Regulation and control system and method of oxygen generator for respiratory medicine department

Abstract

The invention relates to the technical field of oxygen generator control, in particular to an oxygen generator regulation and control system and method for the respiratory medicine department, and the method comprises the steps: obtaining the patient state abnormal degree of each unstable sequence segment in a respiratory frequency sequential sequence of a patient, and combining an oxygen saturation sequential sequence with a respiratory depth sequential sequence, the method comprises the following steps: obtaining the probability that each unstable sequence segment is noise, decomposing each unstable sequence segment so as to obtain the final abnormal degree of the patient state of each unstable sequence segment, obtaining prediction data, inputting the prediction data into a PID controller, and outputting an oxygenerator regulation and control instruction at the current moment. Different prediction weights are given to the noise data, the stable data and the unstable data in the time sequence, the influence of the noise data is reduced, and the importance of the unstable data when the patient is abnormal is improved, so that the accuracy of the prediction data is guaranteed, and the accuracy of dynamic regulation and control of the oxygen machine is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of oxygen concentrator control, and in particular to a control system and method for an oxygen concentrator used in respiratory medicine. Background Art

[0002] Oxygen concentrator is a medical device. Its application in respiratory medicine is mainly to provide a continuous supply of oxygen to help patients with respiratory dysfunction or hypoxia maintain normal blood oxygen levels. It is widely used in medical treatment, emergency treatment and home care. The dynamic flow control of the oxygen concentrator is to adjust the oxygen output according to the patient's real-time oxygen demand to ensure that the patient obtains sufficient oxygen without wasting resources, effectively improving the effect of oxygen therapy and the patient's comfort.

[0003] Predicting the patient's oxygen demand in the future is the basis of dynamic regulation. Predictive regulation is generally achieved by real-time monitoring of the patient's physiological parameters such as breathing rate, depth, and oxygen saturation. Existing problems: The monitoring data of the sensor worn on the patient's body will inevitably be affected by the patient's movement, and the sensor itself may have certain measurement errors and the electromagnetic interference and mechanical vibration that may exist in the working environment of the oxygen concentrator, resulting in abnormal noise data fluctuations in the monitoring data. When the patient is in an abnormal state, it will also cause monitoring data fluctuations, such as emotional excitement, anxiety, or sudden pain stimulation. There is currently a situation where data fluctuations caused by abnormal conditions are misjudged as noise data fluctuations, which will affect the authenticity of monitoring data collection, and then affect the accuracy of data prediction achieved through monitoring data. The biased monitoring data prediction results may lead to low control accuracy of the oxygen concentrator, that is, the dynamic regulation of the oxygen concentrator flow is inaccurate. Summary of the invention

[0004] The present invention provides a control system and method for an oxygen concentrator for respiratory medicine to solve the existing problems.

[0005] The present invention provides a respiratory oxygen concentrator control system and method using the following technical solutions: An embodiment of the present invention provides a method for controlling an oxygen concentrator for respiratory medicine, the method comprising the following steps: Obtaining the patient's oxygen saturation time series, respiratory rate time series, and respiratory depth time series; The respiratory frequency time series is divided into a number of stable sequence segments and unstable sequence segments, and the initial abnormality degree of each unstable sequence segment is obtained according to the difference in respiratory frequency between the stable sequence segment and the unstable sequence segment; According to the initial abnormal degree of each unstable sequence segment in the respiratory frequency time series, the oxygen saturation time series and the respiratory depth time series, the possibility that each unstable sequence segment in the respiratory frequency time series is noise is obtained; Decompose each unstable sequence segment in the respiratory frequency time series to obtain a trend item; obtain the true abnormality degree of each unstable sequence segment in the respiratory frequency time series according to the peak value in the trend item, the differential value of the data in the trend item, the possibility that each unstable sequence segment in the respiratory frequency time series is noise, and the initial abnormality degree; According to the actual abnormal degree of each unstable sequence segment in the respiratory frequency time series, the predicted data is obtained; the predicted data is input into the PID controller, and an oxygen concentrator flow control instruction at the current moment is output.

[0006] Furthermore, the step of dividing the respiratory frequency time series into a plurality of stable sequence segments and unstable sequence segments includes the following specific steps: In the respiratory rate timing sequence, The first The normalized value of the absolute value of the difference in respiratory frequency is recorded as Instability of breathing rate; The respiratory frequency whose instability is less than the preset first threshold is recorded as a stable respiratory frequency, and the respiratory frequency whose instability is greater than or equal to the preset first threshold is recorded as an unstable respiratory frequency; Adjacent stable respiratory frequencies constitute a stable sequence segment, and adjacent unstable respiratory frequencies constitute an unstable sequence segment.

[0007] Furthermore, the initial abnormality degree of each unstable sequence segment is obtained according to the difference in respiratory frequency between the stable sequence segment and the unstable sequence segment, and the specific steps include the following: In the respiratory rate timing sequence, The mean of all respiratory rates in the unstable sequence minus the The normalized value of the difference between the mean values ​​of all respiratory frequencies in all stable sequence segments adjacent to the unstable sequence segment is recorded as The relative differences of the unstable sequence segments; According to The relative differences, durations, and respiratory rates of the unstable sequence segments are obtained. The initial abnormality level of an unstable sequence segment.

[0008] Furthermore, according to The relative differences, durations, and respiratory rates of the unstable sequence segments are obtained. The initial abnormality level of an unstable sequence segment includes the following specific steps: The first The difference between the maximum and minimum of all respiratory rates in the unstable sequence segment is The product of the variances of all respiratory frequencies in the unstable sequence segment is recorded as The instability degree of each unstable sequence segment; The first The instability degree of the unstable sequence segment, The relative differences of the unstable sequence segments and the The product of the durations of unstable sequence segments is recorded as The initial abnormality level of an unstable sequence segment.

[0009] Furthermore, the possibility that each unstable sequence segment in the respiratory frequency time series is noise is obtained according to the initial abnormality degree of each unstable sequence segment in the respiratory frequency time series, the oxygen saturation time series, and the respiratory depth time series, including the following specific steps: Using the start and end time of each unstable sequence segment in the respiratory frequency time series, a number of unstable sequence segments in the oxygen saturation time series and the respiratory depth time series are respectively divided; According to the method of obtaining the relative difference of each unstable sequence segment in the respiratory frequency time series, the relative difference of each unstable sequence segment in the oxygen saturation time series and the respiratory depth time series is obtained respectively; According to the difference between the relative differences of each unstable sequence segment in the respiratory rate time series, the oxygen saturation time series and the respiratory depth time series, the possibility that each unstable sequence segment in the respiratory rate time series is noise is obtained.

[0010] Further, the possibility that each unstable sequence segment in the respiratory frequency time series is noise is obtained according to the difference between the relative differences of each unstable sequence segment in the respiratory frequency time series, the oxygen saturation time series and the respiratory depth time series, and the specific steps include the following: Combine the respiratory rate time series with the respiratory depth time series The absolute value of the difference between the relative differences of the unstable sequence segments plus the absolute value of the difference between the respiratory rate time series and the oxygen saturation time series The sum of the absolute values ​​of the relative differences of the unstable sequence segments is recorded as the first sum; Combine the respiratory rate time series with the respiratory depth time series The DTW distance of the unstable sequence segment plus the DTW distance of the respiratory rate time series and the oxygen saturation time series The sum of the DTW distances of unstable sequence segments is recorded as the second sum; The product of the first sum and the second sum is recorded as the first sum in the respiratory frequency time series. The probability that an unstable sequence segment is noise.

[0011] Furthermore, the actual abnormality degree of each unstable sequence segment in the respiratory frequency time series sequence is obtained according to the peak value in the trend item, the differential value of the data in the trend item, the possibility that each unstable sequence segment in the respiratory frequency time series sequence is noise, and the initial abnormality degree, including the following specific steps: In the respiratory rate timing sequence In the trend item of an unstable sequence segment, the sequence consisting of the maximum value in the trend item and all the data before the maximum value is recorded as the target sequence, and the sequence consisting of the maximum value in the trend item and all the data after the maximum value is recorded as the reference sequence; The ratio of the number of negative numbers in the first-order difference sequence of the target sequence to the number of data in the target sequence is recorded as the first ratio; The ratio of the number of positive numbers in the first-order difference sequence of the reference sequence to the number of data in the reference sequence is recorded as the second ratio; The product of the mean of the first ratio and the second ratio and the number of peaks in the trend term is recorded as The noise of unstable sequence segments affects the credibility; According to The noise impact credibility of each unstable sequence segment, the possibility of being noise, and the initial abnormality degree of each unstable sequence segment in the respiratory rate time series are calculated to obtain the true abnormality degree of each unstable sequence segment in the respiratory rate time series.

[0012] Furthermore, according to The noise influence credibility, the possibility of being noise and the initial abnormality of each unstable sequence segment are calculated to obtain the true abnormality of each unstable sequence segment in the respiratory frequency time series, including the following specific steps: Calculate the The noise impact credibility of the unstable sequence segment is The inversely proportional normalized value of the product of the probability that the unstable sequence segment is noise is obtained, and the inversely proportional normalized value is added to the The normalized value of the product of the initial abnormality of the unstable sequence segment is recorded as the first in the respiratory frequency time series. The true abnormality of the unstable sequence segment.

[0013] Furthermore, the step of obtaining the prediction data according to the actual abnormality degree of each unstable sequence segment in the respiratory frequency time series includes the following specific steps: The respiratory rate timing sequence The sum of the actual abnormality degree of the unstable sequence segment and the preset second threshold is recorded as the first in the respiratory frequency time series. The weight of each respiratory rate in the unstable sequence segment; Setting the weight of each respiratory frequency in each stable sequence segment in the respiratory frequency time series sequence to a preset third threshold; According to the weight of each respiratory frequency in the respiratory frequency time series, the weighted ARIMA model is used to predict the respiratory frequency time series to obtain the predicted data; According to the method of obtaining the predicted data of the respiratory frequency time series, the predicted data of the respiratory depth time series and the oxygen saturation time series are obtained respectively.

[0014] The present invention also proposes a control system for an oxygen concentrator for respiratory medicine, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program stored in the memory to implement the steps of the aforementioned method for controlling an oxygen concentrator for respiratory medicine.

[0015] The beneficial effects of the technical solution of the present invention are: In an embodiment of the present invention, the initial abnormal degree of each unstable sequence segment in the patient's respiratory frequency time series is obtained, thereby determining the initial abnormal degree of each unstable sequence segment, and providing data support for the possibility and true abnormal degree of the subsequent unstable sequence segment being noise. Combined with the oxygen saturation time series and the respiratory depth time series, the possibility of each unstable sequence segment being noise is obtained, thereby analyzing the influence of noise, further ensuring the accuracy of abnormal patient state detection, thereby improving the accuracy of oxygen supply regulation. Each unstable sequence segment is decomposed to obtain the true abnormal degree of each unstable sequence segment, thereby obtaining predicted data, thereby obtaining the true true abnormal degree under noise interference removal, ensuring the credibility of the predicted data, thereby improving the credibility of the oxygen concentrator flow control instruction. The predicted data is input into the PID controller, and an oxygen concentrator flow control instruction at the current moment is output. So far, the present invention reduces the influence of noise data by assigning different prediction weights to noise data, stable data and unstable data in the time series, that is, it can eliminate the influence of noise on the accuracy of unstable data caused by abnormal state, improve the importance of unstable data when the patient is abnormal, thereby ensuring the accuracy of predicted data, and improving the accuracy of dynamic flow control of oxygen concentrators for respiratory medicine. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A flowchart of a method for controlling an oxygen concentrator for respiratory medicine according to the present invention; Figure 2 Schematic diagram of the global data trend changes in the unstable sequence segment in the respiratory frequency time series without noise influence. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation, structure, features and effects of a respiratory oxygen concentrator control system and method proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0019] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0020] The specific scheme of a control system and method for an oxygen concentrator for respiratory medicine provided by the present invention is described in detail below with reference to the accompanying drawings.

[0021] See also Figure 1 , which shows a flow chart of a method for controlling an oxygen concentrator for respiratory medicine provided by an embodiment of the present invention, the method comprising the following steps: Step S001: Obtain the patient's oxygen saturation time series, respiratory rate time series, and respiratory depth time series.

[0022] The SpO2 sensor and the respiratory rate and depth sensors worn on the patient are used to collect oxygen saturation, respiratory rate and respiratory depth in real time, respectively, to obtain an oxygen saturation time series sequence, a respiratory rate time series sequence and a respiratory depth time series sequence, respectively.

[0023] It should be noted that the main respiratory parameters of patients that need to be monitored for dynamic control of oxygen concentrator flow are oxygen saturation, respiratory rate and breathing depth. This is because when the amount of oxygen inhaled by the patient decreases, the oxygen saturation will decrease, and the oxygen concentrator needs to increase the output flow. Conversely, when the amount of oxygen inhaled by the patient increases, the oxygen saturation will increase, and the oxygen concentrator needs to reduce the output flow. Among them, the collection frequency of the three types of data is once every 10 seconds, and the collection time is from the beginning of wearing the oxygen concentrator to the current moment. This is described as an example. Since the patient needs to wear an oxygen concentrator, the respiratory changes caused by strenuous exercise are not considered in this embodiment.

[0024] Step S002: Divide the respiratory frequency time series into a plurality of stable sequence segments and unstable sequence segments, and obtain the initial abnormality degree of each unstable sequence segment according to the difference in respiratory frequency between the stable sequence segment and the unstable sequence segment.

[0025] It should be noted that under normal circumstances, the patient's oxygen saturation, respiratory rate, and breathing depth change little over time. This is mainly because the human body has a series of self-regulatory mechanisms to maintain physiological homeostasis and ensure the normal operation of body functions. However, when the respiratory frequency time series is affected by noise or abnormal conditions, the patient's respiratory rate will fluctuate, and breathing will often become irregular, which is manifested as disordered respiratory rhythm or irregular changes in depth, causing unstable fluctuations in the data. In order to facilitate the subsequent analysis of the possibility that each unstable sequence segment is noise and the true degree of abnormality, the data characteristics of the unstable sequence segment are analyzed in combination with the difference in respiratory frequency between the stable sequence segment and the unstable sequence segment to quantify the initial abnormality of each unstable sequence segment.

[0026] Preferably, in one embodiment of the present invention, the method for obtaining the initial abnormality degree of each unstable sequence segment in the respiratory frequency time series sequence includes: In the respiratory rate timing sequence, The first The normalized value of the absolute value of the difference in respiratory frequency is recorded as Instability of breathing rate.

[0027] In the above manner, the instability of each respiratory frequency is obtained.

[0028] It should be noted that: in this embodiment, the instability of the last respiratory frequency is taken as the instability of the second to last respiratory frequency, and this is used as an example for description. Among them, the absolute value of the difference between adjacent respiratory frequencies is normalized to between 0 and 1 using the minimum and maximum standard method, which is a well-known technology.

[0029] The first threshold is preset to be 0.3, and this is taken as an example for description.

[0030] In the respiratory frequency timing sequence, the smaller the instability, the greater the possibility that the corresponding respiratory frequency is a stable respiratory frequency, and the greater the instability, the greater the possibility that the corresponding respiratory frequency is an unstable respiratory frequency. Therefore, the respiratory frequency with instability less than the preset first threshold is recorded as a stable respiratory frequency, and the respiratory frequency with instability greater than or equal to the preset first threshold is recorded as an unstable respiratory frequency.

[0031] In the respiratory frequency time series, adjacent stable respiratory frequencies constitute a stable sequence segment, and adjacent unstable respiratory frequencies constitute an unstable sequence segment. Thus, the respiratory frequency time series sequence is divided into a plurality of stable sequence segments and unstable sequence segments.

[0032] It should be noted that: if a certain stable respiratory frequency does not have an adjacent stable respiratory frequency, the stable respiratory frequency is set as the unstable respiratory frequency; if a certain unstable respiratory frequency does not have an adjacent unstable respiratory frequency, the unstable respiratory frequency is set as the stable respiratory frequency, thereby ensuring that the length of the sequence segment is greater than 1. Among them, the stable sequence segment reflects the data when the patient's condition is stable, and the unstable sequence segment reflects the data when the patient's condition is unstable. The greater the difference between the unstable sequence segment and its adjacent stable sequence segment, the greater the change in the patient's respiratory condition.

[0033] In the respiratory rate timing sequence, The mean of all respiratory rates in the unstable sequence minus the The normalized value of the difference between the mean values ​​of all respiratory frequencies in all stable sequence segments adjacent to an unstable sequence segment is recorded as the value of the first respiratory frequency time series. The relative differences of the unstable sequence segments.

[0034] What needs to be explained is: The calculation formula for the relative difference of unstable sequence segments is: In the formula, The respiratory rate timing sequence The relative difference of unstable sequence segments, The respiratory rate timing sequence The average of all respiratory rates in an unstable sequence segment, is the respiratory rate timing sequence The average of all respiratory rates in all stable sequence segments adjacent to an unstable sequence segment. It is a linear normalization function, which is used to normalize the data value to between 0 and 1. Normalization is to eliminate the dimension, which is convenient for the subsequent comparative analysis between data of different dimensions. When the respiratory frequency changes in the unstable sequence segment are larger and more drastic, and the duration of the unstable sequence segment is longer, it means that the patient needs to make a larger change in the breathing pattern and a longer time to restore normal breathing, which is more consistent with the data fluctuation characteristics reflected by the real abnormal condition.

[0035] In the respiratory rate timing sequence, The difference between the maximum and minimum of all respiratory rates in the unstable sequence segment is The product of the variances of all respiratory frequencies in the unstable sequence segment is recorded as the first The instability of the unstable sequence segment. The instability degree of the unstable sequence segment, The relative differences of the unstable sequence segments and the The product of the duration of the unstable sequence segments is recorded as the first The initial abnormality level of an unstable sequence segment.

[0036] What needs to be explained is: The calculation formula for the initial abnormality degree of an unstable sequence segment is: In the formula, The respiratory rate timing sequence The initial abnormality of the unstable sequence segment, The respiratory rate timing sequence The relative difference of unstable sequence segments, The respiratory rate timing sequence The duration of the unstable sequence segment, The respiratory rate timing sequence The variance of all respiratory rates within an unstable sequence segment, and Respectively, The maximum and minimum values ​​of all respiratory rates within an unstable sequence segment. The respiratory rate timing sequence The greater the instability of an unstable sequence segment, the more irregular the breathing is and the larger the range of respiratory frequency variation is.

[0037] Step S003: According to the initial abnormality degree of each unstable sequence segment in the respiratory frequency time series sequence, the oxygen saturation time series sequence and the respiratory depth time series sequence, the possibility that each unstable sequence segment in the respiratory frequency time series sequence is noise is obtained.

[0038] It should be noted that the monitoring data of the sensor worn on the patient's body will inevitably be affected by the patient's movement, and the sensor itself may have certain measurement errors and the electromagnetic interference and mechanical vibration that may exist in the working environment of the oxygen concentrator, resulting in abnormal noise data fluctuations in the monitoring data, which will lead to a low credibility of the initial abnormality degree calculated above. Therefore, it is necessary to distinguish the noise data fluctuations and reduce the impact of noise on the respiratory rate data.

[0039] It should be further explained that: in the data time series collected by different types of sensors, the probability of noise data appearing simultaneously in different types of sensors is low, and the probability of noise data of similar size is also low. This is because the time of occurrence of noise data is random, and the size is also random. When patients are emotionally excited, anxious, or experience sudden pain stimulation, it usually leads to an increase in breathing rate and depth to increase oxygen intake and increase blood oxygen saturation to relieve the discomfort felt by the body. When the patient's discomfort gradually eases, the breathing rate and depth will decrease, causing the blood oxygen saturation to gradually return to a more normal level. That is, when the patient's state changes, these three types of data change at the same time, and the change trends are similar.

[0040] Preferably, in one embodiment of the present invention, a method for obtaining the possibility that each unstable sequence segment in the respiratory frequency time series is noise includes: The oxygen saturation time series and the breathing depth time series are divided into a number of stable sequence segments and unstable sequence segments using the start and end time of each stable sequence segment and each unstable sequence segment in the respiratory frequency time series.

[0041] According to the method of obtaining the relative difference of each unstable sequence segment in the respiratory frequency time series, the relative difference of each unstable sequence segment in the oxygen saturation time series and the respiratory depth time series is obtained respectively.

[0042] Combine the respiratory rate time series with the respiratory depth time series The absolute value of the difference between the relative differences of the unstable sequence segments plus the absolute value of the difference between the respiratory rate time series and the oxygen saturation time series The sum of the absolute values ​​of the relative differences of the unstable sequence segments is recorded as the first sum. The DTW distance of the unstable sequence segment plus the DTW distance of the respiratory rate time series and the oxygen saturation time series The sum of the DTW distances of the unstable sequence segments is recorded as the second sum. The product of the first sum and the second sum is recorded as the The probability that an unstable sequence segment is noise.

[0043] What needs to be explained is: The formula for calculating the probability that an unstable sequence segment is noise is: In the formula, The respiratory rate timing sequence The probability that an unstable sequence segment is noise, The first The absolute value of the difference in relative differences between unstable sequence segments, The first The absolute value of the difference in relative differences between unstable sequence segments, The first The DTW distance of unstable sequence segments, The first The DTW distance of unstable sequence segments, is the first sum value, is the second sum. The DTW distance is obtained by matching the data of two unstable sequence segments according to the DTW algorithm. The DTW algorithm (Dynamic Time Warping) is a well-known technology. The larger the DTW distance, the less similar the data change trends of the two unstable sequence segments are, that is, the more likely they are noise data. and The larger it is, the more it means that the three types of data do not fluctuate at the same time, that is, the more likely it is noise data.

[0044] Step S004: Decompose each unstable sequence segment in the respiratory frequency time series sequence to obtain a trend item; obtain the actual abnormality degree of each unstable sequence segment in the respiratory frequency time series sequence according to the peak value in the trend item, the differential value of the data in the trend item, the possibility that each unstable sequence segment in the respiratory frequency time series sequence is noise, and the initial abnormality degree.

[0045] It should be noted that the unstable data generated by the influence of noise is not the patient's true breathing rate. Using the breathing rate at this time to realize data prediction for oxygen concentrator regulation will lead to low accuracy of oxygen concentrator regulation. The fluctuation of monitoring data caused by abnormal conditions can show the patient's true breathing state, which is the basis for dynamically adjusting the oxygen concentrator flow rate. According to the possibility of noise, the noise data when the patient's state is stable can be accurately distinguished. However, when the noise data is in a period of time when the patient's state is unstable, it will cause the patient to be emotionally excited, anxious or suddenly painful. The relative difference in the absolute value of the unstable sequence segments of data of different dimensions caused by the patient's emotional excitement, anxiety or sudden pain stimulation is too large, and the DTW distance of the unstable sequence segments of data of different dimensions is too large. Therefore, it is necessary to further analyze the impact of noise during the period of unstable patient status. In the process of gradual relief from emotional excitement, anxiety or sudden pain stimulation, the respiratory rate, depth and oxygen saturation will first increase suddenly, and then gradually decrease until they return to normal. The global data trend change diagram of the unstable sequence segments in the respiratory frequency time series without noise influence is as follows. Figure 2 As shown, Figure 2 The horizontal axis is time and the vertical axis is respiratory rate.

[0046] Here, the greater the true abnormality, the less the corresponding unstable sequence segment is affected by noise fluctuations, the greater the possibility that the respiratory fluctuations are the patient's true respiratory state, and the higher the importance of each respiratory frequency in the corresponding unstable sequence segment in subsequent data prediction; the smaller the true abnormality, the greater the influence of the corresponding unstable sequence segment on noise fluctuations, the lower the possibility that the respiratory fluctuations are the patient's true respiratory state, and the lower the importance of each respiratory frequency in the corresponding unstable sequence segment in subsequent data prediction.

[0047] Preferably, in one embodiment of the present invention, the method for obtaining the true abnormality degree of each unstable sequence segment in the respiratory frequency time series sequence includes: For the respiratory rate timing sequence The unstable sequence segments are decomposed by STL to obtain the trend term.

[0048] Use a peak detection algorithm to obtain several peaks in the trend item.

[0049] It should be noted that the peak detection algorithm and STL decomposition are both well-known technologies, and the specific methods will not be introduced here. The full name of STL decomposition in Chinese is Seasonal-Trend decomposition procedure based on Loess, which can effectively extract long-term trends from time series data.

[0050] In the respiratory rate timing sequence In the trend item of an unstable sequence segment, the sequence consisting of the maximum value in the trend item and all the data before the maximum value is recorded as the target sequence, and the sequence consisting of the maximum value in the trend item and all the data after the maximum value is recorded as the reference sequence.

[0051] It should be noted that if there are multiple maximum values ​​in the trend item, the first maximum value that appears will be taken.

[0052] In the respiratory rate timing sequence In the trend term of the unstable sequence segment, the ratio of the number of negative numbers in the first-order difference sequence of the target sequence to the number of data in the target sequence is recorded as the first ratio, the ratio of the number of positive numbers in the first-order difference sequence of the reference sequence to the number of data in the reference sequence is recorded as the second ratio, and the product of the mean of the first ratio and the second ratio and the number of peaks in the trend term is recorded as the first ratio in the respiratory frequency time series. The noise in the unstable sequence segment affects the credibility.

[0053] In the respiratory rate time series, calculate the The noise impact credibility of the unstable sequence segment is The inverse normalized value of the product of the probability that the unstable sequence segment is noise is obtained, and the inverse normalized value is added to the The normalized value of the product of the initial abnormality of the unstable sequence segment is recorded as the first in the respiratory frequency time series. The true abnormality of the unstable sequence segment.

[0054] What needs to be explained is: The calculation formula for the true abnormality degree of an unstable sequence segment is: In the formula, The respiratory rate timing sequence The true abnormality of the unstable sequence segment, The respiratory rate timing sequence The number of peaks in the trend term of unstable sequence segments, The respiratory rate timing sequence The number of data in the target sequence in the trend item of the unstable sequence segment, The respiratory rate timing sequence The number of negative numbers in the first-order difference sequence of the target sequence in the trend term of the unstable sequence segment, The respiratory rate timing sequence The number of data in the reference sequence in the trend item of the unstable sequence segment, The respiratory rate timing sequence The number of positive numbers in the first-order difference sequence of the reference sequence in the trend term of the unstable sequence segment, The respiratory rate timing sequence The probability that an unstable sequence segment is noise, The respiratory rate timing sequence The initial abnormality level of an unstable sequence segment. is the first ratio, is the second ratio. Represents the first The noise in the unstable sequence segment affects the credibility. It is a linear normalization function used to normalize data values ​​to between 0 and 1. is an exponential function with a natural constant as the base. To present the inverse proportional relationship and normalization processing, the implementer can set the inverse proportional function and normalization function according to the actual situation.

[0055] It should be further explained that the acquisition of the first-order difference sequence is a well-known technology. The first-order difference refers to the difference or change between each data point in a time series and its previous data point. Since there should be only one peak in the trend term of the unstable sequence segment without noise influence, and the target sequence and the reference sequence have increasing and decreasing trends respectively, and The larger the value is, the more serious the influence of noise on the unstable sequence segment is. right Correction is performed, and the greater the noise effect, the The less accurate, so use right Correction is performed to obtain the true degree of abnormality.

[0056] Step S005: Obtain prediction data according to the actual abnormality degree of each unstable sequence segment in the respiratory frequency timing sequence; input the prediction data into the PID controller, and output an oxygen concentrator flow control instruction at the current moment.

[0057] The second threshold is preset to 0.5, and the third threshold is preset to 1, and this is used as an example for description.

[0058] The respiratory rate timing sequence The sum of the actual abnormality degree of the unstable sequence segment and the preset second threshold is recorded as the first in the respiratory frequency time series. The weight of each breathing rate within an unstable sequence segment.

[0059] According to the above method, the weight of each respiratory frequency in each unstable sequence segment in the respiratory frequency time series is obtained.

[0060] The weight of each respiratory frequency in each stable sequence segment in the respiratory frequency time series sequence is set to a preset third threshold.

[0061] Thus, the weight of each respiratory frequency in the respiratory frequency time series is obtained.

[0062] According to the weight of each respiratory frequency in the respiratory frequency time series, the weighted ARIMA model is used to predict the respiratory frequency time series to obtain predicted data.

[0063] It should be noted that the weighted ARIMA model (Weighted Autoregressive Integrated Moving Average) is a well-known technology, and the specific method is not introduced here. In this embodiment, a smaller weight is given to the data affected by noise, and a larger weight is given to the monitoring data when the patient is in an abnormal state. In this way, the noise effect is reduced in the process of obtaining the predicted data, and more important monitoring data when the patient is in an abnormal state is considered, which ensures the accuracy of the predicted data.

[0064] According to the method of obtaining the predicted data of the respiratory frequency time series, the predicted data of the respiratory depth time series and the oxygen saturation time series are obtained respectively.

[0065] The respiratory rate timing sequence, the respiratory depth timing sequence and the oxygen saturation timing sequence as well as the predicted data of the respiratory rate timing sequence, the respiratory depth timing sequence and the oxygen saturation timing sequence are input into the PID controller, and an oxygen concentrator flow control instruction at the current moment is output.

[0066] The oxygen concentrator flow control instruction at the current moment is used to control the oxygen concentrator flow at the next moment after the current moment.

[0067] It should be noted that the dynamic control of the oxygen concentrator flow rate using a PID (proportional-integral-differential) controller is a common and effective method. The PID controller is a well-known control technology. According to the above method, the oxygen concentrator flow control instructions at each subsequent moment are obtained, such as increasing the oxygen supply, reducing the oxygen supply, and keeping the oxygen supply unchanged, thereby completing the dynamic control of the oxygen concentrator flow rate.

[0068] In summary, in an embodiment of the present invention, the patient's oxygen saturation timing sequence, respiratory rate timing sequence and respiratory depth timing sequence are obtained to obtain the initial abnormality of each unstable sequence segment in the respiratory rate timing sequence, and the oxygen saturation timing sequence and the respiratory depth timing sequence are combined to obtain the possibility that each unstable sequence segment in the respiratory rate timing sequence is noise, and each unstable sequence segment in the respiratory rate timing sequence is decomposed to obtain the true abnormality of each unstable sequence segment in the respiratory rate timing sequence, and the predicted data is obtained according to the true abnormality of each unstable sequence segment in the respiratory rate timing sequence, and the predicted data is input into the PID controller to output an oxygen concentrator flow control instruction at the current moment. The present invention reduces the influence of noise data by assigning different prediction weights to noise data, stable data and unstable data in the timing sequence, and increases the importance of unstable data when the patient is abnormal, thereby ensuring the accuracy of the predicted data and improving the accuracy of the dynamic control of the oxygen concentrator flow.

[0069] The present invention also provides an oxygen concentrator control system for respiratory medicine, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program stored in the memory to implement the steps of the aforementioned method for controlling an oxygen concentrator for respiratory medicine.

[0070] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for controlling an oxygen concentrator for respiratory medicine, characterized in that: The method comprises the following steps: Obtaining the patient's oxygen saturation time series, respiratory rate time series, and respiratory depth time series; The respiratory frequency time series is divided into a number of stable sequence segments and unstable sequence segments, and the initial abnormality degree of each unstable sequence segment is obtained according to the difference in respiratory frequency between the stable sequence segment and the unstable sequence segment; According to the initial abnormal degree of each unstable sequence segment in the respiratory frequency time series, the oxygen saturation time series and the respiratory depth time series, the possibility that each unstable sequence segment in the respiratory frequency time series is noise is obtained; Decompose each unstable sequence segment in the respiratory frequency time series to obtain a trend item; obtain the true abnormality degree of each unstable sequence segment in the respiratory frequency time series according to the peak value in the trend item, the differential value of the data in the trend item, the possibility that each unstable sequence segment in the respiratory frequency time series is noise, and the initial abnormality degree; According to the actual abnormal degree of each unstable sequence segment in the respiratory frequency time series, the predicted data is obtained; the predicted data is input into the PID controller, and an oxygen concentrator flow control instruction at the current moment is output; The method of dividing the respiratory frequency time series into a plurality of stable sequence segments and unstable sequence segments includes the following specific steps: In the respiratory rate timing sequence, The first The normalized value of the absolute value of the difference in respiratory frequency is recorded as Instability of breathing rate; The respiratory frequency whose instability is less than the preset first threshold is recorded as a stable respiratory frequency, and the respiratory frequency whose instability is greater than or equal to the preset first threshold is recorded as an unstable respiratory frequency; Adjacent stable respiratory frequencies constitute a stable sequence segment, and adjacent unstable respiratory frequencies constitute an unstable sequence segment.

2. A method for controlling an oxygen concentrator for respiratory medicine according to claim 1, characterized in that: The method of obtaining the initial abnormality degree of each unstable sequence segment according to the difference in respiratory frequency between the stable sequence segment and the unstable sequence segment includes the following specific steps: In the respiratory rate timing sequence, The mean of all respiratory rates in the unstable sequence minus the The normalized value of the difference between the mean values ​​of all respiratory frequencies in all stable sequence segments adjacent to the unstable sequence segment is recorded as The relative differences of the unstable sequence segments; According to The relative differences, durations, and respiratory rates of the unstable sequence segments are obtained. The initial abnormality level of an unstable sequence segment.

3. A method for controlling an oxygen concentrator for respiratory medicine according to claim 2, characterized in that: According to the The relative differences, durations, and respiratory rates of the unstable sequence segments are obtained. The initial abnormality level of an unstable sequence segment includes the following specific steps: The first The difference between the maximum and minimum of all respiratory rates in the unstable sequence segment is The product of the variances of all respiratory frequencies in the unstable sequence segment is recorded as The instability degree of each unstable sequence segment; The first The instability degree of the unstable sequence segment, The relative differences of the unstable sequence segments and the The product of the durations of unstable sequence segments is recorded as The initial abnormality level of an unstable sequence segment.

4. A method for controlling an oxygen concentrator for respiratory medicine according to claim 2, characterized in that: The method of obtaining the possibility that each unstable sequence segment in the respiratory frequency time series is noise according to the initial abnormality degree of each unstable sequence segment in the respiratory frequency time series, the oxygen saturation time series, and the respiratory depth time series includes the following specific steps: Using the start and end time of each unstable sequence segment in the respiratory frequency time series, a number of unstable sequence segments in the oxygen saturation time series and the respiratory depth time series are respectively divided; According to the method of obtaining the relative difference of each unstable sequence segment in the respiratory frequency time series, the relative difference of each unstable sequence segment in the oxygen saturation time series and the respiratory depth time series is obtained respectively; According to the difference between the relative differences of each unstable sequence segment in the respiratory rate time series, the oxygen saturation time series and the respiratory depth time series, the possibility that each unstable sequence segment in the respiratory rate time series is noise is obtained.

5. A method for controlling an oxygen concentrator for respiratory medicine according to claim 4, characterized in that: The method of obtaining the possibility that each unstable sequence segment in the respiratory frequency time series is noise according to the difference between the relative differences of each unstable sequence segment in the respiratory frequency time series, the oxygen saturation time series and the respiratory depth time series includes the following specific steps: Combine the respiratory rate time series with the respiratory depth time series The absolute value of the difference between the relative differences of the unstable sequence segments plus the absolute value of the difference between the respiratory rate time series and the oxygen saturation time series The sum of the absolute values ​​of the relative differences of the unstable sequence segments is recorded as the first sum; Combine the respiratory rate time series with the respiratory depth time series The DTW distance of the unstable sequence segment plus the DTW distance of the respiratory rate time series and the oxygen saturation time series The sum of the DTW distances of unstable sequence segments is recorded as the second sum; The product of the first sum and the second sum is recorded as the first sum in the respiratory frequency time series. The probability that an unstable sequence segment is noise.

6. A method for controlling an oxygen concentrator for respiratory medicine according to claim 1, characterized in that: The method of obtaining the true abnormality degree of each unstable sequence segment in the respiratory frequency time series according to the peak value in the trend item, the differential value of the data in the trend item, the possibility that each unstable sequence segment in the respiratory frequency time series is noise, and the initial abnormality degree includes the following specific steps: In the respiratory rate timing sequence In the trend item of an unstable sequence segment, the sequence consisting of the maximum value in the trend item and all the data before the maximum value is recorded as the target sequence, and the sequence consisting of the maximum value in the trend item and all the data after the maximum value is recorded as the reference sequence; The ratio of the number of negative numbers in the first-order difference sequence of the target sequence to the number of data in the target sequence is recorded as the first ratio; The ratio of the number of positive numbers in the first-order difference sequence of the reference sequence to the number of data in the reference sequence is recorded as the second ratio; The product of the mean of the first ratio and the second ratio and the number of peaks in the trend term is recorded as The noise of unstable sequence segments affects the credibility; According to The noise impact credibility of each unstable sequence segment, the possibility of being noise, and the initial abnormality degree of each unstable sequence segment in the respiratory rate time series are calculated to obtain the true abnormality degree of each unstable sequence segment in the respiratory rate time series.

7. A method for controlling an oxygen concentrator for respiratory medicine according to claim 6, characterized in that: According to the The noise influence credibility, the possibility of being noise and the initial abnormality of each unstable sequence segment are calculated to obtain the true abnormality of each unstable sequence segment in the respiratory frequency time series, including the following specific steps: Calculate the The noise impact credibility of the unstable sequence segment is The inversely proportional normalized value of the product of the probability that the unstable sequence segment is noise is obtained, and the inversely proportional normalized value is added to the The normalized value of the product of the initial abnormality of the unstable sequence segment is recorded as the first in the respiratory frequency time series. The true abnormality of the unstable sequence segment.

8. A method for controlling an oxygen concentrator for respiratory medicine according to claim 1, characterized in that: The step of obtaining the prediction data according to the actual abnormal degree of each unstable sequence segment in the respiratory frequency time series includes the following specific steps: The respiratory rate timing sequence The sum of the actual abnormality degree of the unstable sequence segment and the preset second threshold is recorded as the first in the respiratory frequency time series. The weight of each respiratory rate in the unstable sequence segment; Setting the weight of each respiratory frequency in each stable sequence segment in the respiratory frequency time series sequence to a preset third threshold; According to the weight of each respiratory frequency in the respiratory frequency time series, the weighted ARIMA model is used to predict the respiratory frequency time series to obtain the predicted data; According to the method of acquiring the predicted data of the respiratory frequency time series, the predicted data of the respiratory depth time series and the oxygen saturation time series are obtained respectively.

9. A control system for an oxygen concentrator for respiratory medicine, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the computer program is executed by a processor, the steps of a method for controlling an oxygen concentrator for respiratory medicine as described in any one of claims 1 to 8 are implemented.

Images