A severe pneumonia patient targeted atomization auxiliary administration system combined with respiratory parameters

Abstract

The present application relates to the technical field of biomedical engineering, and particularly relates to a severe pneumonia patient targeted atomization auxiliary drug delivery system combined with respiratory parameters. The system comprises: a historical clustering module for clustering a plurality of historical data based on key features of the historical data to obtain a plurality of data class clusters; a mapping construction module for determining a drug delivery efficiency factor corresponding to each data class cluster according to key features of historical data included in each data class cluster; a waveform analysis module for analyzing waveform similarity between each monitoring waveform and the plurality of data class clusters in a plurality of continuous monitoring waveforms included in a monitoring period to determine a near neighbor class cluster of each monitoring waveform; and a dose regulation module for determining an atomization drug delivery dose of a target regulation period based on a drug delivery efficiency factor corresponding to the near neighbor class cluster of each monitoring waveform. The present application can improve drug deposition effect of pneumonia patients in the atomization treatment process.

Description

Technical Field

[0001] This invention relates to the field of biomedical engineering, specifically to a targeted nebulized adjuvant drug delivery system for patients with severe pneumonia that incorporates respiratory parameters. Background Technology

[0002] Currently, patients with severe pneumonia often have disordered breathing patterns, and traditional nebulized drug delivery is inefficient and has poor lung deposition.

[0003] Specifically, the dosage of traditional nebulization is usually determined by medical staff in advance and kept constant during nebulization treatment. However, the actual breathing pattern of patients with severe pneumonia often deviates from the ideal breathing pattern. This makes it difficult to adapt the constant nebulization dosage to the patient's actual breathing situation, resulting in a less than expected drug deposition effect. Summary of the Invention

[0004] The purpose of this invention is to provide a targeted nebulization-assisted drug delivery system for critically ill pneumonia patients that incorporates respiratory parameters, in order to solve the technical problem of poor drug deposition in existing nebulization drug delivery control schemes.

[0005] In a first aspect, one embodiment of the present invention provides a targeted nebulization-assisted drug delivery system for critically ill pneumonia patients, incorporating respiratory parameters, the system comprising: The historical clustering module is used to cluster multiple historical data based on key features of historical data to obtain multiple data clusters. The historical data is respiratory data of historical pneumonia patients. The key features include the respiratory cycle, peak respiratory parameters, inspiratory phase slope, and expiratory phase slope of the corresponding historical pneumonia patients. The mapping construction module is used to determine the dosing efficiency factor corresponding to each data cluster based on the key features of the historical data included in each data cluster; The waveform analysis module is used to analyze the waveform similarity between each monitoring waveform and multiple data clusters among multiple consecutive monitoring waveforms included in the monitoring period, so as to determine the nearest neighbor cluster of each monitoring waveform. The multiple consecutive monitoring waveforms are multiple consecutive respiratory waveforms of the target pneumonia patient monitored before the next control time. The number of multiple consecutive monitoring waveforms is a set number. The nearest neighbor cluster is the data cluster with the highest waveform similarity to the corresponding monitoring waveform among the multiple data clusters. The dose control module is used to determine the nebulized drug delivery dose for the target control period based on the drug delivery efficiency factor corresponding to the nearest neighbor cluster of each monitored waveform. The next control time is the start time of the target control period. The nebulization treatment process of the target pneumonia patient corresponds to multiple consecutive control periods. The multiple control periods have the same duration and include the target control period.

[0006] In some embodiments, the step of clustering multiple historical data based on key features of historical data to obtain multiple data clusters includes: In multiple historical data sets, the consistency of multiple consecutive respiratory waveforms included in each historical data set is analyzed to obtain the waveform steady-state coefficient of each historical data set. Among multiple historical data sets, those with waveform steady-state coefficients greater than the steady-state coefficient threshold are identified as key historical data. Based on the key features of key historical data, multiple key historical data are clustered to obtain multiple data clusters.

[0007] In some embodiments, the step of analyzing the consistency of multiple consecutive respiratory waveforms included in each historical data set to obtain the waveform steady-state coefficient of each historical data set includes: The multiple consecutive respiratory waveforms included in each historical data point are subjected to time-series normalization to obtain multiple standard waveforms corresponding to each historical data point. In each historical data point, among the multiple standard waveforms, the cross-correlation coefficient between the first standard waveform and other standard waveforms is calculated to obtain the cross-correlation coefficient between the multiple waveforms corresponding to each historical data point. The steady-state coefficient of each historical data point is determined based on the mean and standard deviation of the cross-correlation coefficients of multiple waveforms corresponding to each historical data point.

[0008] In some embodiments, the step of determining the waveform steady-state coefficient of each historical data point based on the mean and standard deviation of the cross-correlation coefficients of multiple waveforms corresponding to each historical data point includes: The mean of the cross-correlation coefficients of multiple waveforms corresponding to each historical data point is determined as its steady-state numerator, and the sum of the standard deviation of the cross-correlation coefficients of multiple waveforms corresponding to each historical data point and the value of 1 is determined as its steady-state denominator. Calculate the ratio of the steady-state numerator to the steady-state denominator for each historical data point to obtain the waveform steady-state coefficient for each historical data point.

[0009] In some embodiments, the drug administration efficiency factor is positively correlated with the respiratory cycle of the corresponding historical data, the drug administration efficiency factor is positively correlated with the peak value of the respiratory parameters of the corresponding historical data, the drug administration efficiency factor is negatively correlated with the inspiratory phase slope of the corresponding historical data, and the drug administration efficiency factor is negatively correlated with the expiratory phase slope of the corresponding historical data.

[0010] In some embodiments, the step of determining the nebulized drug delivery dose for the target control period based on the dosing efficiency factor corresponding to the nearest neighbor cluster of each monitored waveform includes: Based on the dosing efficiency factor corresponding to the nearest neighbor cluster of each monitoring waveform and the waveform similarity thereto, the correction efficiency factor of each monitoring waveform is determined. The correction efficiency factors of multiple monitoring waveforms are weighted and calculated to obtain the target efficiency factor for the target control period. The nebulized drug delivery dose for the target control period is determined based on the target efficiency factor and the preset drug delivery adjustment dose for the target control period.

[0011] In some embodiments, the calculation weight of the correction efficiency factor is negatively correlated with the time-domain distance of the corresponding monitoring waveform, and the time-domain distance is used to indicate the time interval between the end time of the corresponding monitoring waveform and the next control time.

[0012] In some embodiments, the system further includes a risk control module, the risk control module being used for: When the number of nearest neighbor clusters of multiple monitoring waveforms is greater than or equal to the number threshold, the degree of respiratory disturbance in the target pneumonia patient is analyzed based on the degree of waveform change of the multiple monitoring waveforms to obtain the respiratory disturbance coefficient. The nebulized drug dosage for the target regulation period is determined based on the respiratory disturbance coefficient.

[0013] In some embodiments, the step of analyzing the degree of respiratory disturbance in a target pneumonia patient based on the waveform changes of the plurality of monitored waveforms to obtain a respiratory disturbance coefficient includes: In the multiple monitoring waveforms, the ratio of tidal volume to inspiratory duration for each monitoring waveform is calculated to obtain the ventilation efficiency index for each monitoring waveform. Among the multiple monitoring waveforms, the variation amplitudes of the peak inhalation velocity and the inhalation duration of adjacent monitoring waveforms are analyzed to obtain multiple airflow mutation indices. The respiratory disturbance coefficient is determined by the average of the ventilation efficiency index of multiple monitoring waveforms and the average of multiple airflow mutation indices.

[0014] In some embodiments, the step of analyzing the variation amplitude of the peak inspiratory velocity and the variation amplitude of the inspiratory duration of adjacent monitoring waveforms to obtain multiple airflow mutation indices includes: The target flow rate difference is obtained by analyzing the absolute difference between the peak inspiratory flow rate of the first monitoring waveform and the peak inspiratory flow rate of the second monitoring waveform. The first and second monitoring waveforms are any two adjacent monitoring waveforms among multiple monitoring waveforms. The target duration difference is obtained by analyzing the absolute difference between the inhalation duration of the first monitoring waveform and the inhalation duration of the second monitoring waveform. The ratio of the target flow rate difference to the standard flow rate value is calculated to obtain the first mutation factor, and the ratio of the target duration difference to the standard duration value is calculated to obtain the second mutation factor, wherein the standard flow rate value is the average of the peak inspiratory flow rates of the plurality of monitoring waveforms, and the standard duration value is the average of the inspiratory duration of the plurality of monitoring waveforms; The sum of the first mutation factor and the second mutation factor is determined as the airflow mutation index that corresponds to both the first monitoring waveform and the second monitoring waveform.

[0015] Secondly, another embodiment of the present invention provides a targeted nebulized adjunctive drug delivery method for critically ill pneumonia patients combined with respiratory parameters, the method comprising: Based on the key features of historical data, multiple historical data are clustered to obtain multiple data clusters. The historical data are respiratory data of historical pneumonia patients. The key features include the respiratory cycle, peak respiratory parameters, inspiratory phase slope, and expiratory phase slope of the corresponding historical pneumonia patients. Based on the key characteristics of the historical data included in each data cluster, determine the dosing efficiency factor corresponding to each data cluster; In the monitoring period, the waveform similarity between each monitoring waveform and multiple data clusters is analyzed to determine the nearest neighbor cluster of each monitoring waveform. The multiple consecutive monitoring waveforms are multiple consecutive respiratory waveforms of the target pneumonia patient monitored before the next control time. The number of multiple consecutive monitoring waveforms is a set number. The nearest neighbor cluster is the data cluster with the highest waveform similarity to the corresponding monitoring waveform among the multiple data clusters. Based on the dosing efficiency factor corresponding to the nearest neighbor cluster of each monitoring waveform, the nebulized dosing dose for the target control period is determined. The next control time is the start time of the target control period. The nebulized treatment process of the target pneumonia patient corresponds to multiple consecutive control periods. The multiple control periods have the same duration and include the target control period.

[0016] Thirdly, in another embodiment of the present invention, an electronic device is provided, including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method described in the second aspect above.

[0017] Fourthly, in another embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the method described in the second aspect above.

[0018] The present invention has the following beneficial effects: This invention first performs clustering processing on multiple historical data points based on the respiratory cycle, peak respiratory parameters, inspiratory phase slope, and expiratory phase slope of historical pneumonia patients to identify various respiratory patterns corresponding to pneumonia patients. Then, based on the key data features of the data clusters corresponding to each respiratory pattern, it determines the dosing efficiency factor for each respiratory pattern to establish a mapping relationship between respiratory patterns and dosing efficiency. Subsequently, it analyzes in real time the similarity between multiple consecutive monitoring waveforms of the target pneumonia patient and the data clusters corresponding to different respiratory patterns, and determines the respiratory pattern with the most similar monitoring waveform and its dosing efficiency factor. Finally, it determines the nebulized drug dosage for the next control period to dynamically adapt to the real-time respiratory status of the target pneumonia patient and improve the drug deposition effect during nebulized treatment. Attached Figure Description

[0019] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of a targeted nebulization-assisted drug delivery system for critically ill pneumonia patients that incorporates respiratory parameters, provided in an embodiment of the present invention. Figure 2 This is a schematic flowchart of a targeted nebulized adjuvant drug delivery method for critically ill pneumonia patients combined with respiratory parameters, provided by an embodiment of the present invention. Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0021] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a targeted nebulization-assisted drug delivery system for critically ill pneumonia patients based on respiratory parameters, as proposed by the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0022] Unless otherwise defined, 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 pertains.

[0023] The following description, in conjunction with the accompanying drawings, details the specific implementation of a targeted nebulization-assisted drug delivery system for critically ill pneumonia patients based on respiratory parameters, provided by this invention.

[0024] In one embodiment, the present invention provides a targeted nebulized adjunctive drug delivery system for critically ill pneumonia patients that incorporates respiratory parameters, such as... Figure 1 As shown, the system 100 includes: The historical clustering module 101 is used to cluster multiple historical data based on key features of historical data to obtain multiple data clusters.

[0025] The historical data refers to the respiratory data of patients with a history of pneumonia, and the key features include the respiratory cycle, peak respiratory parameters, inspiratory phase slope, and expiratory phase slope of the corresponding patients with a history of pneumonia.

[0026] In this invention, historical pneumonia patients should be understood as severe pneumonia patients in the historical clinical case database. The datasets corresponding to multiple historical patients contain complete respiratory mechanics records of different disease stages, different distribution of diseased lung areas, and different ventilation function states to ensure the diversity and clinical representativeness of the dataset samples.

[0027] Among them, the respiratory cycle indicates the duration of one breath for the corresponding historical pneumonia patient, the peak respiratory parameter indicates the peak airway pressure or positive end-expiratory pressure of the corresponding historical pneumonia patient during the corresponding respiratory process, the inspiratory phase slope is used to indicate the steepness of the inspiratory phase waveform of the corresponding historical pneumonia patient during the corresponding respiratory process, and the expiratory phase slope is used to indicate the steepness of the expiratory phase waveform of the corresponding historical pneumonia patient during the corresponding respiratory process.

[0028] Analysis revealed that respiratory cycle, peak respiratory parameters, inspiratory slope, and expiratory slope can characterize the respiratory status of pneumonia patients to a certain extent, comprehensively reflect the respiratory pattern of pneumonia patients, and guide the drug administration efficiency of pneumonia patients in the corresponding respiratory pattern (which can be approximately understood as the drug deposition efficiency in the corresponding respiratory model).

[0029] Specifically, the steps of clustering multiple historical data points based on key features to obtain multiple data clusters include: In multiple historical data sets, the consistency of multiple consecutive respiratory waveforms included in each historical data set is analyzed to obtain the waveform steady-state coefficient of each historical data set. Among multiple historical data sets, those with waveform steady-state coefficients greater than the steady-state coefficient threshold are identified as key historical data. Based on the key features of key historical data, multiple key historical data are clustered to obtain multiple data clusters.

[0030] In the above settings, the consistency of multiple consecutive respiratory waveforms included in each historical data is first analyzed to determine the waveform steady-state coefficient of each historical data, that is, to determine the data reliability of the waveform corresponding to each historical data. Then, based on the setting of the steady-state coefficient threshold, historical data with insufficient data reliability are screened out, and clustering is performed on the more reliable key historical data after screening to ensure that the multiple data clusters obtained by clustering accurately represent multiple breathing modes.

[0031] The above respiratory waveforms are acquired based on flow sensors or pressure sensors. Specifically, the flow sensor is connected in series in the respiratory tubing of the pneumonia patient, while the pressure sensor is connected to the side hole of the respiratory tubing of the pneumonia patient through a thin tube. As the pneumonia patient breathes, the flow sensor or pressure sensor can acquire the corresponding respiratory waveform (composed of multiple flow values ​​or multiple pressure values).

[0032] In this invention, the waveform steady-state coefficient ranges from 0 to 1, and the above-mentioned steady-state coefficient threshold can be set to 0.85 based on experience.

[0033] In this invention, the K-means clustering algorithm is used to complete the above clustering process. The initial number of clusters corresponding to the K-means clustering algorithm is determined according to the elbow method, and the distance index of the K-means clustering algorithm is determined based on the key feature differences of different key historical data.

[0034] In this invention, before analyzing the differences in key features of different key historical data, the key features of each key historical data are numerically normalized. Specifically, the ratio of the respiratory cycle of the key historical data to the reference respiratory cycle is determined as its corresponding respiratory cycle normalization value; the ratio of the peak value of the respiratory parameter of the key historical data to the reference peak value of the respiratory parameter is determined as its corresponding respiratory parameter peak normalization value; the ratio of the inspiratory slope of the key historical data to the inspiratory slope reference slope is determined as its corresponding inspiratory slope normalization value; and the ratio of the expiratory slope of the key historical data to the expiratory slope reference slope is determined as its corresponding expiratory slope normalization value.

[0035] The aforementioned reference respiratory cycle is the maximum value among multiple respiratory cycles corresponding to multiple historical data. The aforementioned reference peak value of respiratory parameters is the maximum value among multiple peak values ​​of respiratory parameters corresponding to multiple historical data. The aforementioned reference slope of inspiratory phase is the maximum value among multiple inspiratory phase slopes corresponding to multiple historical data. The aforementioned reference slope of expiratory phase is the maximum value among multiple expiratory phase slopes corresponding to multiple historical data.

[0036] The distance index of the K-means clustering algorithm is obtained by accumulating the absolute differences of the normalized values ​​of the respiratory cycle, the normalized values ​​of the respiratory parameter peaks, the normalized values ​​of the inspiratory phase slope, and the normalized values ​​of the expiratory phase slope of different key historical data.

[0037] The steps for analyzing the consistency of multiple consecutive respiratory waveforms within each historical data set to obtain the waveform steady-state coefficient for each historical data set include: The multiple consecutive respiratory waveforms included in each historical data point are subjected to time-series normalization to obtain multiple standard waveforms corresponding to each historical data point. In each historical data point, among the multiple standard waveforms, the cross-correlation coefficient between the first standard waveform and other standard waveforms is calculated to obtain the cross-correlation coefficient between the multiple waveforms corresponding to each historical data point. The steady-state coefficient of each historical data point is determined based on the mean and standard deviation of the cross-correlation coefficients of multiple waveforms corresponding to each historical data point.

[0038] In this invention, multiple flow rates or pressure values ​​that constitute a corresponding respiratory waveform are processed using linear interpolation, so that the number of multiple flow rates or pressure values ​​corresponding to the respiratory waveform after interpolation is a set number (e.g., set to 1000 based on experience), thereby completing the time-series standardization processing of each respiratory waveform (it should be understood that the inspiratory phase slope and expiratory phase slope are obtained based on the multiple flow rates or pressure values ​​that constitute the corresponding respiratory waveform).

[0039] In the above settings, time-series standardization measures are implemented to ensure the smooth execution of subsequent cross-correlation coefficient calculations.

[0040] The step of determining the waveform steady-state coefficient of each historical data point based on the mean and standard deviation of the cross-correlation coefficients of multiple waveforms corresponding to each historical data point includes: The mean of the cross-correlation coefficients of multiple waveforms corresponding to each historical data point is determined as its steady-state numerator, and the sum of the standard deviation of the cross-correlation coefficients of multiple waveforms corresponding to each historical data point and the value of 1 is determined as its steady-state denominator. Calculate the ratio of the steady-state numerator to the steady-state denominator for each historical data point to obtain the waveform steady-state coefficient for each historical data point.

[0041] Based on the above ratio calculation, the central tendency and degree of variation of the cross-correlation coefficients of multiple waveforms can be combined to more accurately quantify the consistency of multiple respiratory waveforms corresponding to historical data.

[0042] The larger the waveform steady-state coefficient, the higher the consistency of the multiple consecutive respiratory waveforms included in the historical data, which means that the corresponding historical data is more reliable.

[0043] The mapping construction module 102 is used to determine the dosing efficiency factor corresponding to each data cluster based on the key features of the historical data included in each data cluster.

[0044] Specifically, the drug administration efficiency factor is positively correlated with the respiratory cycle of the corresponding historical data, the drug administration efficiency factor is positively correlated with the peak value of the respiratory parameters of the corresponding historical data, the drug administration efficiency factor is negatively correlated with the inspiratory phase slope of the corresponding historical data, and the drug administration efficiency factor is negatively correlated with the expiratory phase slope of the corresponding historical data.

[0045] Analysis revealed that a breathing pattern with a gentle curve change significantly promotes drug deposition in the patient's lungs, while a breathing pattern with a rapid and drastic curve change has a weaker effect on drug deposition. Based on this, the present invention sets a dosing efficiency factor corresponding to data clusters. for: in, This represents the cluster respiratory cycle corresponding to the data cluster (the average of multiple respiratory cycles corresponding to the data cluster). This represents the peak value of the respiratory parameter corresponding to the data cluster (the average of multiple respiratory parameter peak values ​​corresponding to the data cluster). This represents the slope of the gas inhalation phase corresponding to the data cluster (the average of multiple gas inhalation phase slopes corresponding to the data cluster). This represents the expiratory phase slope corresponding to the data cluster (the average of multiple expiratory phase slopes corresponding to the data cluster). Indicator normalization functions (such as Max-Min normalization functions) are designed to map dosing efficiency factors to the [0,1] interval.

[0046] It should be noted that the calculation formula for the dosing efficiency factor is a data-driven empirical feature model, used to quantify the dosing efficiency of clustering at the algorithm level, rather than an absolute physical derivation.

[0047] A higher dosing efficiency factor indicates a better drug deposition effect in the corresponding respiratory mode, which in turn means that a higher dose can be administered in the corresponding respiratory mode.

[0048] The waveform analysis module 103 is used to analyze the waveform similarity between each monitoring waveform and multiple data clusters among multiple consecutive monitoring waveforms included in the monitoring period, so as to determine the nearest neighbor cluster of each monitoring waveform.

[0049] The multiple consecutive monitoring waveforms are multiple consecutive respiratory waveforms of the target pneumonia patient monitored before the next control time. The number of the multiple consecutive monitoring waveforms is a set number. The nearest neighbor cluster is the data cluster with the highest waveform similarity to the corresponding monitoring waveform among multiple data clusters.

[0050] The above-mentioned number can be set to 15 based on experience.

[0051] The dose control module 104 is used to determine the nebulized drug delivery dose for the target control period based on the drug delivery efficiency factor corresponding to the nearest neighbor cluster of each monitoring waveform. The next control time is the start time of the target control period. The nebulized treatment process of the target pneumonia patient corresponds to multiple consecutive control periods. The multiple control periods have the same duration and include the target control period.

[0052] In this invention, the nebulizer used in nebulization therapy is specifically a vibrating mesh nebulizer. The dosage is controlled by adjusting the duty cycle of the piezoelectric ceramic of the nebulizer (to change the aerosol generation rate). Specifically, when analysis determines that an increased dosage is needed, the duty cycle of the piezoelectric ceramic of the nebulizer is increased accordingly; when analysis determines that a decreased dosage is needed, the duty cycle of the piezoelectric ceramic of the nebulizer is decreased accordingly.

[0053] It should be understood that the aforementioned multiple consecutive monitoring waveforms should be understood as the multiple consecutive respiratory waveforms that are closest to the next control time among the multiple respiratory waveforms collected for the target pneumonia patient.

[0054] In the application, the nebulization treatment process for the target pneumonia patient was divided into multiple control periods, and the nebulized drug dose for the target pneumonia patient was set to the minimum drug dose (i.e., the minimum duty cycle of the piezoelectric ceramic of the nebulizer) during the first control period.

[0055] By setting adjustable time periods, this invention can avoid frequent adjustments to the nebulized drug dosage for target pneumonia patients, thereby mitigating the discomfort that may result from high-frequency adjustments to the nebulized drug dosage. This provides a better nebulized treatment experience for target pneumonia patients while ensuring that the nebulized drug dosage is flexibly adapted to their recent respiratory status.

[0056] By using multiple consecutive monitoring waveforms collected recently to guide the nebulized drug delivery dosage for the next control period, it is possible to accurately track changes in the user's respiratory status while minimizing interference from short-term data fluctuations, making the nebulized drug delivery dosage determined in each control period more accurate and reliable.

[0057] Specifically, the steps for determining the nebulized drug delivery dose during the target control period based on the dosing efficiency factor corresponding to the nearest neighbor cluster of each monitored waveform include: Based on the dosing efficiency factor corresponding to the nearest neighbor cluster of each monitoring waveform and the waveform similarity thereto, the correction efficiency factor of each monitoring waveform is determined. The correction efficiency factors of multiple monitoring waveforms are weighted and calculated to obtain the target efficiency factor for the target control period. The nebulized drug delivery dose for the target control period is determined based on the target efficiency factor and the preset drug delivery adjustment dose for the target control period.

[0058] The calculation weight of the correction efficiency factor is negatively correlated with the time-domain distance of the corresponding monitoring waveform, and the time-domain distance is used to indicate the time interval between the end time of the corresponding monitoring waveform and the next control time.

[0059] The above-mentioned dosage adjustment should be understood as the difference between the maximum dosage and the minimum dosage (the above two dosage boundary values ​​are manually set by the attending physician of the target pneumonia patient before the start of nebulization). After determining the target efficiency factor for the target control period, the product of the target efficiency factor for the target control period and the dosage adjustment is determined as the dosage adjustment amplitude for the target control period, and the sum of the dosage adjustment amplitude for the target control period and the minimum dosage is determined as the nebulization dosage for the target control period.

[0060] Setting the calculation weight of the correction efficiency factor to be negatively correlated with the time domain distance of the corresponding monitoring waveform is to adapt to the characteristic that the monitoring waveform closer to the next control time has higher use value, so that the target efficiency factor of the determined target control period can more accurately track the respiratory status of the target pneumonia patient in the next control period.

[0061] In one example, the reciprocal of the time-domain distance between each monitoring waveform can be used to determine the corresponding time-distance index in multiple consecutive monitoring waveforms. Then, the sum of the time-distance indices corresponding to each monitoring waveform is calculated to obtain the time-domain reference value. Finally, the ratio of the time-distance index corresponding to each monitoring waveform to the time-domain reference value is determined as the calculation weight corresponding to each monitoring waveform.

[0062] In some embodiments, the system 100 further includes a risk control module, the risk control module being used for: When the number of nearest neighbor clusters of multiple monitoring waveforms is greater than or equal to the number threshold, the degree of respiratory disturbance in the target pneumonia patient is analyzed based on the degree of waveform change of the multiple monitoring waveforms to obtain the respiratory disturbance coefficient. The nebulized drug dosage for the target regulation period is determined based on the respiratory disturbance coefficient.

[0063] In actual nebulization therapy scenarios, the respiratory state of the target pneumonia patient is not always stable. Due to various factors, the target pneumonia patient may exhibit a relatively chaotic respiratory state during certain periods of nebulization therapy (i.e., the number of neighbor clusters of multiple monitoring waveforms is greater than or equal to a threshold). In this case, the aforementioned method of drug delivery efficiency factor based on neighbor clusters is difficult to effectively track the patient's condition under chaotic respiratory patterns. Therefore, this embodiment sets up an analysis of the degree of respiratory disturbance of the target pneumonia patient based on the degree of waveform change of the multiple monitoring waveforms, so as to quickly track the respiratory state by combining the degree of respiratory disturbance exhibited by the target pneumonia patient in real time, and then determine the nebulization drug delivery dose during the target control period.

[0064] It should be understood that if the number of nearest neighbor clusters of multiple monitoring waveforms is greater than or equal to the number threshold, the aforementioned steps for weighting the drug administration efficiency factor based on nearest neighbor clusters will be skipped.

[0065] In some implementations, when the respiratory disturbance coefficient (with a numerical range of [0,1]) is greater than or equal to the disturbance coefficient threshold (which may be set to 0.8 based on experience), the current nebulized drug delivery dose of the target pneumonia patient is forcibly adjusted to the minimum drug delivery dose, and a risk warning message is output to prompt relevant medical staff to manage the severe respiratory disturbance state currently exhibited by the target pneumonia patient.

[0066] When the respiratory disturbance coefficient is less than the disturbance coefficient threshold, the product of the respiratory disturbance coefficient and the descent dose (the difference between the nebulized drug dose in the current control period and the minimum drug dose) is calculated to obtain the drug dose reduction in the target control period. The difference between the nebulized drug dose in the current control period and the drug dose reduction in the target control period is determined as the nebulized drug dose in the target control period.

[0067] Specifically, the step of analyzing the degree of respiratory disturbance in the target pneumonia patient based on the waveform changes of the multiple monitored waveforms to obtain a respiratory disturbance coefficient includes: In the multiple monitoring waveforms, the ratio of tidal volume to inspiratory duration for each monitoring waveform is calculated to obtain the ventilation efficiency index for each monitoring waveform. Among the multiple monitoring waveforms, the variation amplitudes of the peak inhalation velocity and the inhalation duration of adjacent monitoring waveforms are analyzed to obtain multiple airflow mutation indices. The respiratory disturbance coefficient is determined by the average of the ventilation efficiency index of multiple monitoring waveforms and the average of multiple airflow mutation indices.

[0068] In this invention, tidal volume specifically indicates the amount of air inhaled by the target pneumonia patient under the corresponding monitoring waveform. The aforementioned ventilation efficiency index is used to indicate the inspiratory efficiency of the target pneumonia patient under the corresponding monitoring waveform. The higher the value, the higher the acceptance of the nebulized drug by the target pneumonia patient during breathing under the corresponding monitoring waveform.

[0069] Among the multiple monitoring waveforms, the more unstable the variation of the peak inspiratory flow rate of adjacent monitoring waveforms, the more chaotic the respiratory state of the target pneumonia patient is before the next control period (there is a risk of turbulence and ineffective ventilation), and the lower the acceptance of nebulized drugs by the target pneumonia patient under the corresponding monitoring waveform.

[0070] Similarly, among the multiple monitoring waveforms, the more unstable the variation in inspiratory duration of adjacent monitoring waveforms, the more chaotic the respiratory state of the target pneumonia patient is before the next control period, and the lower the acceptance of nebulized drugs by the target pneumonia patient under the corresponding monitoring waveform.

[0071] The aforementioned airflow mutation index is used to predict the degree of ventilation disorder in the target pneumonia patient during the next control period.

[0072] The step of analyzing the variation amplitudes of the peak inspiratory velocity and the inspiratory duration of adjacent monitoring waveforms to obtain multiple airflow mutation indices includes: The target flow rate difference is obtained by analyzing the absolute difference between the peak inspiratory flow rate of the first monitoring waveform and the peak inspiratory flow rate of the second monitoring waveform. The first and second monitoring waveforms are any two adjacent monitoring waveforms among multiple monitoring waveforms. The target duration difference is obtained by analyzing the absolute difference between the inhalation duration of the first monitoring waveform and the inhalation duration of the second monitoring waveform. The ratio of the target flow rate difference to the standard flow rate value is calculated to obtain the first mutation factor, and the ratio of the target duration difference to the standard duration value is calculated to obtain the second mutation factor, wherein the standard flow rate value is the average of the peak inspiratory flow rates of the plurality of monitoring waveforms, and the standard duration value is the average of the inspiratory duration of the plurality of monitoring waveforms; The sum of the first mutation factor and the second mutation factor is determined as the airflow mutation index that corresponds to both the first monitoring waveform and the second monitoring waveform.

[0073] For example, the aforementioned respiratory disorder coefficient It can be represented as: in, The average of the ventilation efficiency indices of multiple monitoring waveforms (before being included in the above formula calculation, the maximum ventilation efficiency index monitored in historical pneumonia patients should be used as a reference, and the ventilation efficiency indices of each monitoring waveform should be numerically normalized) is indicated. Indicates the mean of multiple abrupt changes in airflow indices. This is a very small constant (e.g., 0.00001) used to prevent the denominator from being zero.

[0074] In this embodiment, the respiratory status and inspiratory efficiency of the target pneumonia patient before the next control period are combined to accurately predict the degree of respiratory disturbance that the target pneumonia patient may exhibit in the next control period.

[0075] It should be noted that the system provided in the above embodiments is only an example of the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above.

[0076] In one embodiment, the present invention also provides a targeted nebulized adjunctive drug delivery method for critically ill pneumonia patients in conjunction with respiratory parameters, such as... Figure 2 As shown, the method includes: Step S1: Based on the key features of historical data, cluster multiple historical data to obtain multiple data clusters.

[0077] The historical data refers to the respiratory data of patients with a history of pneumonia, and the key features include the respiratory cycle, peak respiratory parameters, inspiratory phase slope, and expiratory phase slope of the corresponding patients with a history of pneumonia. Step S2: Determine the dosing efficiency factor corresponding to each data cluster based on the key features of the historical data included in each data cluster.

[0078] Step S3: Among the multiple consecutive monitoring waveforms included in the monitoring period, analyze the waveform similarity between each monitoring waveform and multiple data clusters to determine the nearest neighbor cluster of each monitoring waveform.

[0079] Among them, the multiple consecutive monitoring waveforms are multiple consecutive respiratory waveforms of the target pneumonia patient monitored before the next control time, the number of the multiple consecutive monitoring waveforms is a set number, and the nearest neighbor cluster is the data cluster with the highest waveform similarity to the corresponding monitoring waveform among multiple data clusters; Step S4: Based on the dosing efficiency factor corresponding to the nearest neighbor cluster of each monitoring waveform, determine the nebulized dosing dose for the target control period.

[0080] Wherein, the next control time is the start time of the target control period, the nebulization treatment process of the target pneumonia patient corresponds to multiple consecutive control periods, the multiple control periods have the same duration, and the multiple control periods include the target control period.

[0081] Furthermore, the targeted nebulization-assisted drug delivery method for critically ill pneumonia patients combined with respiratory parameters provided in the above embodiments and the targeted nebulization-assisted drug delivery system embodiment for critically ill pneumonia patients combined with respiratory parameters belong to the same concept. The specific implementation process is detailed in the system embodiment and will not be repeated here.

[0082] This invention also provides an electronic device. Please refer to [link to relevant documentation]. Figure 3 The electronic device may include a processor 301, a memory 302, and a program 3021 stored in the memory 302 and capable of running on the processor 301.

[0083] When program 3021 is executed by processor 301, it can achieve the following: Figure 2 Any steps in the corresponding method embodiments and the achievement of the same beneficial effects will not be repeated here.

[0084] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by hardware related to program instructions, and the program can be stored in a readable medium.

[0085] This invention also provides a readable storage medium storing a computer program, which, when executed by a processor, can perform the above-described functions. Figure 2 Any step in the corresponding method embodiment can achieve the same technical effect, and will not be repeated here to avoid repetition.

[0086] The computer-readable storage medium of this invention can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0087] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0088] The program code contained on the storage medium can be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0089] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or terminal. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0090] This invention also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to achieve the targeted nebulization-assisted drug delivery method for critically ill pneumonia patients combined with respiratory parameters provided in the above embodiments.

[0091] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0092] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A targeted nebulized adjunctive drug delivery system for critically ill pneumonia patients, incorporating respiratory parameters, characterized in that, The system includes: The historical clustering module is used to cluster multiple historical data based on key features of historical data to obtain multiple data clusters. The historical data is respiratory data of historical pneumonia patients. The key features include the respiratory cycle, peak respiratory parameters, inspiratory phase slope, and expiratory phase slope of the corresponding historical pneumonia patients. The mapping construction module is used to determine the dosing efficiency factor corresponding to each data cluster based on the key features of the historical data included in each data cluster; The waveform analysis module is used to analyze the waveform similarity between each monitoring waveform and multiple data clusters among multiple consecutive monitoring waveforms included in the monitoring period, so as to determine the nearest neighbor cluster of each monitoring waveform. The multiple consecutive monitoring waveforms are multiple consecutive respiratory waveforms of the target pneumonia patient monitored before the next control time. The number of multiple consecutive monitoring waveforms is a set number. The nearest neighbor cluster is the data cluster with the highest waveform similarity to the corresponding monitoring waveform among the multiple data clusters. The dose control module is used to determine the nebulized drug delivery dose for the target control period based on the drug delivery efficiency factor corresponding to the nearest neighbor cluster of each monitored waveform. The next control time is the start time of the target control period. The nebulization treatment process of the target pneumonia patient corresponds to multiple consecutive control periods. The multiple control periods have the same duration and include the target control period.

2. The targeted nebulized adjuvant drug delivery system for critically ill pneumonia patients based on respiratory parameters according to claim 1, characterized in that, The steps for clustering multiple historical data based on key features to obtain multiple data clusters include: In multiple historical data sets, the consistency of multiple consecutive respiratory waveforms included in each historical data set is analyzed to obtain the waveform steady-state coefficient of each historical data set. Among multiple historical data sets, those with waveform steady-state coefficients greater than the steady-state coefficient threshold are identified as key historical data. Based on the key features of key historical data, multiple key historical data are clustered to obtain multiple data clusters.

3. The targeted nebulized adjuvant drug delivery system for critically ill pneumonia patients based on respiratory parameters according to claim 2, characterized in that, The steps for analyzing the consistency of multiple consecutive respiratory waveforms within each historical data set to obtain the waveform steady-state coefficient for each historical data set include: The multiple consecutive respiratory waveforms included in each historical data point are subjected to time-series normalization to obtain multiple standard waveforms corresponding to each historical data point. In each historical data point, among the multiple standard waveforms, the cross-correlation coefficient between the first standard waveform and other standard waveforms is calculated to obtain the cross-correlation coefficient between the multiple waveforms corresponding to each historical data point. The steady-state coefficient of each historical data point is determined based on the mean and standard deviation of the cross-correlation coefficients of multiple waveforms corresponding to each historical data point.

4. The targeted nebulized adjuvant drug delivery system for critically ill pneumonia patients based on respiratory parameters according to claim 3, characterized in that, The steps for determining the steady-state coefficient of each historical data point based on the mean and standard deviation of the cross-correlation coefficients of multiple waveforms corresponding to each historical data point include: The mean of the cross-correlation coefficients of multiple waveforms corresponding to each historical data point is determined as its steady-state numerator, and the sum of the standard deviation of the cross-correlation coefficients of multiple waveforms corresponding to each historical data point and the value of 1 is determined as its steady-state denominator. Calculate the ratio of the steady-state numerator to the steady-state denominator for each historical data point to obtain the waveform steady-state coefficient for each historical data point.

5. The targeted nebulized adjuvant drug delivery system for critically ill pneumonia patients based on respiratory parameters according to claim 1, characterized in that, The drug administration efficiency factor is positively correlated with the respiratory cycle of the corresponding historical data, the drug administration efficiency factor is positively correlated with the peak value of the respiratory parameters of the corresponding historical data, the drug administration efficiency factor is negatively correlated with the inspiratory phase slope of the corresponding historical data, and the drug administration efficiency factor is negatively correlated with the expiratory phase slope of the corresponding historical data.

6. The targeted nebulized adjuvant drug delivery system for critically ill pneumonia patients based on respiratory parameters according to claim 1, characterized in that, The steps for determining the nebulized drug delivery dose during the target control period based on the dosing efficiency factor corresponding to the nearest neighbor cluster of each monitored waveform include: Based on the dosing efficiency factor corresponding to the nearest neighbor cluster of each monitoring waveform and the degree of waveform similarity thereto, the correction efficiency factor of each monitoring waveform is determined. The correction efficiency factors of multiple monitoring waveforms are weighted and calculated to obtain the target efficiency factor for the target control period. The nebulized drug delivery dose for the target control period is determined based on the target efficiency factor and the preset drug delivery adjustment dose for the target control period.

7. The targeted nebulized adjuvant drug delivery system for critically ill pneumonia patients based on respiratory parameters according to claim 6, characterized in that, The calculation weight of the correction efficiency factor is negatively correlated with the time-domain distance of the corresponding monitoring waveform, and the time-domain distance is used to indicate the time interval between the end time of the corresponding monitoring waveform and the next control time.

8. The targeted nebulized adjuvant drug delivery system for critically ill pneumonia patients based on respiratory parameters according to claim 1, characterized in that, The system also includes a risk control module, which is used for: When the number of nearest neighbor clusters of multiple monitoring waveforms is greater than or equal to the number threshold, the degree of respiratory disturbance in the target pneumonia patient is analyzed based on the degree of waveform change of the multiple monitoring waveforms to obtain the respiratory disturbance coefficient. The nebulized drug dosage for the target regulation period is determined based on the respiratory disturbance coefficient.

9. A targeted nebulized adjunctive drug delivery system for critically ill pneumonia patients based on respiratory parameters, as described in claim 8, is characterized in that... The steps for analyzing the degree of respiratory disturbance in the target pneumonia patient based on the waveform changes of the multiple monitored waveforms, and obtaining the respiratory disturbance coefficient, include: In the multiple monitoring waveforms, the ratio of tidal volume to inspiratory duration for each monitoring waveform is calculated to obtain the ventilation efficiency index for each monitoring waveform. Among the multiple monitoring waveforms, the variation amplitudes of the peak inhalation velocity and the inhalation duration of adjacent monitoring waveforms are analyzed to obtain multiple airflow mutation indices. The respiratory disturbance coefficient is determined by the average of the ventilation efficiency index of multiple monitoring waveforms and the average of multiple airflow mutation indices.

10. A targeted nebulized adjunctive drug delivery system for critically ill pneumonia patients based on respiratory parameters, as described in claim 9, is characterized in that... The steps of analyzing the variation amplitudes of the peak inspiratory velocity and the inspiratory duration of adjacent monitoring waveforms to obtain multiple airflow mutation indices include: The target flow rate difference is obtained by analyzing the absolute difference between the peak inspiratory flow rate of the first monitoring waveform and the peak inspiratory flow rate of the second monitoring waveform. The first and second monitoring waveforms are any two adjacent monitoring waveforms among multiple monitoring waveforms. The target duration difference is obtained by analyzing the absolute difference between the inhalation duration of the first monitoring waveform and the inhalation duration of the second monitoring waveform. The ratio of the target flow rate difference to the standard flow rate value is calculated to obtain the first mutation factor, and the ratio of the target duration difference to the standard duration value is calculated to obtain the second mutation factor, wherein the standard flow rate value is the average of the peak inspiratory flow rates of the plurality of monitoring waveforms, and the standard duration value is the average of the inspiratory duration of the plurality of monitoring waveforms; The sum of the first mutation factor and the second mutation factor is determined as the airflow mutation index that corresponds to both the first monitoring waveform and the second monitoring waveform.

Images