26 results about "Arterial pressure waveform" patented technology

The invention relates to the technical field of medical monitoring and intelligent decision making, and particularly discloses an intraoperative noninvasive real-time blood flow monitoring and medication intervention analysis system. Pulse wave oscillation harmonic component characteristics and diastolic attenuation characteristic characteristics are extracted by using variational mode decomposition and a polynomial fitting algorithm; the multi-dimensional features are fused and then input into a deep learning classification model, and accurate recognition of insufficient heart pump efficiency, abnormal peripheral vascular tension and circulation capacity imbalance states is achieved; time sequence prediction and grading early warning are carried out based on the hidden Markov model and the individualized baseline safety interval, and finally a targeted medication scheme is output through the intervention strategy knowledge base.

The invention provides a cardiac postoperative respiratory function monitoring system and method. The method comprises the steps that photoelectric volume pulse wave signals of a patient during cardiac postoperative breathing are collected through an intelligent optical sensor; extracting a heart rate variability signal of the patient, and determining a quantitative index of respiratory sinus arrhythmia of the patient through the heart rate variability signal; determining the arterial pressure variability of the patient according to the arterial pressure waveform, and fusing the arterial pressure variability and the quantitative index of the respiratory sinus arrhythmia to obtain the cardiopulmonary coupling strength; according to the cardiopulmonary coupling strength and the shallow and fast breathing index of the patient, combining a pre-trained failure prediction model during breathing machine withdrawal, outputting a failure risk value during machine withdrawal of the patient; and outputting a machine withdrawal decision support report of the patient according to the failure risk value and a preset individualized early warning threshold value. According to the scheme, the cardiac postoperative withdrawal risk can be evaluated based on the dynamic cooperation mechanism between the cardiovascular system and the respiratory system.

The invention discloses a severe patient blood pressure trend monitoring and intervention decision-making system based on deep learning, and relates to the technical field of medical information processing, which comprises the following steps: acquiring a continuous invasive arterial pressure waveform and carrying out pulse-by-pulse segmentation, and extracting pulse-by-pulse average pressure and a multi-dimensional high-frequency waveform characterization quantity; and calculating a voltage-sharing deviation amount, a high-frequency retention amount and a steady-state collapse eigen index in combination with preorder analysis window data, inputting the data into a time sequence deep learning network to obtain a pseudo trend probability, further obtaining a corrected voltage-sharing slope and a real trend slope, respectively calculating a link checking priority and a real low-voltage intervention priority, and outputting an auxiliary intervention decision. According to the invention, link distortion and real blood pressure deterioration can be distinguished, and the accuracy of trend monitoring and intervention decision is improved.

The invention discloses a central arterial pressure waveform reconstruction method based on a CBL-iTransform model, and relates to the technical field of central arterial pressure evaluation. According to the method, a waveform reconstruction model (CML-iTransform) is obtained through the design of the method, the waveform reconstruction model is based on an improved iTransform architecture, and a one-dimensional CNN and a BiLSTM network are fused, so that the data feature extraction capability in the waveform reconstruction process is remarkably improved, and reconstruction from an RAP waveform to a CAP waveform is realized; wherein the RAP waveform is firstly input into the feature extraction module, then the reconstructed CAP waveform is output through the waveform reconstruction module, the data sample size is expanded through data enhancement, and the model performance is improved; compared with a traditional method and several deep learning network models, the model capable of capturing long and short-term memory dependence is superior to other methods in the aspect of reconstructing the central arterial pressure from the radial arterial pressure, and it is proved that the model is good in reconstruction performance.

A system for monitoring arterial pressure of a patient determines a score that is predictive of responsiveness of the patient to a therapy. Sensed hemodynamic data representative of an arterial pressure waveform of the patient are received by a hemodynamic monitor. Magnitude data and trend data are derived from the hemodynamic data. The score that is predictive of the responsiveness of the patient to the therapy is determined based on the magnitude data and the trend data of the hemodynamic parameter. A representation of the score is output.

The invention provides a split type minimally invasive blood pressure measuring system and method, and the system comprises a disposable pressure conduction card box DPTC which is used for sensing the arterial pressure waveform of a patient and converting the arterial pressure waveform into a basic electric signal; the high-reliability repeatedly pluggable medical interface is used for transmitting the basic electric signal to a reusable processing module RPM; the reusable processing module RPM is used for receiving the basic electric signal and executing a pulse profile analysis algorithm on the basic electric signal so as to solve bleeding flow dynamic parameters; wherein the disposable pressure conduction card box DPTC is mechanically connected with and electrically conducted to the reusable processing module RPM in a detachable mode through the high-reliability medical interface capable of being repeatedly plugged and unplugged, and the disposable pressure conduction card box DPTC is electrically connected to the reusable processing module RPM through the high-reliability medical interface capable of being repeatedly plugged and unplugged. Repeated use of the high-value calculation unit (RPM) is achieved, and the unit cost of advanced hemodynamic monitoring is reduced.

A hemodynamic monitoring system monitors arterial blood pressure of a patient and provides a warning to medical personnel of a predicted future hypotensive event of the patient. Sensed hemodynamic data representative of an arterial pressure waveform of the patient is received by a hemodynamic monitor. The received hemodynamic data is shifted based on a difference between a standard mean arterial pressure (MAP) threshold for hypotension and an adjusted MAP threshold for hypotension to produce adjusted hemodynamic data. A waveform analysis of the adjusted hemodynamic data is performed and a risk score representative of a probability of a future hypotensive event of the patient is determined based on the waveform analysis. In response to the risk score satisfying a predetermined risk criterion, an sensory alert is invoked to produce a sensory signal.

A method for monitoring a patient and providing a fluid responsiveness indicator of the patient includes receiving, by a hemodynamic monitor, sensed hemodynamic data representative of an arterial pressure waveform of the patient; performing, by the hemodynamic monitor, waveform analysis of the hemodynamic data to determine a plurality of hemodynamic parameters; and determining, by the hemodynamic monitor based on the plurality of parameters, an indicator representing fluid responsiveness status for the patient.

The invention provides a non-invasive cardiac expulsion measuring method and system. The method comprises the following steps: inputting preprocessed arterial pressure waveform signals and basic vital sign data into a parameter estimation neural network for feature extraction, and outputting a correction factor cal, a scale factor SF and a waveform correction coefficient; respectively inputting the correction factor cal, the scale factor SF and the waveform correction coefficient into a pulse contour model, a LiDCO power model and a FloTrac standard deviation model for calculation to obtain a cardiac output estimated value CO1, a cardiac output estimated value CO2 and a cardiac output estimated value CO3; and fusing the cardiac output estimated value CO1, the cardiac output estimated value CO2 and the cardiac output estimated value CO3 by adopting a gradient lifting regression tree model, and outputting a final cardiac output value. According to the invention, calibration-free continuous monitoring is realized, and the stability and precision of cardiac output estimation are improved.

A hemodynamic monitor with nociception prediction and detection is disclosed. A hemodynamic monitoring system monitors arterial pressure of a patient and provides a warning of a nociceptive event of the patient to medical personnel. The system includes a hemodynamic sensor that generates hemodynamic data representative of a waveform of arterial pressure of the patient. A hardware processor in the system is configured to execute nociception detection software code to perform waveform analysis of the hemodynamic data to determine a plurality of signal measurements. Detection input features are extracted by the processor from the plurality of signal measurements indicative of a nociceptive event of the patient. A nociception score representative of a probability of the nociceptive event of the patient is determined from the detection input features. A sensory alarm is invoked in response to the nociception score satisfying a predetermined detection criterion.

A portable device is configured to connect directly to an intraosseous (IO) catheter and provide a clinician with actionable information to determine whether the catheter is placed correctly, such as whether the catheter is placed in the medullary cavity of bone. The device provides this information leveraging the presence or absence of arterial pressure waveforms. A method for assessing placement of an intraosseous catheter includes coupling a pressure transducer to an IO catheter placed in tissue, obtaining a continuous pressure waveform from a pressure signal provided by the pressure transducer, and assessing placement of the catheter based on the continuous pressure waveform.

A hemodynamic monitoring system monitors arterial blood pressure of a patient and provides a warning to medical personnel of a predicted future hypotensive event of the patient. Waveform analysis is performed on sensed hemodynamic data representative of an arterial pressure waveform of the patient to determine a plurality of hypotension analysis parameters predictive of a future hypotensive event of the patient. A set of transformed hypotension analysis parameters is generated based on the hypotension analysis parameters and a standard mean arterial pressure (MAP) threshold for hypotension and mean and standard deviation values of the hypotension analysis parameters at an adjusted MAP threshold for hypotension. A risk score representative of a probability of a future hypotensive event of the patient is determined based on the set of transformed hypotension analysis parameters. A sensory alarm is invoked to produce a sensory signal in response to the risk score satisfying a predetermined risk criterion.

The embodiment of the invention discloses a central artery pressure reconstruction method and device based on a deep learning model. The method comprises the following steps: acquiring a current radial artery pressure waveform; the method comprises the following steps: performing data preprocessing on a current radial artery pressure waveform through a preprocessing layer of a model to obtain first time series data, and performing the following processing on the first time series data in sequence through a plurality of residual modules stacked in the model: performing local feature extraction on the input time series data by each residual module through a causal expansion convolution layer of the residual module, intermediate time sequence data is obtained, global feature extraction is conducted on the intermediate time sequence data through an attention layer of the intermediate time sequence data, output time sequence data of the corresponding residual modules are obtained, and the output time sequence data of the last residual module serves as second time sequence data; mapping the second time sequence data into a normalized central arterial pressure waveform through a full connection layer of the model; and performing reverse normalization processing on the normalized central arterial pressure waveform through reverse normalization operation of the model to obtain a central arterial pressure reconstruction result.

A system for predicting acute hypertension for a patient includes a hemodynamic sensor that produces, on an ongoing basis, a hemodynamic sensor signal representative of an arterial pressure waveform of the patient and an integrated hardware unit. The integrated hardware unit includes a system processor, a system memory, and a display including a user interface. The system memory includes instructions that, when executed by the system processor, cause the system to receive the hemodynamic sensor signal representative of the arterial pressure waveform of the patient; extract features from the arterial pressure waveform of the patient; determine, by a machine learning model, a probability of an acute hypertensive event of the patient based on the features extracted from the arterial pressure waveform; and output, to the display, an indication of the probability of the acute hypertensive event of the patient.

This invention discloses a continuous non-invasive blood pressure monitoring system based on fingertip photoplethysmography (PPG). The system includes: an intelligent finger cot terminal for acquiring fingertip PPG signals and adjusting the fingertip contact pressure in real time using a closed-loop control formula to maintain a constant pressure state on the finger blood vessels; a mobile computing terminal for receiving fingertip PPG signals and performing preprocessing operations on the fingertip PPG signals; and a cloud service platform for calculating the preprocessed fingertip PPG signals based on a preset blood pressure calculation model to obtain a continuous blood pressure waveform and estimate hemodynamic parameters based on the continuous blood pressure waveform. The preset blood pressure calculation model is specifically a pulse wave analysis model, a pulse wave propagation time model, or a deep learning mapping model. The hemodynamic parameters are specifically stroke volume and cardiac output. Through the mobile computing terminal and the cloud service platform, continuous arterial pressure waveform reconstruction and physiological parameter calculation are realized, and long-term monitoring accuracy can be maintained through a periodic calibration mechanism.

The methods and systems described herein relate to automatically analyzing arterial pressure waveforms during cardiopulmonary resuscitation using neural networks and other machine learning models or processing methods. The methods and systems may differentially label diastolic and systolic blood pressure coming from chest compression-induced arterial waveforms versus spontaneous heartbeats. In one aspect, a portable device receives arterial pressure data in real time and makes predictions of the systolic pressure and / or diastolic pressure using an on-board machine learning model.

The application discloses a magnetic suspension pulse counterpulsation extracorporeal membrane oxygenation system and a control method thereof, and belongs to the technical field of medical equipment. The system comprises a magnetic suspension blood pump, an oxygenator, a blood pump controller, and an electrocardio and pulse signal acquisition and analysis unit, which continuously collects electrocardiogram data and arterial pressure waveform data of a patient in a predetermined window period to form original data packets with time stamps. The electrocardio and pulse signal acquisition and analysis unit is used for collecting electrocardio signals and / or arterial pressure waveform signals of the patient in real time. The application simulates the hemodynamic effect of in-vivo balloon counterpulsation through the rotation speed control of the extracorporeal magnetic suspension blood pump, realizes pulsatile perfusion synchronized with the heart cycle, solves the problem of increased afterload caused by non-pulsatile blood flow of a traditional extracorporeal membrane oxygenation system, and fundamentally eliminates the risks of hemolysis, platelet destruction, thrombosis and vascular injury caused by the in-vessel balloon.

The invention discloses an integrated hemodynamic monitoring sensor and a target-oriented liquid treatment method. The method comprises the following steps: acquiring an arterial pressure waveform corresponding to at least one cardiac cycle; based on the arterial pressure waveform, the stroke-by-stroke basic features of each cardiac cycle are recognized in real time, and the stroke-by-stroke basic features comprise stroke-by-stroke systolic pressure and stroke-by-stroke diastolic pressure; calculating a pulse-to-pulse pressure difference corresponding to each cardiac cycle; in a preset time window, based on all pulse-by-pulse pressure differences appearing in the time window, through a single analysis operation, a capacity reactivity index which does not depend on estimation of an absolute value of an output quantity per pulse is directly calculated; and, based on the volume reactivity indicator, generating intervention guidance information for the targeted fluid therapy. According to the method, a traditional calculation process is compressed, and a complicated step of estimating the output quantity per stroke is avoided, so that the calculation complexity and the dependence on a physiological model are remarkably reduced, and the real-time performance and the robustness of monitoring and the reliability of clinical guidance are improved.

Methods and systems for spatiotemporal management of motion artifacts / blood pressure drifts in arterial pressure waveforms. The system includes an elastomeric sensor array in contact with a surface patch of skin over a superficial artery of a subject, an actuator mounted over the elastomeric sensor array, and a camera mounted on the actuator to capture image data processed by a controller. The elastomeric sensor array is digitally or mechanically divided into a pulsating region and a non-pulsating region. A controller measures an arterial pressure waveform having motion artifacts caused by deformation of the elastomeric sensor array on the skin above the artery in a pulsating region and above the skin near the artery in a non-pulsating region. Further, the controller measures spatio-temporal information of motion artifacts in the pulsation region and the non-pulsation region, and corrects the arterial pressure waveform by removing the motion artifacts based on the spatio-temporal information to measure the physiological parameter.

A system for predicting acute hypertension for a patient includes a hemodynamic sensor that produces, on an ongoing basis, a hemodynamic sensor signal representative of an arterial pressure waveform of the patient and an integrated hardware unit. The integrated hardware unit includes a system processor, a system memory, and a display including a user interface. The system memory includes instructions that, when executed by the system processor, cause the system to receive the hemodynamic sensor signal representative of the arterial pressure waveform of the patient; extract features from the arterial pressure waveform of the patient; determine, by a machine learning model, a probability of an acute hypertensive event of the patient based on the features extracted from the arterial pressure waveform; and output, to the display, an indication of the probability of the acute hypertensive event of the patient.

The methods and systems described herein relate to automatically analyzing arterial pressure waveforms during cardiopulmonary resuscitation using neural networks and other machine learning models or processing methods. The methods and systems may differentially label diastolic and systolic blood pressure coming from chest compression- induced arterial waveforms versus spontaneous heartbeats. In one aspect, a portable device receives arterial pressure data in real time and makes predictions of the systolic pressure and / or diastolic pressure using an on-board machine learning model.

The invention discloses a non-contact dynamic blood pressure waveform measurement method and system, and the method comprises the steps: inputting the video data of a subject into a face recognition network for detection, and detecting a face region of each frame; dividing the face region of each frame after skin segmentation, screening a plurality of optimal sub-regions from the plurality of sub-regions based on a heuristic strategy, respectively calculating a periodic coefficient of each optimal sub-region, and performing weighted fusion on the plurality of optimal sub-regions based on the periodic coefficients to obtain a time sequence of an RGB (Red, Green, Blue) channel; respectively calculating the fluctuation energy of each candidate channel based on the time sequence of the RGB channel; an optimal channel is selected based on the fluctuation energy, and then an imaging photoplethysmography signal is extracted and obtained; and inputting the imaging photoplethysmography signal into a depth estimation model for processing to obtain an estimation result. The continuous arterial pressure waveform can be accurately estimated based on the high-quality iPPG signal in combination with the depth estimation model, and then the health state of the cardiovascular system is known.

The invention relates to the technical field of biomedical imaging, and discloses a noninvasive hemodynamic monitoring method and system based on photoacoustic-ultrasonic imaging. The method comprises the steps that noninvasive hemodynamic monitoring is executed based on a photoacoustic image and an ultrasonic image, and the noninvasive hemodynamic monitoring comprises the steps that an arterial pressure waveform is obtained by analyzing displacement of arterial blood vessels or intensity changes of preset pixel points in a photoacoustic image or ultrasonic image sequence; the vein blood flow speed is evaluated by analyzing the inter-frame similarity change of a preset pixel area of a vein area in the ultrasonic image sequence; external stimulation is applied to the monitored part to establish a dynamic blood flow state, the change of the diameter of the blood vessel is measured based on the photoacoustic image or the ultrasonic image, and the blood vessel compliance is evaluated in combination with pressure information; according to the invention, non-invasive and integrated monitoring of arterial pressure waveform, venous blood flow, blood vessel diameter and compliance can be realized.

A method and system for spatiotemporal management of motion artifacts / blood pressure drifts in an arterial pressure waveform. The system includes an elastomeric sensor array in touch with a surface patch of skin over a superficial artery of a subject, an actuator mounted over the elastomeric sensor array, and a camera mounted on the actuator to capture image data that a controller processes. The controller measures the arterial pressure waveform having motion artifacts caused by elastomeric sensor array deformation on the skin over the artery in the pulsatile area and over the skin adjacent to the artery in the non-pulsatile area. Further, the controller determines spatiotemporal information of the motion artifact in the pulsatile and non-pulsatile areas, correcting the arterial pressure waveform by removing the motion artifact based on the spatiotemporal information to determine the physiological parameters.

The application discloses a severe patient blood pressure trend monitoring and intervention decision system based on deep learning, relates to the technical field of medical information processing, and comprises the following steps: acquiring continuous invasive arterial pressure waveforms and cutting them beat by beat, extracting beat-by-beat mean pressure and multi-dimensional high-frequency waveform representation quantities, combining previous analysis window data to calculate mean pressure deviation, high-frequency retention quantity and mean stable collapse index, inputting a time series deep learning network to obtain a pseudo-trend probability, further obtaining corrected mean pressure and a true trend slope, respectively calculating link verification priority and true low pressure intervention priority, and outputting auxiliary intervention decision making. The application can distinguish between link distortion and true blood pressure deterioration, and improve the accuracy of trend monitoring and intervention decision making.

A method and system for spatiotemporal management of motion artifacts / blood pressure drifts in an arterial pressure waveform. The system includes an elastomeric sensor array in touch with a surface patch of skin over a superficial artery of a subject, an actuator mounted over the elastomeric sensor array, and a camera mounted on the actuator to capture image data that a controller processes. The controller measures the arterial pressure waveform having motion artifacts caused by elastomeric sensor array deformation on the skin over the artery in the pulsatile area and over the skin adjacent to the artery in the non-pulsatile area. Further, the controller determines spatiotemporal information of the motion artifact in the pulsatile and non-pulsatile areas, correcting the arterial pressure waveform by removing the motion artifact based on the spatiotemporal information to determine the physiological parameters.