Target control oxygen concentration and drug concentration closed-loop conveying system and method for inhalation anesthesia

Abstract

The embodiment of the invention provides a target control oxygen concentration and drug concentration closed-loop conveying system and method for inhalation anesthesia, and relates to the technical field of medical equipment technologies. The method comprises the following steps: acquiring a real-time gas concentration of a target drug, and determining an initial concentration deviation value between the real-time gas concentration and a preset target gas concentration; determining a conveying adjustment strategy based on the initial concentration deviation value, and predicting a system deviation change amount after the conveying adjustment strategy is executed; determining an adjustment acceptance probability according to the system deviation variation and a preset adjustment threshold, and determining whether to execute the conveying adjustment strategy according to the adjustment acceptance probability; and monitoring a state track of the concentration deviation value, and when the state track meets a preset convergence condition, judging that the target gas reaches a target state. According to the invention, the problem of low anesthetic gas control precision is solved, and the effect of improving the anesthetic gas control precision is achieved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of medical devices, and in particular, to a closed-loop delivery system and method for target-controlled oxygen concentration and drug concentration of inhalation anesthesia. BACKGROUND

[0002] Inhalation anesthesia is an important part of modern clinical anesthesia, and its core is to deliver volatile anesthetics and oxygen mixed gas to the patient through the respiratory system to achieve the effect of anesthesia such as sedation, analgesia, and muscle relaxation. The traditional operation of inhalation anesthesia relies heavily on the personal experience and manual adjustment of anesthesiologists, and the anesthesiologists need to frequently manually adjust the fresh gas flow meter and the dial of the anesthetic volatilizer on the anesthesia machine to control the oxygen concentration and anesthetic concentration of the inhaled gas according to the patient's vital sign monitoring data (such as heart rate, blood pressure, end-tidal carbon dioxide, etc.) and indirect judgment of the depth of anesthesia.

[0003] However, this traditional manual control method has limited control accuracy and delay, and it is difficult to respond to physiological changes in patients in real time and accurately, which can easily lead to excessive or insufficient anesthesia, or fluctuations in oxygenation levels, and the frequent adjustment process greatly increases the workload and mental stress of anesthesiologists. SUMMARY

[0004] Embodiments of the present application provide a closed-loop delivery system and method for target-controlled oxygen concentration and drug concentration of inhalation anesthesia to at least solve the problem of low control accuracy of anesthetic gas in related technologies.

[0005] According to an embodiment of the present application, a closed-loop delivery method for target-controlled oxygen concentration and drug concentration of inhalation anesthesia is provided, comprising:

[0006] Obtaining the real-time gas concentration of the target drug, and determining the initial concentration deviation between the real-time gas concentration and the preset target gas concentration, the initial concentration deviation being used to indicate the current system deviation degree;

[0007] Based on the initial concentration deviation, a delivery adjustment strategy is determined, and the system deviation change after executing the delivery adjustment strategy is predicted;

[0008] According to the system deviation change and a preset adjustment threshold, an adjustment acceptance probability is determined, and whether to execute the delivery adjustment strategy is determined according to the adjustment acceptance probability;

[0009] Monitoring the state trajectory of the concentration deviation value, and when the state trajectory meets a preset convergence condition, it is determined that the target gas reaches a target state.

[0010] In one exemplary embodiment, the method further comprises:

[0011] updating the adjustment threshold according to a preset adjustment threshold decay strategy.

[0012] In one example embodiment, the determining the initial concentration deviation value between the real-time gas concentration and the preset target gas concentration comprises:

[0013] obtaining a target gas concentration vector of a target gas and a real-time gas concentration vector, wherein the target gas concentration vector comprises a target oxygen concentration and a target anesthetic concentration, and the real-time gas concentration vector comprises a real-time oxygen concentration and a real-time anesthetic concentration;

[0014] calculating the initial concentration deviation value based on a preset deviation function between the target gas concentration vector and the real-time gas concentration vector.

[0015] In one example embodiment, the determining the delivery adjustment strategy based on the initial concentration deviation value specifically comprises:

[0016] generating a set of random perturbations for fresh oxygen flow and anesthetic output concentration according to the initial concentration deviation value within a preset adjustment range;

[0017] superimposing the random perturbations to a current delivery reference value to form the delivery adjustment strategy.

[0018] In one example embodiment, after determining that the target gas reaches a target state, the method further comprises:

[0019] continuously monitoring the concentration deviation value according to a preset ideal steady state interval of the concentration deviation value;

[0020] when the concentration deviation value exceeds the ideal steady state interval, fine-tuning a delivery intervention stress to constrain the concentration deviation value within the ideal steady state interval.

[0021] In one example embodiment, the method further comprises:

[0022] obtaining prediction information of an external disturbance event;

[0023] calculating a compensatory delivery intervention stress for offsetting an expected impact of the external disturbance event based on the prediction information;

[0024] applying the compensatory delivery intervention stress to the target gas.

[0025] According to another embodiment of the present application, there is provided a closed-loop delivery system for target-controlled oxygen concentration and drug concentration of inhaled anesthesia, comprising:

[0026] a gas concentration collection module, configured to acquire a real-time gas concentration of a target drug, and determine an initial concentration deviation value between the real-time gas concentration and a preset target gas concentration;

[0027] a strategy determination module, configured to determine a delivery adjustment strategy based on the initial concentration deviation value;

[0028] a prediction module, configured to predict a system deviation change after the delivery adjustment strategy is executed;

[0029] a determination module, configured to determine an adjustment acceptance probability according to the system deviation change and a preset adjustment threshold, and determine whether to execute the delivery adjustment strategy according to the adjustment acceptance probability;

[0030] a state determination module, configured to monitor a state trajectory of the concentration deviation value, and determine that the target gas reaches a target state when the state trajectory meets a preset convergence condition.

[0031] In an example embodiment, the system further comprises:

[0032] a threshold adjustment module, configured to update the adjustment threshold according to a preset adjustment threshold decay strategy.

[0033] According to still another embodiment of the present application, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.

[0034] According to still another embodiment of the present application, an electronic device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to execute the steps in any of the above method embodiments.

[0035] By accurately calculating and dynamically adjusting the deviation of the target gas, the automatic adjustment of the anesthetic gas is realized, so that the problem of low control precision of the anesthetic gas can be solved, and the effect of improving the control precision of the anesthetic gas is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0036] Figure 1 is a flowchart of a closed-loop delivery method for target-controlled oxygen concentration and drug concentration of inhaled anesthesia according to an embodiment of the present application;

[0037] Figure 2 is a structural block diagram of a closed-loop delivery system for target-controlled oxygen concentration and drug concentration of inhaled anesthesia according to an embodiment of the present application. DETAILED DESCRIPTION

[0038] The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all of the embodiments of the present application.

[0039] Hereinafter, the terms "first", "second", and the like are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second", and the like can explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0040] In addition, in the present application, the orientation terms such as "up", "down", "left", "right", etc. can include but not limited to the orientation defined by the relative position of the components in the drawings. It should be understood that these directional terms are relative concepts, which are used for relative description and clarification, and can be changed accordingly according to the change of the position of the components in the drawings.

[0041] In the present application, unless otherwise specified and limited, the term "connection" should be understood broadly, for example, "connection" can be fixed connection, or detachable connection, or integral; can be directly connected, or indirectly connected through intermediate medium. In addition, the term "coupling" can be an electrically connected manner for signal transmission.

[0042] As used herein, "about", "approximately", or "approximately" includes the stated value and the average value within an acceptable deviation range of the specific value, wherein the acceptable deviation range is determined by the ordinary skill in the art considering the measurement being discussed and the error related to the measurement of the specific quantity (i.e. the limitation of the measurement system).

[0043] The present embodiment provides a closed-loop delivery system for target-controlled oxygen concentration and drug concentration of inhalation anesthesia, which is usually integrated in a modern anesthesia workstation, and the hardware components include but are not limited to: a central processing unit (as a controller), a memory in communication connection with the central processing unit, a user input interface (such as a touch screen, for an anesthesiologist to set target parameters), a high-precision gas sensor (for real-time monitoring of oxygen, carbon dioxide and volatile anesthetic concentration in the breathing circuit), an electronically controlled mixed gas delivery module (including an electronic oxygen flowmeter and an electronic air / nitrous oxide flowmeter), and an electronically controlled anesthetic volatile apparatus, the central processing unit realizes the closed-loop delivery method for target-controlled oxygen concentration and drug concentration of inhalation anesthesia by executing a specific computer program stored in the memory.

[0044] As Figure 1As shown, a closed-loop delivery method for target-controlled oxygen concentration and drug concentration of inhaled anesthesia includes the following steps:

[0045] S11: Obtain the real-time gas concentration of the target drug, and determine the initial concentration deviation value between the real-time gas concentration and the preset target gas concentration;

[0046] In this embodiment, it is necessary to convert the abstract control target in the surgical process into a specific and calculable physical quantity, which is illustrated by the concentration deviation value and the system deviation value.

[0047] Specifically, the target gas concentration vector set by the anesthesiologist is first obtained , which includes at least two core components: target oxygen concentration and target anesthetic concentration ; for example, the anesthesiologist may set the target to be reached after the induction period of anesthesia: inhaled oxygen concentration 95%, sevoflurane concentration 1.5%, at which time the target gas concentration vector is , where the concentration is expressed in dimensionless volume fraction.

[0048] At the same time, the system collects the current real-time gas concentration vector in real time and at high frequency through the high-precision gas sensor deployed at the inspiratory end or the expiratory end of the Y-shaped joint of the breathing circuit, denoted as , which has the same structure as , that is ; in particular, the sampling frequency of the sensor needs to be high enough to capture the concentration change within the breathing cycle, and the system usually takes the average value within a short time window (such as the past 10 seconds) or the end-expiratory concentration value as the stable reading of the current cycle to filter out noise and transient fluctuations.

[0049] Then the initial concentration deviation value needs to be determined, where the concentration deviation vector corresponding to the concentration deviation value is calculated by a preset deviation function, which can be adjusted according to the requirements, and the difference between the target concentration and the real-time concentration is taken as the deviation function as an example: ; therefore, the initial concentration deviation vector is , and the corresponding value is the initial concentration deviation value, where is the initial concentration measured when the system starts.

[0050] Then the system deviation value is calculated, which can be calculated by the following formula:

[0051]

[0052] The formula below always gives a non-negative system deviation, and the energy is zero if and only if the real-time concentration is exactly equal to the target concentration, thus obtaining the initial system deviation .

[0053] At the same time, some control parameters need to be initialized in this step, including the initial adjustment threshold ,The value of the initial adjustment threshold needs to be set empirically or by system self-calibration, and a higher means that the system has a higher probability of accepting a possible temporary increase in the adjustment action at the beginning, thus having a stronger ability to jump out of a local optimal solution.

[0054] S12: Perform iterative adjustment;

[0055] Specifically, the following steps are included:

[0056] S121: Determine the delivery adjustment strategy based on the current concentration deviation;

[0057] In the first adjustment cycle, the system generates a candidate delivery intervention stress adjustment strategy according to the current state, where the delivery intervention stress is used to indicate the physical quantity output by the anesthesia machine, mainly including fresh oxygen flow and the output concentration set value of the anesthetic vaporizer ; an adjustment strategy is a small change in the current output, i.e. .

[0058] There are many ways to generate this candidate scheme, one simple and effective way is to generate a set of random perturbations within a preset adjustment range; specifically, the system maintains a current delivery intervention stress reference value , then randomly selects a point as a candidate scheme within a neighborhood space centered on with a maximum adjustment step size, for example, can be randomly taken within the interval of L / min, can be randomly taken within the interval of %; adding these random perturbations to the current reference value forms the candidate scheme ; further, this method can be combined with gradient information, i.e. according to the direction of the current concentration deviation , increase the random disturbance in the gradient descent direction to improve the convergence efficiency.

[0059] ​​S122: Predict the change in system deviation after implementing the delivery adjustment strategy;

[0060] In this embodiment, after obtaining the adjustment strategy, it is necessary to predict what will happen if it is executed. At the end of the next adjustment period, the system deviation value The specific value.

[0061] Specifically, this is achieved using a commonly used first-order model:

[0062]

[0063] in, It is a state transition function. These represent relevant physiological parameters of the patient (such as functional residual capacity (FRC), cardiac output, etc., which are not limited here).

[0064] For example, suppose the total volume of a single-room compartment model This includes the patient's functional residual capacity (FRC) and the volume of the anesthesia circuit, and is considered within one adjustment cycle (duration is...). Within the circuit, the concentration changes are mainly determined by the inflow of fresh gas, the patient's gas exchange (absorption of anesthetic drugs and consumption of oxygen), and the outflow of circuit gas.

[0065] Therefore, regarding the concentration of anesthetic drugs Its change can be modeled as:

[0066]

[0067] in, It is the total fresh gas flow rate. It refers to the set concentration of the evaporator in the candidate scheme. The amount of anesthetic drugs ingested by the patient can be approximated as being directly proportional to the concentration in the current circuit, i.e. , It is an uptake coefficient related to the patient's cardiac output and drug solubility; similarly, for oxygen concentration... Its change can be modeled as:

[0068]

[0069] in, The oxygen concentration in the fresh gas is determined by the candidate scheme. It is the patient's oxygen uptake rate.

[0070] Therefore, the predicted concentration at the next time step Using this predictive model, the system can calculate the expected real-time concentration at the next moment. Then, the expected concentration deviation at the next time step can be calculated. , and the expected next time system deviation value , finally, the change of system deviation value is calculated .

[0071] S123: determine the adjustment acceptance probability according to the system deviation change and the preset adjustment threshold value, and determine whether to execute the delivery adjustment strategy according to the adjustment acceptance probability.

[0072] In this embodiment, the decision rule is as follows:

[0073] 1. If the energy change value (i.e. this is a "good" scheme), the adjustment acceptance probability The system will always accept the adjustment action that can improve the state;

[0074] 2. If the energy change value (i.e. this is a "bad" scheme), the adjustment acceptance probability will be calculated by a preset probability acceptance function:

[0075]

[0076] wherein, is the adjustment threshold value of the th period; thus, is inversely proportional to ("bad" is more difficult to be accepted), and is proportional to (the higher the system tolerance, the easier to accept bad schemes), and so on.

[0077] After calculating , the system generates a uniformly distributed random number between 0 and 1 , if , the system decides to execute the candidate scheme; otherwise, the scheme is rejected, and a new candidate scheme is generated in the next period.

[0078] S124: update the adjustment threshold value according to the preset adjustment threshold value decay strategy.

[0079] At the end of each adjustment period, whether the candidate scheme is accepted or not, the system needs to decay the adjustment threshold value to ensure that the algorithm can eventually converge, if always remains at a high level, the system will always be in a random walk state and cannot be stabilized.

[0080] Specifically, the present application is set as:

[0081]

[0082] wherein, is a constant less than 1, called the cooling factor or cooling coefficient; The value of needs to be balanced between convergence speed and optimization quality, a value close to 1 (such as 0.995) means slow cooling, more sufficient search, but long convergence time; a smaller value (such as 0.9) means fast cooling, fast convergence, but may lead to premature convergence to a non-optimal solution, not limited here.

[0083] S13: Monitor the state trajectory, determine the concentration steady-state solidification.

[0084] In this embodiment, while the adjustment cycle is continuously ongoing, it is also necessary to determine when the adjustment process has been completed.

[0085] Specifically, based on continuous monitoring of the system state trajectory, the system deviation value Must be met simultaneously or one of them to determine convergence:

[0086] Energy convergence condition: system deviation value In the continuous adjustment cycles (for example ), its value is less than a preset, very low energy convergence threshold This threshold represents the clinically acceptable concentration error range; for example, if the oxygen concentration error is required to be within ±1%, the anesthetic concentration error is within ±0.1%, then To ensure that the system not only reaches the target, but also stably maintains around the target.

[0087] Temperature end condition: adjustment threshold After continuous attenuation, has dropped to a preset temperature end threshold This threshold is very close to zero, for example ; When is so low, according to the aforementioned acceptance probability formula, the system is almost impossible to accept any solution that will raise the energy, indicating that the adjustment process has lost the motivation for further optimization.

[0088] Once any of the above conditions is met, the iterative adjustment cycle is terminated, and the system state determination module outputs a signal declaring that the target state has been reached, that is, the oxygen concentration and anesthetic concentration in the patient's breathing circuit have accurately and stably reached the target value set by the physician.

[0089] S14: Steady-state maintenance and disturbance response.

[0090] ​In this embodiment, after the system successfully reaches the target state, it is also required to efficiently maintain the steady state in a low-power monitoring mode, and to quickly and intelligently respond to sudden significant disturbances.

[0091] Specifically, in the steady state maintenance phase, the system continuously monitors the gas concentration at a lower frequency (e.g., every 15 seconds), calculates the current concentration deviation value , as long as the size (norm) of the concentration deviation vector remains within a small, predefined ideal steady state interval, the system only performs a very small, compensatory delivery intervention stress adjustment, or does not perform any adjustment, to save energy and drug consumption.

[0092] However, once the concentration deviation value suddenly increases significantly, exceeding the boundary of the ideal steady state interval, the system determines that a significant external disturbance has occurred, at which time the system will execute a disturbance response mechanism, i.e., reset the current adjustment threshold to an intermediate value (e.g., 0.5) much higher than , and then reiterate the adjustment loop.

[0093] Optionally, a proportional-integral (PI) controller can be used to fine-tune the delivery intervention stress to always control it within the ideal steady state interval, for example .

[0094] Specifically: the output of the PI controller, i.e., the fine-tuning amount of the delivery intervention stress , is calculated as follows:

[0095]

[0096] Where:

[0097] is the concentration deviation vector monitored at time .

[0098] is the proportional gain matrix, which determines the response strength to the current deviation.

[0099] is the integral gain matrix, which is used to eliminate long-term static errors.

[0100] is the historical accumulation of deviation since entering the steady state mode.

[0101] In each steady state maintenance monitoring period (e.g., 15 seconds), the system will sequentially perform the following:

[0102] ​S1, calculate the current ;

[0103] S2, update the integral term

[0104] S3, calculate the fine-tuning amount ;

[0105] S4, update the current delivery intervention stress to , where is the reference output at the time of entering the steady state.

[0106] S5, instruct the anesthesia machine to execute the new .

[0107] In another optional embodiment, a predictive model can also be built, which stores the correlation between common surgical events (such as skin incision, internal organs traction, abdominal closure) and the change in anesthesia demand; when the anesthesiologist inputs the information of the upcoming surgical event (for example, "skin incision is expected in 1 minute") through the user interface, the mechanism is triggered.

[0108] Specific calculation process:

[0109] Input acquisition: the system receives the type of event (such as skin incision) and the expected time of occurrence ;

[0110] Impact prediction: based on , the predictive model retrieves the typical impact curve of the event on the demand for anesthetic drugs from the knowledge base . This curve describes how the patient's uptake rate of anesthetic drugs will change after the event occurs;

[0111] Compensation calculation: in order to offset this expected increase in demand, the system needs to deliver additional anesthetic drugs in advance, where the compensatory delivery intervention stress needed to be applied includes a supply pulse that can produce an opposite effect to .

[0112] Application of intervention: at a certain preset time window (for example, 30 seconds in advance) before , the system starts to superimpose the calculated on the current delivery intervention stress.

[0113] The following is illustrated by a specific example.

[0114] Suppose at the beginning of anesthesia, the patient inhales indoor air through the mask, and the breathing circuit is full of air; at this time, the anesthesiologist sets the target oxygen concentration (that is, 95%), and the target sevoflurane concentration (i.e., 1.5%).

[0115] Subsequently, the target concentration vector is obtained. Simultaneously, the gas sensor measures the initial gas concentration in the circuit as the indoor air composition, i.e., the real-time oxygen concentration. (21%), real-time sevoflurane concentration Therefore, the initial real-time gas concentration vector is .

[0116] Next, calculate the initial concentration deviation vector. This means that the current system needs to increase the oxygen concentration by 0.74 by volume fraction and the sevoflurane concentration by 0.015 by volume fraction.

[0117] Then, calculate the initial system deviation value. This refers to the degree of instability of the system's initial state, and subsequent adjustment processes will aim to minimize this value.

[0118] Finally, the system initializes the adjustment threshold according to preset rules; assuming that, based on the system configuration, for this wide range of adjustments from air to high concentrations of oxygen and anesthetic drugs, the initial adjustment threshold is... .

[0119] Subsequently, at the start of the first adjustment cycle (k=1), the system's current transport intervention stress reference value... The output is zero (i.e., the anesthesia machine is not outputting); assuming the system's maximum single-step adjustment for fresh oxygen flow rate is 1.0 L / min and the maximum single-step adjustment for vaporizer concentration is 0.5%; subsequently, the system operates within a range of [-1.0, 1.0] L / min. Generate a random number within the range [-0.5, 0.5]. Generate a random number. Assume the random perturbation generated this time is... L / min, Therefore, the candidate delivery intervention stress adjustment scheme is to set the fresh oxygen flow rate to 0.8 L / min and the evaporator setting to 0.3%. This scheme is denoted as... Meanwhile, oxygen concentration heptafluoroane concentration Assume the system parameters are: L, s (i.e., 1 / 12 min), patient oxygen uptake rate L / min, anesthetic drug uptake coefficient L / min, and current state: , ,but:

[0120] Predicting changes in oxygen concentration:

[0121] Predicted change in anesthetic concentration:

[0122] Predicted next-time concentration: .

[0123] Predicted next-time system deviation: , the corresponding change in system deviation ; since is negative, this indicates that the candidate solution is a "good" solution that improves the system state.

[0124] At this point, according to Rule 1, the acceptance probability is adjusted to , which is less than 1. Therefore, the system decides to adopt this candidate solution.

[0125] The anesthesia machine will then be instructed to output fresh oxygen flow 0.8 L / min, and the vaporizer is set to 0.3%; the system state will be updated to ; after 5 seconds, the true sensor readings will be used to update and , and the next adjustment cycle begins, and so on.

[0126] Suppose at the k = 10th cycle, the system encounters a "bad" candidate solution; suppose the system deviation at this point is , and the adjustment threshold has dropped to ; after calculation, a certain candidate solution yields a change in system deviation ; the system calculates the acceptance probability according to Rule 2: ; then the system generates a random number ; if (approximately 82% probability), the system will still accept this "bad" solution, temporarily allowing the system state to "deteriorate" a little in the hope of escaping the current local optimum and exploring a better region; if , the solution is rejected.

[0127] Similarly, suppose after 300 adjustment cycles (about 25 minutes), the system deviation has values [0.00008, 0.00009, 0.000085,..., 0.000092] in the last 10 cycles (from k = 291 to k = 300). These values are all less than the preset energy convergence threshold ; at this point, the energy convergence condition is met; the system determines that the target state has been reached, and the iteration loop is stopped, and it can switch to a steady-state maintenance mode.

[0128] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be realized by means of software on a general hardware platform as necessary, and of course can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product in essence or in the part that contributes to the prior art, and the computer software product is stored in a storage medium (such as a ROM / RAM, a magnetic disk, or an optical disk), and includes a plurality of instructions for causing a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the method described in each embodiment of the present application.

[0129] In addition, for the aforementioned closed-loop delivery system for target-controlled oxygen concentration and drug concentration for inhalation anesthesia, the system is used to implement the above embodiments and preferred embodiments, which have been described and will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware, or a combination of software and hardware can also be implemented and conceived.

[0130] As shown in Figure 2 , the system further includes, in addition to the aforementioned processor:

[0131] A gas concentration acquisition module 21 is configured to acquire a real-time gas concentration of a target drug, and determine an initial concentration deviation value between the real-time gas concentration and a preset target gas concentration.

[0132] A strategy determination module 22 is configured to determine a delivery adjustment strategy based on the initial concentration deviation value.

[0133] A prediction module 23 is configured to predict a system deviation change after the delivery adjustment strategy is executed.

[0134] A determination module 24 is configured to determine an adjustment acceptance probability according to the system deviation change and a preset adjustment threshold, and determine whether to execute the delivery adjustment strategy according to the adjustment acceptance probability.

[0135] A state determination module 25 is configured to monitor a state trajectory of the concentration deviation value, and determine that the target gas reaches a target state when the state trajectory satisfies a preset convergence condition.

[0136] In an optional embodiment, the system further includes:

[0137] A threshold adjustment module is configured to update the adjustment threshold according to a preset adjustment threshold decay strategy.

[0138] It should be noted that the above various modules can be implemented by software or hardware, and for the latter, the implementation can be achieved in the following ways, but is not limited thereto: the above modules are located in the same processor; or the above various modules are located in different processors in any combination.

[0139] Embodiments of the present application also provide a computer readable storage medium, which stores a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.

[0140] In an example embodiment, the above computer readable storage medium can include, but is not limited to, a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store computer programs.

[0141] Embodiments of the present application also provide an electronic device, which comprises a memory storing a computer program and a processor configured to execute the computer program to perform the steps in any of the above method embodiments.

[0142] In an example embodiment, the above electronic device can further comprise a transmission device connected to the processor and an input and output device connected to the processor.

[0143] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional modules is taken as an example for illustration, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above described functions.

[0144] In the several embodiments provided in the present application, it should be understood that the disclosed device and method can be implemented by other ways. For example, the device embodiments described above are only schematic, and the division of the modules or units is only a logical function division, and there can be another division way in actual implementation, for example, a plurality of units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed units can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0145] The units described as separate components may or may not be physically separate, and the components displayed as units may be a physical unit or multiple physical units, that is, may be located in one place, or also can be distributed to multiple different places. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment of the present application.

[0146] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present alone, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0147] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application essentially or the part of the prior art that contributes to the technical solutions or the whole or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions to make a device (which can be a single-chip microcomputer, a chip, etc.) or a processor execute all or part of the steps of the method of each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0148] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, any change or replacement within the technical scope disclosed in the present application should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A closed-loop delivery method for target-controlled oxygen concentration and drug concentration for inhalation anesthesia, characterized in that, include: The real-time gas concentration of the target drug is obtained, and an initial concentration deviation value is determined between the real-time gas concentration and the preset target gas concentration. The initial concentration deviation value is used to indicate the degree of deviation of the current system. Based on the initial concentration deviation, a delivery adjustment strategy is determined, and the change in system deviation after implementing the delivery adjustment strategy is predicted. The adjustment acceptance probability is determined based on the system deviation change and the preset adjustment threshold, and the delivery adjustment strategy is then executed based on the adjustment acceptance probability. The state trajectory of the monitored concentration deviation is determined to be the target gas when the state trajectory meets the preset convergence condition.

2. The method according to claim 1, characterized in that, The method further includes: The adjustment threshold is updated according to the preset adjustment threshold decay strategy.

3. The method according to claim 1, characterized in that, Determining the initial concentration deviation between the real-time gas concentration and the preset target gas concentration includes: Obtain the target gas concentration vector and the real-time gas concentration vector of the target gas, wherein the target gas concentration vector includes the target oxygen concentration and the target anesthetic concentration, and the real-time gas concentration vector includes the real-time oxygen concentration and the real-time anesthetic concentration; The initial concentration deviation value is calculated based on a preset deviation function between the target gas concentration vector and the real-time gas concentration vector.

4. The method according to claim 1, characterized in that, The determination of the delivery adjustment strategy based on the initial concentration deviation specifically includes: Within a preset adjustment range, a set of random perturbations for fresh oxygen flow rate and anesthetic drug output concentration are generated based on the initial concentration deviation value. The random perturbation is superimposed on the current transmission reference value to form the transmission adjustment strategy.

5. The method according to claim 2, characterized in that, After determining that the target gas has reached the target state, the method further includes: Based on the preset ideal steady-state range of the concentration deviation value, the concentration deviation value is continuously monitored; When the concentration deviation exceeds the ideal steady-state range, the delivery intervention stress is finely adjusted to constrain the concentration deviation within the ideal steady-state range.

6. The method according to claim 1, characterized in that, The method further includes: Obtain predictive information on external disturbance events; Based on the predicted information, a compensatory transport intervention stress is calculated to offset the expected impact of the external disturbance event; The compensating transport intervention stress is applied to the target gas.

7. A closed-loop delivery system for target-controlled oxygen and drug concentrations for inhalation anesthesia, characterized in that, include: A gas concentration acquisition module is used to acquire the real-time gas concentration of the target drug and determine the initial concentration deviation between the real-time gas concentration and the preset target gas concentration. The strategy determination module is used to determine a delivery adjustment strategy based on the initial concentration deviation value; The prediction module is used to predict the amount of system deviation change after the delivery adjustment strategy is implemented; The determination module is used to determine the adjustment acceptance probability based on the system deviation change amount and the preset adjustment threshold, and to determine whether to execute the delivery adjustment strategy based on the adjustment acceptance probability. The state determination module is used to monitor the state trajectory of the concentration deviation value. When the state trajectory meets the preset convergence condition, it is determined that the target gas has reached the target state.

8. The system according to claim 7, characterized in that, The system also includes: The threshold adjustment module is used to update the adjustment threshold according to a preset adjustment threshold decay strategy.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program is configured to perform the method described in any one of claims 1 to 6 when executed.

10. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the method as described in any one of claims 1 to 6.

Images