WO2023077448A1 - 呼吸率监测方法及医疗通气设备 - Google Patents

呼吸率监测方法及医疗通气设备 Download PDF

Info

Publication number
WO2023077448A1
WO2023077448A1 PCT/CN2021/129068 CN2021129068W WO2023077448A1 WO 2023077448 A1 WO2023077448 A1 WO 2023077448A1 CN 2021129068 W CN2021129068 W CN 2021129068W WO 2023077448 A1 WO2023077448 A1 WO 2023077448A1
Authority
WO
WIPO (PCT)
Prior art keywords
signal
respiration rate
ventilation
index
obtaining
Prior art date
Application number
PCT/CN2021/129068
Other languages
English (en)
French (fr)
Inventor
肖杨
伍乐平
冯开诚
袁昇
Original Assignee
深圳迈瑞生物医疗电子股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳迈瑞生物医疗电子股份有限公司 filed Critical 深圳迈瑞生物医疗电子股份有限公司
Priority to PCT/CN2021/129068 priority Critical patent/WO2023077448A1/zh
Priority to CN202180103629.7A priority patent/CN118159323A/zh
Publication of WO2023077448A1 publication Critical patent/WO2023077448A1/zh

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M16/00—Devices for influencing the respiratory system of patients by gas treatment, e.g. mouth-to-mouth respiration; Tracheal tubes

Definitions

  • the present application relates to the field of medical equipment, and more specifically relates to a breathing rate monitoring method and medical ventilation equipment.
  • oxygen therapy is a routine method used to correct hypoxemia in patients and improve tissue oxygen supply by inhaling high-concentration oxygen to increase the amount of dissolved oxygen in plasma.
  • Oxygen therapy in a broad sense refers to the treatment of patients with a gas with a volume fraction higher than that of air oxygen. In layman's terms, it is to change the oxygen concentration in the gas inhaled by the patient. oxygen.
  • Oxygen therapy is suitable for patients receiving invasive ventilation with intubation, or patients receiving non-invasive ventilation and extracorporeal membrane oxygenation therapy. Doctors will choose the timing of oxygen therapy according to the patient's condition and state. The method, as well as the target and duration of oxygen therapy. A large number of studies and practices have proved the effectiveness of oxygen therapy in the treatment process of patients. At the same time, the safety of oxygen use and the standardization of oxygen therapy in the process of oxygen therapy have gradually attracted attention.
  • Respiratory rate is generally identified through changes in the patient's airway pressure or inspiratory flow, and during oxygen therapy, the flow rate and pressure waveform are often susceptible to various interferences, such as leakage, loosening of the oxygen therapy catheter, catheter water or patient activity, etc., thereby affecting the accuracy of the respiration rate.
  • the first aspect of the embodiment of the present application provides a breathing rate monitoring method of a ventilator, including:
  • a third respiration rate of the ventilated subject is obtained according to the first respiration rate and the second respiration rate.
  • the second aspect of the embodiment of the present application provides a respiratory rate monitoring method, the method comprising:
  • the device signal can reflect the breathing rhythm of the ventilation subject
  • the respiration rate of the ventilated subject is obtained according to the device signal.
  • the third aspect of the embodiment of the present application provides a respiratory rate monitoring method, the method comprising:
  • the respiration rate of the ventilated subject is obtained according to the cross-correlation signal.
  • the fourth aspect of the embodiment of the present application provides a respiratory rate monitoring method, the method comprising:
  • the fifth aspect of the embodiment of the present application provides a respiratory rate monitoring method, the method comprising:
  • the one or more signals can reflect the respiratory rhythm of the ventilated subject
  • the sixth aspect of the embodiment of the present application provides a medical ventilation device, which includes:
  • the pressure generating device is used to communicate with the ventilation pipeline, so as to deliver the gas with a set pressure to the ventilated object through the ventilation pipeline;
  • a processor connected to the pressure generating device, is used to control the pressure generating device to generate the gas of the set pressure; the processor is also used to execute the respiration rate monitoring method as described above.
  • respiration rate monitoring method and medical ventilation equipment provided in the embodiments of the present application can improve the accuracy of respiration rate monitoring.
  • Fig. 1 shows a schematic flowchart of a breathing rate monitoring method according to an embodiment of the present application
  • FIG. 2 shows a schematic diagram of a waveform of a first signal according to an embodiment of the present application
  • FIG. 3 shows a schematic diagram of a frequency spectrum of a first signal according to an embodiment of the present application
  • Fig. 4 shows a schematic flow chart of a breathing rate monitoring method according to another embodiment of the present application.
  • Fig. 5 shows a schematic flowchart of a breathing rate monitoring method according to another embodiment of the present application
  • Fig. 6 shows a schematic flowchart of a breathing rate monitoring method according to another embodiment of the present application.
  • Fig. 7 shows a schematic flowchart of a breathing rate monitoring method according to another embodiment of the present application.
  • Fig. 8 shows a schematic block diagram of a medical ventilation device according to an embodiment of the present application.
  • FIG. 1 is a schematic flow chart of the breathing rate monitoring method 100 in an embodiment of the present application, which specifically includes the following steps:
  • step S110 the first signal and the second signal collected during the process of the medical ventilation equipment providing mechanical ventilation for the ventilated subject, the first signal and the second signal can reflect the respiratory rhythm of the ventilated subject;
  • step S120 extracting frequency domain features of the first signal, and obtaining a first respiration rate of the ventilated subject according to the frequency domain features of the first signal;
  • step S130 extracting time-domain features of the second signal, and obtaining a second respiration rate of the ventilated subject according to the time-domain features of the second signal;
  • step S140 a third respiration rate of the ventilation subject is obtained according to the first respiration rate and the second respiration rate.
  • medical ventilation equipment includes ventilators, anesthesia machines, monitors, etc.
  • the process of providing mechanical ventilation for ventilated subjects includes, but is not limited to, the process of providing nasal high-flow oxygen therapy for ventilated subjects.
  • Oxygen therapy is used to correct hypoxemia in patients. It is a process of improving tissue oxygen supply by inhaling high-concentration oxygen to increase the amount of dissolved oxygen in plasma.
  • Nasal high-flow oxygen therapy is to directly mix air and oxygen with a certain oxygen concentration through a nasal catheter.
  • the oxygen therapy method in which high-flow gas is delivered to the patient has the characteristics of high flow, precise oxygen concentration, and heating and humidification.
  • the respiration rate monitoring method 100 of the embodiment of the present application can realize accurate monitoring of respiration rate during nasal high-flow oxygen therapy.
  • the first signal and the second signal are collected, and the first signal and the second signal are signals capable of reflecting the breathing rhythm of the ventilated subject.
  • the first signal includes at least one of the following: a device signal capable of reflecting the breathing rhythm of the subject, a physiological signal, a respiratory signal, and a derivative signal of at least two of the device signal, the physiological signal, and the respiratory signal.
  • the second signal may also include a device signal, a physiological signal, a respiratory signal capable of reflecting the respiratory rhythm of the ventilated subject, and a derivative signal of at least two of the device signal, the physiological signal, and the respiratory signal.
  • the first signal and the second signal may be different signals, for example, the first signal is a certain device signal, and the second signal is a certain physiological signal.
  • the first signal and the second signal may also be the same signal, for example, the first signal and the second signal are both device signals of the same type, and the same signal is subsequently processed differently to obtain different processing results.
  • the signal of the device capable of reflecting the respiratory rhythm includes a signal of a device controlling the magnitude of the ventilation flow in the medical ventilation device.
  • the mechanical ventilation of medical ventilation equipment to complete a breathing cycle needs to go through inhalation trigger, inhalation process, inhalation-exhalation switching and exhalation process.
  • the medical ventilation equipment senses the inhalation action of the ventilated subject, and controls the gas flow in the ventilating circuit through a device that controls the ventilating flow to start delivering air. Therefore, the respiratory rate of the ventilated object can be obtained according to the signal of the device controlling the magnitude of the ventilation flow.
  • the signal of the device controlling the ventilation flow can be the control signal of the device, that is, the signal output from the processor to the device; the signal of the device controlling the ventilation flow can also be the sampling signal of the device, that is, the signal fed back from the device to the processor.
  • the device for controlling the ventilation flow in the medical ventilation equipment may include a turbine for controlling the ventilation flow in the medical ventilation equipment.
  • a turbine generally refers to a centrifugal air compressor. Its working principle is to control the turbine speed, and adjust the output pressure of the turbine through the change of the speed to adjust the flow rate of the airflow.
  • the pressure difference can be obtained according to the target pressure corresponding to the target flow and the real-time pressure corresponding to the real-time flow
  • the target speed of the turbine motor can be obtained according to the real-time pressure and pressure difference
  • the turbine motor can be controlled to run at the target speed, thereby obtaining the target traffic. That is to say, the turbine is based on the pressure control to indirectly realize the flow control.
  • the rotational speed signal of the turbine or the signal of the circuit driving the rotation of the turbine identifies the respiratory rate.
  • the device for controlling the ventilation flow in the medical ventilation equipment may also include the valve for controlling the ventilation flow in the medical ventilation equipment.
  • the valves that control the ventilation flow include proportional valves, large diameter valves, etc. Valves are generally electronically controlled valves.
  • Medical ventilation equipment controls the linear motion of the valve by adjusting the drive current or drive voltage of the valve, and adjusts the flow rate in the ventilation pipeline by changing the opening of the valve.
  • increase the opening of the valve to increase Gas flow reduce the opening of the valve during the expiratory phase to reduce the gas flow.
  • the signal of the valve mainly includes the opening degree signal of the valve. Compared with the turbine, the control of the gas flow by the valve is direct, so the feedback adjustment time is shorter.
  • the physiological signal includes at least one of the following: a blood oxygen signal, an end-tidal carbon dioxide signal, and an esophageal pressure signal of the ventilated subject.
  • Physiological signals can be collected by external sensors and sent to medical ventilation equipment.
  • the blood oxygen signal is the blood oxygen saturation signal, which represents the concentration of blood oxygen in the blood, fluctuates periodically with respiration, and thus reflects the breathing rhythm of the ventilated subject.
  • the end-tidal carbon dioxide signal is the carbon dioxide concentration curve measured during respiration. The ascending branch of the curve corresponds to the expiratory phase, and the descending branch corresponds to the inspiratory phase. Based on this, the inspiratory phase and the expiratory phase can be identified.
  • the esophageal pressure signal represents the pressure in the esophagus of the ventilated subject.
  • the chest volume increases due to the contraction of the respiratory muscles, which reduces the esophageal pressure; , the respiratory muscles gradually relax, and the esophageal pressure gradually increases, so the inspiratory segment and the expiratory segment of the ventilated object can be identified according to the esophageal pressure signal.
  • physiological signals listed above are only examples. In addition to blood oxygen signals, end-tidal carbon dioxide signals, and esophageal pressure signals, physiological signals can also include any other signals that can reflect the respiratory rhythm of the ventilated subject, such as transpulmonary pressure signals, plateau pressure signals, etc. .
  • the respiration signal is a signal directly reflecting the respiration state
  • the respiration signal may be a signal collected by the medical ventilation device itself, specifically including at least one of the following: a flow signal and a pressure signal of mechanical ventilation.
  • the flow signal may be an inspiratory flow signal or an expiratory flow signal.
  • the pressure signal can be a patient-side pressure signal or a machine-side pressure signal.
  • the respiratory signal may also include a tidal volume signal and the like. The flow signal and pressure signal can directly reflect the ventilation state, so the respiratory rate can be accurately identified.
  • the first signal and the second signal may also be derivative signals of any at least two of the above-mentioned signals.
  • the derivative signal may include a cross-correlation signal, which can clearly represent the respiratory fluctuation of the ventilated subject, and amplify the smaller respiratory fluctuation, so that the influence of external interference on the recognition of the respiratory rate can be reduced, and more accurately Identify the respiratory state of a ventilated subject.
  • obtaining the cross-correlation signal of the flow signal and the pressure signal includes performing cross-correlation calculation on the flow signal and the pressure signal according to the preset signal sampling rate and preset sampling time to obtain the cross-correlation signal.
  • the signal sampling rate and sampling time can be set according to actual needs.
  • the preset signal sampling rate indicates the number of pressure values and the number of flow values obtained within 1s, and the preset sampling time specifically limits the time for obtaining pressure values and flow values, that is, if the preset signal sampling The rate is 1KHZ, and the preset sampling time is 20ms.
  • the preset signal sampling rate is 1KHZ, which means that 1000 sampling values of the pressure signal and 1000 sampling values of the flow signal can be obtained within 1s.
  • the preset sampling time is 20ms, which means The pressure signal and flow signal of 20ms are actually obtained. Since the preset signal sampling rate is 1KHZ, 20 sampling values of the pressure signal and 20 sampling values of the flow signal can be obtained within 20ms.
  • the first sampling value is the 20 sampling values of the pressure signal
  • the second sampling value is the 20 sampling values of the flow signal
  • the cross-correlation calculation is performed on the first sampling value and the second sampling value
  • the number of the first sampling value and the second sampling value is determined by the preset signal sampling rate and the preset sampling time.
  • a first sampling value is obtained at a certain moment, a corresponding second sampling value will be obtained at the same time.
  • the cross-correlation data of the pressure signal and the flow signal can be calculated according to the following formula:
  • Corr(k) represents the cross-correlation data of pressure signal and flow signal at time k
  • Flow(i) represents the flow velocity value at time i
  • Pressure(i) represents the pressure value at time i.
  • the above-mentioned preset signal sampling rate is 1KHZ, and the preset sampling time is 20ms, so the sampling values corresponding to the pressure signal and the flow signal are both 20, when calculating the pressure at time k
  • the pressure value and flow velocity value at time k, and the pressure value and flow velocity value at the first 19 moments at time k can be substituted into the above formula for calculation to obtain the pressure and flow velocity at time k cross-correlation data.
  • the first signal can be a device signal, such as a current signal or a rotational speed signal of a turbine
  • the second signal can be Breathing signals, such as flow signals or pressure signals.
  • the second signal may also be a cross-correlation signal of at least two respiratory signals.
  • step S120 the frequency domain feature of the first signal is extracted, and the first respiration rate of the ventilated subject is obtained according to the frequency domain feature of the first signal.
  • the frequency domain feature reflects the global frequency feature of the signal, and hardly provides frequency information in the time domain. Therefore, the first respiration rate of the ventilated subject can be obtained according to the frequency domain feature of the first signal to obtain a more accurate calculation result.
  • the first signal may be transformed from the time domain to the frequency domain, that is, the signal represented by the time axis is transformed into the signal represented by the frequency axis. Since the first signal reflects the respiratory rhythm of the ventilated subject, after being transformed into the frequency domain, the frequency point corresponding to the respiratory frequency in the frequency domain signal should have the largest amplitude.
  • extracting the frequency domain feature of the first signal includes: obtaining a spectrogram of the first signal, and determining the frequency point corresponding to the maximum amplitude in the amplitude-frequency characteristic of the first signal according to the spectrogram;
  • Obtaining the first respiration rate of the ventilated subject by the frequency domain feature includes: converting the frequency point corresponding to the maximum amplitude into the first respiration rate.
  • the spectrum diagram of the first signal can be obtained through discrete Fourier transform (FFT). Specifically, sampling points are extracted from the first signal, and after the sampling points are subjected to discrete Fourier transform, frequency points and their frequency points can be obtained. Corresponding amplitude characteristics.
  • FFT discrete Fourier transform
  • the power spectrum diagram of the first signal may also be acquired, the frequency point corresponding to the maximum power in the power spectrum characteristics of the first signal may be determined according to the power spectrum diagram, and the frequency point corresponding to the maximum power may be converted into the first breath Rate.
  • the power spectrum diagram shows the relationship between signal power and frequency, the abscissa is frequency, and the ordinate is power.
  • a classical spectrum estimation method or a modern spectrum estimation method may be used when acquiring the power spectrum diagram of the first signal.
  • the classical spectrum estimation method includes a direct method, an indirect method, etc.
  • the modern spectrum estimation method includes a parametric model method, a non-parametric method, etc. model method, etc.
  • other frequency domain representation methods may also be used to extract the frequency domain features of the first signal, such as energy spectrum, wavelet transform, and the like.
  • preprocessing may be performed on the first signal, and the preprocessing includes at least one of normalization processing and filtering processing.
  • the normalization process unifies the range of the signal, which is convenient for subsequent calculations; the filtering process can improve the signal-to-noise ratio of the signal and improve the accuracy of respiration rate identification.
  • a corresponding digital filter can be designed for the clutter signal in the signal to filter out the clutter signal and prevent the signal change caused by extreme conditions such as pipeline jitter from affecting the calculation of the respiration rate.
  • step S130 the time-domain feature of the second signal is extracted, and the second respiration rate of the ventilated subject is obtained according to the time-domain feature of the second signal.
  • Step S130 determines the respiratory rate of the ventilated subject through time-domain identification. Time-domain identification calculates the respiratory rate according to the waveform of the second signal, and the calculation speed is faster.
  • extracting the time-domain feature of the second signal includes: obtaining the duration of the inspiratory phase and the duration of the expiratory phase adjacent to the inspiratory phase according to the waveform of the second signal, and then according to the duration of the inspiratory phase The duration and the duration of the expiratory phase yield a second respiration rate.
  • An inspiratory phase and an expiratory phase constitute a breathing cycle.
  • the end point of the inspiratory phase and the end point of the expiratory phase can be identified according to the waveform of the second signal, thereby obtaining the duration of the inspiratory phase and the expiratory phase; according to the duration of the inspiratory phase and the expiratory phase
  • the time can be used to obtain the length of the breathing cycle, and the breathing rate can be obtained according to the length of the breathing cycle, that is, the number of breaths per minute.
  • the duration of the respiratory cycle may also be directly identified according to the waveform of the second signal, without specifically distinguishing the inspiratory phase and the expiratory phase.
  • the duration of the breathing cycle can be obtained according to the distance between two adjacent peaks in the second signal.
  • the second breathing rate can be obtained according to the duration of the breathing cycle.
  • a third respiration rate of the ventilated subject is obtained according to the first respiration rate and the second respiration rate. Since the first respiration rate and the second respiration rate are the results obtained based on frequency domain and time domain analysis respectively, the third respiration rate obtained according to the first respiration rate and the second respiration rate combines the frequency domain characteristics and time domain characteristics of the signal , thus improving the timeliness and accuracy of respiration rate calculation.
  • obtaining the third respiratory rate of the ventilated subject according to the first respiratory rate and the second respiratory rate includes: obtaining the first characteristic index of the first signal according to the frequency domain characteristic of the first signal; obtaining the first characteristic index of the first signal according to the time domain characteristic of the second signal; The characteristic obtains the second characteristic index of the second signal; According to the first characteristic index and the second characteristic index, one of the first respiration rate and the second respiration rate is selected as the third respiration rate; or, according to the first characteristic index and the second characteristic index The index weights the first rate of respiration and the second rate of respiration to obtain a third rate of respiration.
  • the first characteristic index and the second characteristic index represent the validity, strength, change range, etc. of the first signal and the second signal respectively.
  • Calculating the weighted calculation of the first respiration rate and the second respiration rate according to the first characteristic index and the second characteristic index includes weighting the first respiration rate and the second respiration rate according to the first characteristic index and the second characteristic index.
  • the first characteristic index and the second characteristic index can be implemented as signal ratings, for example, level one indicates that the validity of the signal is weak and cannot reflect the respiratory rhythm well; level five indicates that the validity of the signal is strong and can Better reflect the breathing rhythm.
  • level one indicates that the validity of the signal is weak and cannot reflect the respiratory rhythm well
  • level five indicates that the validity of the signal is strong and can Better reflect the breathing rhythm.
  • the first respiration rate and the second respiration rate can be selected to have a higher rating.
  • a high respiration rate serves as the third respiration rate.
  • the first respiration rate and the second respiration rate are weighted and averaged according to the first characteristic index and the second characteristic index to obtain the third respiration rate
  • the first weight can be obtained according to the first characteristic index
  • the weight can be obtained according to the second characteristic index.
  • the second weight is performing a weighted average on the first respiration rate and the second respiration rate according to the first weight and the second weight to obtain a third respiration rate. Among them, the higher the signal rating, the greater the corresponding weight in the weighted average.
  • the first characteristic index and the second characteristic index can also be implemented as the first weight of the first signal and the second weight of the second signal, that is, the first weight is directly obtained according to the frequency domain characteristics of the first signal, and the first weight is obtained according to the second signal
  • the time-domain features of get the second weight if one of the first respiration rate and the second respiration rate is selected as the third respiration rate according to the first characteristic index and the second characteristic index, then when the first weight is 1 and the second weight is 0, The first respiration rate is selected as the third respiration rate, and when the first weight is 0 and the second weight is 1, the second respiration rate is selected as the third respiration rate. If the weighted average of the first respiration rate and the second respiration rate is performed according to the first characteristic index and the second characteristic index, then the weighted average of the first respiration rate and the second respiration rate is directly performed according to the first weight and the second weight.
  • the first characteristic index is obtained according to the frequency domain characteristics of the first signal, including: according to the average amplitude of the spectrogram of the first signal, the maximum amplitude of the spectrogram of the first signal, and the average amplitude of the power spectrogram of the first signal At least one of the power and the maximum power of the power spectrogram of the first signal results in a first characteristic index. For example, if the ratio of the maximum amplitude to the average amplitude of the spectrogram is larger, it means that the respiratory rhythm is more obvious in the frequency domain, and the first respiration rate obtained according to the frequency domain characteristics of the first signal is more accurate, correspondingly the first characteristic The higher the index. Based on a similar principle, if the ratio of the maximum power to the average power of the power spectrum graph is larger, the first characteristic index is higher.
  • obtaining the second characteristic index according to the time-domain characteristic of the second signal includes obtaining the second characteristic index according to a variation range of the second signal.
  • Obtaining the second characteristic index according to the time-domain characteristics of the second signal may also include obtaining the second characteristic index according to the change range of the historical second respiration rate calculated based on the second signal.
  • the index that characterizes the range of change of the historical second respiration rate includes, but not limited to, the variance and standard deviation of the historical second respiration rate. The smaller the variation range of the second signal and the larger the variation range of the historical second respiration rate, it means that the respiratory rhythm is less obvious in the time domain, and thus the second characteristic index is lower.
  • a machine learning model may be used to output the first characteristic index and the second characteristic index.
  • obtaining the first feature index of the first signal according to the frequency domain feature of the first signal includes inputting the frequency domain feature of the first signal into the trained first machine learning model, and obtaining the output of the first machine learning model The first feature index.
  • Obtaining the second feature index of the second signal according to the time domain feature of the second signal including inputting the time domain feature of the second signal into the trained second machine learning model, and obtaining the second feature output by the second machine learning model index.
  • the machine learning model can be a traditional machine learning model or a deep learning model, including but not limited to neural network, support vector machine, linear discriminant analysis, etc.; training methods include but not limited to linear regression, gradient descent and other model training methods.
  • an optimal mapping function from frequency-domain features to the first feature index may be learned, so that the error between the first feature index obtained by frequency-domain feature mapping and the actually calibrated feature index is the smallest.
  • the first feature index output by the first machine learning model can be realized in the form of rating or weight.
  • the training goal is to enable the first characteristic index to distinguish the primary and secondary relationship of frequency components with similar energy, accurately identify the frequency components caused by breathing, and correct the calculation error of respiration rate caused by different frequency components.
  • the network model is trained to obtain a trained machine learning model.
  • the second feature index output by the second machine learning model can also be realized in the form of rating or weight.
  • the third respiration rate may be displayed directly. Since the accuracy of the third respiration rate calculated according to the embodiment of the present application is relatively high, the specific value of the third respiration rate is directly displayed.
  • a trend graph of the third respiration rate may also be displayed, and the trend graph reflects the dynamic trend of the third respiration rate over time.
  • the trend graph of the third respiration rate can have various graphical representations such as a line graph and a histogram.
  • the ROX index can be used as an evaluation index for whether to perform tracheal intubation. For example, for patients with severe pneumonia, after 12 hours of nasal high-flow oxygen therapy, if the ROX index is greater than 4.88, the treatment success rate is higher and the intubation rate is lower; if the ROX index is less than 3.85, tracheal intubation is required Tube.
  • the ROX index can be calculated according to the third respiration rate, blood oxygen saturation and inspired oxygen concentration of the ventilated subject, and the ROX index can be displayed.
  • ROX index (blood oxygen saturation/inhaled oxygen concentration)/respiration rate.
  • the blood oxygen saturation and inspiratory oxygen concentration of the ventilated subject can be obtained through a ventilator or a monitor, and the respiratory rate adopts the third respiratory rate obtained by combining the time domain analysis and frequency domain analysis as described above. Since the time domain and frequency domain The combined method can effectively reduce the influence of interference signals and identify the real respiration rate of the ventilated subject, thus improving the validity and stability of ROX index calculation.
  • the trend graph of the ROX index can also be displayed to reflect the dynamic trend of the ROX index over time.
  • the respiration rate monitoring method 200 of the embodiment of the present application combines time domain analysis and frequency domain analysis to jointly calculate the respiration rate, which can improve the accuracy of respiration rate monitoring.
  • the calculation of respiratory rate can be realized based on the ventilator itself that provides nasal high-flow oxygen therapy, without the need to connect multiple leads for monitoring The instrument monitors the respiration rate.
  • the respiration rate monitoring method 400 includes the following steps:
  • step S410 during the process of the medical ventilation equipment providing mechanical ventilation for the ventilated subject, the device signal of the device controlling the ventilation flow of the medical ventilator is collected, and the device signal can reflect the breathing rhythm of the ventilated subject;
  • step S420 the breathing rate of the ventilated subject is obtained according to the device signal.
  • the respiration rate monitoring method 400 of this embodiment measures the respiration rate of the ventilated object according to the device signal of the device that controls the ventilation flow of the medical ventilation equipment during the process of mechanical ventilation. Respiration rate can reduce errors caused by various interference factors.
  • providing mechanical ventilation to the ventilated subject includes providing nasal high flow oxygen therapy to the ventilated subject. In the process of nasal high-flow oxygen therapy, measuring the respiration rate according to the device signal can avoid errors caused by gas leakage, loosening of the oxygen therapy catheter, water accumulation in the catheter or patient's activities.
  • the device for controlling the ventilation flow in the medical ventilation equipment may include a turbine for controlling the ventilation flow in the medical ventilation equipment.
  • a turbine generally refers to a centrifugal air compressor. Its working principle is to control the turbine speed, and adjust the output pressure of the turbine through the change of the speed to adjust the flow rate of the airflow.
  • the pressure difference can be obtained according to the target pressure corresponding to the target flow and the real-time pressure corresponding to the real-time flow
  • the target speed of the turbine motor can be obtained according to the real-time pressure and pressure difference
  • the turbine motor can be controlled to run at the target speed, thereby obtaining the target traffic. That is to say, the turbine is based on the pressure control to indirectly realize the flow control.
  • the rotational speed signal of the turbine or the signal of the circuit driving the rotation of the turbine identifies the respiratory rate.
  • the device for controlling the ventilation flow in the medical ventilation equipment may also include the valve for controlling the ventilation flow in the medical ventilation equipment.
  • the valves that control the ventilation flow include proportional valves, large diameter valves, etc. Valves are generally electronically controlled valves.
  • Medical ventilation equipment controls the linear motion of the valve by adjusting the drive current or drive voltage of the valve, and adjusts the flow rate in the ventilation pipeline by changing the opening of the valve.
  • increase the opening of the valve to increase Gas flow reduce the opening of the valve during the expiratory phase to reduce the gas flow.
  • the signal of the valve mainly includes the opening degree signal of the valve. Compared with a turbine, the control of the gas flow by the valve is direct, so the feedback regulation time is shorter.
  • obtaining the breathing rate of the ventilated subject according to the device signal is realized by performing time domain analysis on the device signal. Specifically, the time-domain feature of the device signal is extracted, and the respiratory rate of the ventilated subject is obtained according to the time-domain feature of the device signal. Specifically, the duration of the inspiratory phase and the duration of the expiratory phase adjacent to the inspiratory phase can be obtained according to the waveform of the device signal, and can be obtained according to the duration of the inspiratory phase and the duration of the expiratory phase respiration rate. Alternatively, the duration of the respiration cycle can be identified according to the waveform of the device signal, and the respiration rate can be obtained according to the duration of the respiration cycle.
  • obtaining the breathing rate of the ventilated subject according to the device signal is realized by performing frequency domain analysis on the device signal. Specifically, the frequency domain feature of the device signal is extracted, and the respiratory rate of the ventilated subject is obtained according to the frequency domain feature of the device signal. Specifically, it is possible to obtain a spectrogram of the device signal, determine the frequency point corresponding to the maximum amplitude in the amplitude-frequency characteristics of the device signal according to the spectrogram, and convert the frequency point corresponding to the maximum amplitude into the respiration rate. It is also possible to obtain the power spectrum diagram of the device signal, determine the frequency point corresponding to the maximum power in the power spectrum characteristic of the device signal according to the power spectrum diagram, and convert the frequency point corresponding to the maximum power into the respiration rate.
  • Obtaining the respiratory rate of the ventilated subject according to the device signal can also be realized by combining time-domain analysis and frequency-domain analysis, that is, selecting one of the results of time-domain analysis and frequency-domain analysis as the final calculation result of respiratory rate, or , weighting the time-domain analysis results and the frequency-domain analysis results to obtain the final respiration rate calculation result.
  • the ROX index can also be calculated according to the respiratory rate, the oxygen saturation of the ventilated subject, and the inhaled oxygen concentration, and at least one item of the ROX index and the trend graph of the ROX index can be displayed.
  • respiration rate monitoring method 400 has many same or similar contents as the respiration rate monitoring method 100 , for details, please refer to the relevant description above, which will not be repeated here.
  • the respiration rate monitoring method 400 of the embodiment of the present application calculates the respiration rate according to the device signal of the device controlling the ventilation flow, which can reduce errors.
  • the respiration rate monitoring method 500 includes the following steps:
  • step S510 at least two signals collected during the process of providing mechanical ventilation to the ventilated subject by the medical ventilation equipment, the at least two signals can reflect the breathing rhythm of the ventilated subject;
  • step S520 a cross-correlation signal is obtained according to the at least two signals
  • step S530 the respiration rate of the ventilated subject is obtained according to the cross-correlation signal.
  • the respiratory rate monitoring method 500 of this embodiment calculates the respiratory rate based on the cross-correlation signals of at least two signals that can reflect the respiratory rhythm. Since the cross-correlation signals can clearly represent the respiratory fluctuations of the ventilated subject, the smaller respiratory fluctuations are amplified. , so the influence of external interference on the recognition of the respiration rate can be reduced, and the respiration state of the ventilated object can be more accurately recognized.
  • the at least two signals capable of reflecting the respiratory rhythm of the ventilated subject include at least two of the following signals: a device signal capable of reflecting the respiratory rhythm, a physiological signal capable of reflecting the respiratory rhythm, and a respiratory signal capable of reflecting the respiratory rhythm.
  • the device signal includes a signal of a device controlling the magnitude of the ventilation flow in the medical ventilation equipment.
  • Devices for controlling ventilation flow in medical ventilation equipment include but are not limited to turbines and valves for controlling ventilation flow in medical ventilation equipment.
  • Physiological signals include, but are not limited to, blood oxygen signals, end-tidal carbon dioxide signals, and esophageal pressure signals of the ventilated subject.
  • Respiration signals include, but are not limited to, flow and pressure signals of mechanical ventilation.
  • the cross-correlation signal can be a cross-correlation signal of at least two different device signals, a cross-correlation signal of at least two different physiological signals, a cross-correlation signal of at least two different respiratory signals, or at least one device signal and at least one A cross-correlation signal of a physiological signal, a cross-correlation signal of at least one device signal and at least one respiratory signal, and the like.
  • a cross-correlation signal can be a cross-correlation signal of at least two different device signals, a cross-correlation signal of at least two different physiological signals, a cross-correlation signal of at least two different respiratory signals, or at least one device signal and at least one A cross-correlation signal of a physiological signal, a cross-correlation signal of at least one device signal and at least one respiratory signal, and the like.
  • the process of providing mechanical ventilation to the ventilated subject includes the process of providing nasal high-flow oxygen therapy to the ventilated subject.
  • calculating the respiration rate based on cross-correlation signals can reduce errors and improve accuracy.
  • obtaining the respiration rate of the ventilated subject according to the cross-correlation signal includes: extracting the time-domain feature of the cross-correlation signal, and obtaining the respiration rate of the ventilated subject according to the time-domain feature of the cross-correlation signal; or, extracting the frequency-domain feature of the cross-correlation signal , according to the frequency domain characteristics of the cross-correlation signal, the respiratory rate of the ventilated subject is obtained.
  • the respiratory rate of the ventilated subject can also be obtained by combining the time domain and the frequency domain.
  • the ROX index can also be calculated according to the respiratory rate, the oxygen saturation of the ventilated subject, and the inhaled oxygen concentration, and at least one item of the ROX index and the trend graph of the ROX index can be displayed.
  • respiration rate monitoring method 500 has many same or similar contents as the respiration rate monitoring method 100 , for details, please refer to the relevant description above, which will not be repeated here.
  • the respiratory rate monitoring method 500 of the embodiment of the present application calculates the respiratory rate according to the cross-correlation signal, which can improve the accuracy of the respiratory rate calculation.
  • the respiration rate monitoring method 600 includes the following steps:
  • step S610 during the process of the medical ventilation equipment providing nasal high-flow oxygen therapy to the ventilated subject, a signal capable of reflecting the respiratory rhythm of the ventilated subject is acquired;
  • step S620 the respiratory rate of the ventilated subject is obtained according to the signal capable of reflecting the respiratory rhythm of the ventilated subject;
  • step S630 the breathing rate of the ventilated subject is displayed.
  • the respiration rate monitoring method 600 of the embodiment of the present application calculates and displays specific values of the respiration rate during nasal high-flow oxygen therapy, which can provide quantitative reference for users.
  • the respiration rate may be calculated by any method for calculating the respiration rate described above, or other suitable methods may be used to calculate the respiration rate.
  • a trend graph of the respiration rate can also be generated and displayed.
  • the ROX index can also be calculated according to the breathing rate, and displayed as an evaluation index of whether to perform tracheal intubation.
  • a trend graph of the ROX index can be generated and displayed.
  • ROX index (blood oxygen saturation/inhaled oxygen concentration)/respiration rate.
  • the blood oxygen saturation and inspired oxygen concentration of the ventilated subject can be obtained through a ventilator or a monitor.
  • a trend graph of the ROX index may be displayed in the first display area of the display interface, and signs corresponding to different ROX threshold ranges may be displayed in the trend graph of the ROX index.
  • the ROX threshold range can be set by the user.
  • the ROX threshold range at least includes a first threshold range indicating successful treatment and a second threshold range indicating the risk of intubation
  • the coordinate area corresponding to the first threshold range can be displayed as Green
  • the coordinate area corresponding to the second threshold range can be displayed in red
  • the coordinate area corresponding to the second threshold range can be displayed in red
  • the coordinate area corresponding to the first threshold range and the coordinate area corresponding to the second threshold range are transition areas, which may be displayed in gray.
  • real-time respiratory parameters and/or physiological parameters of the ventilated subject can also be displayed in the second display area of the display interface, including but not limited to flow rate, inspired oxygen concentration, ROX index, blood oxygen saturation and respiratory rate, etc., the above parameters Refresh in real time.
  • the display interface includes a first area and a second area, the first area displays a trend graph of the ROX index, and the second area displays real-time refreshed respiratory parameters and/or physiological parameters, so based on this display interface, the user can simultaneously view the ROX The changing trend of the index and the real-time monitoring parameters of the user.
  • the nasal high-flow oxygen therapy mode when a selection instruction for the target time in the trend graph of the ROX index is received, relevant parameters corresponding to the target time are displayed, including but not limited to flow, inhaled oxygen concentration, ROX index, Blood oxygen saturation and respiration rate for user viewing.
  • relevant parameters corresponding to the target moment may be displayed in the first area near the trend graph of the ROX index.
  • the respiration rate monitoring method 600 has many same or similar contents as the respiration rate monitoring method 100 , for details, please refer to the relevant description above, which will not be repeated here.
  • the respiration rate monitoring method 600 of the embodiment of the present application calculates and displays the respiration rate of the ventilated subject during nasal high-flow oxygen therapy, which can provide quantitative reference basis for the user.
  • the respiration rate monitoring method 700 includes the following steps:
  • step S710 one or more signals collected during the process of providing mechanical ventilation to the ventilated subject by the medical ventilation equipment, the one or more signals can reflect the breathing rhythm of the ventilated subject;
  • step S720 extract the time domain information and/or frequency domain information of the one or more signals; input the time domain information and/or frequency domain information into a pre-trained machine learning model, and output the respiratory rate of the ventilated subject.
  • the respiration rate monitoring method 700 of the embodiment of the present application combines time domain analysis or frequency domain analysis to obtain the respiration rate of the ventilated subject. The difference is that the respiration rate monitoring method 700 of the embodiment of the present application uses time domain information and/or frequency domain information as a machine learning model, and the machine learning model directly outputs the respiration rate of the ventilated subject.
  • the time domain information and the frequency domain information may respectively refer to the time domain features and the frequency domain features mentioned above, or may be other information different from the time domain features and the frequency domain features mentioned above, for example, the time domain
  • the information may also be a signal obtained by preprocessing the time-domain signal, and the frequency-domain information may also be a spectrogram, a power spectrogram, or a processed spectrogram or power spectrogram, and the like.
  • at least one signal can also be input into the machine learning model together with time domain information and/or frequency domain information.
  • a signal set that can reflect the respiratory rhythm can be constructed, the time domain information and/or frequency domain information of the signal can be extracted, and the real value of the respiratory rate can be obtained, and the time domain information of the signal and the /or the frequency domain information and the actual value of the respiration rate are used as training samples to train the network model to obtain a trained machine learning model, so that the trained machine learning model can output accurate respiration rate calculation results.
  • the calculation steps of the algorithm can be simplified to reduce the complexity of the machine learning model, so that the machine learning model can be well applied to embedded devices.
  • the patient's autonomous activity is strong, and the movement error caused by the patient's excessively strong autonomous activity will lead to drastic changes in device signals and physiological signals. It requires a machine learning model with strong anti-interference ability to accurately Identify the patient's respiration rate. Therefore, in the model training stage, by simulating extreme application scenarios, the ability of the machine learning model to recognize the respiratory rate in extreme scenarios can be specifically optimized, thereby improving the anti-interference ability of the machine learning model.
  • respiration rate monitoring method 700 has many same or similar contents as the respiration rate monitoring method 100 , for details, please refer to the relevant description above, which will not be repeated here.
  • the respiration rate monitoring method 700 of the embodiment of the present application calculates the respiration rate according to time domain information and/or frequency domain information, which can improve the accuracy of respiration rate calculation.
  • the embodiment of the present application also provides a medical ventilation device, which includes a ventilator, an anesthesia machine, a monitor and other medical devices with a ventilation function.
  • Medical ventilation equipment is used to replace, control or change the physiological respiration of the ventilated subject, improve the respiratory function of the ventilated subject and reduce the respiratory consumption of the ventilated subject by increasing the lung ventilation.
  • the medical ventilation device 800 may be a medical ventilation device with nasal high flow oxygen therapy function.
  • the medical ventilation device 800 can be used to implement the breathing rate monitoring method described above, and only the main functions of the medical ventilation device 800 will be described below, and other specific details can be referred to above.
  • the medical ventilation device 800 includes a pressure generating device 810 and a processor 820 , the pressure generating device 810 is used to communicate with the ventilation circuit, so as to deliver gas at a set pressure to the ventilated subject through the ventilation circuit.
  • the pressure generating device 810 includes a turbine, a gas cylinder, etc., and the processor 820 controls the ventilation flow rate by controlling the pressure generating device 810 .
  • the device for controlling the ventilation flow rate in the medical ventilation equipment may also include a valve, such as a proportional valve, a large diameter valve, and the like.
  • the medical ventilation device 800 may also include sensors for collecting respiratory signals during ventilation.
  • the sensors include but are not limited to pressure sensors and flow sensors.
  • the pressure sensors are used to measure the gas pressure of mechanical ventilation, and the flow sensors are used to measure the gas flow in the ventilation circuit.
  • Sensors such as pressure sensors and flow sensors are connected to the processor 820 in communication, and the measured signals are sent to the processor 820 .
  • the processor 820 is used to control the pressure generating device 810 to generate gas at a set pressure, and the processor 820 is also used to execute the respiration rate monitoring method 100, the respiration rate monitoring method 400, the respiration rate monitoring method 500, and the respiration rate monitoring method described above. Method 600 or respiration rate monitoring method 700 to detect respiration rate of a ventilated subject. More details of the breathing rate monitoring method can be referred to above, and will not be repeated here.
  • the disclosed devices and methods may be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components can be combined or May be integrated into another device, or some features may be omitted, or not implemented.
  • the various component embodiments of the present application may be realized in hardware, or in software modules running on one or more processors, or in a combination thereof.
  • a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all functions of some modules according to the embodiments of the present application.
  • DSP digital signal processor
  • the present application can also be implemented as an apparatus program (for example, a computer program and a computer program product) for performing a part or all of the methods described herein.
  • Such a program implementing the present application may be stored on a computer-readable medium, or may be in the form of one or more signals.
  • Such a signal may be downloaded from an Internet site, or provided on a carrier signal, or provided in any other form.

Landscapes

  • Health & Medical Sciences (AREA)
  • Emergency Medicine (AREA)
  • Pulmonology (AREA)
  • Engineering & Computer Science (AREA)
  • Anesthesiology (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Hematology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

一种呼吸率监测方法（100）及医疗通气设备，方法（100）包括：获取医疗通气设备为通气对象提供机械通气的过程中采集的第一信号和第二信号，第一信号和第二信号能够反映通气对象的呼吸节律（S110）；提取第一信号的频域特征，根据第一信号的频域特征得到通气对象的第一呼吸率（S120）；提取第二信号的时域特征，根据第二信号的时域特征得到通气对象的第二呼吸率（S130）；根据第一呼吸率和第二呼吸率得到通气对象的第三呼吸率（S140）。该呼吸率监测方法（100）能够提高呼吸率监测的准确性。

Description

呼吸率监测方法及医疗通气设备
说明书
技术领域
本申请涉及医疗设备领域，更具体地涉及一种呼吸率监测方法及医疗通气设备。
背景技术
在机械通气过程中，氧疗(Oxygen Therapy)是一种用于纠正病人低氧血症，通过吸入高浓度氧气使血浆中溶解氧量增加来改善组织供氧的常规手段。广义上的氧疗指的是使用高于空气氧体积分数的气体对患者进行治疗，通俗地讲，就是改变病人吸入气体中的氧气浓度，改变浓度的方式取决于病人是采用哪种方式进行吸氧。无论是对于接受插管有创通气的病人、还是对于接受无创通气、体外膜氧合治疗的病人来说，氧疗都是适用的，医生会根据病人的病情、状态来选择氧疗的时机、方式、以及氧疗目标、时长。大量的研究以及实践证明了氧疗对病人治疗过程的有效性，同时，氧疗过程中的用氧安全与氧疗规范问题也逐渐引起重视。
呼吸率的识别一般是通过患者的气道压力或者是吸气流量变化进行识别，而在氧疗过程中，流速和压力波形往往容易受到各种干扰，例如泄露、氧疗导管的松动、导管的积水或患者的活动等，从而影响呼吸率的准确性。
发明内容
在发明内容部分中引入了一系列简化形式的概念，这将在具体实施方式部分中进一步详细说明。本发明的发明内容部分并不意味着要试图限定出所要求保护的技术方案的关键特征和必要技术特征，更不意味着试图确定所要求保护的技术方案的保护范围。
本申请实施例第一方面提供了一种呼吸机的呼吸率监测方法，包括：
获取医疗通气设备为通气对象提供机械通气的过程中采集的第一信号和第二信号，所述第一信号和所述第二信号能够反映所述通气对象的呼吸节律；
提取所述第一信号的频域特征，根据所述第一信号的频域特征得到所述 通气对象的第一呼吸率；
提取所述第二信号的时域特征，根据所述第二信号的时域特征得到所述通气对象的第二呼吸率；
根据所述第一呼吸率和所述第二呼吸率得到所述通气对象的第三呼吸率。
本申请实施例第二方面提供了一种呼吸率监测方法，所述方法包括：
在医疗通气设备为通气对象提供机械通气的过程中，采集控制所述医疗通气设备通气流量大小的器件的器件信号，所述器件信号能够反映所述通气对象的呼吸节律；
根据所述器件信号得到所述通气对象的呼吸率。
本申请实施例第三方面提供了一种呼吸率监测方法，所述方法包括：
获取医疗通气设备为通气对象提供机械通气的过程中采集的至少两种信号，所述至少两种信号能够反映所述通气对象的呼吸节律；
根据所述至少两种信号得到互相关信号；
根据所述互相关信号得到所述通气对象的呼吸率。
本申请实施例第四方面提供了一种呼吸率监测方法，所述方法包括：
在医疗通气设备为通气对象提供经鼻高流量氧疗的过程中，获取能够反映所述通气对象呼吸节律的信号；
根据所述能够反映所述通气对象呼吸节律的信号得到所述通气对象的呼吸率；
显示所述通气对象的呼吸率。
本申请实施例第五方面提供了一种呼吸率监测方法，所述方法包括：
获取医疗通气设备为通气对象提供机械通气的过程中采集的一种或多种信号，所述一种或多种信号能够反映所述通气对象的呼吸节律；
提取所述一种或多种信号的时域信息和/或频域信息；将所述时域信息和/或频域信息输入到预先训练好的机器学习模型中，并输出所述通气对象的呼吸率。
本申请实施例第六方面提供了一种医疗通气设备，所述医疗通气设备包括：
压力产生装置，所述压力产生装置用于与通气管路连通，以通过所述通气管路向通气对象输送设定压力的气体；
处理器，连接所述压力产生装置，用于控制所述压力产生装置产生所述设定压力的气体；所述处理器还用于执行如上所述的呼吸率监测方法。
本申请实施例提供的呼吸率监测方法及医疗通气设备能够提高呼吸率监测的准确性。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
在附图中：
图1示出根据本申请一实施例的呼吸率监测方法的示意性流程图；
图2示出根据本申请一实施例的第一信号的波形的示意图；
图3示出根据本申请一实施例的第一信号的频谱的示意图；
图4示出根据本申请另一实施例的呼吸率监测方法的示意性流程图；
图5示出根据本申请另一实施例的呼吸率监测方法的示意性流程图；
图6示出根据本申请另一实施例的呼吸率监测方法的示意性流程图；
图7示出根据本申请另一实施例的呼吸率监测方法的示意性流程图；
图8示出根据本申请一实施例的医疗通气设备的示意性框图。
具体实施方式
为了使得本申请的目的、技术方案点更为明显，下面将参照附图详细描述根据本申请的示例实施例。显然，所描述的实施例仅仅是本申请的一部分实施例，而不是本申请的全部实施例，应理解，本申请不受这里描述的示例实施例的限制。基于本申请中描述的本申请实施例，本领域技术人员在没有付出创造性劳动的情况下所得到的所有其它实施例都应落入本申请的保护范围之内。
在下文的描述中，给出了大量具体的细节以便提供对本申请更为彻底的理解。然而，对于本领域技术人员而言显而易见的是，本申请可以无需一个或多个这些细节而得以实施。在其他的例子中，为了避免与本申请发生混淆，对于本领域公知的一些技术特征未进行描述。
应当理解的是，本申请能够以不同形式实施，而不应当解释为局限于这里提出的实施例。相反地，提供这些实施例将使公开彻底和完全，并且将本 申请的范围完全地传递给本领域技术人员。
在此使用的术语的目的仅在于描述具体实施例并且不作为本申请的限制。在此使用时，单数形式的“一”、“一个”和“所述/该”也意图包括复数形式，除非上下文清楚指出另外的方式。还应明白术语“组成”和/或“包括”，当在该说明书中使用时，确定所述特征、整数、步骤、操作、元件和/或部件的存在，但不排除一个或更多其它的特征、整数、步骤、操作、元件、部件和/或组的存在或添加。在此使用时，术语“和/或”包括相关所列项目的任何及所有组合。
为了彻底理解本申请，将在下列的描述中提出详细的结构，以便阐释本申请提出的技术方案。本申请的可选实施例详细描述如下，然而除了这些详细描述外，本申请还可以具有其他实施方式。
下面首先参照图1描述本申请一实施例的呼吸率监测方法，图1是本申请一实施例中的呼吸率监测方法100的示意性流程图，具体包括如下步骤：
在步骤S110，获取医疗通气设备为通气对象提供机械通气的过程中采集的第一信号和第二信号，所述第一信号和所述第二信号能够反映所述通气对象的呼吸节律；
在步骤S120，提取所述第一信号的频域特征，根据所述第一信号的频域特征得到所述通气对象的第一呼吸率；
在步骤S130，提取所述第二信号的时域特征，根据所述第二信号的时域特征得到所述通气对象的第二呼吸率；
在步骤S140，根据所述第一呼吸率和所述第二呼吸率得到所述通气对象的第三呼吸率。
其中，医疗通气设备包括呼吸机、麻醉机、监护仪等，为通气对象提供机械通气的过程包括但不限于为通气对象提供经鼻高流量氧疗的过程。氧疗为用于纠正病人低氧血症，通过吸入高浓度氧气使血浆中溶解氧量增加来改善组织供氧的过程，经鼻高流量氧疗是通过鼻塞导管直接将一定氧浓度的空氧混合高流量气体输送给病人的氧疗方式，具有高流量、精确氧浓度以及加温湿化等特点。本申请实施例的呼吸率监测方法100能够在经鼻高流量氧疗的过程中实现呼吸率的准确监测。
具体地，在为通气对象提供机械通气的过程中，采集第一信号和第二信号，第一信号和第二信号为能够反映通气对象的呼吸节律的信号。示例性地， 第一信号包括以下至少一种：能够反映通气对象呼吸节律的器件信号、生理信号、呼吸信号，以及器件信号、生理信号和呼吸信号中至少两种信号的衍生信号。类似地，第二信号也可以包括能够反映通气对象呼吸节律的器件信号、生理信号、呼吸信号，以及器件信号、生理信号和呼吸信号中至少两种信号的衍生信号。第一信号和第二信号可以是不同的信号，例如第一信号为某种器件信号，第二信号为某种生理信号。第一信号和第二信号也可以是相同的信号，例如第一信号和第二信号均为同种器件信号，后续对同种信号进行不同的处理以得到不同的处理结果。
示例性地，能够反映呼吸节律的器件信号包括医疗通气设备中控制通气流量大小的器件的信号。医疗通气设备完成一个呼吸周期的机械通气需要经历吸气触发、吸气过程、吸呼切换及呼气过程。当通气对象主动吸气时，医疗通气设备感知到通气对象的吸气动作，通过控制通气流量大小的器件控制通气管路中的气体流量以开始送气。因此，根据控制通气流量大小的器件的信号可以得到通气对象的呼吸率。控制通气流量大小的器件的信号可以是器件的控制信号，即处理器向器件输出的信号；控制通气流量大小的器件的信号也可以是器件的采样信号，即器件反馈至处理器的信号。
示例性地，医疗通气设备中控制通气流量大小的器件可以包括医疗通气设备中控制通气流量的涡轮。涡轮一般是指离心式空气压缩机，其工作原理是控制涡轮转速，通过转速的改变调节涡轮的输出压力，从而调节气流的流速。具体地，可以根据目标流量对应的目标压力和实时流量对应的实时压力得到压力差，并根据实时压力和压力差得到涡轮电机的目标转速，控制涡轮电机以目标转速运行，从而获得目标压力对应的目标流量。也就是说，涡轮是基于压力的控制来间接实现流量的控制。由于在通气对象处于吸气相时涡轮的电机的转速增加以增大通气管路内的流量，在通气对象处于呼气相时涡轮电机的转速降低以减小通气管路内的流量，因此可以根据涡轮的转速信号或驱动涡轮转动的电路信号识别呼吸频率。
医疗通气设备中控制通气流量大小的器件也可以包括医疗通气设备中控制通气流量的阀门。控制通气流量的阀门包括比例阀、大通径阀等。阀门一般为电控阀门，医疗通气设备通过调节阀门的驱动电流或驱动电压控制阀门直线运动，通过改变阀门的开度调节通气管路内流量的大小，在吸气相增加阀门的开度以增加气体流量，在呼气相减小阀门的开度以减小气体流量。阀 门的信号主要包括阀门的开度信号。与涡轮相比，阀门对气体流量的控制是直接的，因而反馈调节的时间较短。
示例性地，生理信号包括以下至少一种：通气对象的血氧信号、呼末二氧化碳信号、食道压信号。生理信号可以由外部传感器采集并发送至医疗通气设备。其中，血氧信号即血氧饱和度信号，代表血液中血氧的浓度，随呼吸而周期性波动，因而反映通气对象的呼吸节律。呼末二氧化碳信号即在呼吸过程中测得的二氧化碳浓度曲线，曲线的上升支对应呼气阶段，下降支对应吸气阶段，可以据此识别吸气相和呼气相。食道压信号代表通气对象食道内的压力，在通气对象自主吸气时，由于呼吸肌的收缩，导致胸腔容积增大，使得食道压减小；在吸气末段，由于自主吸气趋近结束，呼吸肌逐渐舒张，食道压逐渐升高，因此根据食道压信号可以识别出通气对象的吸气段和呼气段。以上列举的生理信号仅作为示例，除了血氧信号、呼末二氧化碳信号、食道压信号以外，生理信号也可以包括其他任意能够反映通气对象呼吸节律的信号，例如跨肺压信号、平台压信号等。
示例性地，呼吸信号是直接反映呼吸状态的信号，呼吸信号可以是医疗通气设备自身采集的信号，具体包括以下至少一种：机械通气的流量信号和压力信号。流量信号可以是送气流量信号或呼气流量信号。压力信号可以是病人端的压力信号或机器端的压力信号。可选地，呼吸信号也可以包括潮气量信号等。流量信号和压力信号能够直接地反映通气状态，因而能准确识别出呼吸率。
第一信号和第二信号也可以是上述任意至少两种信号的衍生信号。示例性地，衍生信号可以包括互相关信号，互相关信号能够明显地表征出通气对象的呼吸波动，将较小的呼吸波动幅度放大，因此可以减少外界干扰对呼吸率识别的影响，更准确地识别通气对象的呼吸状态。
以流量信号和压力信号为例，获得流量信号和压力信号的互相关信号包括按照预设信号采样率和预设采样时间，对流量信号和压力信号进行互相关计算，获得互相关信号。信号采样率和采样时间可以根据实际需求设定。
具体地，根据预设信号采样率，分别获取预设采样时间内压力信号对应的第一采样值，以及流量信号对应的第二采样值；对第一采样值和第二采样值进行互相关计算，获得互相关数据。预设信号采样率表示在1s内获取的压力值的个数，以及流量值的个数，而预设采样时间具体限定了获取压力值和 流量值的时间，也就是说，若预设信号采样率为1KHZ，预设采样时间为20ms，则预设信号采样率为1KHZ表示在1s内可以获取压力信号的1000个采样值，以及流量信号的1000个采样值，预设采样时间为20ms则表示实际获取20ms的压力信号和流量信号，由于预设信号采样率为1KHZ，因此在20ms内可以获取压力信号的20个采样值和流量信号的20个采样值。在计算互相关数据时，第一采样值即为压力信号的20个采样值，第二采样值即为流量信号的20个采样值，对第一采样值和第二采样值进行互相关计算，即可得到某一时刻压力信号和流量信号的互相关数据。
可以理解的是，第一采样值和第二采样值的数量由预设信号采样率和预设采样时间确定，可以为多个，但是两者数量，且时间点对应，即在预设采样时间的某一时刻获取一个第一采样值时，同时将获取一个对应的第二采样值。
继续以预设信号采样率为1KHZ，预设采样时间为20ms为例，可以根据以下公式计算压力信号和流量信号的互相关数据：
Figure PCTCN2021129068-appb-000001
其中，Corr(k)表示k时刻的压力信号和流量信号的互相关数据，Flow(i)表示i时刻的流速值，Pressure(i)表示i时刻的压力值。
可以理解的是，在本发明的实施例中，上述预设信号采样率为1KHZ，预设采样时间为20ms，因此压力信号和流量信号对应的采样值均为20个，在计算k时刻的压力和流速的互相关数据时，可以根据包括k时刻的压力值和流速值，以及k时刻的前19个时刻的压力值和流速值，代入上述公式中进行计算，以获得k时刻的压力和流速的互相关数据。
在一个具体的实施例中，由于器件信号的频域特征较为明显，呼吸信号的时域特征较为明显，因此第一信号可以是器件信号，例如涡轮的电流信号或转速信号，第二信号可以是呼吸信号，例如流量信号或压力信号。第二信号也可以是至少两种呼吸信号的互相关信号。
在步骤S120，提取第一信号的频域特征，根据第一信号的频域特征得到通气对象的第一呼吸率。频域特征体现了信号的全局频率特征，几乎不提供时域上的频率信息，因此根据第一信号的频域特征得到通气对象的第一呼吸率能够得到更准确的计算结果。
为了提取第一信号的频域特征，首先可以将第一信号从时域变换到频域， 即将以时间轴为坐标表示的信号变换为以频率轴为坐标表示的信号。由于第一信号反映通气对象的呼吸节律，变换到频域以后，其频域信号中呼吸频率对应的频点应具有最大的幅度。
因此，在一个实施例中，提取第一信号的频域特征包括：获取第一信号的频谱图，根据频谱图确定第一信号的幅频特性中最大幅度对应的频点；根据第一信号的频域特征得到通气对象的第一呼吸率包括：将最大幅度对应的频点转换为第一呼吸率。其中，可以通过离散傅里叶变换(FFT)获取第一信号的频谱图，具体地，从第一信号中提取采样点，对采样点进行离散傅里叶变化之后，就可以得到频率点及其对应的幅度特性。
在另一实施例中，也可以获取第一信号的功率谱图，根据功率谱图确定第一信号的功率谱特性中最大功率对应的频点，将最大功率对应的频点转换为第一呼吸率。功率谱图表示信号功率随着频率的变化关系，其横坐标为频率，纵坐标为功率。示例性地，在获取第一信号的功率谱图时，可以采用经典谱估计方法或现代谱估计方法，经典谱估计方法包括直接法、间接法等，现代谱估计方法包括参数模型法、非参数模型法等。除了频谱图和功率谱图之外，也可以采用其他频域表示方法提取第一信号的频域特征，例如能量谱、小波变换等。
示例性地，在提取第一信号的频域特征之前，还可以对第一信号进行预处理，预处理包括归一化处理和滤波处理中的至少一种。归一化处理对信号的量程进行了统一，便于进行后续计算；滤波处理可以使信号的信噪比得到提升，提高了呼吸率识别的准确性。其中，可以针对信号中的杂波信号设计相应的数字滤波器，以滤除杂波信号，防止如管道抖动等极端情况造成的信号改变而影响呼吸率的计算。
在步骤S130，提取第二信号的时域特征，根据第二信号的时域特征得到通气对象的第二呼吸率。步骤S130通过时域识别确定了通气对象的呼吸率，时域识别是根据第二信号的波形计算呼吸率，计算速度更快。
在一个实施例中，提取第二信号的时域特征包括：根据第二信号的波形得到吸气相的持续时间和与吸气相相邻的呼气相的持续时间，之后根据吸气相的持续时间和呼气相的持续时间得到第二呼吸率。一个吸气相和一个呼气相构成一个呼吸周期。示例性地，可以根据第二信号的波形识别吸气相和结束点和呼气相的结束点，由此得到吸气相和呼气相的持续时间；根据吸气相 和呼气相的持续时间可得到呼吸周期的时长，根据呼吸周期的时长即可得到呼吸率，即每分钟的呼吸次数。
在另一个实施例中，在提取第二信号的时域特征时，也可以直接根据第二信号的波形识别呼吸周期的时长，而不具体区分吸气相和呼气相。例如，可以根据第二信号中相邻两个波峰之间的间距得到呼吸周期的时长。得到呼吸周期的时长之后，根据呼吸周期的时长即可得到第二呼吸率。
在步骤S140，根据第一呼吸率和第二呼吸率得到通气对象的第三呼吸率。由于第一呼吸率和第二呼吸率分别为基于频域和时域分析得到的结果，根据第一呼吸率和第二呼吸率得到的第三呼吸率融合了信号的频域特性和时域特性，因而提高了呼吸率计算的及时性和准确性。
示例性地，根据第一呼吸率和第二呼吸率得到通气对象的第三呼吸率，包括：根据第一信号的频域特征得到第一信号的第一特征指数；根据第二信号的时域特征得到第二信号的第二特征指数；根据第一特征指数和第二特征指数选择第一呼吸率和第二呼吸率之一作为第三呼吸率；或者，根据第一特征指数和第二特征指数对第一呼吸率和第二呼吸率进行加权计算，以得到第三呼吸率。其中，第一特征指数和第二特征指数分别表征第一信号和第二信号的有效性、强弱、变化幅度等。根据第一特征指数和第二特征指数对第一呼吸率和第二呼吸率进行加权计算包括根据第一特征指数和第二特征指数对第一呼吸率和第二呼吸率进行加权平均。
示例性地，第一特征指数和第二特征指数可以实现为信号的评级，例如一级表示信号的有效性较弱，不能很好地体现呼吸节律；五级表示信号的有效性较强，能够更好地体现呼吸节律。在该实施例中，若根据第一特征指数和第二特征指数选择第一呼吸率和第二呼吸率之一作为第三呼吸率，则可以选择第一呼吸率和第二呼吸率中评级更高的呼吸率作为第三呼吸率。若根据第一特征指数和第二特征指数对第一呼吸率和第二呼吸率进行加权平均，以得到第三呼吸率，则可以根据第一特征指数得到第一权重，根据第二特征指数得到第二权重，根据第一权重和第二权重对第一呼吸率和第二呼吸率进行加权平均，以得到第三呼吸率。其中，信号评级越高，在加权平均时对应的权重越大。
或者，第一特征指数和第二特征指数也可以实现为第一信号的第一权重和第二信号的第二权重，即直接根据第一信号的频域特征得到第一权重，根 据第二信号的时域特征得到第二权重。在该实施例中，若根据第一特征指数和第二特征指数选择第一呼吸率和第二呼吸率之一作为第三呼吸率，则当第一权重为1、第二权重为0时，选择第一呼吸率作为第三呼吸率，当第一权重为0，第二权重为1时，选择第二呼吸率作为第三呼吸率。若根据第一特征指数和第二特征指数对第一呼吸率和第二呼吸率进行加权平均，则直接根据第一权重和第二权重对第一呼吸率和第二呼吸率进行加权平均。
示例性地，根据第一信号的频域特征得到第一特征指数，包括：根据第一信号的频谱图的平均幅度、第一信号的频谱图的最大幅度、第一信号的功率谱图的平均功率和第一信号的功率谱图的最大功率中的至少一个得到第一特征指数。例如，若频谱图的最大幅度与平均幅度的比值越大，说明呼吸节律在频域上体现得越明显，根据第一信号的频域特征得到的第一呼吸率越准确，相应地第一特征指数越高。基于类似的原理，若功率谱图的最大功率与平均功率的比值越大，则第一特征指数越高。
示例性地，根据第二信号的时域特征得到第二特征指数包括根据第二信号的变化幅度得到第二特征指数。根据第二信号的时域特征得到第二特征指数还可以包括根据基于第二信号计算得到的历史第二呼吸率的变化幅度得到第二特征指数。表征历史第二呼吸率的变化幅度的指标包括但不限于历史第二呼吸率的方差、标准差等。第二信号的变化幅度越小、历史第二呼吸率的变化幅度越大，说明呼吸节律在时域上体现得越不明显，因而第二特征指数越低。
在一些实施例中，可以采用机器学习模型输出第一特征指数和第二特征指数。具体地，根据第一信号的频域特征得到第一信号的第一特征指数，包括将第一信号的频域特征输入到训练好的第一机器学习模型，并获取第一机器学习模型输出的第一特征指数。根据第二信号的时域特征得到第二信号的第二特征指数，包括将第二信号的时域特征输入到训练好的第二机器学习模型，并获取第二机器学习模型输出的第二特征指数。
在第一机器学习模型的训练阶段，构建能够反映呼吸节律的信号集合、提取信号的频域特征并获取用户为其标注的特征指数，将信号的频域特征及用户标注的特征指数作为训练样本，对网络模型进行训练，以得到训练好的机器学习模型。其中，机器学习模型可以是传统的机器学习模型或深度学习模型，包括但不限于神经网络、支持向量机、线性判别分析等；训练方法包 括但不限于线性回归、梯度下降等模型训练方法。示例性地，可以学习一个频域特征到第一特征指数的最优映射函数，使得频域特征映射得到的第一特征指数与实际标定的特征指数的误差最小。第一机器学习模型输出的第一特征指数可以实现为评级或权重的形式。在训练机器学习模型时，训练目标为使第一特征指数能够区分能量接近的频率成分的主次关系，准确识别到由呼吸引起的频率成分，修正不同频率成分导致的呼吸率计算误差。
类似地，在第二机器学习模型的训练阶段，构建能够反映呼吸节律的信号集合、提取信号的时域特征并获取用户为其标注的特征指数，将信号的时域特征及用户标注的特征指数作为训练样本，对网络模型进行训练，以得到训练好的机器学习模型。第二机器学习模型输出的第二特征指数也可以实现为评级或权重的形式。
得到第三呼吸率之后，在一个实施例中，可以直接显示第三呼吸率。由于根据本申请实施例计算得到的第三呼吸率的准确度较高，因而直接显示第三呼吸率的具体数值。此外，也可以显示第三呼吸率的趋势图，趋势图反映了第三呼吸率随时间变化的动态趋势。第三呼吸率的趋势图可以有折线图、柱状图等各种图形化的表现方式。
在为通气对象提供经鼻高流量氧疗的场景下，若出现预后较差的问题，可以将ROX指数作为是否进行气管插管的评价指标。例如，对于重症肺炎患者来说，在进行经鼻高流量氧疗12小时后，若ROX指数大于4.88，则治疗成功率更大，插管率更低；若ROX指数小于3.85，则需要进行气管插管。
因此，在得到第三呼吸率之后，可以根据第三呼吸率、通气对象的血氧饱和度和吸入氧浓度计算ROX指数，并显示ROX指数。其中，ROX指数＝(血氧饱和度/吸入氧浓度)/呼吸率。通气对象的血氧饱和度和吸入氧浓度可以通过呼吸机或者监护仪获得，呼吸率采用如上文所述的时域分析与频域分析结合所得到的第三呼吸率，由于时域与频域结合的方法能够有效的减弱干扰信号的影响，识别出通气对象的真实呼吸率，因而能够提高ROX指数计算的有效性和稳定性。除了直接显示ROX指数的数值以外，还可以显示ROX指数的趋势图，用于反映ROX指数随时间变化的动态趋势。
基于以上描述，本申请实施例的呼吸率监测方法200结合时域分析和频域分析共同计算呼吸率，能够提高呼吸率监测的准确性。尤其是在经鼻高流量氧疗场景下，而使用本申请实施例的呼吸率监测方法200，基于提供经鼻 高流量氧疗的呼吸机自身即可实现呼吸率的计算，无需连接多导连的监护仪进行呼吸率监测。
下面，将参考图4描述根据本申请另一实施例的呼吸率监测方法。如图4所示，呼吸率监测方法400包括如下步骤：
在步骤S410，在医疗通气设备为通气对象提供机械通气的过程中，采集控制所述医疗通气设备通气流量大小的器件的器件信号，所述器件信号能够反映所述通气对象的呼吸节律；
在步骤S420，根据所述器件信号得到所述通气对象的呼吸率。
本实施例的呼吸率监测方法400在机械通气的过程中，根据控制医疗通气设备通气流量大小的器件的器件信号测量通气对象的呼吸率，与根据呼吸信号测量呼吸率相比，根据器件信号测量呼吸率能够减少各种干扰因素导致的误差。在一个实施例中，为通气对象提供机械通气的过程包括为通气对象提供经鼻高流量氧疗的过程。在经鼻高流量氧疗的过程中，根据器件信号测量呼吸率更能够避免由于气体泄露、氧疗导管的松动、导管的积水或者患者的活动等干扰导致的误差。
示例性地，医疗通气设备中控制通气流量大小的器件可以包括医疗通气设备中控制通气流量的涡轮。涡轮一般是指离心式空气压缩机，其工作原理是控制涡轮转速，通过转速的改变调节涡轮的输出压力，从而调节气流的流速。具体地，可以根据目标流量对应的目标压力和实时流量对应的实时压力得到压力差，并根据实时压力和压力差得到涡轮电机的目标转速，控制涡轮电机以目标转速运行，从而获得目标压力对应的目标流量。也就是说，涡轮是基于压力的控制来间接实现流量的控制。由于在通气对象处于吸气相时涡轮的电机的转速增加以增大通气管路内的流量，在通气对象处于呼气相时涡轮电机的转速降低以减小通气管路内的流量，因此可以根据涡轮的转速信号或驱动涡轮转动的电路信号识别呼吸频率。
医疗通气设备中控制通气流量大小的器件也可以包括医疗通气设备中控制通气流量的阀门。控制通气流量的阀门包括比例阀、大通径阀等。阀门一般为电控阀门，医疗通气设备通过调节阀门的驱动电流或驱动电压控制阀门直线运动，通过改变阀门的开度调节通气管路内流量的大小，在吸气相增加阀门的开度以增加气体流量，在呼气相减小阀门的开度以减小气体流量。阀门的信号主要包括阀门的开度信号。与涡轮相比，阀门对气体流量的控制是 直接的，因而反馈调节的时间较短。
在一个实施例中，根据器件信号得到通气对象的呼吸率是通过对器件信号进行时域分析而实现的。具体地，提取器件信号的时域特征，根据器件信号的时域特征得到通气对象的呼吸率。具体地，可以根据器件信号的波形得到吸气相的持续时间和与吸气相相邻的呼气相的持续时间，根据所述吸气相的持续时间和所述呼气相的持续时间得到呼吸率。或者，可以根据器件信号的波形识别呼吸周期的时长，根据呼吸周期的时长得到呼吸率。
在另一个实施例中，根据器件信号得到通气对象的呼吸率是通过对器件信号进行频域分析而实现的。具体地，提取器件信号的频域特征，根据器件信号的频域特征得到通气对象的呼吸率。具体地，可以获取器件信号的频谱图，根据频谱图确定器件信号的幅频特性中最大幅度对应的频点，将最大幅度对应的频点转换为呼吸率。也可以获取器件信号的功率谱图，根据功率谱图确定器件信号的功率谱特性中最大功率对应的频点，将最大功率对应的频点转换为呼吸率。
根据器件信号得到通气对象的呼吸率也可以是结合时域分析与频域分析共同实现的，即在时域分析的结果和频域分析的结果中选择其一作为最终的呼吸率计算结果，或者，对时域分析的结果和频域分析的结果进行加权以得到最终的呼吸率计算结果。
根据器件信号得到呼吸率之后，还可以显示呼吸率和呼吸率的趋势图中的至少一项。进一步地，在经鼻高流量氧疗的场景下，还可以根据呼吸率、通气对象的血氧饱和度和吸入氧浓度计算ROX指数，并显示ROX指数和ROX指数的趋势图中的至少一项。
除此之外，呼吸率监测方法400与呼吸率监测方法100还有许多相同或相似的内容，具体可参阅上文的相关描述，此处不再赘述。本申请实施例的呼吸率监测方法400根据控制通气流量大小的器件的器件信号计算呼吸率，能够减少误差。
下面，将参考图5描述根据本申请另一实施例的呼吸率监测方法。如图5所示，呼吸率监测方法500包括如下步骤：
在步骤S510，获取医疗通气设备为通气对象提供机械通气的过程中采集的至少两种信号，所述至少两种信号能够反映所述通气对象的呼吸节律；
在步骤S520，根据所述至少两种信号得到互相关信号；
在步骤S530，根据所述互相关信号得到所述通气对象的呼吸率。
本实施例的呼吸率监测方法500根据能够反映呼吸节律的至少两种信号的互相关信号计算呼吸率，由于互相关信号能够明显地表征出通气对象的呼吸波动，将较小的呼吸波动幅度放大，因此可以减少外界干扰对呼吸率识别的影响，更准确地识别通气对象的呼吸状态。
示例性地，能够反映通气对象呼吸节律的至少两种信号包括以下信号中的至少两种：能够反映呼吸节律的器件信号，能够反映呼吸节律的生理信号，能够反映呼吸节律的呼吸信号。其中，器件信号包括医疗通气设备中控制通气流量大小的器件的信号。医疗通气设备中控制通气流量大小的器件包括但不限于医疗通气设备中控制通气流量的涡轮和阀门。生理信号包括但不限于通气对象的血氧信号、呼末二氧化碳信号、食道压信号。呼吸信号包括但不限于机械通气的流量信号和压力信号。互相关信号可以是至少两种不同器件信号的互相关信号，至少两种不同生理信号的互相关信号，至少两种不同呼吸信号的互相关信号，也可以是至少一种器件信号和至少一种生理信号的互相关信号，至少一种器件信号和至少一种呼吸信号的互相关信号等。互相关信号的具体计算方式可以参照上文。
示例性地，为通气对象提供机械通气的过程包括为通气对象提供经鼻高流量氧疗的过程。在经鼻高流量氧疗的过程中，根据互相关信号计算呼吸率更能够减小误差，提高准确性。
示例性地，根据互相关信号得到通气对象的呼吸率包括：提取互相关信号的时域特征，根据互相关信号的时域特征得到通气对象的呼吸率；或者，提取互相关信号的频域特征，根据互相关信号的频域特征得到通气对象的呼吸率。进一步地，也可以采用时域与频域相结合的方式得到通气对象的呼吸率。
根据互相关信号得到呼吸率之后，还可以显示呼吸率和呼吸率的趋势图中的至少一项。进一步地，在经鼻高流量氧疗的场景下，还可以根据呼吸率、通气对象的血氧饱和度和吸入氧浓度计算ROX指数，并显示ROX指数和ROX指数的趋势图中的至少一项。
除此之外，呼吸率监测方法500与呼吸率监测方法100还有许多相同或相似的内容，具体可参阅上文的相关描述，此处不再赘述。本申请实施例的呼吸率监测方法500根据互相关信号计算呼吸率，能够提高呼吸率计算的准 确性。
下面，将参考图6描述根据本申请另一实施例的呼吸率监测方法。如图6所示，呼吸率监测方法600包括如下步骤：
在步骤S610，在医疗通气设备为通气对象提供经鼻高流量氧疗的过程中，获取能够反映所述通气对象呼吸节律的信号；
在步骤S620，根据所述能够反映所述通气对象呼吸节律的信号得到所述通气对象的呼吸率；
在步骤S630，显示所述通气对象的呼吸率。
以往在经鼻高流量氧疗的过程中，由于难以准确计算呼吸率，因此不会显示呼吸率的数值。本申请实施例的呼吸率监测方法600在经鼻高流量氧疗的过程中计算并显示呼吸率的具体数值，能够为用户提供定量化的参照依据。其中，可以采用上文所述的任意一种计算呼吸率的方法计算呼吸率，也可以采用其他合适的方法计算呼吸率。
除了显示通气对象的呼吸率以外，还可以生成并显示呼吸率的趋势图。进一步地，还可以根据呼吸率计算ROX指数，并显示ROX指数，作为是否进行气管插管的评价指标。此外，还可以生成并显示ROX指数的趋势图。其中，ROX指数＝(血氧饱和度/吸入氧浓度)/呼吸率。通气对象的血氧饱和度和吸入氧浓度可以通过呼吸机或者监护仪获得。
在一个实施例中，可以在显示界面的第一显示区域显示ROX指数的趋势图，并在ROX指数的趋势图中显示不同ROX阈值范围对应的标识。其中，ROX阈值范围可以由用户自行设置，具体地，ROX阈值范围至少包括表示治疗成功的第一阈值范围和表示有插管风险的第二阈值范围，第一阈值范围对应的坐标区域可以显示为绿色，第二阈值范围对应的坐标区域可以显示为红色，当ROX趋势线处于绿色区域则提示治疗成功，当ROX趋势线处于红色区域则提示有插管风险。第一阈值范围对应的坐标区域与第二阈值范围对应的坐标区域之间为过渡区域，可以显示为灰色。
同时，还可以在显示界面的第二显示区域显示通气对象的实时的呼吸参数和/或生理参数，包括但不限于流量、吸入氧浓度、ROX指数、血氧饱和度和呼吸率等，上述参数实时刷新。由于显示界面包括第一区域和第二区域，第一区域显示有ROX指数的趋势图，第二区域显示有实时刷新的呼吸参数和/或生理参数，因此基于该显示界面，用户可以同时查看ROX指数的变化趋势和用户的实时监测参数。
进一步地，在经鼻高流量氧疗模式下，当接收到对ROX指数的趋势图中目标时刻的选择指令时，显示目标时刻对应的相关参数，包括但不限于流量、吸入氧浓度、ROX指数、血氧饱和度和呼吸率，以便用户查看。示例性地，目标时刻对应的相关参数可以显示在第一区域中、ROX指数的趋势图附近。除此之外，呼吸率监测方法600与呼吸率监测方法100还有许多相同或相似的内容，具体可参阅上文的相关描述，此处不再赘述。本申请实施例的呼吸率监测方法600在经鼻高流量氧疗的过程中计算并显示通气对象的呼吸率，能够为用户提供定量化的参照依据。
下面，将参考图7描述根据本申请另一实施例的呼吸率监测方法。如图7所示，呼吸率监测方法700包括如下步骤：
在步骤S710，获取医疗通气设备为通气对象提供机械通气的过程中采集的一种或多种信号，所述一种或多种信号能够反映所述通气对象的呼吸节律；
在步骤S720，提取所述一种或多种信号的时域信息和/或频域信息；将所述时域信息和/或频域信息输入到预先训练好的机器学习模型中，并输出所述通气对象的呼吸率。
与呼吸率监测方法100类似，本申请实施例的呼吸率监测方法700结合时域分析或频域分析得到通气对象的呼吸率。不同之处在于，本申请实施例的呼吸率监测方法700将时域信息和/或频域信息作为机器学习模型，机器学习模型直接输出通气对象的呼吸率。其中，时域信息和频域信息可以分别指上文所述的时域特征和频域特征，也可以是不同于上文所述的时域特征和频域特征的其他信息，例如，时域信息还可以是对时域信号进行预处理所得到的信号，频域信息还可以是频谱图、功率谱图或经处理后的频谱图或功率谱图等。在一些实施例中，还可以将至少一种信号与时域信息和/或频域信息一同输入到机器学习模型中。
示例性地，在机器学习模型的训练阶段，可以构建能够反映呼吸节律的信号集合、提取信号的时域信息和/或频域信息，并获取呼吸率的真实值，将信号的时域信息和/或频域信息及呼吸率的真实值作为训练样本，对网络模型进行训练，以得到训练好的机器学习模型，使得训练好的机器学习模型能够输出准确的呼吸率计算结果。
在一些实施例中，由于常用的机器学习模型对设备计算能力要求较高，因而可以简化算法计算步骤来降低机器学习模型的复杂度，使机器学习模型 能够很好的应用于嵌入式设备。在经鼻高流量氧疗模式下，病人自主活动较强，病人过于强烈的自主活动引起的运动误差将导致器件信号、生理信号等发生剧烈变化，需要机器学习模型具有很强的抗干扰能力才能准识别病人的呼吸率。因而在模型训练阶段，可以通过模拟极端应用场景，特异地优化机器学习模型在极端场景下对呼吸率的识别能力，从而提高机器学习模型的抗干扰能力。除此之外，呼吸率监测方法700与呼吸率监测方法100还有许多相同或相似的内容，具体可参阅上文的相关描述，此处不再赘述。本申请实施例的呼吸率监测方法700根据时域信息和/或频域信息计算呼吸率，能够提高呼吸率计算的准确性。
参照图8，本申请实施例还提供了一种医疗通气设备，该医疗通气设备包括呼吸机、麻醉机、监护仪等具备通气功能的医疗设备。医疗通气设备用于代替、控制或改变通气对象的生理呼吸，通过增加肺通气量来改善通气对象的呼吸功能并减轻通气对象的呼吸消耗。在一些实施例中，医疗通气设备800可以是具有经鼻高流量氧疗功能的医疗通气设备。医疗通气设备800可以用于实现上文所述的呼吸率监测方法，以下仅对医疗通气设备800的主要功能进行描述，其他具体细节可以参见上文。
如图8所示，医疗通气设备800包括压力产生装置810和处理器820，压力产生装置810用于与通气管路连通，以通过通气管路向通气对象输送设定压力的气体。压力产生装置810包括涡轮、气瓶等，处理器820通过控制压力产生装置810来控制通气流量。除了压力产生装置810以外，医疗通气设备中控制通气流量大小的器件还可以包括阀门，例如比例阀、大通径阀等。
医疗通气设备800还可以包括传感器，用于在通气过程中采集呼吸信号。传感器包括但不限于压力传感器和流量传感器，压力传感器用于测量机械通气的气体压力，流量传感器用于测量通气管路内的气体流量。压力传感器、和流量传感器等传感器与处理器820通信连接，并将测得的信号发送至处理器820。
处理器820用于控制压力产生装置810产生设定压力的气体，处理器820还用于执行上文所述的呼吸率监测方法100、呼吸率监测方法400、呼吸率监测方法500、呼吸率监测方法600或呼吸率监测方法700，以检测通气对象的呼吸率。呼吸率监测方法的更多细节可以参照上文，在此不做赘述。
尽管这里已经参考附图描述了示例实施例，应理解上述示例实施例仅仅 是示例性的，并且不意图将本申请的范围限制于此。本领域普通技术人员可以在其中进行各种改变和修改，而不偏离本申请的范围和精神。所有这些改变和修改意在被包括在所附权利要求所要求的本申请的范围之内。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
在本申请所提供的几个实施例中，应该理解到，所揭露的设备和方法，可以通过其它的方式实现。例如，以上所描述的设备实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个设备，或一些特征可以忽略，或不执行。
在此处所提供的说明书中，说明了大量具体细节。然而，能够理解，本申请的实施例可以在没有这些具体细节的情况下实践。在一些实例中，并未详细示出公知的方法、结构和技术，以便不模糊对本说明书的理解。
类似地，应当理解，为了精简本申请并帮助理解各个发明方面中的一个或多个，在对本申请的示例性实施例的描述中，本申请的各个特征有时被一起分组到单个实施例、图、或者对其的描述中。然而，并不应将该本申请的方法解释成反映如下意图：即所要求保护的本申请要求比在每个权利要求中所明确记载的特征更多的特征。更确切地说，如相应的权利要求书所反映的那样，其发明点在于可以用少于某个公开的单个实施例的所有特征的特征来解决相应的技术问题。因此，遵循具体实施方式的权利要求书由此明确地并入该具体实施方式，其中每个权利要求本身都作为本申请的单独实施例。
本领域的技术人员可以理解，除了特征之间相互排斥之外，可以采用任何组合对本说明书(包括伴随的权利要求、摘要和附图)中公开的所有特征以及如此公开的任何方法或者设备的所有过程或单元进行组合。除非另外明确陈述，本说明书(包括伴随的权利要求、摘要和附图)中公开的每个特征可以由提供相同、等同或相似目的的替代特征来代替。
此外，本领域的技术人员能够理解，尽管在此所述的一些实施例包括其它实施例中所包括的某些特征而不是其它特征，但是不同实施例的特征的组 合意味着处于本申请的范围之内并且形成不同的实施例。例如，在权利要求书中，所要求保护的实施例的任意之一都可以以任意的组合方式来使用。
本申请的各个部件实施例可以以硬件实现，或者以在一个或者多个处理器上运行的软件模块实现，或者以它们的组合实现。本领域的技术人员应当理解，可以在实践中使用微处理器或者数字信号处理器(DSP)来实现根据本申请实施例的一些模块的一些或者全部功能。本申请还可以实现为用于执行这里所描述的方法的一部分或者全部的装置程序(例如，计算机程序和计算机程序产品)。这样的实现本申请的程序可以存储在计算机可读介质上，或者可以具有一个或者多个信号的形式。这样的信号可以从因特网网站上下载得到，或者在载体信号上提供，或者以任何其他形式提供。
应该注意的是上述实施例对本申请进行说明而不是对本申请进行限制，并且本领域技术人员在不脱离所附权利要求的范围的情况下可设计出替换实施例。在权利要求中，不应将位于括号之间的任何参考符号构造成对权利要求的限制。本申请可以借助于包括有若干不同元件的硬件以及借助于适当编程的计算机来实现。在列举了若干装置的单元权利要求中，这些装置中的若干个可以是通过同一个硬件项来具体体现。单词第一、第二、以及第三等的使用不表示任何顺序。可将这些单词解释为名称。
以上所述，仅为本申请的具体实施方式或对具体实施方式的说明，本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。本申请的保护范围应以权利要求的保护范围为准。

Claims (42)

  1. 一种呼吸率监测方法，其特征在于，所述方法包括：
    获取医疗通气设备为通气对象提供机械通气的过程中采集的第一信号和第二信号，所述第一信号和所述第二信号能够反映所述通气对象的呼吸节律；
    提取所述第一信号的频域特征，根据所述第一信号的频域特征得到所述通气对象的第一呼吸率；
    提取所述第二信号的时域特征，根据所述第二信号的时域特征得到所述通气对象的第二呼吸率；
    根据所述第一呼吸率和所述第二呼吸率得到所述通气对象的第三呼吸率。
  2. 根据权利要求1所述的方法，其特征在于，所述第一信号包括以下至少一种：能够反映呼吸节律的器件信号，能够反映呼吸节律的生理信号，能够反映呼吸节律的呼吸信号，以及所述器件信号、所述生理信号和所述呼吸信号中至少两种信号的衍生信号；所述第二信号包括以下至少一种：能够反映呼吸节律的器件信号，能够反映呼吸节律的生理信号，能够反映呼吸节律的呼吸信号，以及所述器件信号、所述生理信号和所述呼吸信号中至少两种信号的衍生信号。
  3. 根据权利要求2所述的方法，其特征在于，所述器件信号包括所述医疗通气设备中控制通气流量大小的器件的信号。
  4. 根据权利要求3所述的方法，其特征在于，所述医疗通气设备中控制通气流量大小的器件包括所述医疗通气设备中控制通气流量的涡轮和阀门中的至少一种。
  5. 根据权利要求2-4中任一项所述的方法，其特征在于，所述生理信号包括以下至少一种：所述通气对象的血氧信号、呼末二氧化碳信号、食道压信号。
  6. 根据权利要求2-5中任一项所述的方法，其特征在于，所述呼吸信号包括以下至少一种：所述机械通气的流量信号和压力信号。
  7. 根据权利要求2-6中任一项所述的方法，其特征在于，所述第一信号包括所述医疗通气设备中控制通气流量的涡轮的电流信号或转速信号，所述第二信号包括所述机械通气的流量信号或压力信号。
  8. 根据权利要求1-7中任一项所述的方法，其特征在于，所述提取所述第一信号的频域特征，包括：获取所述第一信号的频谱图，根据所述频谱图确定所述第一信号的幅频特性中最大幅度对应的频点；
    所述根据所述第一信号的频域特征得到所述通气对象的第一呼吸率，包 括：将所述最大幅度对应的频点转换为所述第一呼吸率。
  9. 根据权利要求1-7中任一项所述的方法，其特征在于，所述提取所述第一信号的频域特征，包括：获取所述第一信号的功率谱图，根据所述功率谱图确定所述第一信号的功率谱特性中最大功率对应的频点；
    所述根据所述第一信号的频域特征得到所述通气对象的第一呼吸率，包括：将所述最大功率对应的频点转换为所述第一呼吸率。
  10. 根据权利要求8或9所述的方法，其特征在于，在提取所述第一信号的频域特征之前，还包括：
    对所述第一信号进行预处理，所述预处理包括归一化处理和滤波处理中的至少一种。
  11. 根据权利要求1-10中任一项所述的方法，其特征在于，所述提取所述第二信号的时域特征，包括：根据所述第二信号的波形得到吸气相的持续时间和与所述吸气相相邻的呼气相的持续时间；
    所述根据所述第二信号的时域特征得到所述通气对象的第二呼吸率，包括：根据所述吸气相的持续时间和所述呼气相的持续时间得到所述第二呼吸率。
  12. 根据权利要求1-10中任一项所述的方法，其特征在于，所述提取所述第二信号的时域特征，包括：根据所述第二信号的波形识别呼吸周期的时长；
    所述根据所述第二信号的时域特征得到所述通气对象的第二呼吸率，包括：根据所述呼吸周期的时长得到所述第二呼吸率。
  13. 根据权利要求1-12中任一项所述的方法，其特征在于，所述根据所述第一呼吸率和所述第二呼吸率得到所述通气对象的第三呼吸率，包括：
    根据所述第一信号的频域特征得到所述第一信号的第一特征指数；
    根据所述第二信号的时域特征得到所述第二信号的第二特征指数；
    根据所述第一特征指数和所述第二特征指数选择第一呼吸率和所述第二呼吸率之一作为所述第三呼吸率；或者，根据所述第一特征指数和所述第二特征指数对所述第一呼吸率和所述第二呼吸率进行加权计算，以得到所述第三呼吸率。
  14. 根据权利要求13所述的方法，其特征在于，所述根据所述第一信号的频域特征得到第一特征指数，包括：
    根据所述第一信号的频谱图的平均幅度、所述第一信号的频谱图的最大幅度、所述第一信号的功率谱图的平均功率和/或所述第一信号的功率谱图的 最大功率得到所述第一特征指数。
  15. 根据权利要求13所述的方法，其特征在于，所述根据所述第二信号的时域特征得到第二特征指数，包括：
    根据所述第二信号的变化幅度，和/或基于所述第二信号计算得到的历史第二呼吸率的变化幅度，得到所述第二特征指数。
  16. 根据权利要求13所述的方法，其特征在于，所述根据所述第一信号的频域特征得到所述第一信号的第一特征指数，包括：
    将所述频域特征输入到训练好的第一机器学习模型，并获取所述第一机器学习模型输出的所述第一特征指数。
  17. 根据权利要求13所述的方法，其特征在于，所述根据所述第二信号的时域特征得到所述第二信号的第二特征指数，包括：
    将所述时域特征输入到训练好的第二机器学习模型，并获取所述第二机器学习模型输出的所述第二特征指数。
  18. 根据权利要求1-17中任一项所述的方法，其特征在于，所述为通气对象提供机械通气的过程包括为所述通气对象提供经鼻高流量氧疗的过程。
  19. 根据权利要求1-18中任一项所述的方法，其特征在于，还包括：显示所述第三呼吸率和/或所述第三呼吸率的趋势图。
  20. 根据权利要求1-19中任一项所述的方法，其特征在于，还包括：根据所述第三呼吸率、所述通气对象的血氧饱和度和吸入氧浓度计算ROX指数，并显示所述ROX指数和/或所述ROX指数的趋势图。
  21. 一种呼吸率监测方法，其特征在于，所述方法包括：
    在医疗通气设备为通气对象提供机械通气的过程中，采集控制所述医疗通气设备通气流量大小的器件的器件信号，所述器件信号能够反映所述通气对象的呼吸节律；
    根据所述器件信号得到所述通气对象的呼吸率。
  22. 根据权利要求21所述的方法，其特征在于，所述根据所述器件信号得到所述通气对象的呼吸率，包括：
    提取所述器件信号的时域特征，根据所述器件信号的时域特征得到所述通气对象的呼吸率；
    或者，提取所述器件信号的频域特征，根据所述器件信号的频域特征得到所述通气对象的呼吸率。
  23. 根据权利要求22所述的方法，其特征在于，所述医疗通气设备中控制通气流量大小的器件包括所述医疗通气设备中控制通气流量的涡轮，或者， 所述医疗通气设备中控制通气流量大小的器件包括所述医疗通气设备中控制通气流量的阀门。
  24. 根据权利要求23所述的方法，其特征在于，所述涡轮的信号包括所述涡轮的电流信号或转速信号，所述阀门的信号包括所述阀门的开度信号。
  25. 根据权利要求21-24中任一项所述的方法，其特征在于，所述医疗通气设备中控制通气流量大小的器件的信号包括所述器件的控制信号或采样信号。
  26. 根据权利要求21-25中任一项所述的方法，其特征在于，所述为通气对象提供机械通气的过程包括为所述通气对象提供经鼻高流量氧疗的过程。
  27. 根据权利要求21-26中任一项所述的方法，其特征在于，还包括：显示所述呼吸率和/或所述呼吸率的趋势图。
  28. 根据权利要求26所述的方法，其特征在于，还包括：根据所述呼吸率、所述通气对象的血氧饱和度和吸入氧浓度计算ROX指数，并显示所述ROX指数和/或所述ROX指数的趋势图。
  29. 一种呼吸率监测方法，其特征在于，所述方法包括：
    获取医疗通气设备为通气对象提供机械通气的过程中采集的至少两种信号，所述至少两种信号能够反映所述通气对象的呼吸节律；
    根据所述至少两种信号得到互相关信号；
    根据所述互相关信号得到所述通气对象的呼吸率。
  30. 根据权利要求29所述的方法，其特征在于，所述根据所述互相关信号得到所述通气对象的呼吸率，包括：
    提取所述互相关信号的时域特征，根据所述互相关信号的时域特征得到所述通气对象的呼吸率；
    或者，提取所述互相关信号的频域特征，根据所述互相关信号的频域特征得到所述通气对象的呼吸率。
  31. 根据权利要求29或30所述的方法，其特征在于，所述至少两种信号包括以下信号中的至少两种：能够反映呼吸节律的器件信号，能够反映呼吸节律的生理信号，能够反映呼吸节律的呼吸信号。
  32. 根据权利要求29-31中任一项所述的方法，其特征在于，所述为通气对象提供机械通气的过程包括为所述通气对象提供经鼻高流量氧疗的过程。
  33. 根据权利要求29-32中任一项所述的方法，其特征在于，还包括：显示所述呼吸率和/或所述呼吸率的趋势图。
  34. 根据权利要求32所述的方法，其特征在于，还包括：根据所述呼吸 率、所述通气对象的血氧饱和度和吸入氧浓度计算ROX指数，并显示所述ROX指数和/或所述ROX指数的趋势图。
  35. 一种呼吸率监测方法，其特征在于，所述方法包括：
    在医疗通气设备为通气对象提供经鼻高流量氧疗的过程中，获取能够反映所述通气对象呼吸节律的信号；
    根据所述能够反映所述通气对象呼吸节律的信号得到所述通气对象的呼吸率；
    显示所述通气对象的呼吸率。
  36. 根据权利要求35所述的方法，其特征在于，还包括：
    根据所述呼吸率计算ROX指数，并显示所述ROX指数和/或所述ROX指数的趋势图。
  37. 根据权利要求36所述的方法，其特征在于，所述显示所述ROX指数和/或所述ROX指数的趋势图，包括：
    在显示界面的第一显示区域显示所述ROX指数的趋势图，并在所述ROX指数的趋势图中显示不同ROX阈值范围对应的标识；
    在所述显示界面的第二显示区域显示所述通气对象的实时的呼吸参数和/或生理参数。
  38. 根据权利要求37所述的方法，其特征在于，所述显示所述通气对象的呼吸率，包括：
    将所述呼吸率实时显示在所述第二显示区域。
  39. 根据权利要求38所述的方法，其特征在于，还包括：当接收到对所述ROX指数的趋势图中目标时刻的选择指令时，显示以下至少一项：所述目标时刻对应的呼吸率、流量、吸入氧浓度、ROX指数、血氧饱和度。
  40. 一种呼吸率监测方法，其特征在于，所述方法包括：
    获取医疗通气设备为通气对象提供机械通气的过程中采集的一种或多种信号，所述一种或多种信号能够反映所述通气对象的呼吸节律；
    提取所述一种或多种信号的时域信息和/或频域信息；将所述时域信息和/或频域信息输入到预先训练好的机器学习模型中，并输出所述通气对象的呼吸率。
  41. 根据权利要求40所述的方法，其特征在于，还包括：将所述一种或多种信号与所述时域信息和/或频域信息一同输入到所述机器学习模型中。
  42. 一种医疗通气设备，其特征在于，所述医疗通气设备包括：
    压力产生装置，所述压力产生装置用于与通气管路连通，以通过所述通 气管路向通气对象输送设定压力的气体；
    处理器，连接所述压力产生装置，用于控制所述压力产生装置产生所述设定压力的气体；所述处理器还用于执行权利要求1-41中任一项所述的呼吸率监测方法。
PCT/CN2021/129068 2021-11-05 2021-11-05 呼吸率监测方法及医疗通气设备 WO2023077448A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2021/129068 WO2023077448A1 (zh) 2021-11-05 2021-11-05 呼吸率监测方法及医疗通气设备
CN202180103629.7A CN118159323A (zh) 2021-11-05 2021-11-05 呼吸率监测方法及医疗通气设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/129068 WO2023077448A1 (zh) 2021-11-05 2021-11-05 呼吸率监测方法及医疗通气设备

Publications (1)

Publication Number Publication Date
WO2023077448A1 true WO2023077448A1 (zh) 2023-05-11

Family

ID=86240404

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/129068 WO2023077448A1 (zh) 2021-11-05 2021-11-05 呼吸率监测方法及医疗通气设备

Country Status (2)

Country Link
CN (1) CN118159323A (zh)
WO (1) WO2023077448A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101843489A (zh) * 2009-03-26 2010-09-29 深圳市理邦精密仪器有限公司 一种呼吸信号处理方法
CN109414204A (zh) * 2016-06-22 2019-03-01 皇家飞利浦有限公司 用于确定针对对象的呼吸信息的方法和装置
US20190371460A1 (en) * 2018-04-26 2019-12-05 Respivar LLV Detection and Display of Respiratory Rate Variability, Mechanical Ventilation Machine Learning, and Double Booking of Clinic Slots, System, Method, and Computer Program Product
CN111432866A (zh) * 2017-11-22 2020-07-17 费雪派克医疗保健有限公司 用于呼吸流治疗系统的呼吸速率监测
CN113368351A (zh) * 2021-06-07 2021-09-10 中国人民解放军总医院第一医学中心 经鼻高流量呼吸频率监测方法及其呼吸支持设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101843489A (zh) * 2009-03-26 2010-09-29 深圳市理邦精密仪器有限公司 一种呼吸信号处理方法
CN109414204A (zh) * 2016-06-22 2019-03-01 皇家飞利浦有限公司 用于确定针对对象的呼吸信息的方法和装置
CN111432866A (zh) * 2017-11-22 2020-07-17 费雪派克医疗保健有限公司 用于呼吸流治疗系统的呼吸速率监测
US20190371460A1 (en) * 2018-04-26 2019-12-05 Respivar LLV Detection and Display of Respiratory Rate Variability, Mechanical Ventilation Machine Learning, and Double Booking of Clinic Slots, System, Method, and Computer Program Product
CN113368351A (zh) * 2021-06-07 2021-09-10 中国人民解放军总医院第一医学中心 经鼻高流量呼吸频率监测方法及其呼吸支持设备

Also Published As

Publication number Publication date
CN118159323A (zh) 2024-06-07

Similar Documents

Publication Publication Date Title
TWI658816B (zh) 週期性呼吸的即時檢測之方法與器件
RU2737295C2 (ru) Аппарат для механической искусственной вентиляции легких и мониторинга дыхания
JP2020171797A (ja) 睡眠段階を決定するシステム及び方法
CN108135493B (zh) 用于通气机械参数估计的异常检测设备和方法
RU2712749C2 (ru) Системы и способы оптимизации искусственной вентиляции легких на основании модели
AU2021203928B2 (en) Patient specific auto-flowrate control
RU2540149C2 (ru) Система и способ количественного определения растяжимости легких у субъекта, самостоятельно осуществляющего вентиляцию
US12109038B2 (en) Systems and methods for using breath events in sleep staging
EP3634555B1 (en) Apparatus for treatment of respiratory disorders
CN113555082B (zh) 一种呼吸功能的智能化引导训练方法
CN112754465B (zh) 一种压力控制机械通气下肺部准静态顺应性估测方法
WO2023077448A1 (zh) 呼吸率监测方法及医疗通气设备
CN117597063A (zh) 用于检测睡眠障碍事件的方法和设备
CN111513721B (zh) 一种呼吸节律发生器及其控制方法
CN111840931A (zh) 双水平呼吸功能监测及干预设备
CN110428892A (zh) 一种基于排痰器的智能远程监测装置及监测方法
CN212880869U (zh) 双水平呼吸功能监测及干预设备
WO2023148190A1 (en) Systems and methods for screening, diagnosis, detection, monitoring and/or therapy
WO2022133942A1 (zh) 医疗通气设备及通气监测方法
WO2023094966A1 (en) End tidal carbon dioxide measurement during high flow oxygen therapy
CN114668384A (zh) 一种改进的压力控制机械通气下肺部准静态顺应性估测方法及装置
Arnal et al. Mechanical Ventilation
Lizza et al. 680: RISK FACTORS FOR DEATH FROM VENTILATOR-ASSOCIATED PNEUMONIA IN THE UNITED STATES FROM 2008–2011
NZ723063B2 (en) Real-time detection of periodic breathing

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21962961

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 202180103629.7

Country of ref document: CN