Anesthetic gas output control system and method for anesthesia machine

Abstract

The invention relates to an anesthetic gas output control system for an anesthesia machine and a method thereof, and relates to the technical field of anesthesia machines, the system comprises a data acquisition module used for collecting breathing parameters and gas state parameters of a patient and constructing a breathing dynamics model containing nonlinear correction; the concentration prediction module is used for constructing a gas mixing concentration prediction model with pressure dynamic compensation according to the airway pressure of the anesthetic gas output by the respiratory dynamic model; the parameter control module is used for constructing a control objective function based on the concentration deviation, the flow change rate and the pressure deviation of the anesthetic gas; the self-adaptive compensation module is used for determining a self-adaptive compensation factor based on the concentration deviation and the pressure change rate of the anesthetic gas; the flow correction module is used for calculating flow correction values of various anesthetic gases; and the gas output module is used for outputting the anesthetic gas according to the flow correction values of various anesthetic gases. The system can improve the accuracy of anesthetic gas output control.

Description

Technical Field

[0001] The present invention relates to the technical field of anesthesia machines, and particularly to an anesthesia gas output control system, method, electronic device, and non-transitory computer-readable storage medium for an anesthesia machine. Background Art

[0002] An anesthesia machine is a medical device that provides anesthesia gas to patients during surgery. One of its core functions is to mix oxygen, nitrous oxide, volatile anesthetics (such as isoflurane, sevoflurane, etc.) in a set ratio and stably output them to ensure the anesthesia state of patients during surgery. The existing anesthesia gas output control methods mainly use mechanical or electronic flow control valves, and achieve the flow regulation of different gases through components such as flow meters, pressure sensors, and proportional valves, and output stable mixed gas through a gas mixer.

[0003] However, the existing control methods generally have problems such as response lag, limited control accuracy, and poor adaptability to the lung functions of different patients. For example, the traditional proportional valve adjustment mechanism is difficult to achieve real-time high-precision control of the output flow in a rapidly changing clinical environment. Especially when the patient's lung compliance or ventilation resistance changes, it may cause a deviation between the actual inhaled anesthesia gas concentration and the set value. Summary of the Invention

[0004] The present invention aims at the technical problems existing in the prior art, and provides an anesthesia gas output control system, method, electronic device, and non-transitory computer-readable storage medium for an anesthesia machine, which can improve the accuracy of anesthesia gas output control.

[0005] The technical solutions for the present invention to solve the above technical problems are as follows: The present invention provides an anesthesia gas output control system for an anesthesia machine, and the system includes: A data acquisition module, configured to collect the respiratory parameters and gas state parameters of a patient, and construct a respiratory dynamics model including non-linear correction; A concentration prediction module, configured to construct a gas mixture concentration prediction model with pressure dynamic compensation according to the airway pressure of the anesthesia gas output by the respiratory dynamics model; A parameter control module, configured to construct a control objective function based on the concentration deviation, flow rate change rate, and pressure deviation of the anesthesia gas, and control the concentration, flow rate, and pressure of the anesthesia gas to approach their respective target values; An adaptive compensation module, configured to determine an adaptive compensation factor based on the concentration deviation and pressure change rate of the anesthesia gas; A flow correction module, configured to calculate the flow correction values of various types of the anesthesia gas; A gas output module, configured to output anesthesia gas according to the flow correction values of various types of the anesthesia gas.

[0006] Optionally, the data acquisition module is further configured to: Obtain real-time measurement values of the patient's lung compliance, airway resistance, and respiratory rate; Synchronously collect real-time flows, airway pressures, and gas concentrations of various gases output by the anesthesia machine; Construct the respiratory dynamics model according to the real-time measurement values of the patient's lung compliance, airway resistance, and respiratory rate, and the real-time flows, airway pressures, and gas concentrations of various gases output by the anesthesia machine.

[0007] Optionally, the expression of the respiratory dynamics model is:

[0008] where, is pressure, C is lung compliance, is gas flow, R is airway resistance, is a non-linear correction coefficient, and f is the respiratory rate.

[0009] Optionally, the non-linear correction coefficient is determined through the following steps: Obtain basic parameters under different body postures through training with clinical big data; the basic parameters include real-time respiratory waveforms; Use a Kalman filter to dynamically correct the real-time respiratory waveforms to obtain correction parameters; Based on the recursive least squares method, online update the correction parameters to obtain the non-linear correction coefficient.

[0010] Optionally, the concentration prediction module is further configured to: Obtain the ratio of the airway pressure of the anesthetic gas to the standard pressure to obtain a pressure normalization factor; Perform weighted summation on the concentrations of each type of anesthetic gas to obtain a mixed concentration; Construct the gas mixed concentration prediction model according to the pressure normalization factor and the mixed concentration.

[0011] Optionally, the expression of the gas mixed concentration prediction model is:

[0012] where, is the predicted mixed concentration of the anesthetic gas at time is the concentration of the i-th type of anesthetic gas at time t, is the weight of the i-th type of anesthetic gas, are the first correction parameter, the second correction parameter, and the third correction parameter respectively, is the standard pressure.

[0013] Optionally, the parameter control module is further configured to: Obtain the target anesthetic gas mixing concentration and the reference pressure; Obtain the concentration deviation of the anesthetic gas according to the difference between the predicted mixing concentration of the anesthetic gas and the target anesthetic gas mixing concentration; Obtain the pressure deviation of the anesthetic gas according to the difference between the current airway pressure of the anesthetic gas and the reference pressure.

[0014] Optionally, the adaptive compensation module is further configured to: Obtain a reference factor representing the reference gain; Determine the airway pressure change rate of the anesthetic gas according to the current airway pressure of the anesthetic gas; Determine the adaptive compensation factor according to the concentration deviation, the airway pressure change rate, and the reference factor of the anesthetic gas.

[0015] Optionally, the flow correction module is further configured to: Determine the change rate of the concentration deviation of the anesthetic gas; Obtain an integral regulation coefficient and a differential regulation coefficient; Correct the current flow rates of various types of the anesthetic gas according to the change rate of the concentration deviation, the concentration deviation, and the adaptive compensation factor of the anesthetic gas to obtain the flow correction values of various types of the anesthetic gas.

[0016] The present invention further provides an anesthetic gas output control method for an anesthesia machine, and the method includes: Collect the respiratory parameters and gas state parameters of a patient, and construct a respiratory dynamics model including non-linear correction; Construct a gas mixing concentration prediction model with pressure dynamic compensation according to the airway pressure of the anesthetic gas output by the respiratory dynamics model; Construct a control objective function based on the concentration deviation, the flow rate change rate, and the pressure deviation of the anesthetic gas, and control the concentration, flow rate, and pressure of the anesthetic gas to approach their respective target values; Determine an adaptive compensation factor based on the concentration deviation and the pressure change rate of the anesthetic gas; Calculate the flow correction values of various types of the anesthetic gas; Output the anesthetic gas according to the flow correction values of various types of the anesthetic gas.

[0017] In addition, to achieve the above object, the present invention further provides an electronic device, comprising: a memory for storing a computer software program; and a processor for reading and executing the computer software program, thereby implementing an anesthesia gas output control method for an anesthesia machine as described above.

[0018] In addition, to achieve the above object, the present invention further provides a non-transitory computer-readable storage medium storing a computer software program, which, when executed by a processor, implements an anesthesia gas output control method for an anesthesia machine as described above.

[0019] The beneficial effects of the present invention are as follows: (1) By monitoring the patient's respiratory parameters in real time and establishing an accurate respiratory dynamics model, the present invention ensures that the output anesthesia gas concentration meets the patient's needs. Using a gas mixing prediction model, it can dynamically predict the future gas concentration based on factors such as gas flow, pressure, and concentration, avoiding concentration overshoot or insufficiency and improving control accuracy.

[0020] (2) The present invention introduces an adaptive compensation factor that can be dynamically adjusted according to the patient's real-time respiratory state instead of using fixed parameter control. Combined with an integral-differential regulation mechanism, it can automatically adapt to different patients' physiological states and meet personalized anesthesia needs.

[0021] (3) Through a dynamic compensation mechanism, the present invention can quickly respond to changes in respiratory parameters, avoid the accumulation of concentration deviation, and ensure that the output anesthesia gas concentration is always within the optimal range.

[0022] In summary, through technologies such as precise control, adaptive regulation, multi-objective optimization, and dynamic compensation, the present invention realizes the intelligent management of anesthesia gas, improves control accuracy, adaptability, and safety, while reducing gas waste and environmental pollution, and has broad clinical application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a scenario diagram of an anesthesia gas output control method for an anesthesia machine provided by the present invention; Figure 2 is a schematic structural diagram of an anesthesia gas output control system for an anesthesia machine provided by the present invention; Figure 3 is a flowchart of an anesthesia gas output control method for an anesthesia machine provided by the present invention; Figure 4 is a schematic hardware structure diagram of a possible electronic device provided by the present invention; Figure 5 is a schematic hardware structure diagram of a possible computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0024] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part rather than all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0025] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality of" means two or more unless otherwise specifically defined.

[0026] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or having more advantages than other embodiments. The following description is provided to enable any person skilled in the art to make and use the present invention. Details are set forth for the purpose of explanation in the following description. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without these specific details. In other instances, well-known structures and processes are not described in detail to avoid unnecessary details from obscuring the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0027] Please refer to Figure 1 , Figure 1 which is a scenario diagram of an anesthetic gas output control method for an anesthetic machine provided by the present invention. As Figure 1 shown, the terminal and the server are connected through a network, for example, through a wired or wireless network connection, etc. Among them, the terminal may include, but is not limited to, portable terminals such as mobile phones and tablets installed with various network platform applications, as well as fixed terminals such as computers, inquiry machines, and advertising machines. Among them, the server provides various business services for users, including a service push server, a user recommendation server, etc.

[0028] It should be noted that Figure 1The scenario diagram of an anesthetic gas output control method for an anesthetic machine shown is merely an example. The terminals, servers, and application scenarios described in the embodiments of the present invention are for more clearly explaining the technical solutions of the embodiments of the present invention, and do not limit the technical solutions provided by the embodiments of the present invention. Those of ordinary skill in the art can know that with the evolution of the system and the emergence of new business scenarios, the technical solutions provided by the embodiments of the present invention are equally applicable to similar technical problems.

[0029] Among them, the terminal can be used for: Collect the respiratory parameters and gas state parameters of the patient, and construct a respiratory dynamics model including non-linear correction; Construct a gas mixture concentration prediction model with pressure dynamic compensation according to the airway pressure of the anesthetic gas output by the respiratory dynamics model; Construct a control objective function based on the concentration deviation, flow rate change rate, and pressure deviation of the anesthetic gas, and control the concentration, flow rate, and pressure of the anesthetic gas to approach their respective target values; Determine an adaptive compensation factor based on the concentration deviation and pressure change rate of the anesthetic gas; Calculate the flow rate correction values of various types of the anesthetic gas; Output the anesthetic gas according to the flow rate correction values of various types of the anesthetic gas.

[0030] Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of an anesthetic gas output control system for an anesthetic machine provided by the present invention.

[0031] As Figure 2 shown, an anesthetic gas output control system for an anesthetic machine proposed in the embodiments of the present invention includes: A data acquisition module 201, which is used to collect the respiratory parameters and gas state parameters of the patient, and construct a respiratory dynamics model including non-linear correction; A concentration prediction module 202, which is used to construct a gas mixture concentration prediction model with pressure dynamic compensation according to the airway pressure of the anesthetic gas output by the respiratory dynamics model; A parameter control module 203, which is used to construct a control objective function based on the concentration deviation, flow rate change rate, and pressure deviation of the anesthetic gas, and control the concentration, flow rate, and pressure of the anesthetic gas to approach their respective target values; An adaptive compensation module 204, which is used to determine an adaptive compensation factor based on the concentration deviation and pressure change rate of the anesthetic gas; A flow rate correction module 205, which is used to calculate the flow rate correction values of various types of the anesthetic gas; A gas output module 206, which is used to output the anesthetic gas according to the flow rate correction values of various types of the anesthetic gas.

[0032] In some embodiments, the data acquisition module 201 is further configured to: Obtain real-time measurement values of the patient's lung compliance, airway resistance, and respiratory rate; Synchronously collect real-time gas flow rates, airway pressures, and gas concentrations output by the anesthesia machine; Construct the respiratory dynamics model based on the real-time measurement values of the patient's lung compliance, airway resistance, and respiratory rate, and the real-time gas flow rates, airway pressures, and gas concentrations output by the anesthesia machine.

[0033] In some embodiments, the expression of the respiratory dynamics model is:

[0034] where is pressure, C is lung compliance, is gas flow rate, R is airway resistance, is a non-linear correction coefficient, and f is respiratory rate.

[0035] Specifically, represents the airway pressure of the patient at time t. C represents the expansion ability of the lungs. represents the amount of gas flowing through the airway per unit time. R represents the degree of obstruction to gas flow. reflects the non-linear effect of gas flow rate. f represents the number of breaths per minute.

[0036] Lung compliance part , C is lung compliance, indicating the degree to which the lungs can expand under a certain pressure. The greater the compliance, the stronger the lung expansion ability and the lower the airway pressure. is the gas flow rate, the volume of gas passing through the airway per unit time, usually in units of L / min. The integral term represents the response of the lungs to gas flow, similar to an elastic volume expansion. represents the influence of lung compliance on airway pressure. The greater the compliance, the smaller the response of pressure to flow rate. is the integral of the gas flow rate, representing the cumulative effect of gas flow on pressure, that is, considering the gradual pressure change caused by gas flow on lung expansion.

[0037] Lung compliance part mainly reflects the influence of lung expansion. Through the integral of the gas flow rate, the "absorption" process of the lungs to gas flow can be seen. If the lung compliance C is large, the airway pressure will be low.

[0038] Airway resistance part , where \(R\) is the airway resistance, which reflects the resistance encountered during gas flow and is usually related to factors such as the shape and viscosity of the airway. is the gas flow rate, representing the amount of gas flowing through the airway. is the product of airway resistance and flow rate, used to describe the impact of airway resistance on airway pressure. The greater the airway resistance, the greater the airway pressure, and this pressure is linearly related to the flow rate. This part describes the change in airway pressure caused by the restrictive effect of airway resistance on gas flow. The greater the airway resistance, the higher the pressure inside the airway during gas flow.

[0039] Non - linear correction term , is the non - linear correction coefficient, which controls the non - linear effect of flow rate on pressure change. is the square term of the gas flow rate, indicating that the effect of gas flow rate on pressure is non - linear, that is, when the flow rate increases, the amplitude of pressure increase becomes larger. represents the periodic change of breathing, where \(f\) is the breathing frequency. This sine function is used to simulate the periodic change of gas flow rate, reflecting the patient's breathing cycle (inhalation and exhalation). This part considers the non - linear effect of gas flow rate on airway pressure, especially the change in flow rate during the breathing cycle. When the flow rate increases, the pressure increases faster, and with different breathing frequencies, the pressure change is periodic. This correction term simulates the natural fluctuation of airway pressure during the patient's normal breathing process.

[0040] describes how the lungs respond to gas flow. The higher the lung compliance, the smaller the impact of the change in gas flow rate on pressure. represents the linear effect of airway resistance on airway pressure. The greater the airway resistance, the more restricted the gas flow and the higher the pressure. Simulates the periodic change of airway pressure through the non - linear correction coefficient and the periodic function, especially the impact of flow rate change on airway pressure during breathing.

[0041] In summary, the core function of this model of the present invention is to accurately simulate the change of airway pressure during the patient's breathing process by considering the non - linear effects of lung compliance, airway resistance, and flow rate. Lung compliance determines how gas flow rate affects airway pressure, airway resistance determines the linear effect of flow rate change on pressure, and the non - linear correction term precisely simulates the periodic non - linear effect of flow rate change on pressure. This model helps to accurately control the output of anesthetic gas, ensuring that the output of anesthetic gas can be adjusted according to the patient's respiratory dynamics characteristics under different breathing states.

[0042] In some embodiments, the non - linear correction coefficient is determined by the following steps: Obtain basic parameters under different postural characteristics through clinical big data training; the basic parameters include real-time respiratory waveforms; Use a Kalman filter to dynamically correct the real-time respiratory waveform to obtain correction parameters; Based on the recursive least squares method, update the correction parameters online to obtain the non-linear correction coefficient.

[0043] Specifically, clinical big data can be used to build a model to extract respiratory waveform data corresponding to different postural characteristics (such as age, height, weight, lung function) from a large number of clinical cases, forming a preliminary basic model parameter library. These parameters can help judge the respiratory response characteristics of patients.

[0044] Dynamic correction of real-time respiratory data (using a Kalman filter), the respiratory waveforms monitored during actual surgery may have noise or fluctuations. A Kalman filter can be used to smooth and correct these real-time data to extract more accurate and stable respiratory characteristic parameters.

[0045] Online self-learning optimization (recursive least squares method) can use the recursive least squares method (RLS) to update the correction parameters in real time, continuously optimize the model, and adapt to the current state changes of the patient. Finally, a non-linear correction coefficient is output to more realistically reflect the current respiratory dynamics state of the patient.

[0046] In some embodiments, the concentration prediction module 202 is further configured to: Obtain the ratio of the airway pressure of the anesthetic gas to the standard pressure to obtain a pressure normalization factor; Perform a weighted sum of the concentrations of each type of anesthetic gas to obtain a mixed concentration; Construct the gas mixture concentration prediction model according to the pressure normalization factor and the mixed concentration.

[0047] In some embodiments, the expression of the gas mixture concentration prediction model is:

[0048] Wherein, is the predicted anesthetic gas mixture concentration at time is the concentration of the i-th type of anesthetic gas at time t, is the weight of the i-th type of anesthetic gas, are the first correction parameter, the second correction parameter, and the third correction parameter respectively, is the standard pressure.

[0049] In specific implementation, this formula is used to predict the anesthetic gas mixture concentration at the future time t+Δt , which is the core prediction link in the control system, provides the target value for the next control action (such as flow regulation).

[0050] Sum of weighted concentrations of each gas Represents the concentrations of various anesthetic gases at the current moment According to the set weights Perform weighted mixing. The mixing ratio coefficient of each gas, The sum value of is 1. Without considering external influencing factors (such as pressure changes, time decay, etc.), a "theoretically ideal" anesthetic mixing concentration is obtained.

[0051] Dynamic correction term Used to correct the deviation of the ideal mixing concentration, and the time decay factor Is that the anesthetic gas concentration in the body is not constant and will decay over time due to natural processes such as volatilization and absorption. The parameter Is to control the decay rate. The larger the value, the faster the concentration changes. The closer to the start time of the operation, the greater the correction amount; the farther away, the smaller the correction.

[0052] Pressure normalization factor , Is the current airway pressure of the patient. Is the standard airway pressure for normalization. Is the non-linear exponent that adjusts the influence degree of pressure on the concentration. γ = 1: Linear correction. γ > 1: The pressure influence is significant, simulating patients with poor lung compliance. γ < 1: The pressure influence is small.

[0053] Is the overall correction intensity factor, used to amplify or weaken the weight of the entire correction term. It is the core adjustment parameter of this prediction model and can obtain the optimal value through clinical data fitting.

[0054] In summary, the present invention can calculate in advance the anesthetic gas mixing concentration at the next moment, provide feedforward information for the controller, can automatically adjust the prediction value according to the patient's airway pressure and time changes, can reduce the gap between the corrected ideal concentration and the actual physiological absorption / response, and can provide an accurate input basis for subsequent optimization of the objective function, flow regulation, etc.

[0055] In some embodiments, the parameter control module 203 is further configured to: Obtain the target anesthetic gas mixing concentration and the reference pressure; According to the difference between the predicted mixing concentration of the anesthetic gas and the target anesthetic gas mixing concentration, obtain the concentration deviation of the anesthetic gas; According to the difference between the current airway pressure of the anesthetic gas and the reference pressure, obtain the pressure deviation of the anesthetic gas.

[0056] In some embodiments, the control objective function can be expressed as:

[0057] where J is the function value of the control objective function, is the predicted anesthetic gas mixture concentration, is the target anesthetic gas mixture concentration, is the reference pressure, are the first weight, the second weight, and the third weight.

[0058] In specific implementation, J represents the overall performance evaluation index of the control system. The smaller the value, the better the control effect. The control system will minimize J through an optimization algorithm to achieve optimal control.

[0059] Square term of anesthetic concentration deviation Ensures precise control of the anesthetic gas concentration, prevents overdose or underdose, and ensures the safety and effectiveness of the anesthetic effect. is the predicted gas mixture concentration (from the aforementioned prediction model), is the target anesthetic concentration set by the doctor. This term measures the error between the output concentration of the system and the target concentration, and the smaller the error, the better. is the first weight, indicating the degree of emphasis of the system on concentration accuracy.

[0060] Smoothness term of flow rate adjustment Avoids frequent or drastic adjustment of gas output, extends the equipment life, reduces system oscillation, and improves patient comfort. is the change rate of gas flow rate (i.e., "adjustment speed"). This term measures the smoothness of the system's adjustment of the flow rate. The more drastic the flow rate change, the larger the integral value. is the penalty coefficient for the adjustment rate.

[0061] Pressure deviation term Controls pressure fluctuations, protects lung tissue, and avoids lung damage caused by high pressure or insufficient ventilation caused by low pressure. P is the current airway pressure (output by the respiratory dynamics model). is the desired or reference pressure (set by the doctor or historical mean), indicating the degree of deviation of the actual airway pressure from the normal reference value. represents the degree of emphasis of the control system on maintaining pressure stability.

[0062] In summary, the control object of is the anesthetic concentration, which is used to improve the accuracy of anesthetic control. the control object of is the smoothness of the output flow rate, which is used to reduce adjustment mutations and enhance system stability. The controlled object is the airway pressure, which is used to ensure the breathing safety of the patient and avoid pressure injury or insufficient ventilation. Each item is weighted and combined through weights, and finally a unified optimization goal is formed for the control system to use.

[0063] The control objective function J of the present invention is the core of the adaptive control system, comprehensively considering the accuracy of the anesthetic concentration, the smoothness of the system adjustment, and the safety of the respiratory system. In actual operation, the control strategy can be continuously adjusted through algorithms (such as model predictive control MPC, gradient descent, genetic algorithm, etc.) to minimize J, so as to achieve intelligent, precise, and dynamic anesthetic management.

[0064] In some embodiments, the adaptive compensation module 204 is further configured to: Obtain a reference factor representing the reference gain; Determine the airway pressure change rate of the anesthetic gas according to the current airway pressure of the anesthetic gas; Determine the adaptive compensation factor according to the concentration deviation of the anesthetic gas, the airway pressure change rate, and the reference factor.

[0065] In some embodiments, the adaptive compensation factor can be expressed as:

[0066] Wherein, is the adaptive compensation factor, is the reference factor, and the concentration deviation , which represents the deviation between the predicted anesthetic gas mixture concentration and the target anesthetic gas mixture concentration, are the first dynamic adjustment parameter, the second dynamic adjustment parameter, and the third dynamic adjustment parameter respectively, is the reference factor of the reference gain.

[0067] This formula is used to dynamically calculate the adaptive compensation factor , which will be used in the control system to adjust the response intensity of the gas output, making the control more flexible, stable, and having individual adaptation ability. is the reference factor, which represents the basic control intensity of the control system in the default / static situation, and is set by experience or system calibration.

[0068] The concentration deviation , is the predicted gas concentration (from the prediction model), is the set target concentration, represents the deviation between the system prediction value and the target value, and is used to dynamically correct the control strength.

[0069] Error nonlinear amplification function , is the hyperbolic tangent function, with an output range of (-1, 1), and has non-linear saturation characteristics. is the error amplification factor, making the system more sensitive or less sensitive to concentration deviations. is the dynamic adjustment intensity, controlling the magnification factor. Specifically, when the concentration deviation is small, the correction strength is small; when the concentration deviation increases, the system increases the response strength, but is limited by tanh to prevent over-adjustment; a dynamic and smooth response enhancement mechanism is achieved.

[0070] Pressure change penalty factor , is the airway pressure change rate, indicating the instability degree of the respiratory system state, is the third dynamic adjustment parameter, controlling the sensitivity to pressure changes. If the airway pressure fluctuates violently, the penalty factor approaches 0, and the control system output is suppressed; if the pressure is stable, the penalty term approaches 1, and the system works normally. When the patient's breathing state is unstable, the control gain is automatically reduced to avoid over-reaction or induced risks of the system.

[0071] In summary, the present invention can automatically adjust the control strength according to the actual concentration deviation, the greater the error, the faster the reaction. When the patient's pressure fluctuates greatly, the control output is automatically slowed down to prevent risks. Using tanh and exponential functions, mutations or oscillations are avoided, and the adaptability requirements of different patients are adjusted through various parameters.

[0072] In some embodiments, the flow correction module 205 is further configured to: Determine the change rate of the concentration deviation of the anesthetic gas; Obtain the integral adjustment coefficient and the differential adjustment coefficient; According to the change rate of the concentration deviation of the anesthetic gas, the concentration deviation, and the adaptive compensation factor, correct the current flow rate of each type of anesthetic gas to obtain the flow correction value of each type of anesthetic gas.

[0073] In some embodiments, the flow correction value of each type of anesthetic gas can be expressed as:

[0074] Wherein, is the correction amount of the i-th type of anesthetic gas, is the current flow rate of the i-th type of anesthetic gas, is the integral adjustment coefficient, is the differential adjustment coefficient.

[0075] Specifically, this formula is used to dynamically calculate the correction amount of the i-th type of anesthetic gas , to achieve more precise anesthesia concentration control and respond to changes in the patient's state. It is a typical "Proportion + Integral + Derivative + Adaptive Gain" control structure (P+I+D+K).

[0076] Current reference flow rate × Adaptive gain term: , is the flow rate of the 𝑖-th anesthetic gas originally set by the system (such as isoflurane, nitrous oxide, etc.), Adaptive gain coefficient (from the aforementioned dynamic gain formula). It realizes automatic amplification or attenuation of the original flow output based on the system state (such as concentration deviation, airway pressure change), reflecting the "intelligent adjustment" mechanism.

[0077] Integral regulation term (I term): , is the error of the mixed anesthesia concentration, is the integral regulation coefficient. It accumulates the concentration deviation for a long time. When the system error exists for a long time but the amplitude is not large, the integral term can gradually "fill the deviation" to eliminate the steady-state error. It also plays a role in slowly correcting the deviation.

[0078] Derivative regulation term (D term): , is the change rate of the concentration deviation, is the derivative regulation coefficient. This term performs predictive regulation on the system response: when the concentration deviation is increasing or decreasing rapidly, control actions are taken in advance. It reduces overshoot, suppresses oscillation, and improves response sensitivity.

[0079] The control action of is real-time adaptive adjustment, responding based on the patient's current physiological state. The control action of is to compensate for long-term errors and improve stability. The control action of is to quickly respond to the error trend, reduce delay and overshoot.

[0080] In summary, the present invention can accurately respond to the target concentration, avoid over-anesthesia / under-anesthesia, each gas can be independently corrected, adapt to the needs of different patients, has a fast adaptation ability to sudden changes (such as the awakening period, surgical stimulation), and forms a control closed-loop through "error → gain → output → concentration → error".

[0081] Please refer to Figure 3 , which provides a flowchart of a method for controlling the output of anesthetic gas for an anesthesia machine according to the present invention, including the following steps: Step 301, collect the patient's respiratory parameters and gas state parameters, and construct a respiratory dynamics model including non-linear correction; Step 302, construct a gas mixture concentration prediction model with pressure dynamic compensation according to the airway pressure of the anesthetic gas output by the respiratory dynamics model; Step 303: Construct a control objective function based on the concentration deviation, flow rate change rate, and pressure deviation of the anesthetic gas, and control the concentration, flow rate, and pressure of the anesthetic gas to approach their respective target values; Step 304: Determine an adaptive compensation factor based on the concentration deviation and pressure change rate of the anesthetic gas; Step 305: Calculate the flow rate correction values for various anesthetic gases; Step 306: Output the anesthetic gas according to the flow rate correction values of various anesthetic gases.

[0082] For the specific embodiments and beneficial effects of the above steps 301 - 306, please refer to the description of the above-mentioned modules 201 - 206, which will not be elaborated here.

[0083] Please refer to Figure 4 , Figure 4 which is a schematic diagram of an embodiment of an electronic device provided by an embodiment of the present invention. As Figure 4 shown, an embodiment of the present invention provides an electronic device 400, including a memory 410, a processor 420, and a computer program 411 stored on the memory 410 and executable on the processor 420. When the processor 420 executes the computer program 411, the following steps are implemented: Collect the respiratory parameters and gas state parameters of the patient, and construct a respiratory dynamics model including non-linear correction; Construct a gas mixture concentration prediction model with pressure dynamic compensation according to the airway pressure of the anesthetic gas output by the respiratory dynamics model; Construct a control objective function based on the concentration deviation, flow rate change rate, and pressure deviation of the anesthetic gas, and control the concentration, flow rate, and pressure of the anesthetic gas to approach their respective target values; Determine an adaptive compensation factor based on the concentration deviation and pressure change rate of the anesthetic gas; Calculate the flow rate correction values for various anesthetic gases; Output the anesthetic gas according to the flow rate correction values for various anesthetic gases.

[0084] Please refer to Figure 5 , Figure 5 which is a schematic diagram of an embodiment of a computer-readable storage medium provided by an embodiment of the present invention. As Figure 5 shown, this embodiment provides a computer-readable storage medium 500, on which a computer program 411 is stored. When the computer program 411 is executed by a processor, the following steps are implemented: Collect the respiratory parameters and gas state parameters of the patient, and construct a respiratory dynamics model including non-linear correction; Construct a prediction model for the gas mixture concentration with pressure dynamic compensation based on the airway pressure of the anesthetic gas output according to the respiratory dynamics model; Construct a control objective function based on the concentration deviation, flow rate change rate, and pressure deviation of the anesthetic gas, and control the concentration, flow rate, and pressure of the anesthetic gas to approach their respective target values; Determine an adaptive compensation factor based on the concentration deviation and pressure change rate of the anesthetic gas; Calculate the flow correction values of various types of the anesthetic gas; Output the anesthetic gas according to the flow correction values of various types of the anesthetic gas.

[0085] It should be noted that in the above embodiments, the descriptions of the respective embodiments have their own focuses. For the parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0086] Those skilled in the art should understand that the embodiments of the present invention can be provided as a system, method, or computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0087] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, and the combination of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded computers, or other programmable data processing devices to generate a machine, so that the instructions executed by the processors of the computer or other programmable data processing devices generate a system for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0088] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction system that implements the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0089] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one process or a plurality of processes and / or blocks Figure 1 one process or a plurality of processes and / or blocks Figure 1 or steps for implementing the functions specified in one block or a plurality of blocks.

[0090] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn of the basic inventive concept. Therefore, the appended claims are intended to be construed to cover the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0091] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. An anesthetic gas output control system for an anesthesia machine, characterized in that: The system comprises: A data acquisition module is used to collect the patient's respiratory parameters and gas state parameters and construct a respiratory dynamics model including nonlinear correction; A concentration prediction module, used to construct a gas mixture concentration prediction model with pressure dynamic compensation according to the airway pressure of the anesthetic gas output by the respiratory dynamics model; A parameter control module, used to construct a control objective function based on the concentration deviation, flow rate change rate and pressure deviation of the anesthetic gas, and control the concentration, flow rate and pressure of the anesthetic gas to be close to respective target values; An adaptive compensation module, used to determine an adaptive compensation factor based on a concentration deviation and a pressure change rate of the anesthetic gas; A flow correction module, used for calculating the flow correction value of each type of anesthetic gas; The gas output module is used to output anesthetic gas according to the flow correction value of each type of anesthetic gas.

2. The anesthetic gas output control system for an anesthesia machine according to claim 1, characterized in that: The data acquisition module is also used for: Obtaining real-time measurements of the patient's lung compliance, airway resistance, and respiratory rate; Synchronously collect the real-time flow, airway pressure and gas concentration of each gas output by the anesthesia machine; The respiratory dynamics model is constructed based on the real-time measured values ​​of the patient's lung compliance, airway resistance, and respiratory frequency, as well as the real-time flow rate, airway pressure, and gas concentration of each gas output by the anesthesia machine.

3. The anesthetic gas output control system for an anesthesia machine according to claim 2, characterized in that: The expression of the respiratory dynamics model is: in, is the pressure, C is the lung compliance, is the gas flow, R is the airway resistance, is the nonlinear correction coefficient, and f is the respiratory frequency.

4. The anesthetic gas output control system for an anesthesia machine according to claim 3, characterized in that: The nonlinear correction coefficient is determined by the following steps: Obtain basic parameters under different body posture characteristics through clinical big data training; the basic parameters include real-time respiratory waveform; Using a Kalman filter to dynamically correct the real-time respiratory waveform to obtain correction parameters; The correction parameter is updated online based on the recursive least square method to obtain the nonlinear correction coefficient.

5. The anesthetic gas output control system for an anesthesia machine according to claim 4, characterized in that: The concentration prediction module is also used for: Obtaining the ratio of the airway pressure of the anesthetic gas to the standard pressure to obtain a pressure normalization factor; Performing weighted summation on the concentration of each type of anesthetic gas to obtain a mixed concentration; The gas mixture concentration prediction model is constructed according to the pressure normalization factor and the mixture concentration.

6. The anesthetic gas output control system for an anesthesia machine according to claim 5, characterized in that: The expression of the gas mixture concentration prediction model is: in, It is predicted The concentration of anesthetic gas mixture at each moment, is the concentration of the i-th type of anesthetic gas at time t, is the weight of the anesthetic gas of type i, are the first correction parameter, the second correction parameter and the third correction parameter respectively, is the standard pressure.

7. The anesthetic gas output control system for an anesthesia machine according to claim 6, characterized in that: The parameter control module is also used for: Obtain target anesthetic gas mixture concentration and reference pressure; Obtaining a concentration deviation of the anesthetic gas according to a difference between the predicted mixed concentration of the anesthetic gas and the target mixed concentration of the anesthetic gas; The pressure deviation of the anesthetic gas is obtained according to the difference between the current airway pressure of the anesthetic gas and the reference pressure.

8. The anesthetic gas output control system for an anesthesia machine according to claim 7, characterized in that: The adaptive compensation module is also used for: obtaining a reference factor representing a reference gain; determining a rate of change of the airway pressure of the anesthetic gas according to the current airway pressure of the anesthetic gas; The adaptive compensation factor is determined according to the concentration deviation of the anesthetic gas, the airway pressure change rate, and the reference factor.

9. The anesthetic gas output control system for an anesthesia machine according to claim 8, characterized in that: The flow correction module is also used for: determining a concentration deviation change rate of the anesthetic gas; Obtaining integral adjustment coefficient and differential adjustment coefficient; According to the concentration deviation change rate and concentration deviation of the anesthetic gas, and the adaptive compensation factor, the current flow rate of each type of anesthetic gas is corrected to obtain the flow correction value of each type of anesthetic gas.

10. A method for controlling the output of an anesthetic gas for an anesthesia machine, characterized in that: The method comprises: Collect the patient's respiratory parameters and gas state parameters, and build a respiratory dynamics model including nonlinear correction; According to the airway pressure of the anesthetic gas output by the respiratory dynamics model, a gas mixture concentration prediction model with pressure dynamic compensation is constructed; Constructing a control objective function based on the concentration deviation, flow rate change rate and pressure deviation of the anesthetic gas to control the concentration, flow rate and pressure of the anesthetic gas to be close to respective target values; determining an adaptive compensation factor based on a concentration deviation and a pressure change rate of the anesthetic gas; Calculating flow correction values ​​of various types of anesthetic gases; Anesthetic gas output is performed according to the flow correction value of each type of anesthetic gas.

Images