedge pressure data, and high-quality time windows of data are utilized to distinguish them from low-quality time windows of data using a set of hemodynamic data features. In some implementations, hemodynamic data features are extracted from clinical PAP and wedge pressure waveforms and their associated data windows. Data windows may be distinguished as derived from PAP or wedge pressure waveforms based on their quality and assigned a quality score or any other quality indicator. A machine learning model can be trained to distinguish the quality of PAP and wedge pressure waveform windows. In some implementations, quality is determined by being able to distinguish windows of the wedge pressure waveform from windows of the PAP waveform.

[0110] In some implementations, quality is assessed based on whether a waveform window is above or below thresholds for various hemodynamic parameters. For many hemodynamic parameters, the PAP waveform and the wedge position waveform are expected to fall within certain ranges, as determined by clinical data. Furthermore, some hemodynamic parameters are expected to be highly distinguishable between the PAP waveform and the wedge position waveform, as determined by clinical data. By utilizing these expected ranges or expected differences between the waveforms, these waveform windows can be assessed for quality. In some implementations, a waveform window is determined to be above a quality standard if it meets one or more criteria. In some implementations, a waveform window is determined to be below a quality standard if it fails to meet one or more criteria.

[0111] Parameter thresholds can be based on one or more qualitative, quantitative, or semi-quantitative factors that can assess the quality of a window. Non-limiting examples of thresholds that can be used to identify parameters can be based on expert experience and / or metrics identified in the literature. Parameter thresholds that can be used (alone or in combination) as window quality metrics include (but are not limited to) pressure rise / fall above a threshold, including (but not limited to) mean pressure and pulse pressure; mean wedge pressure lower than pulmonary artery diastolic pressure; blood oxygen rise / fall above a threshold; elevated respiratory-induced fluctuations in wedge position compared to pulmonary artery position; and / or morphological features such as clearly defined pressure waves (e.g., "a" and "v" waves). Using one or more quality features, a quality score can be generated for the waveform window, which can be a categorical, quantitative, or semi-quantitative quality score. Qualitative categories can be binary (e.g., good or bad) and / or qualitative rankings (e.g., poor, fair, good).

[0112] In some implementations, multiple assessments of quality may be combined and treated as factors and / or requirements for the quality assessment. For example, the quality of a window may be determined using multiple weighting factors, each of which may be combined to generate an overall determination of quality. Alternatively, or in addition, the quality of a window may need to satisfy all of one or more requirements to meet a quality standard, and failing to meet any one of the one or more requirements may fail to meet that standard. In some implementations, when a machine learning model is combined with one or more hemodynamic parameter thresholds, the thresholds may be applied as preconditions for input to the model, in an ensemble with the model, or as a subsequent assessment of the model.

[0113] 11A and 11B present an example of assessing the quality of a waveform window. In particular, FIG. 11A presents a table of assessments that can be made based on binary criteria (e.g., true / false, 0-1, etc.) to classify waveform windows. These assessments utilize the probability (or likelihood) of PCWP at a PAP position, where the mean PCWP pressure is less than the mean PAP diastolic pressure. Based on a binary decision, quality can be assessed. Similarly, FIG. 14B ... the mean PCWP pressure (PCWP Mean ) is the mean PAP diastolic pressure (PAP Diastolic ) is smaller than the mean PCWP pulse pressure (PCWP PulsePress ) and mean PCWP pressure (PCWP Mean ) is greater than or less than the determinant value. While a specific formula is shown in FIG. 11B, various formulas can be generated or modified depending on the specific parameters utilized in the formula. Furthermore, any formula for generating a hyperplane can be given, where the weights a and b and the determinant value c can be exposed as a formula describing the hyperplane.

[0114] 12 presents an assessment of the quality 1202 of a window of waveform 300 overlaid on the waveform. The wedge location portion 1204 of waveform 300 can be assessed as a quantitative or qualitative quality score. As can be seen, a small window of wedge location portion 1204 is of "Okay quality."

[0115] Method 1000 performs PCWP measurements. In certain implementations, the PCWP is measured according to a respiratory cycle. In some implementations, the PCWP is the pressure measured after the completion of a respiratory cycle (i.e., the end-expiratory pressure or the average of the end-expiratory pressures). In some implementations, the PCWP is the average pressure measured over a number of respiratory cycles (e.g., 1, 2, 3, or 4 respiratory cycles) during wedging. In some implementations, the PCWP is the average pressure measured over a period of time (e.g., between 2 and 20 seconds) during wedging. In some implementations, a PCWP measurement is obtained and then evaluated for quality.

[0116] The quality assessment can be used to improve the determination of PCWP. In some implementations, the quality assessment is used to improve the determination of the PCWP measurement. In some implementations, the quality of multiple windows of the wedge position waveform is determined, and if a certain number of windows fail to meet the quality standard, the PCWP measurement is not determined. In some implementations, only windows that meet the quality standard are used to determine the PCWP measurement. In some implementations, windows that fail to meet the quality standard are discarded before determining the PCWP measurement.

[0117] Method 1000 reports a quality assessment of the PCWP and / or PCWP acquisition. In some implementations, the quality of the acquired PCWP and / or PCWP measurement is displayed on a display screen of the monitoring system. In some implementations, the quality rating is saved in memory or transmitted to another computing device for storage or downstream analysis. In some implementations, a low or "bad" quality score is used to notify a clinician that a repeat PCWP measurement is recommended. In some implementations, a low or "bad" quality score is used to automatically repeat the PCWP measurement. Once the PCWP measurement (or repeated PCWP measurement) is complete, the monitoring system can exit PCWP mode (432).

[0118] In determining quality, some systems and / or methods of the present disclosure are directed to identifying an optimized combination of input parameters to generate a quality rating for the pressure waveform. The goal of optimization can be any one or any combination of reduced effort, reduced cost, reduced risk, increased reliability, increased efficacy, reduced side effects, reduced toxicity, and mitigation of drug resistance, among other benefits.

[0119] Blood pressure waveforms have various distinguishable characteristics that can be identified within a single heartbeat waveform (e.g., a single cardiac cycle of systole and diastole) or across multiple heartbeat waveforms (e.g., multiple cardiac cycles). Referring to Figures 13A and 13B, general waveform characteristics are illustrated for a single heartbeat. In particular, Figure 13A illustrates portions of the waveform representing systole and diastole, as well as the ascending and descending limbs within a single heartbeat. Figure 13B illustrates granular characteristics of the heartbeat waveform, identifying the systolic onset, peak pressure, and decline, as well as the dicrotic notch, diastolic outflow, and end-diastolic pressure.

[0120] In addition to the characteristics identified in Figures 13A and 13B, numerous systems and / or methods identify, measure, or calculate various additional characteristics within the waveform of a single heartbeat. Referring to Figures 14A through 14F, waveform phase characteristics identified from a single heartbeat can include one or more of contractility (Figure 14A), pulmonary artery compliance (Figure 14B), stroke volume (Figure 14C), vascular tone (Figure 14D), afterload (Figure 14E), and / or the entire cardiac cycle (Figure 14F). The characteristics represented in each of Figures 14A through 14F are the shaded portions of the waveform. In addition to single measurements, various systems and / or methods determine one or more determinable characteristics. Such determinable characteristics may be determined from one or more of each phase within the pressure waveform, including (but not limited to) the mean, maximum, minimum, duration, area, standard deviation, slope, derivative (as the difference in pressure with respect to time (dP / dt)) of the phase, trend, deviation from trend, variation, variance, and combinations thereof. Some systems and / or methods also determine one or more morphological characteristics. Such morphological characteristics may be determined from one or more waveform phases, and such morphological features include (but are not limited to) frequency content (fft), skewness, kurtosis, any other morphological characteristic determinable within a waveform, and combinations thereof. Additional systems and / or methods use one or more of the aforementioned characteristics (e.g., phase characteristics, determinable characteristics, morphological characteristics, etc.) to determine one or more of complexity (e.g., entropy measures such as approximate entropy and / or sample entropy), baroreflex sensitivity (e.g., via cross-correlation analysis), variability, variance, and combinations thereof.

[0121] Based on the pressure waveform, various systems and / or methods further extract one or more parameters of heart rate, respiratory rate, stroke volume, pulse pressure, mean pulmonary artery pressure (mPAP), pulmonary artery systolic pressure (sPAP), pulmonary artery diastolic pressure (dPAP), pulse pressure variability, stroke volume variability, heart rate variability, cardiac output, pulmonary peripheral resistance, vascular compliance, vascular elasticity, and right ventricular contractility (dP / dt).

[0122] Some catheters (e.g., Swan-Ganz catheters) include temperature probes, optical fibers, and / or other components that can provide additional measurements. As such, some systems and / or methods can extract characteristics such as cardiac output, stroke volume, ejection fraction, end-diastolic volume, blood temperature, blood oxygenation, other measurements that may be obtained from the catheter, and combinations thereof. It should be noted that the aforementioned additional measurements may be measured directly (e.g., a single measurement) or extracted from the waveform. In addition, many systems and / or methods extract additional characteristics from any of such additional measurements (e.g., determinable features, morphological features, etc.) as previously described.

[0123] Various systems and methods utilize one or more of the aforementioned characteristics and characteristic types (e.g., morphological characteristics, phase characteristics, etc.) to identify wedge transitions and / or quality of pressure waveforms in PCWP procedures, as described in further detail below.

[0124] Hemodynamic Monitoring and Computing System A computing system for performing PCWP measurements and assessing PCWP quality according to the various methods and processes of the present disclosure typically utilizes a processing system including one or more of a CPU, a GPU, and / or a neural processing engine. As described herein, finger arterial pressure can be recorded in real time using a computing system and converted to radial artery pressure.

[0125] The computing system may be housed within the hemodynamic monitoring system with a direct wired connection between the monitoring and components, including the pulmonary artery catheter (e.g., a Swan-Ganz catheter). Alternatively, the computing system may be housed separately from the hemodynamic monitoring system and components and receive the acquired pulmonary artery pressure via a wireless connection (e.g., WiFi, cellular, Bluetooth, etc.). The computing system may be implemented on any suitable computing device, such as (but not limited to) the hemodynamic monitoring system, a tablet, and / or a portable computer.

[0126] An exemplary computing system that may be utilized to perform the various methods and processes of the present disclosure is illustrated in Figure 15. The computing system 1500 includes a processor system 1502, an I / O interface 1504, and a memory system 1506. As can be readily appreciated, the processor system 1502, the I / O interface 1504, and the memory system 1506 may be implemented using any of a variety of components suitable for the requirements of a particular application, including (but not limited to) a CPU, a GPU, an ISP, a DSP, a wireless modem (e.g., WiFi, Bluetooth modem), a serial interface, volatile memory (e.g., DRAM) and / or non-volatile memory (e.g., SRAM and / or NAND flash).

[0127] In the illustrated example, the memory system can store various data, applications, and models. The listed data, applications, and models are a representative sample of what may be stored in memory, and it should be understood that various memory systems may store some or all of the various data, applications, and models listed. Furthermore, any combination of data, applications, and models may be stored, and in some implementations, various data, applications, and / or models are temporarily stored.

[0128] In some implementations, the memory system 1506 can store one or more applications for (for example) determining system readiness for PCWP 1508, detecting balloon inflation and / or deflation points 1510, detecting respiratory cycles 1512, measuring PCWP 1514, and assessing the quality of PCWP acquisition 1516. The various applications can be provided as individual processes or as an ensemble of processes, each of which can be utilized to provide automated acquisition and quality assessment of PCWP measurements. The real-time PCWP results and quality ratings 1518 can also optionally be stored on the memory system 1506 and / or displayed on a display screen via the I / O interface 1504.

[0129] While a particular computing system is described above with reference to FIG. 15 , it will be readily understood that the computing and / or other processes utilized in performing PCWP measurements and assessing the quality of PCWP measurements may be implemented in any of a variety of processing devices, including combinations of processing devices. Accordingly, the computing device should be understood as not limited to a particular monitoring system, computing system, and / or particular application and model. A computing device may be implemented to perform the processes, combinations of processes, and / or modified versions of the processes described herein using any of the combinations of systems described herein and / or modified versions of the systems described herein.

[0130] The systems and methods of the present disclosure may be utilized within a hemodynamic monitoring system. Typically, a hemodynamic monitoring system includes a pulmonary artery catheter (PAC, e.g., a Swan-Ganz catheter). Shown in FIG. 16 is an example of a hemodynamic monitoring system 1600 that may be utilized to measure an individual's PCWP. Within the patient is a PAC 1620, which may include one or more sensors, such as (for example) a pressure sensor, a thermal sensor (e.g., for measuring cardiac output via thermodilution), or an optical fiber (e.g., photometric or other optical measurement). The PAC 1620 may also include a balloon near its distal end for performing a wedging procedure within the pulmonary artery. The PAC 1620 may be coupled to the hemodynamic monitoring system 1600. A pump system may be included to inflate the balloon.

[0131] The hemodynamic monitoring system 1600 may include a computing system such as (for example) the system depicted and described with reference to FIG. 8. The hemodynamic monitoring system 1600 may include a processor system 1602 and an I / O interface 1604 for inputting and outputting data, such as data communicated between the hemodynamic monitoring system 1600, the sensors of the PAC 1620, and a user interface. The hemodynamic monitoring system 1600 may utilize a number of applications stored in a memory system 1606 that are executed by the processor system 1602. Applications that may be stored in the memory system 1606 include a real-time PAP acquisition application 1608, a real-time PCWP acquisition application 1610, and a real-time extraction of hemodynamic parameters 1612 for operating the hemodynamic monitoring system.

[0132] 16, it will be readily understood that the various hemodynamic monitoring systems and / or other medical monitoring devices utilized in performing hemodynamic monitoring may be implemented in any of a variety of configurations. Accordingly, the various systems and methods described herein should not be understood as being limited to a particular hemodynamic monitoring system, but instead may be implemented using any of a variety of hemodynamic or medical monitoring systems capable of measuring PAP and PCWP.

[0133] (Example) Example 1 1. A calculation method for performing a pulmonary capillary wedge pressure (PCWP) measurement on an individual and assessing the quality of the PCWP measurement, comprising: acquiring a blood pressure waveform of the individual, the waveform including a blood pressure measurement obtained from a pulmonary artery location and a blood pressure measurement obtained from a wedge location, the blood pressure waveform being acquired using a pulmonary artery catheter; determining PCWP measurements from blood pressure measurements from the wedge positions using a computing system; using a computing system to determine a quality assessment for the PCWP measurement using a machine learning model configured to provide a quality assessment for the PCWP measurement based on blood pressure measurements obtained from the pulmonary artery location and blood pressure measurements obtained from the wedge location; Calculation methods, including:

[0134] Example 2 The method according to example 1, wherein the PCWP measurement and the quality assessment are each determined in real time.

[0135] Example 3 The method of example 2, further comprising digitally communicating with a computing system to display the PCWP measurements and quality assessments on a display screen.

[0136] Example 4 4. The method of any one of Examples 1, 2, or 3, wherein the computing system and the pulmonary artery catheter are part of a hemodynamic monitoring system.

[0137] Example 5 The step of acquiring a blood pressure waveform includes: inserting a pulmonary artery catheter into a central vein of the individual; directing a pulmonary artery catheter into the pulmonary artery; inflating a balloon at or near the distal end of the pulmonary artery catheter to allow the pulmonary artery catheter to move into a wedging position; The method of any one of Examples 1 to 4, comprising:

[0138] Example 6 6. The method of example 5, further comprising using a computing system to evaluate blood pressure measurements obtained from the pulmonary artery location in real time for artifacts before inflating the balloon.

[0139] Example 7 The method of example 6, wherein the artifacts include one or more of measurements taken during patient movement, measurements taken during catheter flushing, and measurements showing flat lines, measurements showing underattenuation, and measurements showing overattenuation.

[0140] Example 8 Detection of artifacts due to flushing, improper zeroing, or patient movement is based on the maximum PAP (PAP max ) is greater than the threshold, the minimum PAP (PAP min ) is less than the threshold, and / or the maximum PAP minus the minimum PAP (PAP max -PAP min 8. The method of any one of claims 6 to 7, wherein the blood pressure is detected when a blood pressure measurement obtained from a pulmonary artery location is greater than a threshold value.

[0141] Example 9 Detection of artifacts based on flat lines or overattenuation was determined by subtracting the minimum PAP value from the maximum PAP value (PAP max -PAP min 9. The method of any one of claims 6, 7, or 8, wherein the PAP is detected when ) is less than a threshold value, and PAP is a blood pressure measurement obtained from a pulmonary artery location.

[0142] Example 10 10. The method of any one of Examples 5 to 9, wherein the pulmonary artery catheter comprises a lumen configured to measure blood pressure.

[0143] Example 11 11. The method of any one of Examples 1 to 10, wherein the pulmonary artery catheter is a Swan-Ganz catheter.

[0144] Example 12 the machine learning model is based on at least one feature selected from the group consisting of waveform phase features, decidable features, and morphological features; Waveform phase features are selected from contractility, pulmonary artery compliance, stroke volume, vascular tone, afterload, and the entire cardiac cycle, The determinable features are determined based on waveform phase features and are selected from mean, maximum, minimum, duration, area, standard deviation, slope, derivative, trend, deviation from trend, variance, and variance of phase; 12. The method of any one of Examples 1 to 11, wherein the morphological features are based on waveform features and are selected from frequency content, skewness, and kurtosis.

[0145] Example 13 13. The method of example 12, wherein the machine learning model is based on one or more of approximate entropy, sample entropy, baroreflex sensitivity, variability, and change.

[0146] Example 14 The step of obtaining PCWP measurements includes: 14. The method of any one of Examples 1 to 13, comprising determining a respiratory cycle of the individual, wherein determining a PCWP measurement value is based on the respiratory cycle of the individual.

[0147] Example 15 15. The method of example 14, wherein determining the PCWP measurement comprises determining a blood pressure measurement from a wedge position at the end of expiration of the respiratory cycle.

[0148] Example 16 15. The method of example 14, wherein determining the PCWP measurement comprises averaging blood pressure measurements from the wedge position over one or more respiratory cycles.

[0149] Example 17 In real time, a computing system is used to calculate the transition from the pulmonary artery position to the wedge position or from the wedge position to the pulmonary artery position. extracting one or more hemodynamic features from the blood pressure measurements at the pulmonary artery location and the blood pressure measurements at the wedge location; determining a fuzzy logic value for each of the one or more hemodynamic features based on a change in value between the blood pressure measurement at the pulmonary artery location and the blood pressure measurement at the wedge location using a fuzzy logic membership function; 17. The method of any one of Examples 1 to 16, further comprising detecting in real time by

[0150] Example 18 18. The method of example 17, wherein the one or more features include at least one of a statistical moment, a percentile value of the data, a histogram of the data, a diastolic pressure, a median pressure, a mean pressure, a systolic pressure, a pulse pressure, Shannon's entropy, a number of peaks above a percentile, a number of valleys below a percentile, a number of average crossings, an area under the curve, a singular vector coefficient after principal component analysis, a subsampled signal, a determinable feature, a waveform phase feature, and a morphological feature.

[0151] Example 19 The method of example 18, wherein the morphological features are selected from frequency content, skewness, and kurtosis, the waveform phase features are selected from contractility, pulmonary artery compliance, stroke volume, vascular tone, afterload, and total cardiac cycle, and the determinable features are selected from mean, maximum, minimum, duration, area, standard deviation, slope, derivative, trend, deviation from trend, variance, and variance of phase.

[0152] Example 20 20. The method of example 18 or 19, wherein the one or more characteristics include mean pressure and pulse pressure.

[0153] Example 21 dividing the blood pressure measurements obtained from the pulmonary artery location and the blood pressure measurements obtained from the wedge location into time windows; extracting features from a time window of blood pressure measurements taken from the pulmonary artery location and blood pressure measurements taken from the wedge location; further comprising The machine learning model is trained to detect whether the extracted features for the time window are derived from blood pressure measurements taken from a pulmonary artery location or a wedge location, and determining, using a computing system, a quality assessment for the PCWP measurements using the machine learning model includes: 21. The method of any one of Examples 1 to 20, comprising inputting the extracted features from the time windows into a machine learning model to generate a quality assessment for each time window based on whether the extracted features for each time window can be distinguished as being derived from a pulmonary artery location or a wedge location.

[0154] Example 22 The method of Example 21, wherein the quality assessment is categorical.

[0155] Example 23 The method of Example 22, wherein the categories are qualitative rankings.

[0156] Example 24 The step of determining, using a computing system, a quality assessment for the PCWP measurement using a machine learning model includes: 24. The method of example 21, 22, or 23, comprising determining whether one or more extracted features for a time window are above or below a threshold.

[0157] Example 25 One or more extracted features are Mean , PAP Diastolic , and PCWP PulsePress Including PCWP Mean is the average pressure measurement taken at the wedge position, and PAP Diastolic is the diastolic pressure at the pulmonary artery, and PCWP PulsePress The method of example 24, wherein σ is the pulse pressure at the wedge position.

[0158] Example 26 High quality, PCWP Mean <PAP Diastolic AND a×PCWP PulsePress +b×PCWP Mean The method of Example 25, wherein a, b, and c are determinant values, is indicated when a, b, and c are determinant values.

[0159] Example 27 Medium quality is PCWP Mean <PAP Diastolic AND a×PCWP PulsePress +b×PCWP Mean The method of any one of Examples 25 to 26, wherein a, b, and c are determinant values.

[0160] Example 28 Low quality PCWP Mean ≧PAP Diastolic The method of Example 25, 26, or 27, wherein

[0161] Example 29 29. The method of any one of Examples 21 to 28, further comprising using a computing system to assign to each time window its quality rating.

[0162] Example 30 30. The method of any one of Examples 21 to 29, further comprising digitally communicating with a computing system to display the quality assessment of one or more time windows on a display screen.

[0163] Example 31 31. The method of any one of Examples 21 to 30, wherein using a computing system, determining the PCWP measurement value comprises averaging blood pressure measurements obtained from wedge positions in a time window determined to have a quality above a threshold.

[0164] Example 32 The step of determining a PCWP measurement using a computing system includes: filtering out blood pressure measurements taken from wedge locations in the time window determined to have a quality below a threshold; averaging the non-excluded blood pressure measurements obtained from the wedge positions of the time window; 32. The method of any one of Examples 21 to 31, comprising:

[0165] Example 33 33. The method of example 31 or 32, comprising the step of digitally communicating with a computing system to display the quality assessment of one or more time windows on a display screen.

[0166] Example 34 1. A hemodynamic monitoring system for performing pulmonary capillary wedge pressure (PCWP) measurements and assessing the quality of the PCWP measurements, comprising: a pulmonary artery catheter configured to obtain blood pressure measurements obtained from a pulmonary artery location and blood pressure measurements obtained from a wedge location, the pulmonary artery catheter including an inflatable balloon; 1. A computing system in communication with a pulmonary artery catheter, the computing system comprising: a processor system; a display screen digitally connected to the processor system; A memory system containing one or more applications, the applications being connected to a processor system, obtaining a blood pressure measurement at a pulmonary artery location; inflating the balloon, which allows the catheter to move to a wedging position; obtaining a blood pressure measurement at the wedge position; generating a blood pressure waveform from blood pressure measurements taken from the pulmonary artery location and blood pressure measurements taken from the wedge location; determining PCWP measurements from blood pressure measurements from the wedge positions; determining a quality assessment for the PCWP measurement using a machine learning model configured to provide a quality assessment for the PCWP measurement based on blood pressure measurements obtained from the pulmonary artery location and blood pressure measurements obtained from the wedge location; displaying one or more of the blood pressure waveform, the PCWP measurement, or a quality assessment of the PCWP measurement on a display screen; a memory system that can command a computing system comprising: A hemodynamic monitoring system comprising:

[0167] Example 35 35. The system of example 34, wherein a blood pressure waveform is generated and displayed on a display screen in real time.

[0168] Example 36 36. The system of example 34 or 35, wherein PCWP measurements are determined and displayed on a display screen in real time.

[0169] Example 37 37. The system of example 34, 35, or 36, wherein a quality assessment for the PCWP measurement is determined and displayed on a display screen in real time.

[0170] Example 38 A system described in any one of Examples 34 to 37, wherein the pulmonary artery catheter comprises an inner lumen for measuring blood pressure and a balloon that allows the pulmonary artery catheter to be moved into a wedged position.

[0171] Example 39 The system of any one of Examples 34 to 38, wherein the catheter is a Swan-Ganz catheter.

[0172] Example 40 One or more applications may be installed on a processor system. A system described in any one of Examples 34 to 39, which can be instructed to evaluate blood pressure measurements obtained from a pulmonary artery location for artifacts in real time before inflating the balloon.

[0173] Example 41 The system of Example 40, wherein the artifacts include one or more of measurements taken during patient movement, measurements taken during catheter flushing, and measurements showing flat lines, measurements showing underattenuation, and measurements showing overattenuation.

[0174] Example 42 Detection of artifacts due to flushing, improper zeroing, or patient movement is based on the maximum PAP (PAP max ) is greater than the threshold, the minimum PAP (PAP min ) is less than the threshold, and / or the maximum PAP minus the minimum PAP (PAP max -PAP min 42. The system of claim 40 or 41, wherein the PAP is detected when the PAP is greater than a threshold, and the PAP is a blood pressure measurement obtained from a pulmonary artery location.

[0175] Example 43 Detection of artifacts based on flat lines or overattenuation was determined by subtracting the minimum PAP value from the maximum PAP value (PAP max -PAP min 43. The system of claim 40, 41, or 42, wherein the PAP is detected when PAP is less than a threshold value, and PAP is a blood pressure measurement obtained from a pulmonary artery location.

[0176] Example 44 the machine learning model is based on at least one feature selected from the group consisting of waveform phase features, decidable features, and morphological features; Waveform phase features are selected from contractility, pulmonary artery compliance, stroke volume, vascular tone, afterload, and the entire cardiac cycle, The determinable features are determined based on waveform phase features and are selected from mean, maximum, minimum, duration, area, standard deviation, slope, derivative, trend, deviation from trend, variance, and variance of phase; 44. The system of any one of Examples 34 to 43, wherein the morphological features are based on waveform features and are selected from frequency content, skewness, and kurtosis.

[0177] Example 45 The system of Example 44, wherein the machine learning model is based on one or more of approximate entropy, sample entropy, baroreflex sensitivity, variability, and change.

[0178] Example 46 One or more applications may be installed on a processor system. A system described in any one of Examples 34 to 45, which can instruct the determination of a respiratory cycle, and the determination of a PCWP measurement value is based on the individual's respiratory cycle.

[0179] Example 47 The system of Example 46, wherein one or more applications can instruct the processor system to determine a blood pressure measurement from a wedge position at the end of exhalation of a respiratory cycle and generate a PCWP measurement.

[0180] Example 48 The system of Example 46, wherein one or more applications can instruct the processor system to determine blood pressure measurements from wedge positions over one or more respiratory cycles.

[0181] Example 49 One or more applications may be installed on a processor system. The transition from the pulmonary artery position to the wedge position or from the wedge position to the pulmonary artery position is extracting one or more hemodynamic features from the blood pressure measurements at the pulmonary artery location and the blood pressure measurements at the wedge location; determining a fuzzy logic value for each of the one or more hemodynamic features based on a change in value between the blood pressure measurement at the pulmonary artery location and the blood pressure measurement at the wedge location using a fuzzy logic membership function; 49. The system of any one of Examples 34 to 48, wherein the system is capable of directing real-time detection by

[0182] Example 50 The system of Example 49, wherein the one or more features include at least one of a statistical moment, a percentile value of the data, a histogram of the data, a diastolic pressure, a median pressure, a mean pressure, a systolic pressure, a pulse pressure, Shannon's entropy, a number of peaks above a percentile, a number of valleys below a percentile, a number of average crossings, an area under the curve, a singular vector coefficient after principal component analysis, a subsampled signal, a determinable feature, a waveform phase feature, and a morphological feature.

[0183] Example 51 The system of Example 50, wherein the morphological features are selected from frequency content, skewness, and kurtosis, the waveform phase features are selected from contractility, pulmonary artery compliance, stroke volume, vascular tone, afterload, and the entire cardiac cycle, and the determinable features are selected from mean, maximum, minimum, duration, area, standard deviation, slope, derivative, trend, deviation from trend, variance, and variance of the phase.

[0184] Example 52 The system of example 50 or 51, wherein the one or more characteristics include mean pressure and pulse pressure.

[0185] Example 53 One or more applications may be installed on a processor system. dividing the blood pressure measurements obtained from the pulmonary artery location and the blood pressure measurements obtained from the wedge location into time windows; extracting features from a time window of blood pressure measurements taken from the pulmonary artery location and blood pressure measurements taken from the wedge location; inputting the extracted features from the time windows into a machine learning model to generate a quality assessment for each time window, the quality assessment being based on whether the extracted features for each time window can be distinguished as being derived from a pulmonary artery location or a wedge location to generate a quality assessment for the PCWP, the machine learning model being trained to detect whether the extracted features for a time window are derived from blood pressure measurements taken from a pulmonary artery location or a wedge location; and 53. The system of any one of Examples 34 to 52, wherein the system is capable of instructing:

[0186] Example 54 The system of Example 53, wherein the quality assessment is categorical.

[0187] Example 55 The system of Example 54, wherein the categories are qualitative rankings.

[0188] Example 56 The system of Examples 53, 54, or 55, wherein the one or more applications can instruct the processor system to determine whether one or more extracted features for a time window are above or below a threshold and generate a quality assessment for the PCWP measurement.

[0189] Example 57 One or more extracted features are Mean , PAP Diastolic , and PCWP PulsePress Including PCWP Mean is the average pressure measurement taken at the wedge position, and PAP Diastolic is the diastolic pressure at the pulmonary artery, and PCWP PulsePress is the pulse pressure at the wedge position.

[0190] Example 58 High quality is PCWP Mean <PAP Diastolic AND a×PCWP PulsePress +b×PCWP Mean 58. The system of Example 57, wherein a, b, and c are determinant values, and wherein a, b, and c are determinant values.

[0191] Example 59 Medium quality is PCWP Mean <PAP Diastolic AND a×PCWP PulsePress +b×PCWP Mean 59. The system of Example 57 or 58, wherein a, b, and c are determinant values.

[0192] Example 60 Low quality PCWP Mean ≧PAP Diastolic 60. The system of Example 57, 58, or 59, wherein:

[0193] Example 61 One or more applications may be installed on a processor system. A system described in any one of Examples 53 to 60, which is capable of instructing each time window to be assigned its quality rating.

[0194] Example 62 One or more applications may be installed on a processor system. A system described in any one of Examples 53 to 61, which can instruct the quality assessment of one or more time windows to be displayed on a display screen.

[0195] Example 63 One or more applications may be installed on a processor system. A system described in any one of Examples 53 to 62, which can be instructed to generate a PCWP measurement by averaging blood pressure measurements obtained from wedge positions in a time window determined to have quality above a threshold.

[0196] Example 64 One or more applications may be installed on a processor system. filtering out blood pressure measurements taken from wedge locations in the time window determined to have a quality below a threshold; averaging the non-excluded blood pressure measurements taken from the wedge positions of the time window to generate a PCWP measurement; 64. The system of any one of Examples 53 to 63, which is capable of instructing:

[0197] Example 65 One or more applications may be installed on a processor system. A system described in any one of Examples 53 to 64, which is capable of digitally communicating with a computing system to instruct the display of quality assessments of one or more time windows on a display screen.

[0198] Example 66 1. A calculation method for performing a pulmonary capillary wedge pressure (PCWP) measurement on an individual, comprising: acquiring a blood pressure waveform of the individual using a pulmonary artery catheter, the waveform including blood pressure measurements obtained from a pulmonary artery location, the pulmonary artery catheter being connected to a hemodynamic monitoring system; evaluating blood pressure measurements obtained from the pulmonary artery location for artifacts while blood pressure measurements are being obtained from the pulmonary artery location using a hemodynamic monitoring system; After determining that the blood pressure measurements obtained from the pulmonary artery location are free of artifact, using the hemodynamic monitoring system to inflate a balloon at or near the distal end of the pulmonary artery catheter to allow the pulmonary artery catheter to move to a wedging position; further acquiring a blood pressure waveform for the individual using the pulmonary artery catheter, the waveform including a blood pressure measurement obtained from the wedge location; determining PCWP measurements from blood pressure measurements from the wedge positions using a hemodynamic monitoring system; Calculation methods, including:

[0199] Example 67 The method of Example 66, wherein the PCWP measurements are determined in real time.

[0200] Example 68 The method described in Example 67, further comprising the step of displaying the PCWP measurement value on a display screen of the hemodynamic processing system.

[0201] Example 69 The method of Example 66, 67, or 68, wherein the artifacts include one or more of measurements taken during patient movement, measurements taken during catheter flushing, and measurements showing flat lines, measurements showing underattenuation, and measurements showing overattenuation.

[0202] Example 70 Detection of artifacts due to flushing, improper zeroing, or patient movement is based on the maximum PAP (PAP max ) is greater than the threshold, the minimum PAP (PAP min ) is less than the threshold, and / or the maximum PAP minus the minimum PAP (PAP max -PAP min 70. The method of any one of Examples 66-69, wherein the blood pressure is detected when (PAP) is greater than a threshold value, and PAP is a blood pressure measurement obtained from a pulmonary artery location.

[0203] Example 71 Detection of artifacts based on flat lines or overattenuation was determined by subtracting the minimum PAP value from the maximum PAP value (PAP max -PAP min 71. The method of any one of Examples 66-70, wherein the blood pressure is detected when (PAP) is less than a threshold value, and PAP is a blood pressure measurement obtained from a pulmonary artery location.

[0204] Example 72 72. The method of any one of Examples 66 to 71, wherein the pulmonary artery catheter comprises an internal lumen configured to measure blood pressure.

[0205] Example 73 73. The method of any one of Examples 66 to 72, wherein the pulmonary artery catheter is a Swan-Ganz catheter.

[0206] Example 74 1. A hemodynamic monitoring system for performing pulmonary capillary wedge pressure (PCWP) measurements, comprising: a pulmonary artery catheter configured to obtain blood pressure measurements obtained from a pulmonary artery location and blood pressure measurements obtained from a wedge location, the pulmonary artery catheter including an inflatable balloon; 1. A computing system in communication with a pulmonary artery catheter, the computing system comprising: a processor system; a display screen digitally connected to the processor system; A memory system containing one or more applications, the applications being connected to a processor system, obtaining a blood pressure measurement at a pulmonary artery location; evaluating blood pressure measurements obtained from a pulmonary artery location for artifacts; inflating a balloon after determining that the blood pressure measurement obtained from the pulmonary artery location is free of artifact, wherein inflating the balloon allows the catheter to move to a wedging position; obtaining a blood pressure measurement at the wedge position; generating a blood pressure waveform from blood pressure measurements taken from the pulmonary artery location and blood pressure measurements taken from the wedge location; determining PCWP measurements from blood pressure measurements from the wedge positions; PCWP measurement value is displayed on the display screen. a memory system that can command a computing system comprising: A hemodynamic monitoring system comprising:

[0207] Example 75 The system of example 74, wherein the PCWP measurement is determined in real time.

[0208] Example 76 The system described in Example 74 or 75, wherein the artifacts include one or more of measurements taken during patient movement, measurements taken during catheter flushing, and measurements showing flat lines, measurements showing underattenuation, and measurements showing overattenuation.

[0209] Example 77 Detection of artifacts due to flushing, improper zeroing, or patient movement is based on the maximum PAP (PAP max ) is greater than the threshold, the minimum PAP (PAP min) is less than the threshold, and / or the maximum PAP minus the minimum PAP (PAP max -PAP min 77. The system of any one of claims 74, 75, or 76, wherein the PAP is detected when the PAP is greater than a threshold, and the PAP is a blood pressure measurement obtained from a pulmonary artery location.

[0210] Example 78 Detection of artifacts based on flat lines or overattenuation was determined by subtracting the minimum PAP value from the maximum PAP value (PAP max -PAP min 78. The system of any one of Examples 74 to 77, wherein the PAP is detected when the PAP is less than a threshold value, and PAP is a blood pressure measurement obtained from a pulmonary artery location.

[0211] Example 79 A system described in any one of Examples 74 to 78, wherein the pulmonary artery catheter has an inner lumen configured to measure blood pressure.

[0212] Example 80 The system of any one of Examples 74 to 79, wherein the pulmonary artery catheter is a Swan-Ganz catheter.

[0213] Example 81 1. A computational method for detecting a transition between a pulmonary artery location and a wedge location, comprising: acquiring a blood pressure waveform of the individual using a pulmonary artery catheter, the waveform including blood pressure measurements obtained from a pulmonary artery location, the pulmonary artery catheter being connected to a hemodynamic monitoring system; using a hemodynamic monitoring system to inflate a balloon at or near the distal end of the pulmonary artery catheter to allow the pulmonary artery catheter to move to a wedging position; detecting a transition from a pulmonary artery position to a wedge position using a hemodynamic monitoring system; further acquiring a blood pressure waveform for the individual using the pulmonary artery catheter, the waveform including a blood pressure measurement obtained from the wedge location; using a hemodynamic monitoring system to deflate a balloon at or near the distal end of the pulmonary artery catheter to allow the pulmonary artery catheter to move back into the pulmonary artery location; detecting a transition from the wedge position to the pulmonary artery position using a hemodynamic monitoring system; Calculation methods, including:

[0214] Example 82 The steps of detecting a transition from a pulmonary artery position to a wedge position and detecting a transition from a wedge position to a pulmonary artery position include: extracting one or more hemodynamic features from the blood pressure measurements at the pulmonary artery location and the wedge location; 82. The method of claim 81, each comprising using a fuzzy logic membership function to determine a fuzzy logic value for each hemodynamic feature among the one or more hemodynamic features based on the change in value between the blood pressure measurement at the pulmonary artery position and the blood pressure measurement at the wedge position.

[0215] Example 83 83. The method of example 82, wherein the one or more features include at least one of a statistical moment, a percentile value of the data, a histogram of the data, a diastolic pressure, a median pressure, a mean pressure, a systolic pressure, a pulse pressure, Shannon's entropy, a number of peaks above a percentile, a number of valleys below a percentile, a number of average crossings, an area under the curve, a singular vector coefficient after principal component analysis, a subsampled signal, a determinable feature, a waveform phase feature, and a morphological feature.

[0216] Example 84 The method of example 82 or 83, wherein the morphological features are selected from frequency content, skewness, and kurtosis, the waveform phase features are selected from contractility, pulmonary artery compliance, stroke volume, vascular tone, afterload, and total cardiac cycle, and the determinable features are selected from mean, maximum, minimum, duration, area, standard deviation, slope, derivative, trend, deviation from trend, variance, and variance of the phase.

[0217] Example 85 The method of example 82, 83, or 84, wherein the one or more characteristics include mean pressure and pulse pressure.

[0218] Example 86 The method of any one of Examples 81 to 85, further comprising determining a pulmonary capillary wedge pressure (PCWP) measurement from blood pressure measurements from the wedge position using a hemodynamic monitoring system.

[0219] Example 87 87. The method of any one of Examples 81 to 86, wherein the pulmonary artery catheter comprises an internal lumen configured to measure blood pressure.

[0220] Example 88 The method of any one of Examples 81 to 88, wherein the pulmonary artery catheter is a Swan-Ganz catheter.

[0221] Example 89 1. A hemodynamic monitoring system for detecting a transition between a pulmonary artery position and a wedge position, comprising: a pulmonary artery catheter configured to obtain blood pressure measurements obtained from a pulmonary artery location and blood pressure measurements obtained from a wedge location, the pulmonary artery catheter including an inflatable balloon; 1. A computing system in communication with a pulmonary artery catheter, the computing system comprising: a processor system; a display screen digitally connected to the processor system; A memory system containing one or more applications, the applications being connected to a processor system, obtaining a blood pressure measurement at a pulmonary artery location; inflating the balloon, which allows the catheter to move to a wedging position; Detecting a transition from a pulmonary artery position to a wedge position; obtaining a blood pressure measurement at the wedge position; Deflating the balloon at or near the distal end of the pulmonary artery catheter to allow the pulmonary artery catheter to move back into the pulmonary artery location; Detecting the transition from the wedge position to the pulmonary artery position a memory system that can command a computing system comprising: A hemodynamic monitoring system comprising:

[0222] Example 90 One or more applications may be installed on a processor system. extracting one or more hemodynamic features from the blood pressure measurements at the pulmonary artery location and the blood pressure measurements at the wedge location; determining, using fuzzy logic membership functions, a fuzzy logic value for each hemodynamic feature of the one or more hemodynamic features based on a change in value between the blood pressure measurement at the pulmonary artery location and the blood pressure measurement at the wedge location, the fuzzy logic value being utilized to detect a transition from the pulmonary artery location to the wedge location and from the wedge location to the pulmonary artery location; The system described in Example 89, which can instruct:

[0223] Example 91 The system of Example 90, wherein the one or more features include at least one of statistical moments, percentile values of the data, a histogram of the data, diastolic pressure, median pressure, mean pressure, systolic pressure, pulse pressure, Shannon's entropy, number of peaks above the percentile, number of valleys below the percentile, number of average crossings, area under the curve, singular vector coefficients after principal component analysis, subsampled signals, determinable features, waveform phase features, and morphological features.

[0224] Example 92 The system of Example 90 or 91, wherein the morphological features are selected from frequency content, skewness, and kurtosis, the waveform phase features are selected from contractility, pulmonary artery compliance, stroke volume, vascular tone, afterload, and the entire cardiac cycle, and the determinable features are selected from mean, maximum, minimum, duration, area, standard deviation, slope, derivative, trend, deviation from trend, variance, and variance of the phase.

[0225] Example 93 The system of Examples 90, 91, or 92, wherein the one or more characteristics include mean pressure and pulse pressure.

[0226] Example 94 One or more applications may be installed on a processor system. determining a pulmonary capillary wedge pressure (PCWP) measurement from the blood pressure measurements from the wedge position; The pulmonary capillary wedge pressure (PCWP) measurement value is displayed on the display screen. 94. The system of any one of Examples 89 to 93, which is capable of instructing:

[0227] Example 95 A system described in any one of Examples 89 to 94, wherein the pulmonary artery catheter has an inner lumen configured to measure blood pressure.

[0228] Example 96 The system of any one of Examples 89 to 95, wherein the pulmonary artery catheter is a Swan-Ganz catheter. [Explanation of symbols]

[0229] 102 Inflated Balloon 104 Pulmonary artery 106 Catheter 202 Waveform 204 Pressure waveform 206 Catheter 300 waveforms 302, 304, 306 areas 310 Breathing Cycle 400 ways 420 Action 422 PCWP Mode 424 Balloon 428 Balloon 432 PCWP mode 440 Calculation Process 444 Balloon inflation point 446 Breathing Cycle 448 Balloon Deflation Point 450 PCWP acquisition 500 calculation method 600 calculation method 702, 704, 706, 708 transition 710, 712 transition 800 calculation method 1000 calculation method 1202 Quality 1204 Wedge position part 1500 Computer Processing System 1502 processor system 1504 I / O interface 1506 Memory System 1508 Determining System Readiness for PCWP 1510 Balloon inflation and / or deflation point detection 1512 Breathing Cycle Detection 1514 PCWP measurements 1516 PCWP Acquisition Quality Assessment 1518 Real-time PCWP results and quality ratings 1600 Hemodynamic Monitoring System 1602 processor system 1604 I / O interface 1606 Memory System 1608 Real-time PAP acquisition application 1610 Real-time PCWP acquisition application 1612 Real-time extraction of hemodynamic parameters 1620 PAC

Claims

1. 1. A computational method for performing a pulmonary capillary wedge pressure (PCWP) measurement on an individual and assessing the quality of said PCWP measurement, comprising: acquiring a blood pressure waveform of the individual, the waveform including a blood pressure measurement taken from a pulmonary artery location and a blood pressure measurement taken from a wedge location, the blood pressure waveform being acquired using a pulmonary artery catheter; determining PCWP measurements from the blood pressure measurements from the wedge positions using a computing system; using the computing system to determine a quality assessment for the PCWP measurement using a machine learning model configured to provide a quality assessment for the PCWP measurement based on the blood pressure measurements obtained from the pulmonary artery location and the blood pressure measurements obtained from the wedge location; Calculation methods, including:

2. The method of claim 1 , wherein the PCWP measurement and the quality assessment are each determined in real time.

3. The method of claim 2 , further comprising the step of digitally communicating with the computing system to display the PCWP measurements and the quality assessment on a display screen.

4. 4. The method of claim 1, 2, or 3, wherein the computing system and the pulmonary artery catheter are part of a hemodynamic monitoring system.

5. The step of acquiring a blood pressure waveform includes: inserting the pulmonary artery catheter into a central vein of the individual; directing the pulmonary artery catheter into the pulmonary artery; inflating a balloon at or near the distal end of the pulmonary artery catheter to allow the pulmonary artery catheter to move to the wedged position; 5. The method of claim 1, comprising:

6. 6. The method of claim 5, further comprising using the computing system to evaluate the blood pressure measurements obtained from a pulmonary artery location in real time for artifacts before inflating the balloon.

7. The computer processing system is used to determine a transition from a pulmonary artery position to a wedge position or from a wedge position to a pulmonary artery position. extracting one or more hemodynamic features from the blood pressure measurements at the pulmonary artery location and the blood pressure measurements at the wedge location; determining a fuzzy logic value for each of the one or more hemodynamic features based on a change in value between the blood pressure measurement at the pulmonary artery location and the blood pressure measurement at the wedge location using a fuzzy logic membership function; 7. The method of claim 1, further comprising detecting in real time by

8. The method of claim 7 , wherein the one or more characteristics include mean pressure and pulse pressure.

9. dividing the blood pressure measurements obtained from the pulmonary artery location and the blood pressure measurements obtained from the wedge location into time windows; extracting features from the time window of the blood pressure measurements taken from the pulmonary artery location and the blood pressure measurements taken from the wedge location; further comprising The machine learning model is trained to detect whether the extracted features for a time window are derived from the blood pressure measurements taken from the pulmonary artery location or the wedge location, and determining, using the computing system, a quality assessment for the PCWP measurements using the machine learning model includes:

9. The method of claim 1, comprising inputting the extracted features from the time windows into the machine learning model to generate a quality assessment for each time window, the quality assessment being based on whether the extracted features for each time window can be distinguished as being derived from the pulmonary artery location or the wedge location.

10. determining, using the computing system, a quality assessment for the PCWP measurement using a machine learning model, The method of claim 9 , comprising determining whether one or more extracted features for a time window are above or below a threshold.

11. The one or more extracted features are Mean , PAP Diastolic , and PCWP PulsePress Including PCWP Mean is the average pressure measurement taken at the wedge position, and PAP Diastolic is the diastolic pressure at the pulmonary artery, and PCWP PulsePress 11. The method of claim 10, wherein: is the pulse pressure at the wedge location.

12. High quality is PCWP Mean <PAP Diastolic AND a×PCWP PulsePress +b×PCWP Mean 12. The method of claim 11, wherein a, b, and c are determinant values.

13. Medium quality is PCWP Mean <PAP Diastolic AND a×PCWP PulsePress +b×PCWP Mean 13. The method of claim 11 or 12, wherein a, b, and c are determinant values.

14. Low quality is PCWP Mean ≧PAP Diastolic 14. The method of claim 11, 12, or 13, wherein:

15. 15. The method of any one of claims 9 to 14, wherein using a computing system, determining the PCWP measurement comprises averaging blood pressure measurements taken from wedge positions in a time window determined to have a quality above a threshold.

16. 1. A hemodynamic monitoring system for performing pulmonary capillary wedge pressure (PCWP) measurements and assessing the quality of said PCWP measurements, comprising: a pulmonary artery catheter configured to obtain blood pressure measurements obtained from a pulmonary artery location and blood pressure measurements obtained from a wedge location, the pulmonary artery catheter including an inflatable balloon; a computing system in communication with the pulmonary artery catheter, the computing system comprising: a processor system; a display screen in digital communication with said processor system; A memory system containing one or more applications, the applications configured to communicate with the processor system, obtaining a blood pressure measurement at a pulmonary artery location; inflating the balloon, where inflating the balloon allows the catheter to move to a wedging position; obtaining a blood pressure measurement at the wedge position; generating a blood pressure waveform from blood pressure measurements taken from the pulmonary artery location and blood pressure measurements taken from the wedge location; determining a PCWP measurement from the blood pressure measurements from the wedge position; determining a quality assessment for the PCWP measurement using a machine learning model configured to provide a quality assessment for the PCWP measurement based on the blood pressure measurements obtained from the pulmonary artery location and the blood pressure measurements obtained from the wedge location; displaying one or more of the blood pressure waveform, the PCWP measurement, or the quality assessment for the PCWP measurement on the display screen; a memory system that can command a computing system comprising: A hemodynamic monitoring system comprising:

17. 17. The system of claim 16, wherein the blood pressure waveform is generated and displayed on the display screen in real time.

18. 18. The system of claim 16 or 17, wherein the PCWP measurements are determined and displayed on the display screen in real time.

19. 19. The system of claim 16, 17, or 18, wherein the quality assessment for the PCWP measurement is determined and displayed on the display screen in real time.

20. The one or more applications may be configured to:

20. The system of claim 16, wherein the system can be instructed to evaluate the blood pressure measurements obtained from a pulmonary artery location for artifacts in real time before inflating the balloon.

21. The one or more applications may be configured to: The transition from the pulmonary artery position to the wedge position or from the wedge position to the pulmonary artery position is extracting one or more hemodynamic features from the blood pressure measurements at the pulmonary artery location and the blood pressure measurements at the wedge location; determining a fuzzy logic value for each hemodynamic feature of the one or more hemodynamic features based on a change in value between the blood pressure measurement at the pulmonary artery location and the blood pressure measurement at the wedge location using a fuzzy logic membership function; 21. The system of claim 16, wherein the detection can be instructed in real time by

22. 22. The system of claim 21, wherein the one or more characteristics include mean pressure and pulse pressure.

23. The one or more applications may be configured to: dividing the blood pressure measurements obtained from the pulmonary artery location and the blood pressure measurements obtained from the wedge location into time windows; extracting features from the time window of the blood pressure measurements taken from the pulmonary artery location and the blood pressure measurements taken from the wedge location; inputting the extracted features from the time windows into the machine learning model to generate a quality assessment for each time window, the quality assessment being based on whether the extracted features for each time window can be distinguished as being derived from the pulmonary artery location or the wedge location to generate the quality assessment for the PCWP, the machine learning model being trained to detect whether the extracted features for a time window are derived from the blood pressure measurements taken from the pulmonary artery location or the wedge location; and 23. The system of any one of claims 16 to 22, wherein the system is capable of commanding:

24. The one or more applications may be configured to:

24. The system of claim 23, further comprising the step of determining whether one or more extracted features for a time window are above or below a threshold and directing the generation of the quality assessment for the PCWP measurement.

25. The one or more extracted features are Mean , PAP Diastolic , and PCWP PulsePress Including PCWP Mean is the average pressure measurement taken at the wedge position, and PAP Diastolic is the diastolic pressure at the pulmonary artery, and PCWP PulsePress 25. The system of claim 24, wherein: ≈μm is the pulse pressure at the wedge location.

26. High quality is PCWP Mean <PAP Diastolic AND a×PCWP PulsePress +b×PCWP Mean 26. The system of claim 25, wherein a, b, and c are determinant values.

27. Medium quality is PCWP Mean <PAP Diastolic AND a×PCWP PulsePress +b×PCWP Mean 27. The system of claim 25 or 26, wherein a, b, and c are determinant values.

28. Low quality is PCWP Mean ≧PAP Diastolic 28. The system of claim 25, 26, or 27, wherein:

29. The one or more applications may be configured to:

29. A system according to any one of claims 23 to 28, capable of commanding the quality assessment for one or more time windows to be displayed on the display screen.

30. The one or more applications may be configured to:

30. The system of any one of claims 23 to 29, wherein the system can be instructed to generate the PCWP measurement by averaging blood pressure measurements taken from wedge positions in a time window determined to have a quality above a threshold.

Images