A respiratory oxygen inhaler oxygen flow control system

Abstract

The present application relates to oxygen inhalation machine technical field, specifically to a kind of oxygen inhalation machine oxygen flow control system in pneumology, including data acquisition unit, for obtaining the relevant parameters of effective oxygen flow adjustment;Still including data processing unit, data processing unit includes oxygen demand calculation module, oxygen flow calculation module, oxygen flow adjustment module and parameter abnormality alarm module.The present application is by real-time acquisition the physiological parameters of patient, i.e.the relevant parameters of influence oxygen flow adjustment, the relevant parameters of acquisition are calculated and handled by data processing unit, the predicted oxygen demand of patient can be obtained, and then the oxygen adjustment amount that oxygen inhalation machine needs to adjust is calculated by predicted oxygen demand, finally the oxygen flow that can meet the individual needs of different patients is obtained, compared with the traditional oxygen adjustment mode, the individual needs of each patient can be more accurately responded in this scheme, thereby the accuracy of oxygen supply is improved, and the risk caused by insufficient or excess is avoided.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of oxygen inhalation machines, in particular to an oxygen flow control system of an oxygen inhalation machine in a respiratory department. BACKGROUND

[0002] An oxygen inhalation machine is a medical device used to provide oxygen support, widely used in hospitals, home care and emergency situations. With the aging of the population and the increase of respiratory diseases, oxygen therapy plays an important role in improving the quality of life of patients, reducing symptoms and improving survival rates.

[0003] After searching, Chinese patent No. CN202011030690.7 discloses an oxygen flow control system and method of a respiratory support device. The above scheme detects and collects the oxygen flow of the inlet pipeline in real time through the flow sensor, and the processor judges whether the oxygen flow of the inlet pipeline changes. If it changes, return to the processor initialization, and the flow sensor collects the oxygen flow of the inlet pipeline again. Compare the collected oxygen flow with the standard oxygen flow. Within the preset deviation value range, control the aperture of the proportional valve through the fuzzy control circuit, and then adjust the oxygen flow of the inlet pipeline to output stable oxygen flow to the user end.

[0004] Most of the traditional oxygen inhalation machine flow adjustment methods rely on flow sensors, but in clinical practice, this method has certain limitations. For example, the respiratory changes of patients, activity status, individual differences in oxygen demand make the accurate control of oxygen flow complicated. In addition, different disease states (such as chronic obstructive pulmonary disease, pneumonia, heart failure, etc.) need to be adjusted more finely according to specific factors.

[0005] Therefore, an oxygen flow control system of an oxygen inhalation machine in a respiratory department is proposed to solve the above problems. SUMMARY

[0006] Technical problems to be solved

[0007] In view of the above shortcomings of the prior art, the present application provides an oxygen flow control system of an oxygen inhalation machine in a respiratory department, which can effectively solve the problem that the oxygen flow of the oxygen inhalation machine in the prior art cannot be finely adjusted according to the individual differences of patients.

[0008] Technical scheme

[0009] To achieve the above purpose, the present application is realized by the following technical scheme:

[0010] The present application provides an oxygen flow control system of an oxygen inhalation machine in a respiratory department, comprising a data acquisition unit for acquiring relevant parameters for effective oxygen flow adjustment;

[0011] Further comprising a data processing unit, the data processing unit comprising:

[0012] a predicted oxygen demand calculation module for constructing an oxygen demand prediction model according to relevant parameters and calculating a predicted oxygen demand

[0013] an oxygen flow calculation module for calculating an oxygen demand according to relevant parameters and oxygen demand constructing an oxygen regulation model and calculating an oxygen adjustment amount ΔO;

[0014] an oxygen flow adjustment module for calculating an oxygen flow based on a predicted oxygen demand and an oxygen adjustment amount ΔO wherein a PID control and an acceleration response mechanism are introduced to optimize the oxygen flow O f adjustment speed;

[0015] a parameter anomaly alarm module for defining a warning range of relevant parameters and detecting whether there are abnormal items in the relevant parameters, and issuing an alarm if the relevant parameters have abnormal items.

[0016] Further, the relevant parameters include: heart rate HR, body movement intensity A, carbon dioxide emission CO2, blood oxygen saturation SpO2, respiratory rate f R , tidal volume V T , positive end-expiratory pressure PEEP.

[0017] Further, the way of constructing the oxygen demand prediction model comprises:

[0018] defining relevant parameters that have a nonlinear relationship with the predicted oxygen demand , based on a polynomial regression model to obtain Y = β0+ β1·X1+ β2·X2+... + β n ·X k + β n+1 ·X1 2 + β n+2 ·X2 2 +... + β n+k ·X k 2 +... + ε; where Y is the dependent variable, i.e. the predicted oxygen demand β0is the intercept of the model; X is the independent variable, i.e. the relevant parameters, k represents the number of independent variables; β1, β2, β3, …, β n are the regression coefficients corresponding to the independent variables X k , and n represents the total number of regression coefficients; X1 2 , X2 2 , …, X k 2is the square term of independent variable X; and ε is the error term; then the oxygen demand prediction model is evaluated to obtain the mean square error (MSE) of the oxygen demand prediction model, the optimal coefficient vector β, and the determination coefficient R 2 and the residual error ε.

[0019] Further, the manner of evaluating the oxygen demand prediction model comprises:

[0020] the loss function is defined as the mean square error wherein N is the total number of samples; is the model prediction value, i.e. the predicted oxygen demand Y i is the true value, i.e. the actual oxygen demand O d ;

[0021] the optimal coefficient vector β is solved based on the least square method, i.e. β = (X matrix T X matrix ) -1 X matrix T Y vector ; wherein X matrix is the independent variable matrix, Y vector is the dependent variable vector, X matrix T is the transpose of the independent variable matrix X matrix , X matrix T X matrix represents the transpose of the independent variable matrix X matrix T and the independent variable matrix X matrix itself, (X matrix T X matrix ) -1 represents the inverse matrix of the matrix X matrix T X matrix , X matrix T Y vector represents the product of the transpose of the independent variable matrix X matrix and the dependent variable vector Y vector ;

[0022] the determination coefficient R is defined as wherein the error square sum is the total square sum wherein is the mean value of the dependent variable Y;

[0023] the residual error ε is defined as ε i represents the residual error of the i-th sample.

[0024] Further, the way of constructing the oxygen regulation model comprises:

[0025] Define the oxygen regulation amount

[0026] ΔO = K adj ·(HR target -HR) + K PEEP ·(PEEP target -PEEP) + K SpO2 ·(SpO2 target -SpO2):

[0027] In the formula, HR target is the target heart rate that needs to be adjusted for the patient, K adj represents the adjustment coefficient of the difference between the current heart rate HR of the patient and the target heart rate HR target ; PEEP target is the target positive end-expiratory pressure value that needs to be adjusted for the patient, K PEEP represents the adjustment coefficient of the difference between the current positive end-expiratory pressure PEEP of the patient and the target positive end-expiratory pressure PEEP target ; SpO2 target is the target blood oxygen saturation that needs to be adjusted for the patient, K SpO2 represents the adjustment coefficient of the difference between the current blood oxygen saturation SpO2 of the patient and the target blood oxygen saturation SpO2 target .

[0028] Further, the way of optimizing the oxygen flow regulation speed by the PID control and the acceleration response mechanism comprises:

[0029] An acceleration response factor t, i.e. a time point t, is introduced, and then an oxygen flow dynamic regulation model is defined, obtaining the oxygen flow O f (t) at the tth moment, i.e. the current flow value to be calculated; in the formula, G p is a proportional gain; e(t) represents the error at the current moment, and the calculation formula is G i is an integral gain; G d is a differential gain; and G acc is an acceleration response gain.

[0030] Further, the way of obtaining the integral gain G i comprises: first setting G i = 0 as an initial value, then gradually increasing the integral gain G i , observing the response of the oxygen flow dynamic regulation model, and recording the oxygen flow O i after adjustment of each integral gain G f(t) and the error e(t) at the current time until the steady-state error of the oxygen flow dynamic adjustment model approaches zero, the optimal integral gain G is determined i ;

[0031] The differential gain G d is obtained in the following way: first, calculate the error change Δe(t) = e(t) - e(t-1); then use the differential gain G d to update the current output of the oxygen flow dynamic adjustment model: oxygen flow O f (t) = O f (t-1) + K d · Δe(t); then apply a changing input signal, i.e., the predicted oxygen demand and detect the change in O f (t), while recording the error e(t) and the error change Δe(t); next, adjust the value of the differential gain G d until the output fluctuation of the oxygen flow dynamic adjustment model is reduced and the response is smooth, and the optimal value of the differential gain G d is determined;

[0032] The accelerated response gain G acc is obtained in the following way: use the accelerated response gain G acc to update the current output of the oxygen flow dynamic adjustment model: oxygen flow O f (t) = O f (t-1) + K acc · Δe(t); then apply a rapidly changing input signal, i.e., the predicted oxygen demand Then observe the change in oxygen flow O f (t) when the predicted oxygen demand changes, and whether the oxygen flow dynamic adjustment model can return to a new steady state; finally, gradually adjust the value of the accelerated response gain G acc using real-time monitoring data; specifically, set a threshold η for error change, when |Δe(t)| > η, trigger the adjustment of the accelerated response gain G acc , and the adjustment formula is G acc (t) = G acc (t-1) + α· Δe(t); in the formula, G acc (t-1) represents the value of the accelerated response gain at time point t-1; and α is the step size.

[0033] Further, the pre-warning range of the related parameters is defined as follows:

[0034] The pre-warning range of heart rate HR is [HR min , HR max ], and HR minthe lowest heart rate warning threshold, HR max the highest heart rate warning threshold;

[0035] the warning range of blood oxygen saturation SpO2 [SpO2 min , SpO2 max ], SpO2 min the lowest blood oxygen saturation warning threshold, SpO2 max the highest blood oxygen saturation warning threshold;

[0036] the warning range of respiratory rate f R [f Rmin , f Rmax ], f Rmin the lowest respiratory rate warning threshold, f Rmax the highest respiratory rate warning threshold;

[0037] the warning range of tidal volume V T [V Tmin , V Tmax ], V Tmin the lowest tidal volume warning threshold, V Tmax the highest tidal volume warning threshold;

[0038] the warning range of carbon dioxide discharge CO2 less than or equal to CO2 max , CO2 max the highest unilateral upper limit of carbon dioxide discharge;

[0039] the warning range of positive end-expiratory pressure PEEP [PEEP min , PEEP max ], PEEP min the lowest positive end-expiratory pressure warning threshold, PEEP max the highest positive end-expiratory pressure warning threshold;

[0040] the warning range of body motion intensity A less than or equal to A max , A max the highest unilateral upper limit of body motion.

[0041] Further, the manner of detecting whether the related parameters have abnormal items includes:

[0042] sequentially checking whether the heart rate HR, the blood oxygen saturation SpO2, the respiratory rate f R , the tidal volume V T , the carbon dioxide discharge CO2, the positive end-expiratory pressure PEEP, and the body motion intensity A exceed their warning ranges or unilateral upper limits, and if so, the abnormal items are obtained.

[0043] Beneficial effects

[0044] Compared with the prior art, the technical scheme provided by the present application has the following beneficial effects:

[0045] The present application can more accurately respond to the individual needs of each patient, thereby improving the accuracy of oxygen supply and avoiding risks caused by insufficient or excessive supply.

[0046] The present application can more accurately respond to the individual needs of each patient, thereby improving the accuracy of oxygen supply and avoiding risks caused by insufficient or excessive supply.

[0047] Finally, the present application sets up a parameter abnormality alarm module, which can alarm when the oxygen flow O f The present application can more accurately respond to the individual needs of each patient, thereby improving the accuracy of oxygen supply and avoiding risks caused by insufficient or excessive supply. The present application can more accurately respond to the individual needs of each patient, thereby improving the accuracy of oxygen supply and avoiding risks caused by insufficient or excessive supply. BRIEF DESCRIPTION OF DRAWINGS

[0048] In order to more clearly illustrate the technical schemes in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0049] Figure 1 The structure of the oxygen flow control system of the oxygen inhaler in the embodiment of the present application is shown in the schematic diagram.

[0050] Figure 2 The working process of the parameter abnormality alarm module in the embodiment of the present application is shown in the schematic diagram. DETAILED DESCRIPTION

[0051] The technical solutions and advantages of the embodiments of the present application will be described clearly and completely below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present application.

[0052] The present application will be further described below with reference to the embodiments.

[0053] Embodiment:

[0054] The present application provides a respiratory oxygen inhalation machine oxygen flow control system, refer to the attached Figure 1 The system comprises a data acquisition unit and a data processing unit.

[0055] The data acquisition unit is used to acquire relevant parameters affecting oxygen flow regulation, i.e. physiological parameters of the patient, and the relevant parameters include:

[0056] The heart rate HR of the patient, which reflects the number of heartbeats per minute (unit: times / min), directly affects the body's demand for oxygen, and an increase in heart rate usually indicates an increase in physical activity or metabolic rate, thereby increasing the demand for oxygen, which is obtained by a heart rate monitor;

[0057] The patient's activity intensity A, which refers to the patient's activity, and the higher the intensity, the greater the demand for oxygen, and quantifying the activity intensity A can help assess the patient's condition and the amount of oxygen needed to supplement; its acquisition method is: A = ω1·S A + ω2·S HR + ω3·S TQ , wherein S A represents the activity intensity score of the patient, by wearing a motion sensor on the patient, then based on the motion sensor to obtain the motion trajectory, speed, acceleration and other information of the patient, and calculate the activity duration and activity intensity of the patient, and finally convert it into a quantitative activity index, by analyzing the obtained acceleration data, the activity intensity can be divided into static, light, moderate and high activity, and the motion intensity is distinguished by different threshold values, common activity threshold values include metabolic equivalent METS, and thus the activity intensity score S A of the patient can be obtained; S HR represents the heart rate score of the patient, which can be obtained by a motion sensor or a heart rate detector; S TQrepresents the patient's activity time score, which can also be obtained through motion sensors; ω1, ω2, and ω3 are corresponding weight factors, which can be adjusted based on clinical experience;

[0058] The patient's carbon dioxide emissions (CO2) refer to the amount of carbon dioxide produced by the patient's body metabolism, which is usually proportional to the oxygen consumption. An increase in carbon dioxide indicates that the body is consuming more oxygen, so its quantitative information is crucial for regulating oxygen supply. The carbon dioxide emissions (CO2) can be monitored in real time through a breathalyzer (unit: L / min);

[0059] The patient's blood oxygen saturation SpO2 indicates the saturation level of oxygen in the blood and directly reflects the patient's oxygen intake. A decrease in blood oxygen saturation SpO2 indicates insufficient oxygen supply or a malfunction of the patient's respiratory system. Blood oxygen saturation SpO2 is obtained through real-time monitoring using a pulse blood pressure monitor and is usually output as a percentage.

[0060] The patient's respiratory rate f R , refers to the number of times a patient breathes per minute (unit: breaths / min), which is usually proportional to the body's demand for oxygen. A higher respiratory rate indicates that the body is working hard to obtain more oxygen. It is monitored in real time through respiratory monitoring equipment;

[0061] The tidal volume V breathed by the patient T , which represents the volume of air inhaled per breath (unit: L), tidal volume V T The size of will affect the amount of oxygen that can be provided in each breath, so it is an important parameter for regulating oxygen flow, which can be obtained through real-time monitoring of the respiratory flow meter;

[0062] The patient's positive end-expiratory pressure (PEEP) refers to the positive pressure in the patient's lung airway at the end of exhalation. PEEP can reduce the patient's resistance during inspiration and maintain the development of the patient's alveoli, thereby increasing the functional residual capacity and the effective ventilation area of ​​the lungs, which helps to improve the exchange of oxygen and carbon dioxide and reduce the demand for high-concentration oxygen. It is obtained through airway pressure sensor monitoring and is obtained as PEEP = P exp -P atm , where P exp Indicates the pressure value of the last exhalation phase of each respiratory cycle of the patient, P atm is the atmospheric pressure value;

[0063] Oxygen flow rate O f , refers to the actual volume of oxygen provided to the patient by the oxygen concentrator. It is an important parameter that directly affects the patient's oxygen supply and is obtained by monitoring the oxygen supply pipeline through a flow meter.

[0064] The data processing unit comprises a predicted oxygen demand calculation module, an oxygen flow calculation module, and an oxygen flow adjustment module. The predicted oxygen demand calculation module is configured to calculate and process the relevant parameters obtained by the data acquisition unit to obtain the predicted oxygen demand of the patient predicted oxygen demand reflects the amount of oxygen required by the patient in a specific physiological state, directly affecting the adjustment of oxygen flow to ensure that the patient receives sufficient oxygen; the oxygen flow calculation module is configured to calculate the predicted oxygen demand as an input item, and obtain an oxygen adjustment amount ΔO through calculation and processing. The oxygen flow adjustment module is configured to adjust the oxygen flow of the oxygen inhalation machine based on the oxygen adjustment amount ΔO and the predicted oxygen demand to obtain the oxygen flow O that meets the oxygen demand of the patient f , and then control the real-time oxygen flow output by the oxygen inhalation machine.

[0065] Specifically, the predicted oxygen demand calculation module calculates and processes the relevant parameters in the following manner: defining the predicted oxygen demand as a function of the relevant parameters, the relevant parameters include:

[0066] heart rate HR, the relationship between heart rate HR and oxygen demand may be linear to some extent, because an increase in heart rate HR usually means that the body needs more oxygen to meet the pumping demand of the heart, but this relationship is not completely linear, because an increase in heart rate HR may also be a reflection of other factors (such as body temperature, pain, anxiety, etc.), which may not directly increase the demand for oxygen;

[0067] physical activity intensity A, the relationship between physical activity intensity A and oxygen demand is usually positively correlated but nonlinear; when the intensity of exercise is low, the increase in oxygen demand may be proportional to the increase in physical activity intensity A; when the intensity of exercise is high, the increase in oxygen demand may become less significant;

[0068] carbon dioxide emission CO2, the relationship between oxygen demand and carbon dioxide emission CO2 is usually linearly correlated, because there is a certain proportional relationship between oxygen consumption and carbon dioxide production in the metabolic process, but under extreme conditions or in certain pathological states, this proportion may change;

[0069] blood oxygen saturation SpO2, when blood oxygen saturation SpO2 is within the normal range, the body can maintain appropriate oxygen supply, but once SpO2 drops, especially below 90%, oxygen demand will increase sharply, because the body needs more oxygen to maintain the function of vital organs;

[0070] respiratory rate f R , under normal circumstances, the respiratory rate f RAn increase in oxygen intake can result from an increase in ventilation, but this relationship is not linear because too rapid breathing (such as hyperventilation) can result in excessive carbon dioxide elimination, causing respiratory alkalosis, which can adversely affect oxygen transport and utilization;

[0071] Tidal volume V T , increasing the tidal volume V T can improve the intake of oxygen, but this increase is limited, and too large a tidal volume can cause alveolar overinflation and barotrauma.

[0072] Then build a polynomial regression model, namely the oxygen demand prediction model:

[0073] Y = β0+ β1·X1+ β2·X2+... + β n ·X k + β n+1 ·X1 2 + β n+2 ·X2 2 +... + β n+k ·X k 2 +... + ε;

[0074] In the formula, Y (predicted oxygen demand ) is the dependent variable; β0 is the intercept of the model; X is the independent variable, k represents the number of independent variables, X k represents the kth independent variable X, and in this case, the independent variable X has six relevant parameters, namely X1 (heart rate HR), X2 (intensity of body movement A), X3 (carbon dioxide discharge CO2), X4 (oxygen saturation SpO2), X5 (respiratory rate f R ), X6 (tidal volume V T ); β1, β2, β3, …, β n are the regression coefficients corresponding to the independent variable X k , indicating the degree of influence of a unit change in the independent variable X on the predicted oxygen demand , n represents the total number of regression coefficients related to the model; X1 2 , X2 2 , …, X k 2 are the square terms of the independent variable X, X k 2 represents the square term of the kth independent variable, indicating a non-linear relationship; ε is the error term. In this scheme, the relationship between the dependent variable and the independent variable is non-linear, so the square or higher power of the independent variable can explain the interaction between the variables, better fitting the data on different data segments, thus providing more accurate prediction results.

[0075] After the oxygen demand prediction model is completed, it needs to be evaluated to determine the fitting degree and prediction ability of the polynomial regression model. The specific evaluation methods include:

[0076] First, define the loss function as mean square error In the formula, N is the total number of samples; is the predicted value of the model, i.e. the predicted oxygen demand Y i is the true value, i.e. the actual oxygen demand O d . Specifically, collect the historical data set of relevant parameters and the actual oxygen demand O d of a number of sample patients; then clean the data set, check for missing values and outliers in the data set, and perform appropriate processing (such as imputing missing values and removing outliers) to ensure data integrity and quality, then import the historical data set of patients into the oxygen demand prediction model, i.e. the predicted oxygen demand Then by calculating the MSE, the difference between the predicted value and the true value of the model, i.e. the difference between the predicted oxygen demand and the actual oxygen demand O d can be measured. The square form of MSE can effectively focus on larger errors, as the square of the error will also be magnified. The smaller the value of MSE, the better the prediction ability of the polynomial regression model.

[0077] Then, in order to improve the prediction accuracy of the oxygen demand prediction model as a whole, the coefficient vector β (containing the regression coefficients of all independent variables X in the polynomial regression model, such as k independent variables X, then β is a k*1 column vector) is optimized by minimizing MSE. The optimization method is: solve the coefficient vector β by least squares method matrix T X matrix ) - 1 X matrix T Y vector ;

[0078] In the formula, X matrix is the independent variable matrix, containing all independent variable values, each row represents the observation value of a sample, i.e. the historical data set of relevant parameters in this case, and each column represents an independent variable, i.e. the relevant parameters in this scheme. For example, in this case, the historical data set of relevant parameters is converted into a table format, which can be represented as:

[0079] HR A CO2 SpO2 f R ]]> V T ]]> 70 1 0.03 95 16 500 75 2 0.04 97 18 550 ... ... ... ... ... ...

[0080] Then extract the data from the above table to form the independent variable matrix X matrixN*m, where N is the number of observations and m is the number of independent variables, 6 in the above example;

[0081] Y vector is the dependent variable vector, a vector containing all the real measurements of the dependent variable, i.e. the actual oxygen demand O d of all the sample patients in the case; d corresponding to the oxygen demand value of each observation; for example, in the case, the actual oxygen demand O d of all the sample patients is arranged into a one-dimensional array, which can be represented as:

[0082]

[0083]

[0084] The dependent variable vector Y vector is then created, which is of shape N*1;

[0085] For example, if there are two historical data sets, they are:

[0086] The first historical data set is:

[0087] HR: 70, A: 1, CO2: 0.03, SpO2: 95, f R : 16, V T : 500

[0088] O d : 250

[0089] The second historical data set is:

[0090] HR: 75, A: 2, CO2: 0.04, SpO2: 97, f R : 18, V T : 550

[0091] O d : 270

[0092] The construction of the independent variable matrix X matrix and the dependent variable vector Y vector is as follows:

[0093]

[0094] X matrix T is the transpose of the independent variable matrix X matrix , which exchanges rows and columns, so that the number of rows of the independent variable matrix X matrix becomes the number of independent variables, and the number of columns becomes the number of observations, with a shape of m*N;

[0095] X matrix T X matrix denotes the transpose of the independent variable matrix X matrix T and the independent variable matrix X matrix itself, which is an m*m matrix (the number of independent variables is the same as the number of dependent variables), the elements of which represent the correlation between the independent variables X;

[0096] (X matrix T X matrix ) -1 denotes the matrix X matrix T X matrix , the inverse of which is used to adjust the mutual influence between the independent variables X when solving the coefficient vector β;

[0097] X matrix T Y vector denotes the product of the transpose of the independent variable matrix X matrix and the dependent variable vector Y vector , which is an m*1 column vector, and this product can determine the influence of each independent variable X on the dependent variable Y, indicating the weighted contribution of the dependent variable Y to the independent variable X;

[0098] Further, through the above formula, an optimal coefficient vector β can be obtained, so that the polynomial regression model can best fit the observed data, minimize the difference between the predicted value and the true value, i.e., the difference between the predicted oxygen demand and the actual oxygen demand O d , thereby improving the accuracy of the oxygen flow O f adjustment, and more accurately providing the required amount of oxygen to the patient, avoiding excess or deficiency.

[0099] Then, the determination coefficient R is defined to evaluate the goodness of fit of the oxygen demand prediction model, where the sum of squared errors is used to measure the difference between the predicted value and the true value; the total sum of squares is used to measure the difference between the predicted value and the mean, and the mean of the dependent variable Y. Further, the determination coefficient R 2 is calculated through the above formula, and the value obtained is between 0 and 1, and the closer to 1 indicates that the polynomial regression model fits better.

[0100] Finally, the residual error ε i is defined, which represents the residual error of the i-th sample. By comparing each predicted value with the corresponding residual error ε iA residual plot (usually a scatter plot) is drawn, and then the random distribution of the residuals ε is observed in the residual plot. If the residual plot presents a random scatter, it indicates that the polynomial regression model assumption is well satisfied. If the residuals ε are observed to change with the change of the predicted values , such as the shape of the hole or other patterns, it indicates that the polynomial regression model is not suitable.

[0101] In summary, in the present solution, by calculating the mean square error MSE, the coefficient vector β, the determination coefficient R 2 and the residual ε, the prediction ability of the oxygen demand prediction model can be effectively evaluated.

[0102] Further, in the present case, after calculating the predicted oxygen demand of the patient by the oxygen demand prediction model , the predicted oxygen demand is input into the oxygen flow calculation module. The oxygen flow calculation module combines the above-mentioned related parameters to construct a regression model, i.e., an oxygen regulation model, and calculates and processes the oxygen regulation amount ΔO. Then, the oxygen flow O is calculated and processed by the predicted oxygen demand and the oxygen regulation amount ΔO. f .

[0103] Specifically, the construction method of the oxygen regulation model, i.e., the calculation and processing method of the oxygen regulation amount ΔO, includes:

[0104] Define the oxygen regulation amount

[0105] ΔO = K adj ·(HR target -HR) + K PEEP ·(PEEP target -PEEP) + K SpO2 ·(SpO2 target -SpO2); In the formula, the oxygen regulation amount ΔO represents the adjustment degree of the oxygen quality according to the difference between the current physiological state and the target state of the patient; HR target is the target heart rate that needs to be adjusted by the patient, which is usually set by the doctor according to the specific needs of the patient; K adj represents the adjustment coefficient of the difference between the current heart rate HR and the target heart rate HR target of the patient; PEEP target is the target end-expiratory positive pressure value that needs to be adjusted by the patient, which is usually set as the ideal PEEP value to optimize the oxygenation of the patient; K PEEP represents the adjustment coefficient of the difference between the current end-expiratory positive pressure PEEP and the target end-expiratory positive pressure PEEP target of the patient; SpO2 target is the target blood oxygen saturation that needs to be adjusted by the patient, which is usually set as the ideal SpO2 value to ensure that the patient obtains sufficient oxygen; KSpO2 an adjustment factor representing the difference between the current blood oxygen saturation SpO2 of the patient and the target blood oxygen saturation SpO2 target .

[0106] oxygen flow O f The calculation processing mode of the oxygen flow O

[0107] It is worth mentioning that after the oxygen flow O f calculated by the oxygen flow calculation module, the oxygen flow O f is quickly fed back to the oxygen inhalation machine system, so as to adjust the oxygen flow O f . In the process of adjusting the oxygen flow O f , the adjustment speed of the oxygen flow O f needs to be controlled to avoid the situation that the adjustment speed of the oxygen flow O f is too slow, resulting in a critical situation of the patient due to insufficient oxygen supply, or the situation that the adjustment speed of the oxygen flow O f is too fast, causing fluctuations in oxygen supply, affecting the comfort and safety of the patient. Therefore, in order to accurately adjust the adjustment speed of the oxygen flow O f , the PID control and acceleration response mechanism are introduced into the oxygen flow calculation module to process the adjustment speed of the oxygen flow, and the processing mode of the PID control and acceleration response mechanism includes:

[0108] An acceleration response factor t is introduced, t represents a time point, and then an oxygen flow dynamic adjustment model is defined to obtain the oxygen flow O f (t) at the t time, that is, the current flow value to be calculated.

[0109] In the formula, O f (t-1) represents the oxygen flow at the previous time t-1, which is the reference value of the current oxygen flow adjustment;

[0110] G p is the proportional gain, which is used to control the influence degree of the current error on the oxygen flow adjustment; e(t) represents the error at the current time, and the calculation formula is , which represents the difference between the target oxygen demand and the current oxygen flow; G p ·e(t) represents the error at the current time multiplied by the proportional gain, and the contribution of the error at the current time to the adjustment of the oxygen flow is obtained;

[0111] G i is the integral gain, which is used to accumulate the errors at all previous time points to compensate for long-term errors; , which represents the sum of the error values from the 0th time to the tth time, reflecting the total error in the past period of time. It represents the accumulated error in the past multiplied by the integral gain, which is used to help accurately adjust the oxygen flow rate to eliminate the steady-state error of the system;

[0112] G d is the differential gain, which indicates the effect of the current error change rate on the oxygen flow adjustment; [e(t)-e(t-1)] indicates the difference between the error at the current moment and the error at the previous moment, indicating the change in error; G d [e(t)-e(t-1)] represents the change in error multiplied by the differential gain, which is used to account for the rate of change of the error, help predict future behavior, and provide a dynamic response to the oxygen flow rate;

[0113] G acc To accelerate the response gain, it is a new adjustment factor, representing the sensitivity of flow adjustment; G acc [e(t) - e(t-1)] represents the change in error multiplied by the acceleration response gain, providing an acceleration response factor t to further adjust the oxygen flow rate so that it can respond quickly when the error changes significantly, especially when the physiological state changes rapidly.

[0114] Furthermore, through the above-mentioned oxygen flow dynamic adjustment model, it can be ensured that the oxygen flow can be adjusted quickly and accurately when the patient's physiological parameters change rapidly, so that the oxygen inhaler can more effectively provide the required oxygen flow in different situations.

[0115] Among them, the integral gain G i The historical error is weighted so that the oxygen flow dynamic regulation model can reach the target value in the long term. i Ways to obtain include:

[0116] First set G i =0 as the initial value; then gradually increase the integral gain G i For example, you can choose to increase by 0.1 or 0.05 each time to observe the response of the oxygen flow dynamic regulation model; then record the output oxygen flow rate O of the oxygen flow dynamic regulation model after each adjustment. f (t) and the error e(t) at the current moment; finally, until the steady-state error of the oxygen flow dynamic regulation model is observed Close to zero, determine the optimal integral gain G i .

[0117] For example, suppose oxygen demand is predicted Initial oxygen flow O f (0) = 8 L / min, the initial cumulative error is 0;

[0118] Calculate initial error

[0119] Update cumulative error CE = 0 + e(0) = 0 + 2 = 2;

[0120] Select integral gain G i = 0.1, update oxygen flow O f (1) = O f (0) + K i · CE = 8 + 0.1 · 2 = 8.2;

[0121] Calculate error at next time

[0122] Update cumulative error CE = 0 + e(1) = 2 + 1.8 = 3.8;

[0123] Adjust integral gain G i = 0.2, update oxygen flow O f (2) = O f (1) + K i · CE = 8.2 + 0.2 · 3.8 = 8.96;

[0124] Continue this process by repeating the above steps to continuously calculate, gradually adjust integral gain G i , and monitor the performance of the oxygen flow dynamic adjustment model until the optimal integral gain G i value is found.

[0125] Where, the derivative gain G d is the rate used to respond to error changes, predict the future behavior of the oxygen flow dynamic adjustment model, and help to slow down the oscillation of the oxygen flow dynamic adjustment model, increase stability. The way to get derivative gain G d includes:

[0126] First, calculate the error change amount Δe(t) = e(t) - e(t-1), that is, the difference between the current error and the previous error at each time point t;

[0127] Second, use the derivative gain G d to update the current output of the oxygen flow dynamic adjustment model:

[0128] Oxygen flow O f (t) = O f (t-1) + K d · Δe(t);

[0129] Then apply a rapidly changing input signal, that is, predict the oxygen demand For example from 10 L / min to 15 L / min suddenly;

[0130] Then, monitor the actual output O f (t) of the oxygen flow dynamic adjustment model after each input of the rapidly changing input signal, and record the error e(t) and the error change amount Δe(t);

[0131] Next, adjust the value of the differential gain G d ; initially set a small initial value, for example, G d = 0.1; then gradually increase G d , for example, by 0.1 or 0.2 each time;

[0132] After that, monitor the output oxygen flow O d (t) of the oxygen flow dynamic adjustment model and the error e(t) when the differential gain G f is adjusted, and pay attention to the stability and response time of the oxygen flow dynamic adjustment model;

[0133] Finally, adjust the value of the differential gain G d until the output fluctuation of the oxygen flow dynamic adjustment model is reduced and the response is more stable, and no significant delay is caused, to determine the optimal value of the differential gain G d .

[0134] For example, assume that the set condition is the predicted oxygen demand The initial oxygen flow O f (0) = 15 L / min;

[0135] Calculate the initial error

[0136] Time step 1: set the initial value of the differential gain G d to 0.1;

[0137] Calculate the error at the next time

[0138] Calculate the error change amount Δe(1) = e(1) - e(0) = 5 - 5 = 0;

[0139] Update the oxygen flow O f (1) = O f (0) + K d · Δe(1) = 15 + 0.1 · 0 = 15;

[0140] Time step 2: assume that the set condition changes to the predicted oxygen demand

[0141] Calculate the current error

[0142] Calculate the error change amount Δe(2) = e(2) - e(1) = 10 - 5 = 5;

[0143] Update the oxygen flow O f (2) = O f (1) + K d · Δe(2) = 15 + 0.1 · 5 = 15.5;

[0144] Continue this process, and repeat the above steps and adjust the differential gain G d If the response is slow, increase the differential gain G d (e.g. adjust to 0.2), observe whether the response time is shortened and no oscillation is introduced, and finally determine the optimal value of the differential gain G d .

[0145] Where the acceleration response gain G acc is to accelerate the response of the oxygen flow dynamic adjustment model to significant error changes. The acceleration response gain G acc is obtained in the following way:

[0146] First, calculate the error change Δe(t) = e(t) - e(t-1);

[0147] Second, update the current output of the oxygen flow dynamic adjustment model using the acceleration response gain G acc :

[0148] Oxygen flow O f (t) = O f (t-1) + K acc · Δe(t);

[0149] Then, apply a rapidly changing input signal, i.e. a predicted oxygen demand for example from 20 L / min to 45 L / min suddenly, simulate a sudden pathological condition, and monitor how the oxygen flow dynamic adjustment model responds;

[0150] Then, observe the changes in the oxygen flow O f (t) output by the oxygen flow dynamic adjustment model under these rapid changes, and whether the oxygen flow dynamic adjustment model can quickly return to a new steady state;

[0151] Finally, use the real-time monitored data to gradually adjust the value of the acceleration response gain G acc . Specifically, set a threshold η for error changes, when |Δe(t)| > η, trigger the adjustment of the acceleration response gain G acc , and the adjustment formula is: acceleration response gain G acc (t) = G acc (t-1) + α · Δe(t); where G acc(t-1) represents the acceleration response gain value at time point t-1, which is the basis for feedback adjustment based on the previous oxygen flow dynamic adjustment model state; a is a step, which is a constant, determining the amplitude of each adjustment. If the value of a is larger, the adjustment speed of the acceleration response gain will be faster, and the oxygen flow dynamic adjustment model will be more sensitive to error changes. If the value of a is smaller, the adjustment speed of the acceleration response gain will be slower, and the oxygen flow dynamic adjustment model will be more stable in response to error changes, but it will not be able to respond to rapid changes in errors. For example, set the initial value of the acceleration response gain G acc 0.1, then gradually try to increase or decrease, and dynamically adjust the error changes according to the response of the oxygen flow dynamic adjustment model. And in order to prevent over-adjustment, set the maximum and minimum values of the acceleration response gain G acc accmin ≤G acc (t)≤G accmax .

[0152] For example, assume that the set condition is the predicted oxygen demand The initial oxygen flow O f (0) = 25 L / min, and the initial acceleration response gain G acc = 0.1.

[0153] Time step 0:

[0154] Calculate the current error

[0155] Time step 1: simulate a rapid change in the set condition value

[0156] Calculate the new error

[0157] Calculate the error change Δe(1) = e(1) - e(0) = 15 - 5 = 10.

[0158] Update the oxygen flow O f (1) = O f (0) + K acc · Δe(1) = 25 + 0.1 · 10 = 26.

[0159] Record the output of the oxygen flow dynamic adjustment model at this time, and the oxygen flow O f (1) = 26 L / min.

[0160] Continue this process and repeat the above calculations in each subsequent time step, and analyze the response of the oxygen flow dynamic adjustment model to rapid changes.

[0161] By monitoring error changes, sudden change tests, and establishing feedback loops, the acceleration response gain G​acc , ensure that the oxygen flow dynamic adjustment model can quickly respond in the face of significant error changes, thereby ensuring the stability and effectiveness of the oxygen flow dynamic adjustment model.

[0162] Notably, the data processing unit further includes a parameter anomaly alarm module, which sets a warning threshold for the above-mentioned related parameters (i.e., physiological parameters of the patient) during the adjustment process of the oxygen flow O f of the patient, and there is a complex mutual relationship between the above-mentioned related parameters (i.e., physiological parameters of the patient) and the oxygen demand of the patient. When estimating the predicted oxygen demand , if there is an abnormal item in the related parameters, even if the calculated result can meet the requirements, it will lead to misjudgment of the patient's state, and thus cause major clinical crises and decision errors. The parameter anomaly alarm module sets a warning threshold for the above-mentioned related parameters, and when any parameter is abnormal during the calculation of the predicted oxygen demand , it will trigger an early warning to remind medical personnel, thereby significantly improving patient safety and treatment effectiveness.

[0163] Specifically, the early warning method of the parameter anomaly alarm module includes defining the early warning range of the related parameters, including:

[0164] the early warning range of heart rate HR [HR min , HR max ], where HR min is the minimum heart rate warning threshold, and HR max is the maximum heart rate warning threshold;

[0165] the early warning range of blood oxygen saturation SpO2 [SpO2 min , SpO2 max ], where SpO2 min is the minimum blood oxygen saturation warning threshold, and SpO2 max is the maximum blood oxygen saturation warning threshold;

[0166] the early warning range of respiratory rate f R [f Rmin , f Rmax ], where f Rmin is the minimum respiratory rate warning threshold, and f Rmax is the maximum respiratory rate warning threshold;

[0167] the early warning range of tidal volume V T [V Tmin , V Tmax ], where V Tmin is the minimum tidal volume warning threshold, and V Tmax is the maximum tidal volume warning threshold;

[0168] the early warning range of carbon dioxide excretion is less than or equal to CO2 max , and CO2max A unilateral cap on maximum CO2 emissions;

[0169] Warning range of positive end-expiratory pressure (PEEP) min ,PEEP max ], PEEP min is the minimum positive end-expiratory pressure warning threshold, PEEP max is the maximum positive end-expiratory pressure warning threshold;

[0170] The warning range of body movement intensity A is less than or equal to A max , A max It is the unilateral upper limit of the highest body movement.

[0171] Define an alarm mechanism to check whether each parameter exceeds the threshold range, such as Figure 2 As shown: Check the heart rate HR in turn to see if it exceeds the warning range. If so, an alarm will be issued. Otherwise, continue to check whether the blood oxygen saturation SpO2 exceeds the warning range. If so, an alarm will be issued. Otherwise, continue to check the respiratory rate f R Is it beyond the warning range? If yes, an alarm is issued. Otherwise, continue to detect the tidal volume V T Whether it exceeds the warning range, if so, an alarm is issued; otherwise, continue to detect whether the carbon dioxide emissions CO2 exceed the unilateral upper limit, if so, an alarm is issued; otherwise, continue to detect whether the positive end-expiratory pressure PEEP exceeds the warning range, if so, an alarm is issued; otherwise, continue to detect whether the body movement intensity A exceeds the unilateral upper limit, if so, an alarm is issued; otherwise, it indicates that all relevant parameters are normal.

[0172] By monitoring and acquiring patients' physiological parameters in real time and comparing them with preset thresholds, the system can promptly identify abnormal conditions and trigger alarms, providing medical staff with automated and timely feedback, enabling prompt implementation of necessary medical interventions and improving patient safety and quality of care. Furthermore, through the comprehensive monitoring of multiple related parameters, a more comprehensive assessment of the patient's physiological status can be achieved, reducing the risk associated with errors in a single parameter.

[0173] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An oxygen flow control system for a respiratory oxygen inhaler, comprising a data acquisition unit for obtaining relevant parameters for effective oxygen flow regulation, characterized in that: It also includes a data processing unit, which includes: The oxygen demand prediction calculation module is used to build an oxygen demand prediction model based on relevant parameters and calculate the predicted oxygen demand Oxygen flow calculation module, used to calculate oxygen flow according to relevant parameters and oxygen demand Construct an oxygen regulation model and calculate the oxygen regulation amount ΔO; Oxygen flow regulation module, based on predicted oxygen demand The oxygen flow rate is calculated by adding the oxygen adjustment amount ΔO PID control and accelerated response mechanism are introduced to control the oxygen flow rate O f Adjust speed for optimization; The parameter abnormality alarm module is used to define the warning range of relevant parameters and detect whether there are abnormal items in the relevant parameters. If there are abnormal items in the relevant parameters, an alarm will be issued; Related parameters include: heart rate HR, physical activity intensity A, carbon dioxide emissions CO2, blood oxygen saturation SpO2, respiratory rate f R , tidal volume V T , positive end-expiratory pressure (PEEP); Ways to build an oxygen demand prediction model include: Defining and predicting oxygen requirements There are related parameters with nonlinear relationships, and based on the polynomial regression model, we get Y=β0+β1·X1+β2·X2+...+β n ·X k +β n+1 X1 2 +β n+2 X2 2 +...+β n+k ·X k 2 +...+ε; where Y is the dependent variable, i.e., the predicted oxygen demand β0 is the intercept of the model; X is the independent variable, that is, the relevant parameter, k represents the number of independent variables; β1, β2, β3, ..., β n is the corresponding independent variable X k The regression coefficient of n represents the total number of regression coefficients; X1 2 , X2 2 ,…,X k 2 is the square term of the independent variable X; ε is the error term; then the oxygen demand prediction model is evaluated to obtain the mean square error MSE, the optimal coefficient vector β, and the determination coefficient R of the oxygen demand prediction model 2 and the residual ε.

2. The oxygen flow control system of a respiratory oxygen inhaler according to claim 1, characterized in that: The method of evaluating the oxygen demand prediction model includes: Define the loss function as mean square error Where N is the total number of samples; is the model prediction value, that is, the predicted oxygen demand Y i is the true value, that is, the actual oxygen demand O d ; Solve the optimal coefficient vector β=(X matrix T X matrix ) -1 X matrix T Y vector Where, X matrix is the independent variable matrix, Y vector is the dependent variable vector, X matrix T is the independent variable matrix X matrix The transpose of X matrix T X matrix represents the transpose of the independent variable matrix X matrix T and the independent variable matrix X matrix The product of itself, (X matrix T X matrix ) -1 Represents the matrix X matrix T X matrix The inverse matrix, X matrix T Y vector Represents the independent variable matrix X matrix The transpose of the dependent variable vector Y vector The product of Defining the coefficient of determination In the formula, the sum of squared errors is Total sum of squares in is the mean of the dependent variable Y; Defining residuals ε i represents the residual of the i-th sample.

3. The oxygen flow control system of a respiratory oxygen inhaler according to claim 2, characterized in that: The method of constructing the oxygen regulation model includes: Defining oxygen regulation ΔO=K adj ·(HR target -HR)+K PEEP ·(PEEP target -PEEP)+K SpO2 ·(SpO2 target -SpO2): In the formula, HR target The target heart rate that needs to be adjusted for the patient, K adj Indicates the patient's current heart rate HR and target heart rate HR target Adjustment coefficient for the difference between target K is the target positive end-expiratory pressure value that needs to be adjusted for the patient. PEEP Indicates the patient's current PEEP and target PEEP target Adjustment factor for the difference between target The target blood oxygen saturation that needs to be adjusted for the patient, K SpO2 Indicates the patient's current blood oxygen saturation SpO2 and target blood oxygen saturation SpO2 target The adjustment factor for the difference between the two.

4. The oxygen flow control system of a respiratory oxygen inhaler according to claim 1, characterized in that: The PID control and acceleration response mechanism optimizes the oxygen flow rate adjustment speed in the following ways: Introduce the acceleration response factor t, that is, time point t, and then define the dynamic regulation model of oxygen flow. Get the oxygen flow rate O at time t f (t), that is, the current flow value to be calculated; where G p is the proportional gain; e(t) represents the error at the current moment, and the calculation formula is O f (t-1) represents the oxygen flow rate at the previous moment t-1, which is the reference value for the current oxygen flow rate adjustment; G i is the integral gain; G d is the differential gain; G acc is the acceleration response gain.

5. The oxygen flow control system of a respiratory oxygen inhaler according to claim 4, characterized in that: The integral gain G i The acquisition method includes: first set G i =0 as the initial value, and then gradually increase the integral gain G i , while observing the response of the oxygen flow dynamic regulation model and recording the integral gain G each time i Adjusted oxygen flow O f (t) and the error e(t) at the current moment, until the steady-state error of the oxygen flow dynamic regulation model Close to zero, determine the optimal integral gain G i ; The differential gain G d The acquisition method includes: first calculating the error change Δe(t) = e(t)-e(t-1); then using the differential gain G d Update the current output of the oxygen flow dynamic regulation model: oxygen flow O f (t) = O f (t-1)+K d Δe(t); then a varying input signal is applied, i.e., the predicted oxygen demand and detect O f (t), and record the error e(t) and the error change Δe(t); then adjust the differential gain G d Until the output fluctuation of the oxygen flow dynamic regulation model is reduced and the response is stable, determine the differential gain G d optimal value; The acceleration response gain G acc The ways to obtain include: using the acceleration response gain G acc Update the current output of the oxygen flow dynamic regulation model: oxygen flow O f (t) = O f (t-1)+K acc Δe(t); then a rapidly changing input signal is applied, i.e. the predicted oxygen demand Then observe and predict oxygen demand When the oxygen flow rate O f (t), and whether the oxygen flow dynamic regulation model can return to a new steady state; finally, using the real-time monitoring data, the acceleration response gain G is gradually adjusted. acc Specifically, a threshold value η of the error change is set. When |Δe(t)|>η, the acceleration response gain G is triggered. acc The adjustment formula is G acc (t) = G acc (t-1)+α·Δe(t); where G acc (t-1) represents the acceleration response gain value at time point t-1; α is the step size.

6. The oxygen flow control system for a respiratory oxygen inhaler according to claim 1, characterized in that: The warning range of the defined relevant parameters includes: Heart rate HR warning range [HR min ,HR max ], HR min is the minimum heart rate warning threshold, HR max is the maximum heart rate warning threshold; Warning range of blood oxygen saturation SpO2 [SpO2 min ,SpO2 max ], SpO2 min The lowest blood oxygen saturation warning threshold, SpO2 max is the highest blood oxygen saturation warning threshold; Respiratory rate f R Warning range [f Rmin ,f Rmax ], f Rmin is the minimum respiratory rate warning threshold, f Rmax is the maximum respiratory rate warning threshold; Tidal volume V T Warning range [V Tmin ,V Tmax ],V Tmin is the minimum tidal volume warning threshold, V Tmax is the maximum tidal volume warning threshold; The warning range of carbon dioxide emissions is less than or equal to CO2 max , CO2 max A unilateral cap on maximum CO2 emissions; Warning range of positive end-expiratory pressure (PEEP) min ,PEEP max ], PEEP min is the minimum positive end-expiratory pressure warning threshold, PEEP max is the maximum positive end-expiratory pressure warning threshold; The warning range of body movement intensity A is less than or equal to A max , A max It is the unilateral upper limit of the highest body movement.

7. The oxygen flow control system for a respiratory oxygen inhaler according to claim 6, characterized in that: The method of detecting whether there are abnormal items in the relevant parameters includes: Check heart rate HR, blood oxygen saturation SpO2, respiratory rate f in turn R , tidal volume V T , carbon dioxide emissions, positive end-expiratory pressure PEEP, and body movement intensity A exceed their warning range or unilateral upper limit. If they exceed their warning range or unilateral upper limit, they are abnormal items.

Images