46 results about "Respiratory flow" patented technology

The invention discloses a system and a method for monitoring and analyzing a breathing mode of an individual. The system integrates a first sensing device for a nasal cavity and a second sensing device for an oral cavity through monitoring equipment worn on the head and the face. The core of the method is that synchronous quantitative calculation of mouth and nose breathing flow is achieved for the first time through the schemes of hardware decoupling (parallel ultrasonic measurement of oral geometry and flow velocity) and algorithm decoupling (calculation of nasal cavity flow and area from coupling signals in combination with user calibration). According to the invention, the core biomarker ONFR is obtained, and the problem of ambiguity of oral respiration and apnea in the prior art is solved. The invention further discloses a multi-level precision framework, artifact recognition based on double IMUs and a'digital phenotype 'risk early warning technology based on cloud AI. The invention has important application value in the fields of sleep health, sports physiology and the like.

The invention provides a portable respiratory flow measuring instrument calibration method and system, and the method comprises the steps: sequentially connecting a gas generation device, a to-be-calibrated portable respiratory flow measuring instrument and a high-precision gas flow calibration instrument in series, constructing a stable gas flow channel, and ensuring that gas flow sequentially flows through each instrument; starting a gas generation device, and synchronously acquiring data after the gas flow is stable, namely an original measurement physical quantity vector x, a theoretical flow value and actual flow data; repeating the acquisition process to obtain a data set covering the full scale; the collected data are input into terminal equipment, a proper machine learning algorithm is selected for training according to the instrument principle, the target is to learn the relation between x and x, and a flow function which is applicable to the full scale and finally forms correction is obtained; in actual operation, the instrument calculates theoretical flow through x collected in real time, the trained flow is called for correction, and a high-precision flow value is output. The technical problems that in the prior art, equipment is complex, cost is high, operation is tedious, efficiency is low, intelligence and precision are insufficient, and scene adaptability is single are solved.

This application provides a method, system, and device for ventilator mask recognition based on transfer learning. The method collects time-series data of respiratory flow and pressure using flow and pressure sensors inside a home ventilator; a data preprocessing module cleans the time-series data to obtain high-quality respiratory flow and pressure time-series data; a data segmentation module divides the preprocessed time-series data into discrete flow and pressure data segments; a transfer learning module transfers the parameters of the source model to the target model, and the target model is trained and fine-tuned using the segmented discrete flow and pressure data segments to obtain the final mask type recognition model. The final mask type recognition model can accurately predict the ventilator mask type based on respiratory flow and pressure signals. This application utilizes transfer learning to improve the robustness of the model to mask type recognition across individuals and devices.

Methods and apparatus infer or indicate sleep stage(s) of a patient from a respiratory flow rate signal of the patient. The method may include applying a plurality of detection pathways to a signal representing a respiratory flow rate of the patient, wherein each detection pathway is configured to generate start events and end events indicating start times and end times of episodes respectively of a corresponding sleep stage, wherein each start event and each end event has a priority; and combining the start events and end events based on their priorities to produce an indication of the sleep stage of the patient. The apparatus may include a sensor configured to generate a signal representing a property of a flow of air within a patient interface; and a processor configured to implement a method of inferring a sleep stage of the patient from the signal.

The present application relates to the technical field of sleep intervention, in particular to an intelligent sleep instrument and a sleep instrument control method, the system comprising a respiratory mutation recognition module, a slow wave initiation linkage module, a pharyngeal cavity contraction evaluation module, an intervention section positioning module and a delay trigger control module. In the present application, the extreme points densely appearing in the continuous cycle are accurately positioned as the key nodes of respiratory abnormalities through the identification of the mutation of nasal respiratory flow, and the slow wave initiation stage closely related to the respiratory mutation is screened out and marked as the linkage period in combination with the power curve change trend of the electroencephalogram signal. The pharyngeal cavity state is dynamically evaluated through the change of acoustic echo in the period, the intelligent postponement and delay processing of the intervention behavior are realized through the comparison of the trigger point of the intervention action and the boundary of the platform section, the accuracy of the sleep intervention timeliness and the adaptability of the intervention execution are improved, and the respiratory event control effect and the sleep continuity are significantly improved.

The invention discloses an intelligent control method and system for a noninvasive respirator, and relates to the technical field of intelligent control of respirators. According to the method, airway flow and pulse wave signals are obtained through signal collection and respiratory phase recognition, the end-expiratory pause time period is positioned, a time-frequency image is constructed and preprocessed to obtain a high-resolution enhanced time-frequency energy image, and cardiac oscillation components are recognized and separated to obtain pure respiratory flow signals. The autonomous inspiration effort is judged through double triggering conditions, and air supply control is achieved; verifying parameters are evaluated and adaptively updated based on the respiratory cycle, and personalized configuration parameters are locked; the problems of false triggering and leakage triggering air supply caused by cardiac airway flow oscillation interference generated by cardiac pulsation in the ventilation process of the noninvasive breathing machine are effectively solved, and the accuracy and reliability of air supply triggering of the breathing machine are remarkably improved.

The application discloses a kind of self-adapting oxygen supply control equipment, belong to oxygen supply control equipment technical field.It includes: acquisition module is used to obtain and time stamp alignment user breathing state signal;Calculation module is used to preprocess respiratory flow and pressure signal, calculate signal quality index;Identification module is used to establish basic parameter set, constructs feature vector, and identifies breathing phase;Determination module is used to calculate respiratory demand score, and determines target oxygen supply interval;Correction module and control module are used to output target oxygen supply parameter vector in target oxygen supply interval by oxygen supply target prediction model, after phase differentiation correction and safety constraint, generate final execution control quantity, and convert into instruction oxygen supply equipment execution.This equipment is through the alignment of multiple source breathing signals, feature extraction and closed-loop safety correction, realizes the accurate adaptation of oxygen supply output and real-time physiological demand.

An apparatus for treating respiratory disorders in a patient is disclosed. The apparatus includes a pressure generator configured to deliver a flow of air at positive pressure through a patient interface to an airway of the patient, a sensor configured to generate a signal representative of a respiratory flow of the patient, and a controller. And a controller configured to control the pressure generator to deliver a ventilation therapy with a base pressure and pressure support through the patient interface, an apnea being detected from the signal representative of a respiratory flow of the patient, controlling the pressure generator to deliver one or more detected breaths to the patient during the apnea, determining patency of the airway of the patient from a waveform of the respiratory flow signal responsive to one of the one or more detected breaths, an effective duration of the apnea is calculated based on the patency of the airway, and a setpoint of the base pressure for the ventilation therapy is adjusted in response to the apnea based on the effective duration of the apnea.

The application discloses a CBCT-based child obstructive sleep apnea syndrome identification system and relates to the technical field of medical networks, and comprises the following steps: acquiring a CBCT image and physiological characteristic parameters of a child, performing airway segmentation and reconstructing an airway surface model; establishing an airway respiratory flow field based on the model, setting boundary conditions for simulation, extracting dynamic characteristics to construct first discriminant characteristics; inputting the first discriminant characteristics into a classification model to determine whether the first discriminant characteristics are in a fuzzy discriminant interval; if the first discriminant characteristics are not in the interval, directly outputting an obstructive sleep apnea syndrome type; if the first discriminant characteristics are in the interval, extracting airway cross-section structure information, fusing the first discriminant characteristics to obtain second discriminant characteristics; and matching the characteristics with preset rules to determine whether to adopt enhanced classification or structure registration for secondary discrimination, finally outputting a child apnea syndrome type, and improving the reliability and accuracy of the final diagnosis result.

The application discloses a kind of methods for predicting dust miner's breath flow based on random forest algorithm, including dust miner's breath flow prediction system, the dust miner's breath flow prediction system is by miner's breath characteristic parameter monitoring component, respirator and algorithm prediction module Composition, further include: the miner's breath characteristic parameter monitoring component includes heart rate detector, blood oxygen detection device, temperature tester and portable individual breath monitor, the respirator is viscoelastic silica gel half mask, the respirator is equipped with exhalation valve, the half mask inside and outside both sides are evenly distributed with pressure sensor, the algorithm prediction module is by information receiving unit, central processing unit and information output unit Composition, miner's breath characteristic parameter real-time upload to information receiving unit, and import central processing unit and algorithm prediction are carried out data processing after, and output by information output unit, the method prediction model of the present application is robust, and prediction accuracy is high.

The application discloses a combustion mode-based metabolite testing device and method. The metabolite testing device comprises a combustion control module, a respiratory gas flow control module, an exhaled gas heating and humidifying control module, a respiratory gas separation module, a control unit and a computer. The combustion control module is used for simulating human exhaled gas; the respiratory gas flow control module is used for simulating human respiratory flow; the exhaled gas heating and humidifying control module is used for simulating the temperature and humidity state of human exhaled gas; and the respiratory gas separation module is used for simulating the human mouth and nose breathing process. The control unit is responsible for the control of motors and valves, and the computer is responsible for data acquisition, calculation analysis and result display. The testing method is to set human metabolic parameters, connect a human metabolic tester and test, and finally perform quality inspection analysis on the metabolic parameters of the human metabolic tester according to the test result. The application can be applied to the application scene of human metabolic tester accuracy evaluation, and realizes easy, economical and effective verification of the human metabolic tester.

This invention discloses a gas mixing flow control method and system for a ventilator, comprising: A1: collecting and preprocessing time-series data of airway pressure and respiratory flow; A2: constructing a respiratory noise reduction and enhancement gating mechanism to extract noise-reduced respiratory features; A3: extracting sleep posture features based on the noise-reduced respiratory features; A4: calculating the probability distribution of sleep posture states at each time step based on the sleep posture features using global average pooling and a classification layer, and selecting the state code corresponding to the maximum probability to obtain the sleep posture state sequence; A5: extracting comprehensive respiratory features; A6: extracting gas mixing features based on the comprehensive respiratory features; A7: outputting the gas mixing flow result based on the gas mixing features and controlling the operation of the ventilator's oxygen solenoid valve and air fan. This invention can solve the problem of traditional methods failing to address the mismatch between ventilator parameter adjustments and the turning rhythm of elderly COPD patients.

The invention comprises a method of operating a breathing apparatus comprising measuring a baseline breath flow parameter being respiratory rate and / or tidal volume or a parameter derived therefrom, varying the flow rate provided by the breathing apparatus, measuring a current breath flow parameter being respiratory rate and / or tidal volume or a parameter derived therefrom, comparing the baseline and current breath flow parameters, and altering operation of the breathing apparatus based on the comparison. The invention also comprises a breathing apparatus that implements the above method.

The application provides a respiratory impedance detection method, comprising the steps of: generating an oscillating airflow at a fixed frequency f, collecting respiratory pressure and respiratory flow data of a subject under the oscillating airflow respectively; segmenting the data length of the respiratory pressure and respiratory flow according to the repetition rate respectively; performing Fourier transform on each segmented respiratory pressure and respiratory flow, calculating the respiratory impedance and respiratory reactance of each data segment at different frequency values, and obtaining an initial respiratory impedance-frequency graph and an initial respiratory reactance-frequency graph respectively; performing correlation denoising on the multiple respiratory impedance and respiratory reactance at each frequency value respectively, and obtaining a denoised respiratory impedance-frequency graph and a denoised respiratory reactance-frequency graph; and performing K-means clustering calculation on the denoised respiratory impedance-frequency graph and the denoised respiratory reactance-frequency graph respectively, and obtaining a respiratory impedance-frequency curve and a respiratory reactance-frequency curve. The detection method provided by the application has small errors and high accuracy.

The invention relates to a respiratory flow sensor comprising a flow pipe, which has a flow channel and, on the free ends thereof, hose connections for hoses, comprising a cover flap, which is arranged in the flow channel and divides the flow channel into a first flow channel portion and into a second flow channel portion, and comprising connections, which lead into the flow channel on both sides of the cover flap and serve for the reduction of the differential pressure created by the cover flap. Provision is made in the flow channel for a water drainage device, which comprises drainage grooves. The cover flap has a hinge region, which is formed by a first slot and a second slot, which is embodied in an H-shaped manner.

The application discloses a thoracico-abdominal motion respiration flow monitoring method and device, and relates to the field of respiration monitoring. The method comprises the following steps: acquiring a pressure value of a patient pressure monitoring point; the pressure monitoring point comprises a thoracic pressure monitoring point and an abdominal pressure monitoring point; performing data analysis according to the pressure value to determine a displacement change amount of the pressure monitoring point relative to an initial spatial coordinate; performing nonlinear fitting according to the displacement change amount to determine a thoracic volume change amount and an abdominal volume change amount; determining a respiration parameter according to the thoracic volume change amount and the abdominal volume change amount; the respiration parameter comprises a total lung ventilation, a thoracic respiration contribution ratio, an abdominal respiration contribution ratio and a thoraco-abdominal phase difference. The application realizes low-cost and high-precision respiration flow monitoring.

The invention relates to the technical field of intelligent monitoring, in particular to a medical risk monitoring method based on an artificial intelligence model, and the method comprises the steps: collecting thoracic impedance, tissue oxygenation spectrum, microcirculation pressure, respiratory flow and body surface vibration in real time; judging tissue oxygenation abnormity, and generating a suspected risk result; screening an abnormal candidate parameter group based on the risk result and a historical stable sample; candidate parameter fluctuation, frequency band energy, synchronism and pressure offset are calculated, and the risk type is judged; adjusting an oxygen supply threshold, an impedance tolerance and a fluctuation range according to the risk type; and correcting a fluctuation range in combination with risk time distribution and parameter correlation or generating an intervention prompt in combination with an artificial intelligence model. The multi-source physiological parameter fusion analysis model based on artificial intelligence is constructed, and the problems that due to single static data analysis and lack of multi-parameter collaborative judgment, tiny abnormal fluctuation of a postoperative patient cannot be captured in time, and risk events are lagged to find are effectively solved.

The invention relates to patient attachment detection in a respiratory flow therapy system. Systems and methods may determine whether a patient is attached to a breathing device, such as via a patient interface, from a flow parameter signal in the time domain. In addition, these processes may classify patient attachment status into one of four categories: already detached, being attached, already attached, or being detached. The system may include a non-sealed patient interface, such as a nasal cannula in nasal high flow therapy or any other patient interface. Data for the patient to use the respiratory system may provide a long-term trend of treatment compliance and use information and / or progression of respiratory function and / or other physiological functions of the patient.

The invention relates to a breathing machine self-adaptive ventilation pressure control method and a breathing machine. The method comprises the following steps: acquiring a target respiratory flow signal of a current respiratory cycle in a current ventilation treatment stage; predicting and generating expected inspiration time and expected tidal volume of the next respiratory cycle based on the target respiratory flow signal; on the basis of the expected inspiration time, the expected pressure gradient during ventilation in the next respiratory cycle is configured, and on the basis of the expected tidal volume, expected pressure support during ventilation in the next respiratory cycle is configured; based on the expected pressure gradient and the expected pressure support, the ventilation pressure of the next respiratory cycle is configured, so that the pressure gradient during ventilation of the next respiratory cycle is matched with the expected pressure gradient, and the pressure support during ventilation of the next respiratory cycle is matched with the expected pressure support. Self-adaptive ventilation pressure control can be effectively achieved, and ventilation convenience, man-machine synchronism, compliance and treatment effectiveness of a user are improved.

The application provides a processing method of respiratory flow data, comprising: performing integer processing on initial flow data to obtain integer flow data; performing difference processing on the integer flow data to obtain difference flow data, the difference flow data comprising a plurality of difference values arranged in sequence, the difference values comprising zero, positive values and negative values; adding a flag value before a difference value which is a positive value or zero when a previous difference value of the difference value is a negative value, or adding a flag value before a difference value which is a negative value when a previous difference value of the difference value is a positive value or zero; performing absolute value processing on the difference values to obtain absolute values; and encoding the flag values and the absolute values to obtain encoded flow data. The processing method of respiratory flow data provided by the application can effectively improve the compression efficiency of respiratory flow data.

A method for determining a scaled respiratory flow rate and volume during respiration of a patient includes a) successively determining a plurality of values for a difference between a pressure in at least a first location in an upper respiratory tract of the patient and a reference pressure, b) deriving the scaled respiratory flow rate from the plurality of values for the pressure difference by using a first relationship, c) deriving the scaled respiratory volume from the plurality of values for the pressure difference by using a second relationship, and d) displaying the scaled respiratory flow rate derived in step b) and the scaled respiratory volume derived in step c) or a further variable derived from the scaled respiratory flow rate and volume in a graphical representation. Step a) is performed during tidal breathing of the patient. A system for performing the aforementioned method.

The present disclosure relates to a method for non-invasive determination of a hemodynamic parameter of a mechanically ventilated subject (3) based on a point in time (thb) of a heartbeat of the subject and an arrival point in time (tarr_pulm, tarr_sys) at which a blood pressure pulse caused by the heartbeat reaches a point of arrival in the circulatory system of the subject. The method comprises the steps of measuring (S41) a respiratory pressure and / or a respiratory flow, and determining (S43) the point in time (thb) of the heartbeat from a change in the measured respiratory pressure and / or the respiratory flow resulting from a physical impact of the heart on the lungs of the subject (3) during the heartbeat.

This invention discloses a device for precise detection and treatment of sleep apnea under continuous airflow support. This device can simultaneously perform precise identification and treatment of sleep apnea. It integrates precise detection of apnea and hypopnea events during sleep, accurately distinguishing between central and obstructive apnea events, and effectively treating obstructive sleep apnea and hypopnea. It generates a constant positive pressure airflow through a positive pressure airflow generating component consisting of a blower, pressure control assembly, and pressure airflow sensor. This positive pressure airflow is continuously input into an open-face mask equipped with a respiratory flow sensor, enabling the identification of sleep apnea-hypopnea events and the determination of the nature of the apnea. Continuously inputting positive pressure airflow into a nearly sealed nasal mask through the positive pressure airflow generating component can treat or adjust the pressure required for treating sleep apnea.

The present disclosure relates to a method (MO) for providing respiratory timing parameters from respiratory monitoring measurements of a subject, the method comprising the steps of: providing (M1) a respiratory effort signal (E) and a respiratory flow signal (F) of a subject; determining (M2a) an ensemble of peaks (pE) in the respiratory effort signal (E) and determining (M2b) an ensemble of valleys (vE) in the respiratory effort signal (E); and identifying (M3) times associated with the valleys (vE) as preliminary inspiratory onset times (t′io); refining (M4) preliminary inspiratory onset times (t′io) within respective peak-to-peak time intervals (Tpp) of the respiratory effort signal (E) by: determining (M41) first derivative (F1d) of the respiratory flow signal (F) in a respective peak-to-peak interval (Tpp); determining (M42) local peaks (pF1d) and valleys (vF1d) in the respiratory flow signal first derivative (F1d); determining (M43) a time midpoint (tmid) between the time of a local valley (vF1d) in the respiratory flow signal first derivative (F1d) closest in time to the later endpoint in the respective peak-to-peak time interval (Tpp) and the time of a local peak (pF1d) in the respiratory flow signal derivative (F1d) in the respective peak-to-peak time interval (Tpp); evaluating (M44) whether the respiratory effort signal (E) at the determined time midpoint (tmid) satisfies a predetermined inspiratory onset time condition, and if satisfied, selecting (M45) the determined time midpoint (tmid) as an inspiratory onset time (tio) instead of the preliminary inspiratory onset time (t′io) for that peak-to-peak interval (Tpp), whereas if the condition is not satisfied, keep the preliminary inspiratory onset time as the inspiratory onset time for that peak-to-peak interval.

This invention relates to the field of biomedical technology, specifically a method and apparatus for assisting right ventricular angiography based on pressure signal feedback. The method includes: identifying multiple effective pressure acquisition points; acquiring pressure signals from an initial subject based on these points to obtain an initial pressure sequence set; acquiring a second pressure sequence set using a pre-identified respiratory flow sensor; fusing the multiple initial and second pressure sequence sets to obtain a fused pressure sequence; extracting features from the fused pressure sequence to obtain a staged pressure feature set; acquiring a motion quality index sequence; performing pattern recognition matching between the motion quality index sequence and a standard template sequence to obtain a standard motion similarity; and acquiring multimodal motion prompts based on the standard motion similarity. This invention addresses the problem of right ventricular angiography failures requiring multiple manual interventions due to the subject's inability to autonomously, stably, and accurately execute standardized Warburg maneuvers.

Concurrent treatment of obstructive sleep apnea and hypertension in a patient, via a pressure generating system, includes providing a flow of treatment gas to an airway of a patient in accordance with an initial set of flow parameters with respect to an obstructive sleep apnea mode. Responsive to determining that the patient has achieved stable breathing while receiving the flow of treatment gas, the flow parameters are increased above the initial set of flow parameters with respect to a hyper-ventilation mode. The flow of treatment gas is then provided to the airway of the patient in accordance with the increased flow parameters for a predetermined period of time. The increased flow parameters are configured to bring the patient's breath into accordance with target patient breath parameters configured to inflate the patient's lungs beyond a threshold for activating pulmonary stretch receptors of the airway of the patient.

Concurrent treatment of obstructive sleep apnea and hypertension in a patient, via a pressure generating device, includes providing a flow of treatment gas to an airway of a patient in accordance with an initial set of flow parameters with respect to an obstructive sleep apnea mode. Responsive to determining that the patient has achieved stable breathing while receiving the flow of treatment gas, the flow parameters are increased above the initial set of flow parameters with respect to a hyper-ventilation mode. The flow of treatment gas is then provided to the airway of the patient in accordance with the increased flow parameters for a predetermined period of time. The increased flow parameters are configured to bring the patient's breath into accordance with target patient breath parameters configured to inflate the patient's lungs beyond a threshold for activating pulmonary stretch receptors of the airway of the patient.

The invention belongs to the technical field of breathing machines, and relates to a respiratory effort evaluation system based on a respiratory flow autopower spectrum. The system comprises a signal acquisition module used for acquiring a continuous breathing flow signal acquired by a flow sensor of the breathing machine in real time; the self-power spectrum calculation module is used for carrying out preprocessing and time-frequency conversion on the respiratory flow signals and calculating to obtain a self-power spectrum; the extraction module is used for extracting energy of a preset high-frequency band as a high-frequency energy component in the autopower spectrum, and the high-frequency band is higher than a main frequency band corresponding to the basic respiratory frequency of the human body; the statistical analysis module is used for establishing a baseline value for evaluation based on statistical data of high-frequency energy components in the historical respiratory flow data; the evaluation output module is used for comparing the high-frequency energy component at the current moment with the baseline value, when the high-frequency energy component is smaller than the baseline value, the respiratory effort state is evaluated to be abnormal, and otherwise, the respiratory effort state is normal.

The embodiment of the invention belongs to the technical field of respiratory function detection, and relates to a respiratory blocking signal identification method, which comprises the following steps of: synchronously acquiring oral pressure data and respiratory flow data in the ROCC or P0.1 test process of a subject; determining oral pressure peak point data in the oral pressure data; determining a local time window where each oral pressure peak point in the oral pressure peak point data is located; determining the correlation between the oral pressure data and the respiratory flow data in each local time window; and according to the calculation result of the correlation, determining a peak point of which the correlation is higher than a preset threshold value in the oral pressure peak data as an effective peak point, and taking the effective peak point as an identification point of the blocking signal. According to the method, the correlation of the oral pressure data and the respiratory flow data at the initial peak point is determined, the synchronization and trend characteristics of the oral pressure data and the respiratory flow data are investigated by using the related calculation result, and the peak point with relatively high correlation is identified as the blocking signal, so that the identification accuracy of the respiratory blocking signal is improved.

The invention provides a pulmonary nodule real-time positioning system based on patient respiratory fluctuation modeling. The system comprises a multi-source sensing unit, a signal processing module, a respiratory dynamics modeling module, a regionalization sensitivity field module, a disturbance observer, a self-healing registration module, a fusion filtering module and an output and interaction module. A dynamic model with a hysteretic operator is established through multi-source signals such as thoracico-abdominal movement, laryngeal acoustics and vibration, end tidal carbon dioxide, respiratory flow, body position drifting and instrument states, millimeter-level positioning of pulmonary nodules along with respiration is achieved in combination with regionalized sensitivity mapping, errors caused by respiratory movement, local disturbance and body position drifting are effectively solved, and the positioning accuracy of the pulmonary nodules is improved. And the safety and effectiveness of clinical operation are obviously improved.