A ventilator control method and device of a minimum work of breathing directed ventilation algorithm

Abstract

The application relates to the technical field of control, and discloses a ventilator control method and device of a minimum respiratory work guided ventilation algorithm. The method comprises the following steps: acquiring operation data of a ventilator, the ventilator being used for providing respiratory support for a user; determining the first respiratory work of the user according to the operation data; determining the target value of the operation parameter of the ventilator according to the first respiratory work or the operation data, the ventilator operating at the target value of the operation parameter, and the respiratory work of the user being minimum; and controlling the ventilator to operate at the target value of the operation parameter. Through the method, the ventilator can dynamically adjust the value of the operation parameter of the ventilator according to different users, so that the respiratory comfort of the user is improved.

Description

Technical Field

[0001] This application relates to the field of control technology, and in particular to a ventilator control method and device based on a minimum work of breathing guided ventilation algorithm. Background Technology

[0002] A ventilator is a device used to assist or replace a user's spontaneous breathing.

[0003] Currently, when users use ventilators for assisted or alternative breathing, the operating parameters are typically set to either pressure-controlled ventilation or volume-controlled ventilation. Pressure-controlled ventilation involves pre-setting an airway pressure threshold; when the pressure in the airway exceeds this threshold, inhalation ceases and the expiratory phase begins. Volume-controlled ventilation involves pre-setting a target gas delivery capacity; when the actual gas delivery volume reaches this target capacity, inhalation ceases and the expiratory phase begins.

[0004] However, this method of setting ventilator operating parameters cannot adapt to different users, resulting in over-support or under-support of the ventilator, which reduces the user's breathing comfort. Summary of the Invention

[0005] This application provides a ventilator control method based on a minimum work-guided ventilation algorithm, enabling the ventilator to automatically adapt to different users and improve their breathing comfort. Furthermore, this application also provides a corresponding ventilator control device, computer equipment, and computer-readable storage medium based on the minimum work-guided ventilation algorithm.

[0006] In a first aspect, this application provides a ventilator control method based on a minimum work-of-breath guided ventilation algorithm, characterized in that the method includes: acquiring ventilator operating data, the ventilator being used to provide respiratory support to a user; determining a first work-of-breath based on the operating data, the first work-of-breath being used to characterize the energy consumed by the user to overcome elastic and inelastic resistance during lung ventilation when the ventilator is running at current values ​​of operating parameters; determining a target value of the ventilator's operating parameters based on the first work-of-breath or the operating data, the ventilator operating at the target value of the operating parameters, thereby minimizing the user's work-of-breath; and controlling the ventilator to operate at the target value of the operating parameters.

[0007] In one possible implementation, the operational data includes pressure data at a target location, flow data at the target location, and volume data of gas delivered through the target location, where the target location is the tubing of the ventilator and the interface for connecting the user's breathing interface. Determining the first work of breathing based on the operational data includes: inputting the pressure data, flow data, and volume data into a machine learning model for inference to obtain predicted values ​​of airway resistance and lung compliance, where airway resistance characterizes the resistance encountered by gas as it flows through the user's airway, and lung compliance characterizes the user's ability to change lung volume per unit pressure change; inputting the pressure data, flow data, and volume data into a respiratory mechanics model to obtain reference values ​​of airway resistance and lung compliance; and determining the user's first work of breathing based on the predicted values ​​of airway resistance, reference values ​​of airway resistance, predicted values ​​of lung compliance, and reference values ​​of lung compliance.

[0008] In one possible implementation, determining the user's first work of breathing based on the predicted value of airway resistance, the reference value of airway resistance, the predicted value of lung compliance, and the reference value of lung compliance includes: determining a first error value based on the predicted value of airway resistance and the reference value of airway resistance, the first error value indicating the degree to which the predicted value of airway resistance deviates from the reference value of airway resistance; determining a second error value based on the predicted value of lung compliance and the reference value of lung compliance, the second error value indicating the degree to which the predicted value of lung compliance deviates from the reference value of lung compliance; updating the predicted value of airway resistance and the predicted value of lung compliance based on the first error value and the second error value to obtain updated predicted values ​​of airway resistance and lung compliance; and determining the user's first work of breathing based on the updated predicted value of airway resistance, the reference value of airway resistance, the updated predicted value of lung compliance, and the reference value of lung compliance.

[0009] In one possible implementation, determining the user's first work of breathing based on the updated predicted value of airway resistance, the reference value of airway resistance, the updated predicted value of lung compliance, and the reference value of lung compliance includes: determining a fusion value of airway resistance based on the updated predicted value of airway resistance and the reference value of airway resistance; determining a fusion value of lung compliance based on the updated predicted value of lung compliance and the reference value of lung compliance; and determining the user's first work of breathing based on the fusion value of airway resistance and the fusion value of lung compliance.

[0010] In one possible implementation, determining the target value of the ventilator's operating parameters based on the first breathing work or the operating data includes: determining the theoretical optimal value of the operating parameters; if the current value of the ventilator's operating parameters is not equal to the theoretical optimal value of the operating parameters, increasing or decreasing the current value of the operating parameters by a preset step size to obtain the value of the operating parameters after the first adjustment; controlling the ventilator to operate with the value of the operating parameters after the first adjustment to obtain the user's second breathing work; and if the second breathing work is not less than the first breathing work, determining the current value of the operating parameters as the target value of the operating parameters.

[0011] In one possible implementation, the method further includes: when the second breathing work is less than the first breathing work, increasing or decreasing the value of the first adjusted operating parameter by a preset step size to obtain the value of the second adjusted operating parameter; The ventilator is controlled to operate with the values ​​of the second adjusted operating parameters to obtain the user's third breathing work; if the third breathing work is not less than the second breathing work, the values ​​of the first adjusted operating parameters are determined as the target values ​​of the operating parameters.

[0012] In one possible implementation, determining the target value of the ventilator's operating parameters based on the first breathing work or the operating data includes: determining the target value of the ventilator's operating parameters when the first breathing work is less than a first preset threshold or the first breathing work is greater than a second preset threshold; wherein the second preset threshold is greater than the first preset threshold.

[0013] In one possible implementation, the fused value of airway resistance includes the fused value of M airway resistances over M respiratory cycles, with one fused value corresponding to one respiratory cycle; the fused value of lung compliance includes the fused value of M lung compliances over M respiratory cycles, with one fused value corresponding to one respiratory cycle; determining the target value of the ventilator's operating parameters based on the first work of breathing or the operating data includes: determining a first average value based on the fused values ​​of the M airway resistances, and determining a second average value based on the fused values ​​of the M lung compliances; determining the target value of the ventilator's operating parameters when the difference between the fused value of airway resistance in the current respiratory cycle and the first average value is greater than a third preset threshold, or the difference between the fused value of lung compliance in the current respiratory cycle and the second average value is greater than a fourth preset threshold.

[0014] Secondly, embodiments of this application provide a ventilator control device based on a minimum work-of-breath guided ventilation algorithm, characterized in that the device comprises: an acquisition module for acquiring ventilator operating data, the ventilator being used to provide respiratory support to a user; a work-of-breath determination module for determining a first work-of-breath based on the operating data, the first work-of-breath being used to characterize the energy consumed by the user to overcome elastic and inelastic resistance during lung ventilation when the ventilator is running at the current values ​​of its operating parameters; a operating parameter determination module for determining a target value of the ventilator's operating parameters based on the first work-of-breath or the operating data, the ventilator operating at the target value of the operating parameters minimizing the user's work-of-breath; and a control module for controlling the ventilator to operate at the target value of the operating parameters.

[0015] In one possible implementation, the breathing work determination module is specifically used to input the pressure data, flow data, and volume data into a machine learning model for inference to obtain predicted values ​​of airway resistance and lung compliance. The airway resistance characterizes the resistance encountered by gas as it flows through the user's airway, and the lung compliance characterizes the user's ability to change lung volume per unit pressure change. The module also inputs the pressure data, flow data, and volume data into a respiratory mechanics model to obtain reference values ​​for airway resistance and lung compliance. Finally, the module determines the user's first breathing work based on the predicted values ​​of airway resistance, reference values ​​of airway resistance, predicted values ​​of lung compliance, and reference values ​​of lung compliance.

[0016] In one possible implementation, the breathing work determination module is specifically configured to: determine a first error value based on a predicted value of airway resistance and a reference value of airway resistance, the first error value indicating the degree to which the predicted value of airway resistance deviates from the reference value of airway resistance; determine a second error value based on a predicted value of lung compliance and a reference value of lung compliance, the second error value indicating the degree to which the predicted value of lung compliance deviates from the reference value of lung compliance; update the predicted values ​​of airway resistance and lung compliance based on the first error value and the second error value to obtain updated predicted values ​​of airway resistance and lung compliance; and determine the user's first breathing work based on the updated predicted value of airway resistance, the reference value of airway resistance, the updated predicted value of lung compliance, and the reference value of lung compliance.

[0017] In one possible implementation, the breathing work determination module is specifically configured to: determine a fusion value of airway resistance based on the updated predicted value of airway resistance and the reference value of airway resistance; determine a fusion value of lung compliance based on the updated predicted value of lung compliance and the reference value of lung compliance; and determine the user's first breathing work based on the fusion value of airway resistance and the fusion value of lung compliance.

[0018] In one possible implementation, the operating parameter determination module is specifically used to determine the target value of the theoretically optimal operating parameter; when the current value of the operating parameter of the ventilator is not equal to the theoretically optimal value of the operating parameter, the current value of the operating parameter is increased or decreased by a preset step size to obtain the value of the operating parameter after the first adjustment; the ventilator is controlled to operate with the value of the operating parameter after the first adjustment to obtain the user's second breathing work; when the second breathing work is not less than the first breathing work, the current value of the operating parameter is determined as the target value of the operating parameter.

[0019] In one possible implementation, the operating parameter determination module is specifically used to, when the second breathing work is less than the first breathing work, increase or decrease the value of the first adjusted operating parameter by a preset step size to obtain the value of the second adjusted operating parameter; control the ventilator to operate with the value of the second adjusted operating parameter to obtain the user's third breathing work; and when the third breathing work is not less than the second breathing work, determine the value of the first adjusted operating parameter as the target value of the operating parameter.

[0020] In one possible implementation, the operating parameter determination module is specifically used to determine the target value of the operating parameters of the ventilator when the first breathing work is less than a first preset threshold or the first breathing work is greater than a second preset threshold; wherein the second preset threshold is greater than the first preset threshold.

[0021] In one possible implementation, the operating parameter determination module is specifically used to determine a first average value based on the fusion values ​​of the M airway resistances and a second average value based on the fusion values ​​of the M lung compliances; and to determine target values ​​for the operating parameters of the ventilator when the difference between the fusion value of the airway resistance in the current respiratory cycle and the first average value is greater than a third preset threshold, or the difference between the fusion value of the lung compliance in the current respiratory cycle and the second average value is greater than a fourth preset threshold.

[0022] Thirdly, this application provides a computer device including a processor and a memory, the memory being used to store instructions, and the processor executing the instructions stored in the memory to cause the computer device to perform any of the minimum work of breathing guided ventilation algorithms described above for ventilator control.

[0023] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements a ventilator control method of any of the minimum work of breathing guided ventilation algorithms described above.

[0024] Based on the implementation methods provided in the above aspects, this application can be further combined to provide more implementation methods.

[0025] As can be seen from the above technical solutions, this application has the following beneficial effects: The ventilator control system acquires the ventilator's operational data. Then, based on this data, the system determines the initial work of breathing required by the user to overcome elastic and inelastic resistance during ventilation, given the current values ​​of the operating parameters. Further, the system can determine the target values ​​of the operating parameters that minimize the user's work of breathing, based on either the initial work of breathing or the operational data. The system can then control the ventilator to operate at these target values.

[0026] Because the ventilator control system can determine the target values ​​of the ventilator's operating parameters that minimize the user's breathing work based on the ventilator's operating data, and control the ventilator to operate at the target values ​​of the operating parameters, the ventilator can be adapted to different users and improve the user's breathing comfort compared to setting the ventilator's parameters to constant pressure ventilation or constant volume ventilation operating parameters. Attached Figure Description

[0027] Figure 1 A flowchart illustrating a ventilator control method based on a minimum work of breathing guided ventilation algorithm provided in this application embodiment; Figure 2 A schematic flowchart illustrating a method for determining the fusion value of airway resistance and the fusion value of lung compliance, provided in an embodiment of this application; Figure 3 This application provides a flowchart illustrating whether to trigger the determination of target values ​​for operating parameters in an embodiment of the present application. Figure 4 This application provides a schematic flowchart for determining target values ​​of operating parameters in an embodiment of the present application. Figure 5 This is a schematic diagram of a ventilator control device based on optimal breathing work, provided as an embodiment of this application. Detailed Implementation

[0028] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate; this is merely a method of distinction used in describing objects with the same attributes in the embodiments of this application.

[0029] To make the above-mentioned objectives, features and advantages of the embodiments of this application more apparent and understandable, the embodiments of this application will be further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0030] A ventilator is a device used to assist or replace a user's spontaneous breathing.

[0031] Currently, when users use ventilators for assisted or alternative breathing, the operating parameters are typically set to either pressure-controlled ventilation or volume-controlled ventilation. Pressure-controlled ventilation involves pre-setting an airway pressure threshold; when the pressure in the airway exceeds this threshold, inhalation ceases and the expiratory phase begins. Volume-controlled ventilation involves pre-setting a target gas delivery capacity; when the actual gas delivery volume reaches this target capacity, inhalation ceases and the expiratory phase begins.

[0032] However, this method of setting ventilator operating parameters cannot adapt to different users, resulting in over-support or under-support of the ventilator, which reduces the user's breathing comfort.

[0033] Based on this, this application provides a ventilator control method using a minimum work-of-breath guided ventilation algorithm. By using the ventilator's operating data and the user's breathing work, the target value of the operating parameters that minimizes the user's breathing work is determined, thereby improving the user's breathing comfort.

[0034] The ventilator control method based on minimum work of breathing guided ventilation provided in this application embodiment is implemented through a minimum work of breathing guided ventilation (MWBGV) algorithm.

[0035] In the specific implementation of the ventilator control system using the MWBGV algorithm, the ventilator control system first acquires the ventilator's operating data. Then, based on this data, the ventilator control system determines the first respiratory work performed by the user to overcome elastic and inelastic resistance during lung ventilation when the ventilator is operating at its current parameter values. Further, based on the first respiratory work or the ventilator's operating data, the ventilator control system determines the target values ​​of the operating parameters that minimize the user's respiratory work. The ventilator control system can then control the ventilator to operate at the target values ​​of the operating parameters.

[0036] Because the ventilator control system can determine the values ​​of the ventilator's operating parameters that minimize the user's breathing work based on the ventilator's operating data, and control the ventilator to operate at the target values ​​of the operating parameters, the ventilator can be adapted to different users and improve the user's breathing comfort compared to setting the ventilator's parameters to constant pressure ventilation or constant volume ventilation operating parameters.

[0037] To facilitate understanding of the embodiments of this application, the following description, in conjunction with the accompanying drawings, illustrates a ventilator control method based on a minimum work of breathing guided ventilation algorithm provided in this application.

[0038] See Figure 1 , Figure 1 This is a flowchart illustrating a ventilator control method based on a minimum work of breathing guided ventilation algorithm provided in an embodiment of this application.

[0039] in, Figure 1 The ventilator control method based on minimum work of breathing can specifically include the following steps.

[0040] S101: The ventilator control system acquires the ventilator's operating data, and the ventilator is used to provide respiratory support to the user.

[0041] In practice, before the ventilator is started, the ventilator control system can determine the initial values ​​of the ventilator's operating parameters based on the user's information. These initial values ​​may include the target minute ventilation percentage, the inhaled oxygen concentration, the positive end-expiratory pressure (PEEP), the upper limit of the respiratory rate, the lower limit of the respiratory rate, the upper limit of the minute ventilation, and the lower limit of the minute ventilation.

[0042] The target minute ventilation percentage refers to the percentage of a user's target minute ventilation relative to the predicted normal minute ventilation, which is used to reflect the expected level of ventilation support that the ventilator will achieve.

[0043] Inhaled oxygen concentration refers to the proportion of oxygen in the gas inhaled by a ventilator.

[0044] PEEP refers to the positive pressure level maintained in the alveoli at the end of expiration, which is used to prevent alveolar collapse and increase functional residual capacity.

[0045] Respiratory rate refers to the number of breaths a user of a ventilator takes per minute.

[0046] Minute ventilation refers to the total amount of gas entering or exiting a user's lungs per unit of time.

[0047] In one possible implementation, the ventilator control system can determine the initial values ​​of the ventilator's operating parameters based on the user's height, weight, and gender.

[0048] In another possible implementation, the ventilator control system can determine the initial values ​​of the ventilator's operating parameters based on the user's clinical information. In one example, if the user's clinical information indicates chronic obstructive pulmonary disease (COPD), the ventilator control system can set the initial values ​​of the ventilator's operating parameters to a third initial value. This third initial value could be, for example, a target minute ventilation percentage of 90%, an inhaled oxygen concentration of 50%, and a PEEP value of 4 cm⁻¹ (cm⁻¹). ) to 6 cm Within this range, the upper limit of respiratory rate is between 35 and 40 breaths per minute, the lower limit is between 6 and 8 breaths per minute, the upper limit of minute ventilation is between 14 and 18 L / min, and the lower limit of minute ventilation is between 1 and 4 L / min. In cases where the user's clinical information indicates acute respiratory distress syndrome, the ventilator control system can set the initial values ​​of the ventilator's operating parameters to a fourth initial value, for example, a target minute ventilation percentage of 120%, an inhaled oxygen concentration of 50%, and a PEEP of 8 cm⁻¹. Up to 12cm Within this range, the upper limit of respiratory rate is between 35 and 40 breaths per minute, the lower limit is between 6 and 8 breaths per minute, the upper limit of minute ventilation is between 14 and 18 L / min, and the lower limit is between 1 and 4 L / min. In cases where the user's clinical information indicates pneumonia or postoperative recovery, the ventilator control system can set the initial values ​​of the ventilator's operating parameters to the fifth initial value. For example, the fifth initial value could be a target minute ventilation percentage of 100%, an inhaled oxygen concentration of 50%, and a PEEP of 4 cm⁻¹. Up to 6cm Between these limits, the upper limit of respiratory rate is between 35 and 40 breaths per minute, the lower limit of respiratory rate is between 6 and 8 breaths per minute, the upper limit of minute ventilation is between 14 liters per minute (L / min) and 18 L / min, and the lower limit of minute ventilation is between 1 L / min and 4 L / min.

[0049] Furthermore, the ventilator control system can control the ventilator to operate at initial values ​​of its operating parameters. During ventilator operation, the ventilator control system can collect the ventilator's operating data in real time.

[0050] Specifically, sensors can be installed at the target location on the ventilator, and these sensors can collect the ventilator's actual operating data in real time at variable sampling intervals. For example, the ventilator control system can control the sensors to continuously collect the ventilator's operating data at variable sampling intervals between 100 microseconds and 10 milliseconds. The target location can be the ventilator's tubing or the interface used to connect to the user's breathing system.

[0051] In one possible implementation, the real-time operational data of the ventilator acquired by the sensor may include pressure data, flow rate data, and volumetric data of the gas delivered through the target location. The pressure data may include inspiratory pressure, expiratory pressure, plateau pressure, peak pressure, and PEEP data. The flow rate data may include inhaled gas flow rate and exhaled gas flow rate. The volumetric data can be calculated from the flow rate data, using the following formula:

[0052] in, The volumetric data accumulated from time 0 to time t. This is traffic data.

[0053] Plateau pressure refers to the static pressure value in the airway at the end of the inhalation phase, when the inhalation airflow stops and there is no gas flow in the airway.

[0054] Peak pressure refers to the highest pressure value reached in the airway during a respiratory cycle.

[0055] Furthermore, the ventilator control system can employ a cascaded filtering strategy to reduce noise in the collected pressure and flow data. This cascaded filtering strategy can involve first processing the pressure and flow data using a sliding median filter, and then processing the pressure and flow data again using a low-pass filter to obtain the noise-reduced pressure and flow data.

[0056] For example, when applying a sliding median filter to pressure and flow data, the ventilator control system can set the sliding window to 80 sampling points to effectively eliminate impulsive noise caused by user coughing, changes in body position, or fluid buildup in the breathing circuit. Then, the ventilator control system can further filter the pressure and flow data using a fourth-order Butterworth low-pass filter with a cutoff frequency of 40Hz to obtain stable and continuous gas pressure and flow data.

[0057] It is understandable that a respiratory cycle can include an expiratory phase and an inspiratory phase. The ventilator operation data collected by the sensor is the operation data collected by the ventilator in multiple respiratory cycles. The operation data of each respiratory cycle includes the operation data of the expiratory phase and the operation data of the inspiratory phase.

[0058] Therefore, the ventilator control system can segment the expiratory and inspiratory phases of each respiratory cycle within multiple respiratory cycles. Furthermore, the ventilator control system can segment the ventilator's operational data for each respiratory cycle from the sensor-collected data across multiple respiratory cycles into operational data for the expiratory phase and operational data for the inspiratory phase of that respiratory cycle.

[0059] In one possible implementation, the ventilator control system can divide each of the multiple respiratory cycles into an expiratory phase and an inspiratory phase based on a dynamic flow threshold method.

[0060] Specifically, the ventilator control system can determine the peak flow rate data (the maximum value among the flow rate data collected by the sensors across multiple respiratory cycles). Then, the ventilator control system can dynamically set the inspiratory trigger threshold based on the peak flow rate data. For example, the ventilator control system can dynamically determine the inspiratory trigger threshold between 5% and 10% of the peak flow rate data, thereby adapting to changes in flow rate data under different user conditions and avoiding errors in the segmentation of the expiratory and inspiratory phases due to baseline drift in the flow rate data.

[0061] Meanwhile, the ventilator control system can also employ a time window verification mechanism to avoid misjudging the expiratory and inspiratory phases due to fluctuations in flow data.

[0062] Specifically, when the flow rate changes from a negative value to a positive value, and the flow rate remains positive within a preset time window, the ventilator control system determines the moment when the flow rate changes from negative to positive as the start of the inspiratory phase. Conversely, when the flow rate changes from a positive value to a negative value, and the flow rate remains negative within a preset time window, the ventilator control system determines the moment when the flow rate changes from positive to negative as the start of the expiratory phase.

[0063] In one possible implementation, the ventilator control system can dynamically adjust a preset time window based on the user's respiratory rate. For example, when the respiratory rate is below 15 breaths per minute, the ventilator control system can set the preset time window to any value between 150 milliseconds and 200 milliseconds. When the respiratory rate is between 15 and 25 breaths per minute, the ventilator control system can set the preset time window to any value between 100 and 150 milliseconds. When the respiratory rate is above 25 breaths per minute, the ventilator control system can set the preset time window to any value between 50 and 100 milliseconds.

[0064] Furthermore, the ventilator control system can record the start time of inspiration, end time of inspiration, start time of expiration, and end time of expiration of each respiratory cycle by the sensor to construct a complete timestamp sequence of respiratory cycles.

[0065] In one possible implementation, the ventilator control system can also determine the effectiveness of the segmented respiratory cycles.

[0066] Specifically, for each segmented respiratory cycle, the ventilator control system calculates the inspiratory time of that cycle. If the inspiratory time of that cycle is less than a first time threshold or greater than a second time threshold, the ventilator control system discards the pressure and flow data collected by the sensors for that cycle. Then, the ventilator control system uses the operational data from the most recent valid respiratory cycle as a replacement value for the operational data of that cycle. By determining the validity of the respiratory cycles, the ventilator control system can eliminate spurious respiratory cycles caused by the user's cough, turning over, or momentary sensor interference.

[0067] S102: The ventilator control system determines the first breathing work based on the operating data. The first breathing work is used to characterize the energy consumed by the user to overcome elastic and inelastic resistance for lung ventilation when the ventilator is running at the current values ​​of the operating parameters.

[0068] It should be noted that the first respiratory work can be the respiratory work corresponding to any respiratory cycle collected by the sensor, and the ventilator control system can calculate the respiratory work corresponding to each respiratory cycle separately. This embodiment uses the first respiratory work as the respiratory work of the target respiratory cycle as an example to illustrate the subsequent steps.

[0069] Before determining the first work of breathing, the ventilator control system can first determine the fusion values ​​of airway resistance and lung compliance for the target respiratory cycle. (See also...) Figure 2 , Figure 2 A schematic diagram of a process for determining the fusion value of airway resistance and the fusion value of lung compliance is shown.

[0070] Specifically, the ventilator control system first inputs the collected ventilator operating data during the target respiratory cycle into a machine learning model for inference, thereby obtaining a predicted value of airway resistance for the target respiratory cycle. Predictors of lung compliance Among them, airway resistance can be used to characterize the resistance encountered by gas as it flows through the user's airway, while lung compliance can be used to characterize the user's ability to change lung volume under a unit pressure change.

[0071] Furthermore, the ventilator control system can also calculate reference values ​​for airway resistance and lung compliance for the target respiratory cycle based on the respiratory mechanics model.

[0072] The specific expression for the respiratory mechanics model is as follows:

[0073] in, Here are the pressure data at time t, and R is the airway resistance. Here is the traffic data at time t. This refers to the accumulated volume data up to time t. For lung compliance, PEEP is positive end-expiratory pressure.

[0074] Then, the ventilator control system can sample n flow data from the flow data of the target respiratory cycle and n pressure data from the pressure data of the target respiratory cycle, with the n flow data and n pressure data corresponding to the same n sampling points.

[0075] An overdetermined set of equations was established based on a respiratory mechanics model.

[0076] The overdetermined system of equations is as follows:

[0077] in, For the i-th pressure data sampled during the target respiratory cycle, For the i-th flow rate data sampled during the target respiratory cycle, This refers to the i-th volume data sampled during the target respiratory cycle.

[0078] The overdetermined system of equations can be represented in matrix form:

[0079] in, , , .

[0080] The parameter vector can be obtained by using the least squares method:

[0081] Obtain reference values ​​for airway resistance during the target respiratory cycle. Reference values ​​for lung compliance .

[0082] Furthermore, the ventilator control system can calculate the predicted pressure data corresponding to each of the n sampling points in the target respiratory cycle using the following formula:

[0083] in, This represents the predicted pressure data corresponding to the i-th sampling point.

[0084] The root mean square error (RMSE) of the pressure residuals is calculated using the following formula:

[0085] When the RMSE is less than the preset error threshold, the ventilator control system can determine that the respiratory mechanics model can describe the target respiratory cycle well, and determine the reference value of the airway resistance for the calculated target respiratory cycle. Reference values ​​for lung compliance These are high-reliability reference values. When the RMSE is not less than the preset error threshold, the ventilator control system can determine that the quality of the operating data of the target respiratory cycle collected by the sensor is poor. The ventilator control system can then use the high-reliability airway resistance reference value and the high-reliability lung compliance reference value of the previous respiratory cycle as the reference values ​​for airway resistance and lung compliance of the target respiratory cycle.

[0086] In one possible implementation, the ventilator control system can update the predicted values ​​of airway resistance and lung compliance for the target respiratory cycle.

[0087] Specifically, the ventilator control system can calculate the first error value using the following formula: the relative error between the predicted airway resistance value and the reference airway resistance value. The first error value can be used to indicate the extent to which the predicted value of airway resistance deviates from the reference value of airway resistance:

[0088] Furthermore, the ventilator control system can calculate the second error value using the following formula: the relative error between the predicted value and the reference value of lung compliance. The second error value can be used to indicate the extent to which the predicted lung compliance value deviates from the reference value for lung compliance:

[0089] Then, the ventilator control system can calculate the comprehensive error value e based on the first error value and the second error value:

[0090] When e is greater than the preset comprehensive error threshold, the ventilator control system can update the predicted values ​​of airway resistance and lung compliance, obtaining updated predicted values ​​for airway resistance and lung compliance. When e is not greater than the preset comprehensive error threshold, the ventilator control system may not update the predicted values ​​of airway resistance and lung compliance.

[0091] The formula for updating the predicted airway resistance is:

[0092] The update formula for the predicted value of lung compliance is:

[0093] in, This is the updated predicted value for airway resistance. For learning rate, This represents the updated predicted value for lung compliance.

[0094] Furthermore, the ventilator control system can fuse the updated predicted value of airway resistance and the reference value of airway resistance to obtain the fused value of airway resistance for the m-th respiratory cycle, and the ventilator control system can fuse the updated predicted value of lung compliance and the reference value of lung compliance to obtain the fused value of lung compliance for the target respiratory cycle.

[0095] The formula for the fusion of airway resistance is:

[0096] The fusion formula for lung compliance is:

[0097] in, The fusion value representing airway resistance. To integrate weights, Fusion value representing lung compliance.

[0098] To reduce the impact of random fluctuations in operating data and measurement noise on the calculation results of respiratory mechanics parameters and improve the stability of output parameters, the ventilator control system can use the exponentially weighted moving average (EWMA) method to recursively filter the fusion value of airway resistance and the fusion value of lung compliance for the target respiratory cycle.

[0099] Specifically, the respiratory control system can perform recursive filtering using the following formula, taking the m-th respiratory cycle as an example:

[0100] in, This represents the filtered fusion value of airway resistance for the m-th respiratory cycle. This represents the filtered fusion value of lung compliance for the m-th respiratory cycle. As a smoothing factor, The fused value of airway resistance in the m-th respiratory cycle before filtering. The fused value of lung compliance in the m-th respiratory cycle before filtering. This represents the filtered fusion value of airway resistance for the (m-1)th respiratory cycle. This is the filtered fusion value of lung compliance for the (m-1)th respiratory cycle.

[0101] It is understandable that the filtered airway resistance fusion value of the first respiratory cycle can be the unfiltered airway resistance fusion value of the same respiratory cycle, i.e. The filtered lung compliance fusion value of the first respiratory cycle can be compared to the unfiltered lung compliance fusion value of the same respiratory cycle, i.e. .

[0102] In one possible implementation, the ventilator control system can determine the user's elastic breathing work and resistance breathing work during the target respiratory cycle based on the pressure data, flow data, volume data, the fusion value of filtered airway resistance, and the fusion value of filtered lung compliance of the target respiratory cycle.

[0103] Specifically, the ventilator control system can calculate the user's elastic breathing work according to the following formula:

[0104] in, This is a form of flexible breathing exercise. This is the moment when inhalation begins. The moment when the exhalation cycle begins. This represents the fusion value of lung compliance after filtering.

[0105] The ventilator control system can calculate the user's work of breathing with resistance using the following formula:

[0106] in, For resistance breathing work, This is the fused value of the filtered airway resistance.

[0107] Then, the ventilator control system can calculate the user's first breathing work based on the elastic breathing work and the resistance breathing work. The first breathing work is the energy consumed by the user during the target respiratory cycle to overcome elastic and inelastic resistance for lung ventilation when the ventilator is running at the current values ​​of its operating parameters.

[0108] in, This is the first breathing exercise.

[0109] In one possible implementation, since the breathing work of the target respiratory cycle fluctuates greatly, the ventilator control system can use a dynamic sliding window averaging algorithm to filter the breathing work data of the target respiratory cycle, and further employ an exponential decay weight allocation strategy within the sliding window to improve the response sensitivity to changes in the user's respiratory state.

[0110] Specifically, the ventilator control system can calculate the average work of breathing over multiple respiratory cycles using the following formula:

[0111] in, Let K be the average work of breathing and K be the length of the sliding window. Forgetting factor, Let m be the respiratory work of the i-th respiratory cycle, and m be the sequence number of the target respiratory cycle.

[0112] Then, the ventilator control system can determine the average work of breathing as the first work of breathing in the target respiratory cycle.

[0113] In one possible implementation, the ventilator control system can calculate the standard deviation using the following formula. :

[0114] The ventilator control system can be based on The window length K is dynamically adjusted, and the specific expression is:

[0115] Then, the ventilator control system can calculate the coefficient of variation of the first breathing work using the following formula. :

[0116] The forgetting factor can be adjusted based on the coefficient of variation (CV). .

[0117]

[0118] S103: The ventilator control system determines the target values ​​of the ventilator's operating parameters based on the first respiratory work or operating data. The ventilator operates at the target values ​​of the operating parameters, minimizing the user's respiratory work.

[0119] To facilitate understanding of the solutions provided in the embodiments of this application by those skilled in the art, please refer to... Figure 3 , Figure 3 A flowchart illustrating whether to trigger the determination of target values ​​for runtime parameters is shown.

[0120] In one possible implementation, after the ventilator control system receives the first respiratory work, it can determine whether the first respiratory work meets a first triggering condition. The first triggering condition is that the first respiratory work is less than a first preset threshold or the first respiratory work is greater than a second preset threshold.

[0121] When the first respiratory work meets the first triggering condition, the ventilator control system can redetermine the target operating parameters of the ventilator to reduce the user's respiratory work. The second preset threshold is greater than the first preset threshold.

[0122] In another possible implementation, the sensor collects operational data of the ventilator over M respiratory cycles. The ventilator control system calculates the fused values ​​of airway resistance and lung compliance for each of the M respiratory cycles, obtaining the fused values ​​of M airway resistances and M lung compliances. The ventilator control system can calculate the average of the fused values ​​of the M airway resistances, denoted as the first average. Furthermore, the ventilator control system can calculate the average of the fused values ​​of the M lung compliances, denoted as the second average.

[0123] After obtaining the fused values ​​of airway resistance and lung compliance for the current respiratory cycle (i.e., the target respiratory cycle), the ventilator control system can determine whether these values ​​meet a second trigger condition. The second trigger condition is either that the difference between the fused value of airway resistance for the target respiratory cycle and a first average value is greater than a third preset threshold, or that the difference between the fused value of lung compliance for the target respiratory cycle and a second average value is greater than a fourth preset threshold. If the fused values ​​of airway resistance and lung compliance meet the second trigger condition, the ventilator control system can re-determine the target operating parameters of the ventilator to reduce the user's work of breathing.

[0124] In one possible implementation, the ventilator control system can determine whether the work of breathing in each of a series of consecutive respiratory cycles satisfies a first trigger condition. Furthermore, the ventilator control system can also determine whether the fusion value of airway resistance and the fusion value of lung compliance in each of the series of consecutive respiratory cycles satisfies a second trigger condition.

[0125] If the work of breathing in multiple consecutive respiratory cycles meets the first trigger condition, or if the fusion value of airway resistance and the fusion value of lung compliance in multiple consecutive respiratory cycles meets the second trigger condition, the ventilator control system can redetermine the target operating parameters of the ventilator to reduce the user's work of breathing.

[0126] In one possible implementation, to avoid repeated triggering of ventilator operating parameter readjustment within a short period due to unstable ventilator operating parameter adjustments, the ventilator control system can be set to a minimum trigger interval T. Within a time interval T after the ventilator operating parameter values ​​have been readjusted, the ventilator control system will not readjust the ventilator operating parameter values.

[0127] The following example illustrates how to determine the target values ​​for the operating parameters of a ventilator.

[0128] First, the ventilator control system can determine the theoretical optimal values ​​for its operating parameters. In one possible implementation, the ventilator's operating parameters may include respiratory rate and tidal volume. The ventilator control system can first determine the theoretical optimal values ​​for minute ventilation and respiratory rate.

[0129] Specifically, the ventilator control system can calculate the user's ideal weight-benefit (IBW) using the Devine formula, based on the user's height and gender.

[0130] Then, the ventilator control system can calculate the target minute ventilation based on the target minute ventilation percentage and IBW in the initial operating parameters set before the ventilator is started.

[0131]

[0132] in, The target minute ventilation rate is denoted as k; k is a factor related to the minute ventilation rate, typically taken as 100 mL / (kg). ); The percentage of target minute ventilation in the initial operating parameters set before the ventilator is put into operation.

[0133] Furthermore, the ventilator control system can calculate the theoretical optimal value of the respiratory rate using the Otis formula, the specific expression of which is:

[0134] in, This represents the theoretically optimal value for respiratory rate. This represents the actual respiratory rate during the current operation of the ventilator. Dead space refers to the volume of gas that enters the respiratory tract during each breath but does not participate in gas exchange.

[0135] S104: The ventilator control system controls the ventilator to operate at the target values ​​of the operating parameters.

[0136] Because users have spontaneous breathing, there may be slight deviations between the theoretical optimal values ​​and the actual optimal values ​​of the ventilator's operating parameters.

[0137] Therefore, the ventilator control system in this embodiment does not directly control the ventilator to operate at the theoretically optimal value of the operating parameters, but instead starts from the current actual value of the ventilator operating parameters and gradually moves in the direction of decreasing breathing work.

[0138] For ease of understanding, see Figure 4 , Figure 4 A flowchart illustrating a process for determining the actual optimal values ​​of the operating parameters of a ventilator, i.e., determining the target values ​​of the operating parameters, is shown.

[0139] Specifically, the ventilator control system can determine whether the current value of the respiratory rate, one of the ventilator's operating parameters, is equal to the theoretical optimal value. If the ventilator control system determines that the current value of the respiratory rate is not equal to the theoretical optimal value, it can increase or decrease the current value of the respiratory rate by a preset step size to obtain the first adjusted respiratory rate value. For example, when... At that time, Increase Obtain the respiratory rate value after the first adjustment. This is the preset step size. When At that time, Obtain the value of the respiratory rate after the first adjustment.

[0140] Furthermore, the ventilator control system can determine the tidal volume value after the first adjustment based on the respiratory rate and the target ventilation. The specific expression for determining the tidal volume value is:

[0141] in, This represents the tidal volume value after the nth adjustment. For target minute ventilation, This is the value of the respiratory rate after the nth adjustment.

[0142] Then, the ventilator control system can control the ventilator to operate at the first adjusted respiratory rate and tidal volume values ​​to obtain the user's second work of breathing. The second work of breathing refers to the energy consumed by the user in one respiratory cycle to overcome elastic and inelastic resistance during lung ventilation when the ventilator is operating at the first adjusted operating parameters.

[0143] When the second respiratory work is not less than the first respiratory work, the ventilator control system can determine the current operating parameter value as the target value of the operating parameter, that is, determine the current value of the respiratory rate as the target value of the respiratory rate, and determine the current value of the tidal volume as the target value of the tidal volume.

[0144] If the second respiratory work is less than the first respiratory work, the ventilator control system can increase the value of the respiratory rate after the first adjustment by a preset step size to obtain the value of the respiratory rate after the second adjustment.

[0145] Furthermore, the ventilator control system can determine the second adjusted tidal volume value based on the second adjusted respiratory rate value and the target ventilation volume. For the specific process of determining the second adjusted tidal volume value, please refer to the process of determining the tidal volume value after the first adjustment.

[0146] Then, the ventilator control system can control the ventilator to operate at the second adjusted respiratory rate and tidal volume values ​​to obtain the user's third respiratory work. The third respiratory work refers to the energy consumed by the user in one respiratory cycle to overcome elastic and inelastic resistance for lung ventilation when the ventilator is operating at the second adjusted operating parameters.

[0147] When the third respiratory work is not less than the second respiratory work, the ventilator control system can determine the value of the operating parameters after the first adjustment as the target value of the operating parameters. That is, the ventilator control system can determine the value of the respiratory rate after the first adjustment as the target value of the respiratory rate, and the value of the tidal volume after the first adjustment as the target value of the tidal volume.

[0148] If the third respiratory effort is less than the second respiratory effort, the ventilator control system can continue to increase the value of the second adjusted respiratory rate by a preset step size to obtain the value of the third adjusted respiratory rate, until the user's respiratory effort no longer decreases, and the ventilator control system no longer adjusts the value of the respiratory rate.

[0149] Once the target values ​​for the ventilator's operating parameters are determined, namely the target values ​​for the ventilator's respiratory rate and tidal volume, the ventilator control system can control the ventilator to operate at the target values ​​for the respiratory rate and tidal volume, thereby minimizing the user's breathing work.

[0150] Through the methods provided in the above embodiments, the ventilator control system can acquire the ventilator's operating data. Then, the ventilator control system can determine, based on the ventilator's operating data, the first respiratory work performed by the user to overcome elastic and inelastic resistance during lung ventilation when the ventilator is operating at the current values ​​of its operating parameters. Further, the ventilator control system can determine, based on the first respiratory work or the ventilator's operating data, the target value of the operating parameters that minimizes the user's respiratory work. The ventilator control system can then control the ventilator to operate at the target value of the operating parameters. Because the ventilator control system can determine the target value of the ventilator's operating parameters that minimizes the user's respiratory work based on the ventilator's operating data and control the ventilator to operate at the target value of the operating parameters, compared to setting the ventilator's parameters to constant pressure ventilation or constant volume ventilation operating parameters, the ventilator can be adapted to different users, thereby improving the user's breathing comfort.

[0151] The specific implementation steps for training the machine learning model in step S102 are described below.

[0152] First, the ventilator control system can establish a training sample library based on the respiratory data of a large number of users. Each sample includes data such as peak pressure, plateau pressure, average inspiratory flow rate, peak inspiratory flow rate, tidal volume, and PEEP. Then, the ventilator control system can use a standard lung model to offline identify the corresponding airway resistance and lung compliance as training labels. An extreme random tree model is used to establish a nonlinear regression model, and hyperparameters such as the number of decision trees, maximum tree depth, minimum number of samples per leaf node, and number of candidate features are determined through grid search combined with ten-fold cross-validation.

[0153] Then, all historical training data were randomly divided into 10 non-overlapping subsets. One subset was selected as the validation set each time, and the remaining nine subsets were used as the training set. This process was repeated 10 times, ensuring each subset served as a validation set. For different hyperparameter combinations, the mean square root error (MSE) of the 10 validation results was calculated, and the hyperparameter combination with the smallest MSE was selected as the final model parameters. After training, the trained tree structure, node partitioning rules, and leaf node predictions were permanently deployed to the ventilator.

[0154] It is worth noting that other reasonable combinations of steps that can be conceived by those skilled in the art based on the above description also fall within the scope of protection of this application. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to this application.

[0155] Based on the ventilator control method using the minimum work-guided ventilation algorithm provided in the above-described embodiments, this application also provides a ventilator control device using the minimum work-guided ventilation algorithm. The ventilator control device using the minimum work-guided ventilation algorithm will be described below with reference to the accompanying drawings. Since the principle by which the device solves the problem in this embodiment is similar to the ventilator control method using the minimum work-guided ventilation algorithm described above in this application, the implementation of the device can refer to the implementation of the method, and repeated details will not be elaborated further.

[0156] See Figure 5 As shown, this figure is a schematic diagram of the structure of a ventilator control device based on a minimum work of breathing guided ventilation algorithm provided in an embodiment of this application. Figure 5 As shown, the ventilator control device 500 of the minimum work of breathing guided ventilation algorithm includes: The acquisition module 501 is used to acquire the operating data of the ventilator, which is used to provide respiratory support to the user; The breathing work determination module 502 is used to determine a first breathing work based on the operating data. The first breathing work is used to characterize the energy consumed by the user to overcome elastic and inelastic resistance for lung ventilation when the ventilator is running at the current value of the operating parameters. The operating parameter determination module 503 is used to determine the target value of the operating parameters of the ventilator based on the first breathing work or the operating data, wherein the ventilator operates at the target value of the operating parameters and the user's breathing work is minimized; The control module 504 is used to control the ventilator to operate at the target values ​​of the operating parameters.

[0157] In one possible implementation, the breathing work determination module 502 is specifically used to input the pressure data, the flow data, and the volume data into a machine learning model for inference to obtain predicted values ​​of airway resistance and lung compliance. The airway resistance characterizes the resistance encountered by gas as it flows through the user's airway, and the lung compliance characterizes the user's ability to change lung volume under a unit pressure change. The pressure data, flow data, and volume data are input into the respiratory mechanics model to obtain reference values ​​for airway resistance and lung compliance. The user's first work of breathing is determined based on the predicted value of airway resistance, the reference value of airway resistance, the predicted value of lung compliance, and the reference value of lung compliance.

[0158] In one possible implementation, the breathing work determination module 502 is specifically configured to determine a first error value based on the predicted value of the airway resistance and the reference value of the airway resistance, wherein the first error value is used to indicate the degree to which the predicted value of the airway resistance deviates from the reference value of the airway resistance. A second error value is determined based on the predicted value of lung compliance and the reference value of lung compliance, the second error value indicating the degree to which the predicted value of lung compliance deviates from the reference value of lung compliance; Based on the first error value and the second error value, the predicted values ​​of airway resistance and lung compliance are updated to obtain the updated predicted values ​​of airway resistance and lung compliance. The user's first work of breathing is determined based on the updated predicted value of airway resistance, the reference value of airway resistance, the updated predicted value of lung compliance, and the reference value of lung compliance.

[0159] In one possible implementation, the breathing work determination module 502 is specifically used to determine the fused value of the airway resistance based on the updated predicted value of the airway resistance and the reference value of the airway resistance. The fusion value of lung compliance is determined based on the updated predicted value of lung compliance and the reference value of lung compliance; The user's first work of breathing is determined based on the fusion value of the airway resistance and the fusion value of the lung compliance.

[0160] In one possible implementation, the operating parameter determination module 503 is specifically used to determine the target value of the theoretically optimal operating parameters; If the current value of the operating parameter of the ventilator is not equal to the theoretical optimal value of the operating parameter, the current value of the operating parameter is increased or decreased by a preset step size to obtain the value of the operating parameter after the first adjustment. The ventilator is controlled to operate with the values ​​of the first adjusted operating parameters to obtain the user's second breathing work; If the second breathing effort is not less than the first breathing effort, the current value of the operating parameter is determined as the target value of the operating parameter.

[0161] In one possible implementation, the operating parameter determination module 503 is specifically used to increase or decrease the value of the first adjusted operating parameter by a preset step size when the second breathing work is less than the first breathing work, so as to obtain the value of the second adjusted operating parameter. The ventilator is controlled to operate with the values ​​of the second adjusted operating parameters to obtain the user's third breathing work; If the third breathing effort is not less than the second breathing effort, the value of the operating parameter after the first adjustment is determined as the target value of the operating parameter.

[0162] In one possible implementation, the operating parameter determination module 503 is specifically used to determine the target value of the operating parameters of the ventilator when the first breathing work is less than a first preset threshold or the first breathing work is greater than a second preset threshold. Wherein, the second preset threshold is greater than the first preset threshold.

[0163] In one possible implementation, the operating parameter determination module 503 is specifically used to determine a first average value based on the fusion values ​​of the M airway resistances, and to determine a second average value based on the fusion values ​​of the M lung compliances; If the difference between the fused value of airway resistance in the current respiratory cycle and the first average value is greater than a third preset threshold, or if the difference between the fused value of lung compliance in the current respiratory cycle and the second average value is greater than a fourth preset threshold, the target values ​​of the ventilator's operating parameters are determined.

[0164] It should be noted that the specific implementation of each module in this embodiment can be found in the relevant descriptions in the above method embodiments. The module division in this application embodiment is illustrative and only represents a logical functional division; in actual implementation, there may be other division methods. In this application embodiment, each functional module can be concentrated in one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. For example, in the above embodiment, the first acquisition module and the holding module can be the same module or different modules.

[0165] Furthermore, this application also provides a computer device, which includes a processor and a memory. The memory is used to store instructions, and the processor executes the instructions stored in the memory to cause the computer device to execute the ventilator control method of the minimum work of breathing guided ventilation algorithm provided in any of the above embodiments.

[0166] This application also provides a computer-readable storage medium, characterized in that it stores a computer program thereon, wherein the computer program, when executed by a processor, implements the ventilator control method of the minimum work of breathing guided ventilation algorithm provided in any of the above embodiments.

[0167] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems or apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and relevant parts can be referred to the method section.

[0168] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0169] It should also be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0170] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0171] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A ventilator control method based on a minimum work-of-breath guiding ventilation algorithm, characterized in that, The method includes: Acquire operational data of the ventilator, which is used to provide respiratory support to the user; A first breathing work is determined based on the operating data. The first breathing work is used to characterize the energy consumed by the user to overcome elastic and inelastic resistance during lung ventilation when the ventilator is running at the current values ​​of the operating parameters. The target values ​​of the operating parameters of the ventilator are determined based on the first breathing work or the operating data, and the ventilator operates at the target values ​​of the operating parameters, so that the user's breathing work is minimized; Control the ventilator to operate at the target values ​​of the operating parameters.

2. The method according to claim 1, characterized in that, The operational data includes pressure data at the target location, flow data at the target location, and volume data of gas delivered through the target location, where the target location is the tubing of the ventilator and the interface for connecting to the user's breathing interface. Determining the first breathing work based on the operational data includes: The pressure data, flow data, and volume data are input into a machine learning model for inference to obtain predicted values ​​of airway resistance and lung compliance. The airway resistance characterizes the resistance encountered by gas as it flows through the user's airway, and the lung compliance characterizes the user's ability to change lung volume under a unit pressure change. The pressure data, flow data, and volume data are input into the respiratory mechanics model to obtain reference values ​​for airway resistance and lung compliance. The user's first work of breathing is determined based on the predicted value of airway resistance, the reference value of airway resistance, the predicted value of lung compliance, and the reference value of lung compliance.

3. The method according to claim 2, characterized in that, Determining the user's first work of breathing based on the predicted value of airway resistance, the reference value of airway resistance, the predicted value of lung compliance, and the reference value of lung compliance includes: A first error value is determined based on the predicted value of the airway resistance and the reference value of the airway resistance. The first error value is used to indicate the degree to which the predicted value of the airway resistance deviates from the reference value of the airway resistance. A second error value is determined based on the predicted value of lung compliance and the reference value of lung compliance, the second error value indicating the degree to which the predicted value of lung compliance deviates from the reference value of lung compliance; Based on the first error value and the second error value, the predicted values ​​of airway resistance and lung compliance are updated to obtain the updated predicted values ​​of airway resistance and lung compliance. The user's first work of breathing is determined based on the updated predicted value of airway resistance, the reference value of airway resistance, the updated predicted value of lung compliance, and the reference value of lung compliance.

4. The method according to claim 3, characterized in that, The step of determining the user's first work of breathing based on the updated predicted value of airway resistance, the reference value of airway resistance, the updated predicted value of lung compliance, and the reference value of lung compliance includes: The fused value of the airway resistance is determined based on the updated predicted value of the airway resistance and the reference value of the airway resistance. The fusion value of lung compliance is determined based on the updated predicted value of lung compliance and the reference value of lung compliance; The user's first work of breathing is determined based on the fusion value of the airway resistance and the fusion value of the lung compliance.

5. The method according to claim 1, characterized in that, Determining target values ​​for the ventilator's operating parameters based on the first breathing work or the operating data includes: Determine the theoretical optimal values ​​of the operating parameters; If the current value of the operating parameter of the ventilator is not equal to the theoretical optimal value of the operating parameter, the current value of the operating parameter is increased or decreased by a preset step size to obtain the value of the operating parameter after the first adjustment. The ventilator is controlled to operate at the values ​​of the first adjusted operating parameters to obtain the user's second breathing work; If the second breathing effort is not less than the first breathing effort, the current value of the operating parameter is determined as the target value of the operating parameter.

6. The method according to claim 5, characterized in that, The method further includes: If the second breathing work is less than the first breathing work, the value of the first adjusted operating parameter is increased or decreased by a preset step size to obtain the value of the second adjusted operating parameter. The ventilator is controlled to operate with the values ​​of the second adjusted operating parameters to obtain the user's third breathing work; If the third breathing effort is not less than the second breathing effort, the value of the first adjusted operating parameter is determined as the target value of the operating parameter.

7. The method according to claim 1, characterized in that, Determining the target values ​​of the ventilator's operating parameters based on the first respiratory work or the operating data includes: If the first breathing work is less than a first preset threshold or the first breathing work is greater than a second preset threshold, the target values ​​of the operating parameters of the ventilator are determined. Wherein, the second preset threshold is greater than the first preset threshold.

8. The method according to claim 4, characterized in that, The fusion value of airway resistance includes the fusion value of M airway resistance over M respiratory cycles, with one fusion value corresponding to one respiratory cycle. The fusion value of lung compliance includes the fusion value of M lung compliance over M respiratory cycles, with one fusion value corresponding to one respiratory cycle. Determining the target values ​​of the ventilator's operating parameters based on the first respiratory work or the operating data includes: A first average value is determined based on the fusion values ​​of the M airway resistances, and a second average value is determined based on the fusion values ​​of the M lung compliances. If the difference between the fused value of airway resistance in the current respiratory cycle and the first average value is greater than a third preset threshold, or if the difference between the fused value of lung compliance in the current respiratory cycle and the second average value is greater than a fourth preset threshold, the target values ​​of the ventilator's operating parameters are determined.

9. A ventilator control device based on a minimum work-of-breath guiding ventilation algorithm, characterized in that, The device includes: An acquisition module is used to acquire the operating data of the ventilator, which is used to provide respiratory support to the user; The breathing work determination module is used to determine a first breathing work based on the operating data. The first breathing work is used to characterize the energy consumed by the user to overcome elastic and inelastic resistance for lung ventilation when the ventilator is running at the current values ​​of the operating parameters. The operating parameter determination module is used to determine the target value of the operating parameters of the ventilator based on the first breathing work or the operating data, wherein the ventilator operates at the target value of the operating parameters and the user's breathing work is minimized; The control module is used to control the ventilator to operate at the target values ​​of the operating parameters.

10. A computer device, characterized in that, The computer device includes a processor and a memory, the memory being used to store instructions, and the processor executing the instructions stored in the memory to cause the computer device to perform a ventilator control method based on the minimum work of breathing guided ventilation algorithm as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, It stores a computer program, wherein when the computer program is executed by a processor, it implements the ventilator control method of the minimum work of breathing guided ventilation algorithm as described in any one of claims 1 to 8.

Images