A method and system for real-time monitoring of respiratory volume in a medical nebulizer

Abstract

This invention belongs to the field of data monitoring and mainly relates to a method and system for real-time monitoring of respiratory volume in a medical nebulizer. The method includes: acquiring a driving reference signal and a mixed monitoring signal during nebulization treatment; establishing a driving reference frequency band using the driving reference signal; and performing frequency band decoupling on the mixed monitoring signal to separate the carrier component and the respiratory component; generating a leakage characterization result based on the propagation attenuation relationship between the carrier component and the driving reference signal; generating invalid segment results based on the periodic structure and waveform disturbance characteristics of the respiratory component; calculating the apparent respiratory volume of the respiratory waveform segments; and sequentially performing leakage correction and invalid segment removal to obtain the effective respiratory volume monitoring result; based on this, performing window statistics, process quantification analysis, and state determination on the effective respiratory volume monitoring result, and outputting a real-time evaluation result. This scheme can reduce the impact of leakage, crying, and wearing disturbances on the monitoring results.

Description

Technical Field

[0001] This invention belongs to the field of data monitoring and mainly relates to a method, system, electronic device and storage medium for real-time monitoring of respiratory volume of a medical nebulizer. Background Technology

[0002] In nebulizer therapy for young children, the subjects are young, their breathing cooperation is unstable, their behavior is frequently disturbed during treatment, and the mask fit is easily changed. In actual treatment, the aerosol continuously output by the nebulizer changes the pressure, humidity, and acoustic environment inside the mask cavity, causing the collected signals to be superimposed with nebulization-driven disturbances, condensation adhesion disturbances, and the child's actual breathing disturbances. At the same time, children are also prone to crying, head shaking, mouth breathing, and intermittent air leakage at the edge of the mask, which causes the apparent respiratory volume monitored by the device to deviate continuously from the effective inhaled respiratory volume that actually enters the lower airway. This makes it difficult for existing devices to stably distinguish between real respiratory changes, spurious changes caused by air leakage, and ineffective treatment segments such as crying in the context of continuous nebulization output, thus making it difficult to obtain the true effective inhaled respiratory volume that can be used for treatment course assessment.

[0003] To address the aforementioned issues, existing technologies primarily focus on improving the mask fit and stability during nebulization therapy for young children. These technologies typically enhance the fit between the nebulization mask and the child's mouth and nose area, such as by using nebulization masks specifically designed for young children, or by applying external force to assist in securing the mask. This reduces monitoring fluctuations caused by head movement, loosening, or edge leakage during treatment, thereby improving the monitoring stability of the nebulization process and ensuring stable data collection for subsequent analysis of nebulization therapy efficacy.

[0004] However, existing technologies suffer from the problem of monitoring accuracy being easily affected by disturbances. First, in the case of nebulization therapy for young children, while external assistance can indeed improve the stability of monitoring data to some extent, it is still difficult to eliminate data fluctuations caused by unpredictable resistance behaviors such as breath-holding, crying, and resistance to wearing the device during treatment. Therefore, although the collected data can be connected to existing monitoring systems, the final monitoring results are still easily affected by fluctuations, thus affecting the evaluation of the nebulization therapy effect. Moreover, this problem is not limited to nebulization therapy for young children, but is prevalent throughout the entire nebulization therapy process. Even if the patient is cooperative, fluctuations may still occur due to improper placement of the mask by medical staff, insufficient fit between the general device and the individual patient, or unexpected situations such as sneezing suppression or short-term breath-holding. Therefore, simply improving the mask fit or wearing stability through external assistance cannot eliminate the influence of fluctuations from the source of the monitoring data itself. Therefore, introducing a software-level correction mechanism in the nebulization therapy monitoring process to improve the stability of monitoring data and enhance the reliability of nebulization therapy effect evaluation has clear practical significance. Summary of the Invention

[0005] To address the problem that the accuracy of existing monitoring technologies is easily affected by disturbances, this invention provides a method, system, electronic device, and storage medium for real-time monitoring of respiratory volume in a medical nebulizer, thereby solving one or more of the problems mentioned in the background art.

[0006] To solve the above problems, the present invention employs the following technology:

[0007] In a first aspect, the present invention provides a method for real-time monitoring of respiratory volume in a medical nebulizer, comprising:

[0008] Data from the nebulization treatment process is collected to obtain a raw monitoring data set, which includes a driving reference signal and a mixed monitoring signal.

[0009] The hybrid monitoring signal is decoupled by frequency band using the driving reference signal as a constraint to obtain atomization-related components, which include carrier components and breathing components; leakage analysis is performed based on the carrier components to obtain leakage characterization results; invalidity is identified based on the breathing components to obtain invalid segment results; and effective reconstruction is performed using the leakage characterization results and invalid segment results as constraints to obtain effective respiratory volume monitoring results.

[0010] Based on the effective respiratory volume monitoring results, a real-time evaluation is obtained.

[0011] As a preferred embodiment, the hybrid monitoring signal is decoupled in the frequency band using the driving reference signal as a constraint to obtain the atomization correlation component, including:

[0012] Drive analysis is performed based on the drive reference signal to obtain the drive reference frequency band;

[0013] Using the driving reference frequency band as a reference, the frequency band of the mixed monitoring signal is extracted to obtain the carrier component and the breathing component;

[0014] The carrier component and the breathing component are recorded as nebulization-related components.

[0015] As a preferred embodiment, leakage analysis is performed based on the carrier component to obtain leakage characterization results, including:

[0016] The attenuation is obtained by comparing and analyzing the carrier component with the driving reference signal;

[0017] Leakage characterization calculations are performed based on the attenuation situation to obtain leakage characterization results.

[0018] As a preferred implementation, leakage characterization calculations based on attenuation include:

[0019] The attenuation is calculated based on the carrier amplitude parameter set within the current time window to obtain the dynamic leakage coefficient corresponding to the current time window;

[0020] A preset leakage detection interval is used to match the dynamic leakage coefficient with the leakage detection interval and determine the leakage status marker corresponding to the current time window.

[0021] The dynamic leakage coefficient and leakage status label are recorded together as the leakage characterization result.

[0022] As a preferred embodiment, invalid segment identification is performed based on the respiratory components to obtain invalid segment results, including:

[0023] Respiratory waveform segments are obtained by periodically dividing the respiratory components.

[0024] Waveform analysis was performed on respiratory waveform segments to obtain disturbance characterization information;

[0025] Invalid segments are obtained by marking respiratory components with invalid information based on perturbation characterization information.

[0026] As a preferred embodiment, effective reconstruction is performed using the leakage characterization results and the invalid fragment results as constraints to obtain effective respiratory volume monitoring results, including:

[0027] Apparent respiratory volume is obtained by performing an apparent analysis based on respiratory waveform segments.

[0028] The apparent respiratory volume was corrected for leakage using the leakage characterization results as a constraint, and the leakage correction results were obtained.

[0029] Invalid fragment results were used as constraints to screen out invalid leakage correction results, thus obtaining valid respiratory volume monitoring results.

[0030] As a preferred embodiment, apparent respiratory volume is obtained by performing an apparent analysis based on respiratory waveform segments, including:

[0031] Set up the test environment to perform basic coefficient calibration and calculate the basic pressure-volume conversion coefficient table;

[0032] Individualized pressure-volume conversion factors are obtained by making individual adjustments based on the basic pressure-volume conversion factor table.

[0033] Extracting inspiratory time windows and changes in respiratory pressure based on respiratory waveform segments;

[0034] The pressure integral value is obtained by integrating the change in respiratory pressure.

[0035] Apparent respiratory rate is calculated based on individualized pressure-volume conversion factor and pressure integral value.

[0036] As a preferred embodiment, monitoring and evaluation are performed based on the effective respiratory volume monitoring results to obtain real-time evaluation results, including:

[0037] Window statistics are performed based on the effective respiratory volume monitoring results to obtain the respiratory volume statistics;

[0038] Based on the respiratory volume statistics, a process quantitative analysis was performed to obtain quantitative evaluation indicators;

[0039] The status is determined based on quantitative evaluation indicators to obtain the evaluation status result;

[0040] By summarizing respiratory volume statistics, quantitative assessment indicators, and assessment status results, real-time assessment results are obtained.

[0041] As a preferred embodiment, after obtaining the real-time evaluation results, the method further includes:

[0042] Parameters are updated based on real-time assessment results to adapt to the long-term nature of nebulization therapy. Personalized analysis of the real-time assessment results yields an adaptive parameter set for optimizing subsequent treatment outcomes. Specific steps include:

[0043] The real-time evaluation results are collected to form an individualized write-back sample set;

[0044] Key monitoring parameters are updated based on individualized write-back sample sets to generate an adaptive monitoring parameter set;

[0045] An adaptive monitoring parameter set is used in subsequent treatments to optimize the treatment outcome.

[0046] Secondly, the present invention provides a real-time monitoring system for respiratory volume of a medical nebulizer, comprising:

[0047] Nebulization acquisition module: used to acquire data during nebulization treatment to obtain a raw monitoring data set, which includes a driving reference signal and a mixed monitoring signal;

[0048] Data decoupling module: used to perform frequency band decoupling on the hybrid monitoring signal with the driving reference signal as a constraint to obtain atomization-related components, the atomization-related components including carrier components and breathing components;

[0049] Disturbance identification module: used to perform leakage analysis on the carrier component to obtain leakage characterization results; and to perform invalid identification based on the breathing component to obtain invalid segment results;

[0050] Effective reconstruction module: used to perform effective reconstruction based on the leakage characterization results and the invalid segment results to obtain effective respiratory volume monitoring results;

[0051] Real-time assessment module: used to monitor and assess the effective respiratory volume monitoring results to obtain real-time assessment results.

[0052] Thirdly, the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, characterized in that: when the processor executes the computer program, it implements the steps of the method in the first aspect.

[0053] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, characterized in that: when the computer program is executed by a processor, it implements the steps of the method in the first aspect.

[0054] The beneficial effects of this invention are:

[0055] 1. Strong anti-interference capability: By performing frequency band decoupling on the mixed monitoring signals and combining leakage analysis and invalid identification to separate and process disturbance factors, the interference of external disturbances on the monitoring results can be reduced;

[0056] 2. High assessment accuracy: By performing leak correction and ineffective screening on apparent respiratory volume, effective respiratory volume monitoring results are obtained, and real-time assessment is performed based on the effective respiratory volume monitoring results, which can make the assessment results closer to the actual inhalation situation;

[0057] 3. Strong personalized adaptability: By performing personalized analysis on real-time assessment results and updating individualized pressure-volume conversion coefficients, invalid segment discrimination thresholds, and leakage discrimination boundaries, the monitoring parameters in subsequent treatment processes can be gradually adapted to the individual characteristics of the current treatment subject. Attached Figure Description

[0058] Figure 1 This is an exemplary method flowchart of a method for real-time monitoring of respiratory volume in a medical nebulizer provided in an embodiment of the present invention;

[0059] Figure 2 This is a comparison chart showing the effect of a real-time monitoring method for respiratory volume of a medical nebulizer provided in this embodiment of the invention compared to traditional methods. Detailed Implementation

[0060] To make the technical means, creative features, and achieved objectives and effects of this invention easier to understand, the invention is further described below with reference to specific embodiments. However, the following embodiments are merely preferred embodiments of this invention and not all of them. Other embodiments obtained by those skilled in the art based on the embodiments described herein without creative effort are all within the protection scope of this invention. Unless otherwise specified, the experimental methods in the following embodiments are conventional methods, and the materials and reagents used in the following embodiments are commercially available unless otherwise specified.

[0061] Example 1: As Figure 1 As shown in the flowchart of the present invention, this embodiment provides a method for real-time monitoring of respiratory volume in a medical nebulizer, specifically including the following steps:

[0062] Step S1: Collect data during the nebulization treatment process to obtain the raw monitoring data set.

[0063] Specifically, the data to be collected includes a drive reference signal and a mixed monitoring signal. The drive reference signal includes at least one of a compressor pump drive pressure pulsation signal and a vibrating plate drive electrical signal. For nebulizers using a compressor pump to output atomized airflow, the drive reference signal can be the periodic pressure pulsation signal generated during the operation of the compressor pump. For nebulizers using a vibrating plate atomization structure, the drive reference signal can be the periodic drive electrical signal output by the vibrating plate drive circuit. The drive reference signal is used to characterize the drive frequency and propagation rhythm characteristics of the nebulizer during treatment, so that the carrier component corresponding to the atomization propagation can be extracted from the patient-side mixed monitoring signal.

[0064] The method for acquiring the driving reference signal is as follows: a reference acquisition unit is set at the driving end of the nebulizer, and the reference acquisition unit is electrically connected or pressure-coupled to the driving port of the compressor pump or the driving port of the vibrating plate; when the nebulizer starts working, the reference acquisition unit continuously acquires the periodic change signal of the driving side according to the sampling frequency, and writes the acquisition results into the driving reference sequence in chronological order; during the sampling process, the acquired driving reference signal is time-marked and registered, and continuous acquisition is maintained throughout the entire treatment phase.

[0065] The sampling frequency of the driving reference signal is determined through prototype calibration. Specifically, the original waveform of the driving end is acquired while the atomizer is in continuous operation. The upper limits of the dominant frequency band and the upper limits of adjacent harmonic components corresponding to each working stage are statistically analyzed. The unified frequency upper limit covering each statistical upper limit is taken as the upper limit of the retained frequency of the driving reference signal. The sampling frequency is then set to 4 to 8 times the upper limit of the retained frequency. In this embodiment, to ensure the accuracy of subsequent frequency band analysis, the sampling frequency of the driving reference signal is set to more than 200 times per second.

[0066] The mixed monitoring signal specifically includes the mask cavity mixed pressure signal and the near-field acoustic vibration signal. The mask cavity mixed pressure signal refers to the pressure change signal collected in the inner cavity of the mask or at the T-junction connecting the mask and the nebulizer. This pressure change signal includes both pressure fluctuations caused by nebulization propagation and pressure fluctuations caused by the child's breathing. The near-field acoustic vibration signal refers to the acoustic or vibration signal collected at the outer edge of the mask or at the fixing strap. This signal is used to characterize the child's breathing sounds, crying sounds, and wearing disturbances during treatment. The mask cavity mixed pressure signal and the near-field acoustic vibration signal are correlated and recorded to form the mixed monitoring signal on the patient side.

[0067] The method for acquiring the mixed monitoring signal is as follows: a patient-side acquisition unit is set on the inner wall of the mask cavity or at the T-junction connecting the mask and the nebulizer to continuously acquire the mixed pressure signal of the mask cavity; an acoustic acquisition unit is set on the outer edge of the mask or at the strap position to continuously acquire the near-field acoustic signal; during the acquisition process, each acquisition unit is first configured with a unified clock, and then time markers are added to the mixed pressure signal of the mask cavity and the near-field acoustic signal respectively. Subsequently, the driving reference sequence, the mixed pressure signal of the mask cavity, and the near-field acoustic signal are aligned according to a unified time axis to generate the original monitoring data set.

[0068] Furthermore, the pressure acquisition position of the mask cavity can be arranged in the lower part of the inner wall of the mask cavity, and the fixed acquisition position can be determined by bench spray test to have a small waveform dispersion and consistent breathing phase under continuous atomization conditions.

[0069] The sampling frequency of the mask cavity mixed pressure signal is determined by the respiratory waveform calibration method. Specifically, the mask cavity pressure waveform is collected under quiet breathing, mild fluctuating breathing and intermittent air leakage conditions. The upper limit of the respiratory dominant frequency and the upper limit of the pressure waveform edge change frequency are statistically analyzed. The unified upper limit of the frequency covering all statistical upper limits is taken as the upper limit of the retained frequency of the mixed pressure signal. The sampling frequency is then set to 4 to 8 times the upper limit of the retained frequency. In this embodiment, in order to take into account the acquisition accuracy of respiratory changes and acoustic vibration changes, the sampling frequency of the mask cavity mixed pressure signal is set to more than 100 times per second.

[0070] The sampling frequency of the near-field acoustic vibration signal is determined by the acoustic vibration characteristic calibration method. Specifically, the near-field acoustic vibration waveform is collected under normal breathing, crying and wearing disturbance conditions. The upper limit of the dominant frequency and the upper limit of the transient change frequency are statistically analyzed. The unified upper limit of the frequency covering all statistical upper limits is taken as the upper limit of the retained frequency of the near-field acoustic vibration signal. Then, the sampling frequency is set to 4 to 8 times the upper limit of the retained frequency. In this embodiment, the sampling frequency of the near-field acoustic vibration signal is set to more than 8000 times per second.

[0071] Step S2: Decouple the original monitoring data set by frequency band to obtain the atomization-related components;

[0072] Specifically, frequency band decoupling is performed on the original monitoring data set, including:

[0073] Read the drive reference signal and mixed monitoring signal from the original monitoring data set, perform synchronous loading of the drive reference signal and mixed monitoring signal according to a unified time axis, and establish a correspondence between the drive reference signal and mixed monitoring signal within the same time window as decoupling input data.

[0074] Driven analysis based on the driving reference signal yields the driving reference frequency band: The Welch method is used to perform spectral analysis on the driving reference signal within the current time window to extract the center frequency of the main spectral peak in the driving reference signal; a curvature-based boundary detection method is used to aggregate the frequency components continuously distributed on both sides of the main spectral peak to determine the dominant propagation frequency interval corresponding to the current nebulizer driving rhythm, and this dominant propagation frequency interval is determined as the driving reference frequency band; this driving reference frequency band is used to characterize the stable driving propagation range of the current nebulizer during this treatment process, and serves as a frequency reference for subsequently extracting nebulization propagation-related changes from the mixed monitoring signal.

[0075] Furthermore, for multiple consecutive time windows, if the change in the center frequency of the main spectrum peak in adjacent time windows falls within a preset drift range, the corresponding frequency intervals are merged into the same driving reference frequency band; if it exceeds the preset drift range, the driving reference frequency band corresponding to the current time window is re-determined according to the new center frequency of the main spectrum peak. The preset drift range is determined by the driving end rig calibration method: under continuous operation of the nebulizer, driving reference signals are continuously acquired at different treatment stages, the center frequency of the main spectrum peak corresponding to each time window is extracted according to the time window, and the relative offset of the center frequency of the main spectrum peak in adjacent time windows is calculated; then the statistical results of the relative offset within the continuous operation stage are summarized, and the relative offset interval covering the frequency drift bandwidth under stable operation is taken as the preset drift range; in this embodiment, the preset drift range is set to 5% on both sides of the center frequency of the main spectrum peak in the current time window.

[0076] Using the driving reference frequency band as a reference, frequency band extraction is performed on the mixed monitoring signal to obtain the carrier component and the respiratory component. After obtaining the driving reference frequency band, the frequency interval signal corresponding to the driving reference frequency band is extracted from the mixed monitoring signal, the frequency components within this frequency interval are retained, and they are output as the carrier component. The carrier component is used to characterize the high-frequency propagation changes after the nebulizer drive propagates to the patient side. Subsequently, the low-frequency change portion below the driving reference frequency band is extracted from the mixed monitoring signal to obtain the periodic fluctuation component corresponding to the inspiratory and expiratory rhythms, and it is output as the respiratory component. The respiratory component is used to characterize the respiratory changes on the patient side during nebulization treatment.

[0077] Furthermore, to avoid overlap between carrier components and respiratory components in the boundary frequency region, which could lead to chaotic extraction results, a transition isolation zone is set between the driving reference frequency band and the low-frequency respiratory variation range during the frequency band extraction process. For variation components falling into the transition isolation zone, the attribution is determined according to the continuity of amplitude and the stability of period. Components with stable periods and synchronous changes with the driving reference frequency band are assigned to the carrier component, and components with fluctuation rhythm consistent with the respiratory cycle are assigned to the respiratory component.

[0078] The carrier component and the respiratory component are used as nebulization-related components. The carrier component and the respiratory component are recorded in the same decoupling result record and a corresponding time window identifier is attached to form the nebulization-related component corresponding to the current time window. Among them, the carrier component is used as the input for subsequent leakage analysis, and the respiratory component is used as the input for subsequent invalid identification and respiratory volume reconstruction.

[0079] Step S3: Perform leak analysis and invalidity identification on the atomization-related components to obtain leak characterization results and invalid segment results;

[0080] Specifically, leakage analysis and invalid identification are performed on the nebulization-related components, including: reading the carrier component and breathing component in the nebulization-related components; during reading, according to the additional time window identifier, the carrier component and breathing component corresponding to the same time window are synchronously loaded, and the driving reference signal within the time window is used as the reference input for leakage analysis.

[0081] Leakage analysis of the carrier component includes the following steps:

[0082] Based on the comparison and analysis of the carrier component and the driving reference signal, the attenuation situation is obtained: within the driving reference frequency band corresponding to the current time window, Hilbert transform is performed on the driving reference signal and the carrier component respectively to extract the reference carrier amplitude corresponding to the driving reference signal and the mask-side carrier amplitude corresponding to the carrier component; then, with the reference carrier amplitude as the reference, the ratio of the mask-side carrier amplitude to the reference carrier amplitude is determined as the propagation-preservation ratio, and the propagation-preservation ratio is obtained by subtracting 1 from the propagation-preservation ratio.

[0083] Furthermore, to avoid the direct impact of different treatment subjects, different mask assembly states, and different treatment start conditions on the attenuation results, in this embodiment, a segment with good waveform periodicity and stable carrier amplitude changes within three consecutive respiratory cycles is selected as a short-time sealing calibration segment at the beginning of treatment; then, the propagation attenuation ratio of the current time window is normalized with the reference propagation attenuation ratio corresponding to the short-time sealing calibration segment to obtain the normalized attenuation.

[0084] Leakage characterization calculations are performed based on attenuation conditions to obtain leakage characterization results: After obtaining the attenuation conditions, leakage characterization calculations are performed on the attenuation conditions to generate the dynamic leakage coefficient of the mask corresponding to the current time window. The calculation formula is as follows:

[0085] ;

[0086] in, This represents the dynamic leakage coefficient of the mask corresponding to the current time window t. For the mask-side carrier within the current time window in the driving reference frequency band The carrier amplitude on the mask side at that location, The driving reference signal within the current time window in the driving reference frequency band The reference carrier amplitude at that location, This is the reference time window corresponding to the short-time sealed calibration segment. The driving reference signal within the reference time window in the driving reference frequency band The reference carrier amplitude at that location, For the reference time window, the mask-side carrier is in the driving reference frequency band The carrier amplitude on the mask side at that location.

[0087] Then, based on the correspondence between the leakage coefficient and the preset leakage discrimination interval, the leakage status mark of the current time window is determined, and the leakage coefficient and the leakage status mark are written into the leakage characterization result. The leakage characterization result includes at least the dynamic leakage coefficient corresponding to the current time window.

[0088] The leakage discrimination interval was determined through a controlled gap bench test. Specifically, standard gaps of 0 mm, 2 mm, 5 mm, and 10 mm were set between the mask and the standard lung model, respectively. The nebulizer driving conditions were kept consistent, and the dynamic leakage coefficient of the mask and the effective delivery reduction were collected under each standard gap condition. The calibration results under each standard gap condition were then sorted according to the dynamic leakage coefficient of the mask from smallest to largest. The leakage discrimination boundary value was determined according to the distribution boundary of the dynamic leakage coefficient of the mask corresponding to adjacent standard gap conditions, thus forming the leakage discrimination interval. The leakage level corresponding to each leakage discrimination interval was pre-marked.

[0089] The steps for invalid identification of respiratory components include:

[0090] The respiratory waveform is segmented based on the respiratory components: Periodic segmentation is performed on the respiratory components within the current time window, and a moving average filter is applied to obtain the baseline sequence. The baseline sequence is then subtracted from the respiratory components to obtain the baseline-removed respiratory waveform. The baseline-removed respiratory waveform is scanned chronologically. When the amplitude of the current sampling point is greater than that of the adjacent sampling points, the current sampling point is identified as a candidate peak point. When the amplitude of the current sampling point is less than that of the adjacent sampling points, the current sampling point is identified as a candidate trough point. When the time interval between two adjacent candidate peak points is less than the preset minimum respiratory interval, only the one with the larger amplitude is retained. When the time interval between two adjacent candidate trough points is less than the preset minimum respiratory interval, only the one with the smaller amplitude is retained.

[0091] The minimum breathing interval is determined by age group calibration: in this embodiment, it is set to half of the lower limit of a single breathing cycle in a young child's quiet breathing state.

[0092] After obtaining the filtered valley points and peak points, pairing is performed in chronological order. The peak point located between two adjacent valley points is selected, and the previous valley point - the middle peak point - the next valley point is determined as a complete respiratory cycle, thus obtaining the respiratory waveform segments corresponding to each respiratory cycle within this time window.

[0093] Waveform analysis based on respiratory waveform segments yields disturbance characterization information:

[0094] Read the respiratory cycle duration corresponding to each waveform segment, calculate the average and standard deviation of each respiratory cycle duration, and determine the ratio of the standard deviation to the average as the respiratory cycle variation coefficient.

[0095] Based on the previous trough, the middle peak, and the next trough in each waveform segment, calculate the inspiratory duration and expiratory duration of each respiratory cycle, and determine the ratio of inspiratory duration to expiratory duration as the IPR ratio of each respiratory cycle. Then, calculate the average IPR of each respiratory cycle within the current time window, and calculate the standard deviation of the IPR of each respiratory cycle relative to the average value. The standard deviation is determined as the IPR fluctuation value.

[0096] Peak-valley symmetry is obtained by comparing the slopes of the rising and falling segments within each respiratory cycle to quantify the degree of symmetry of the respiratory waveform between the inspiratory and expiratory phases.

[0097] Read the peak amplitude of each respiratory cycle within the current time window, calculate the ratio of the difference in peak amplitude between adjacent respiratory cycles to the peak amplitude of the previous respiratory cycle, and obtain the amplitude change rate corresponding to each adjacent respiratory cycle; then calculate the average value of each amplitude change rate, and determine the average value as the amplitude continuity.

[0098] The respiratory cycle variation coefficient, inspiratory-to-expiratory ratio fluctuation, peak-to-valley symmetry, and amplitude continuity are recorded as perturbation characterization information.

[0099] Invalid segments are identified by marking respiratory components based on perturbation characterization information: The perturbation characterization information is compared with preset invalidity criteria. When the coefficient of variation of the respiratory cycle exceeds the corresponding threshold, the fluctuation value of the inspiratory-to-expiratory ratio exceeds the corresponding threshold, the peak-to-valley symmetry is lower than the corresponding threshold, or the amplitude continuity between adjacent respiratory cycles does not meet the set conditions, the respiratory components in the corresponding time window are marked as invalid segments. When the above indicators do not trigger the invalidity criteria, the respiratory components of the corresponding cycle are marked as valid segments. All segment validity labels are sorted out to obtain invalid segment results.

[0100] The invalidity criteria are determined by sample labeling: respiratory waveform samples under quiet breathing conditions and respiratory waveform samples under disturbed conditions are collected, and the coefficient of variation of respiratory cycle, inspiratory-to-expiratory ratio fluctuation, peak-to-valley symmetry and amplitude continuity of each sample are statistically analyzed. The invalidity threshold is determined based on the distribution boundaries of quiet and disturbed samples.

[0101] Step S4: Based on the leakage characterization results and invalid fragment results, perform effective reconstruction to obtain effective respiratory volume monitoring results.

[0102] Specifically, effective reconstruction is performed based on leakage characterization results and invalid fragment results, including:

[0103] Apparent respiratory volume is obtained through apparent analysis based on respiratory waveform segments: For each respiratory waveform segment, the previous trough, the middle peak, and the next trough are read, and the time interval between the previous trough and the middle peak is determined as the inspiratory time window of that respiratory cycle; then, the change in respiratory pressure within the inspiratory time window is extracted, and the change in respiratory pressure is integrated over time to obtain the pressure integral value corresponding to that respiratory cycle; subsequently, an individualized pressure-volume conversion factor is preset and corrected according to the actual situation, and the pressure integral value is converted into the apparent respiratory volume corresponding to that respiratory cycle; the apparent respiratory volume represents the inhalation volume directly converted from the respiratory waveform segment without leakage correction and invalid screening; in this embodiment, the formula for calculating the apparent respiratory volume corresponding to the nth respiratory cycle is expressed as:

[0104] ;

[0105] in, This represents the apparent respiratory volume corresponding to the nth respiratory cycle. For individualized pressure-volume conversion factor, This represents the inspiratory time window corresponding to the nth respiratory cycle. This represents the change in respiratory pressure within the inspiratory time window.

[0106] The individualized pressure-volume conversion factor was determined in two stages: basic calibration and individual correction. In the basic calibration stage, multiple tidal volume levels, multiple respiratory rate levels, multiple mask dead space levels, and multiple tubing resistance levels were set on the standard lung frame. The standard lung was driven to perform an inspiratory-expiratory cycle under each level combination, and the mask cavity pressure sequence was collected simultaneously. The pressure change within each inspiratory time window was then integrated to obtain the standard pressure integral value corresponding to each level combination. Subsequently, the standard tidal volume under the corresponding level combination was divided by the standard pressure integral value to obtain the basic pressure-volume conversion factor corresponding to that level combination. A basic conversion factor table was established according to the tidal volume level, respiratory rate level, mask dead space level, and tubing resistance level.

[0107] During the individualized correction phase, the patient's age group, mask model, and tubing configuration are first read, and the average respiratory rate within the first 10 seconds after treatment begins is calculated. Then, based on the age group, average respiratory rate, mask dead space setting corresponding to the mask model, and tubing resistance setting corresponding to the tubing configuration, the baseline pressure-volume conversion factor is read from the baseline conversion factor table as the initial conversion factor. Six consecutive stable respiratory cycles are extracted from the 15th to 30th second after treatment begins. A stable respiratory cycle is defined as a respiratory cycle with a dynamic leakage coefficient less than 0.15, and invalid segments are marked as valid segments. The pressure integral value within the inspiratory time window is calculated for each of the six stable respiratory cycles, and the initial apparent respiratory volume corresponding to each stable respiratory cycle is calculated. The six initial apparent respiratory volumes are then sorted in ascending order, the first and last values ​​are removed, and the remaining four values ​​are averaged to obtain the initial average apparent respiratory volume. Determine the reference tidal volume range for quiet breathing through sample calibration. Samples of actual tidal volume during quiet breathing were collected under corresponding age groups, mask models, and tubing configurations. After grouping and sorting by age group, the 25th percentile of each group's actual tidal volume samples was determined as the lower bound of the reference tidal volume interval, and the 75th percentile was determined as the upper bound of the reference tidal volume interval. In this embodiment, for children aged 6 months to 2 years, the reference tidal volume interval was set to 45 ml to 95 ml; for children aged 2 to 5 years, the reference tidal volume interval was set to 80 ml to 160 ml. Subsequently, the initial average apparent respiratory volume was compared with the reference tidal volume interval to determine the individual correction factor. When the initial average apparent respiratory volume falls within the reference tidal volume range, Set to 1; when the initial average apparent respiratory volume is less than the lower bound of the reference tidal volume range, The initial correction value is determined, where, when the initial correction value is greater than 1.25, it will be... Take 1.25; when the initial average apparent respiratory volume is greater than the upper limit of the reference tidal volume range, The initial correction value is determined as follows: when the initial correction value is less than 0.80, then... Take 0.80; calculate last. The product of the initial conversion factor and the pressure-volume conversion factor is used as the individualized pressure-volume conversion factor.

[0108] Using the leakage characterization results as a constraint, leakage correction is applied to the apparent respiratory volume to obtain the leakage correction result: The dynamic leakage coefficient in the leakage characterization results corresponding to the current respiratory waveform segment is read. The result of subtracting the dynamic leakage coefficient from 1 is determined as the effective retention ratio corresponding to this respiratory cycle. The apparent respiratory volume is then multiplied by the effective retention ratio to obtain the leakage correction result. The leakage correction result represents the inhalation volume result after correction for mask leakage. In this embodiment, the formula for calculating the leakage correction result corresponding to the nth respiratory cycle is expressed as:

[0109] ;

[0110] in, This is the leakage correction result for the nth respiratory cycle. This represents the apparent respiratory volume corresponding to the nth respiratory cycle. The average dynamic leakage coefficient is the average value of the dynamic leakage coefficients of each sampling point within the inspiratory time window of the nth respiratory cycle. When the nth respiratory cycle corresponds to multiple sampling points, the average dynamic leakage coefficient is the average value of the dynamic leakage coefficients of each sampling point within the inspiratory time window of that respiratory cycle.

[0111] Invalid segment results are used as constraints to filter out invalid leakage correction results, resulting in effective respiratory volume monitoring results: The validity flag in the invalid segment results corresponding to the current respiratory waveform segment is read; when the validity flag indicates a valid segment, the leakage correction result corresponding to that respiratory cycle is retained as effective respiratory volume; when the validity flag indicates an invalid segment, the leakage correction result corresponding to that respiratory cycle is set to zero, and that respiratory cycle is registered as an invalid cycle and not included in the cumulative effective respiratory volume value; subsequently, the effective respiratory volumes corresponding to each effective respiratory cycle within the current time window are summarized to obtain the effective respiratory volume monitoring results. The effective respiratory volume monitoring results record at least: the apparent respiratory volume corresponding to each respiratory cycle, the effective respiratory volume corresponding to each respiratory cycle, and the cumulative effective respiratory volume value corresponding to the current time window.

[0112] Step S5: Based on the effective respiratory volume monitoring results, conduct monitoring and evaluation to obtain real-time evaluation results.

[0113] Monitoring and evaluation based on effective respiratory volume monitoring results include:

[0114] Based on the effective respiratory volume monitoring results, window statistics are performed to obtain the respiratory volume statistics: The apparent respiratory volume, effective respiratory volume, segment validity marker, and leakage status marker corresponding to each respiratory cycle within the current time window are read; the apparent respiratory volume corresponding to each respiratory cycle is accumulated in the order of the respiratory cycles to obtain the cumulative apparent respiratory volume value; the effective respiratory volume corresponding to each respiratory cycle is accumulated to obtain the cumulative effective respiratory volume value; the respiratory volume deviation value is obtained based on the difference between the cumulative apparent respiratory volume value and the cumulative effective respiratory volume value; subsequently, the total number of respiratory cycles and the number of invalid respiratory cycles within the current time window are statistically analyzed to obtain the percentage of invalid segments; simultaneously, the leakage status markers corresponding to each respiratory cycle are summarized in terms of level, and the highest leakage level is determined as the window leakage level for that time window.

[0115] Based on the statistical results of respiratory volume, a process quantitative analysis was performed to obtain quantitative evaluation indicators: the effective nebulization utilization rate corresponding to the current time window was determined according to the ratio of the cumulative effective respiratory volume to the cumulative apparent respiratory volume; then, taking the current moment as the end moment, a continuous 60 seconds was extracted as a rolling evaluation period, and multiple rolling evaluation periods were constructed by sliding sequentially along the time axis from the start of treatment according to the rolling step length; the effective respiratory volume corresponding to each respiratory cycle within each rolling evaluation period was accumulated to obtain the rolling minute effective ventilation corresponding to each rolling evaluation period; subsequently, the cumulative effective respiratory volume corresponding to adjacent rolling evaluation periods was compared in chronological order to determine the rate of change of effective respiratory volume between adjacent rolling evaluation periods, thus obtaining the short-term change index.

[0116] The status is determined based on quantitative evaluation indicators, resulting in the evaluation status results. An evaluation threshold table corresponding to the age group of the current treatment subject is determined through sample calibration. Specifically, samples are collected from treatment subjects in the corresponding age group under quiet cooperation, mild disturbance, and significant disturbance states, including the cumulative effective respiratory volume, percentage of ineffective segments, effective nebulization utilization rate, rolling minute effective ventilation, and window leakage level. Then, each sample is statistically analyzed according to the status category, and the corresponding evaluation threshold is determined based on the distribution boundaries of the samples in each status category. This generates an evaluation threshold table corresponding to the age group of the current treatment subject. The evaluation threshold table includes at least the target range for cumulative effective respiratory volume, the upper limit for the percentage of ineffective segments, the lower limit for effective nebulization utilization rate, the target range for rolling minute effective ventilation, and the window leakage level. The upper limit of oral leakage level is determined. After obtaining the assessment threshold table, the status of the current time window is judged based on the assessment threshold table. Specifically, the cumulative effective respiratory volume, proportion of ineffective segments, effective nebulization utilization rate, rolling minute effective ventilation, and window leakage level corresponding to the current time window are compared with the corresponding thresholds in the assessment threshold table. When all indicators meet the target conditions, the assessment status of the current time window is determined to be stable. When one indicator does not meet the target conditions and no abnormal judgment condition is triggered, the assessment status of the current time window is determined to be in a state to be adjusted. When two or more indicators do not meet the target conditions, or the window leakage level reaches the abnormal level, the assessment status of the current time window is determined to be abnormal, thus obtaining the assessment status result.

[0117] Finally, the cumulative apparent respiratory volume, cumulative effective respiratory volume, respiratory volume deviation, percentage of invalid segments, effective nebulization utilization rate, rolling minute effective ventilation, short-term change index, window leakage level, and assessment status results corresponding to the current time window are recorded in sequence as assessment result records; then the assessment result records are associated with the current time window identifier, treatment subject identifier, and mask configuration identifier to generate real-time assessment results.

[0118] Example 2: Given that nebulizer therapy is typically a long-term treatment, to better adapt to individual differences, this example provides an exemplary method for performing personalized analysis based on the real-time assessment results given in Example 1, generating an adaptive monitoring parameter set, and using this parameter set to optimize subsequent treatment effects:

[0119] Specifically, after completing the nebulization treatment monitoring in Example 1, the real-time assessment results, leakage characterization results, invalid segment results, and effective respiratory volume monitoring results corresponding to the treatment process are read; then, using the treatment subject identifier, mask model identifier, and tubing configuration identifier as association keys, the historical monitoring records of the same treatment subject are collected to form an individualized write-back sample set. The individualized write-back sample set includes at least a stable respiratory segment set, a leakage segment set, and an invalid segment set.

[0120] The stable respiratory segment set is generated as follows: segments that meet the following conditions are selected from the respiratory waveform segments corresponding to this treatment as stable respiratory segments: the corresponding assessment result is stable, the corresponding dynamic leakage coefficient is less than 0.15, the corresponding invalid segments are marked as valid segments, and the deviation between the corresponding effective respiratory volume and the apparent respiratory volume does not exceed 10% of the apparent respiratory volume; then, each respiratory waveform segment that meets the conditions is written into the stable respiratory segment set. The leaky segment set is generated as follows: respiratory waveform segments whose dynamic leakage coefficient reaches one of the two levels above the leakage discrimination interval and whose invalid segments are marked as valid segments are selected and written into the leaky segment set. The invalid segment set is generated as follows: respiratory waveform segments whose invalid segments are marked as invalid segments are selected, and their corresponding respiratory cycle variation coefficient, inspiratory-to-expiratory ratio fluctuation value, peak-to-valley symmetry, and amplitude continuity are written into the invalid segment set.

[0121] Based on the individualized write-back sample set, key monitoring parameters are updated to generate an adaptive monitoring parameter set. The adaptive monitoring parameter set includes at least the updated individualized pressure-volume conversion factor, the updated invalid segment discrimination threshold, and the updated leakage discrimination boundary.

[0122] The update of the individualized pressure-volume conversion factor involves reading the pressure integral value and effective respiratory volume corresponding to each stable respiratory segment in the stable respiratory segment set; then selecting stable respiratory segment samples from the three most recent consecutive treatments in chronological order, and calculating the ratio of effective respiratory volume to pressure integral value in each treatment; subsequently, assigning increasing weights to the comparison values ​​in chronological order, with the weight of the most recent treatment being 0.50, the previous treatment being 0.30, and the treatment before that being 0.20; and finally, weighted summation of the ratios to obtain the updated individualized pressure-volume conversion factor; if the number of stable respiratory segments in the three most recent consecutive treatments is less than 12, the individualized pressure-volume conversion factor update is not performed, and the currently used individualized pressure-volume conversion factor remains unchanged.

[0123] To update the invalid segment discrimination threshold, the respiratory cycle variation coefficient, I-E-E ratio fluctuation value, peak-valley symmetry, and amplitude continuity corresponding to each invalid segment in the invalid segment set are read. The 60th and 85th percentile values ​​of each indicator in the invalid segment set are calculated and compared with the 85th and 40th percentile values ​​of the corresponding indicators in the stable respiratory segment set. Subsequently, based on the boundary position between the stable respiratory segment set and the invalid segment set, the thresholds for respiratory cycle variation coefficient, I-E-E ratio fluctuation value, peak-valley symmetry, and amplitude continuity are updated. For the coefficient of variation of the respiratory cycle, the fluctuation value of the inspiratory-to-expiratory ratio, and the continuity of amplitude, the midpoint between the upper bound of the corresponding index in the set of stable respiratory segments and the lower bound of the invalid segment set is taken as the updated discrimination threshold. For peak-valley symmetry, the midpoint between the lower bound of the set of stable respiratory segments and the upper bound of the set of invalid segments is taken as the updated discrimination threshold. If the deviation ratio between the updated threshold and the currently used threshold exceeds 20%, then only 20% of the offset is taken as the threshold adjustment range in this update, so as to avoid excessive disturbance to the subsequent monitoring caliber caused by a single treatment abnormality.

[0124] For updating the leakage discrimination boundary, the dynamic leakage coefficient and leakage level of each segment in the leakage segment set are read; then, the dynamic leakage coefficients under the same leakage level are grouped and statistically analyzed to obtain the sample center value corresponding to each leakage level; then, the median value between the sample center values ​​of adjacent leakage levels is taken as the updated leakage level boundary value, thereby generating the updated leakage discrimination boundary; if the number of samples corresponding to a certain leakage level is less than 6, the discrimination boundary corresponding to that leakage level will not be updated, and the original leakage discrimination boundary will continue to be used.

[0125] After updating the above parameters, the updated individualized pressure-volume conversion factor, the updated invalid segment discrimination threshold, and the updated leakage discrimination boundary, along with the treatment subject identifier, mask model identifier, tubing configuration identifier, generation timestamp, and parameter version number, are recorded in the parameter record table to form an adaptive monitoring parameter set. Before the start of subsequent treatment for the same treatment subject, the parameter record with the highest parameter version number and the same treatment subject identifier in the parameter record table is read and used as the adaptive monitoring parameter set corresponding to the current treatment.

[0126] During subsequent treatment:

[0127] When performing invalid identification, the updated invalid segment discrimination threshold is called to mark the respiratory waveform segment as invalid; after performing leak characterization calculation, the updated leak discrimination boundary is called to determine the leak status label.

[0128] When performing apparent respiratory volume conversion, the updated individualized pressure-volume conversion factor is used to calculate the apparent respiratory volume.

[0129] When determining the status, the parameter version number can be added to the original evaluation threshold table, and the real-time evaluation result can be bound and recorded with the version number of the currently invoked adaptive monitoring parameter set to distinguish the monitoring evaluation results under different parameter versions.

[0130] Furthermore, to prevent abnormal treatment processes from contaminating the adaptive monitoring parameter set, this embodiment also sets parameter update gating conditions: when the proportion of stable state time corresponding to a certain treatment is less than 40%, or the proportion of abnormal state time is greater than 30%, parameter updates are not performed, and only the treatment result is retained as a historical record; when the parameter update gating conditions are met for two consecutive treatments of the same patient, formal writing to the adaptive monitoring parameter set is allowed.

[0131] Example 3: This example provides a real-time monitoring system for respiratory volume of a medical nebulizer, specifically including the following:

[0132] Nebulization acquisition module: used to acquire data during nebulization treatment to obtain a raw monitoring data set, which includes a driving reference signal and a mixed monitoring signal;

[0133] Data decoupling module: used to decouple the mixed monitoring signal in the frequency band with the driving reference signal as a constraint, to obtain the nebulization-related component, which includes the carrier component and the breathing component;

[0134] Disturbance identification module: used to perform leakage analysis on carrier components to obtain leakage characterization results; and to perform invalid segment identification based on respiratory components to obtain invalid segment results;

[0135] Effective Reconstruction Module: Used to perform effective reconstruction based on leakage characterization results and invalid fragment results to obtain effective respiratory volume monitoring results;

[0136] Real-time assessment module: Used to monitor and assess the results of effective respiratory volume monitoring to obtain real-time assessment results.

[0137] like Figure 2 The comparison chart of the effects of the present invention and the traditional method is shown in the figure. The black bars in the figure represent the effect of the present invention, and the gray bars represent the effect of the traditional method. The present invention outputs the true and effective respiratory volume through leakage correction and invalid screening. Compared with the traditional method, it not only improves the anti-disturbance ability, but also effectively improves the accuracy of monitoring data by using more accurate data. The present invention adopts a personalized parameter update method, which has better personalized adaptability, thereby providing better decision support for nebulization therapy.

[0138] Example 4: This example provides an electronic device, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the method proposed in the above examples.

[0139] The electronic device can be a terminal, comprising a processor, memory, communication interface, display screen, and input device connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input device can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the device's casing, or an external keyboard, touchpad, or mouse.

[0140] This embodiment provides a storage medium on which a computer program is stored. When the program is executed by a processor, it implements the method proposed in the above embodiment. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0141] Example 5: Taking the nebulization treatment scenario in the outpatient and emergency pediatric department as an example: The patient was a 2-year-9-month-old child. A single nebulization treatment was performed using a mask-type compressor pump nebulizer, with a total treatment time of 420 seconds. The mask model used was M2, and the tubing configuration was T1. The child was able to cooperate basically at the beginning of the treatment, but briefly turned his head and cried once during the middle of the treatment. He resumed stable breathing in the later part of the treatment.

[0142] Data from this nebulization treatment process was collected to obtain the raw monitoring data set. The collected driving reference signal was the compressor pump driving pressure pulsation signal, and the collected mixed monitoring signals included the mask cavity mixed pressure signal and the near-field acoustic vibration signal. Throughout the treatment process, the driving reference signal, the mask cavity mixed pressure signal, and the near-field acoustic vibration signal were continuously recorded, and the three types of signals were written into the same treatment record according to a unified time identifier to form the raw monitoring data set.

[0143] The original monitoring data set is decoupled by frequency band to obtain the nebulization-related components. First, the driving reference signal and the mixed monitoring signal are read, and the correspondence within the same processing unit is established according to the processing method in Example 1. Then, driving analysis is performed based on the driving reference signal to identify the dominant propagation frequency range in this treatment process. Combined with the treatment record, the center frequency of the main spectrum peak of the driving reference signal is stable in the range of 25 Hz to 27 Hz, and the corresponding driving reference frequency band is extracted accordingly. Subsequently, with the driving reference frequency band as a reference, the carrier component is extracted from the mixed monitoring signal, and the respiratory component is extracted from the low-frequency respiratory change part. Thus, the nebulization-related components corresponding to the current treatment process are formed.

[0144] Leakage analysis and invalid segment identification were performed on nebulization-related components to obtain leakage characterization results and invalid segment results. Firstly, in the leakage analysis section, three consecutive respiratory cycles with good waveform periodicity and stable carrier amplitude changes during the initial treatment phase were used as short-term seal calibration segments, serving as the approximate seal benchmark for this treatment. In the initial treatment phase, the ratio of the mask-side carrier amplitude to the reference carrier amplitude remained generally stable, and the obtained dynamic leakage coefficient was mainly distributed between 0.06 and 0.12. During the middle of treatment, when the child turned their head, the dynamic leakage coefficient increased to 0.23 and 0.27, corresponding to a change in leakage level from low to medium. At the re-adhesion surface... After the mask was applied, the dynamic leakage coefficient dropped to around 0.10. Secondly, in the invalid identification section, the respiratory component was divided into cycles to obtain respiratory waveform segments corresponding to each respiratory cycle. The coefficient of variation, inspiratory-to-expiratory ratio fluctuation, peak-to-valley symmetry, and amplitude continuity of the respiratory cycle were statistically analyzed. Taking this treatment as an example, a total of 172 complete respiratory cycles were identified, of which 151 were valid segments and 21 were invalid segments. The 21 invalid segments were mainly concentrated in one crying phase and two short-term breath-holding phases, with the corresponding respiratory cycle coefficient of variation and inspiratory-to-expiratory ratio fluctuation significantly higher than those in the stable breathing phase. Thus, the leakage characterization results and invalid segment results corresponding to this treatment process were obtained.

[0145] Effective respiratory volume monitoring results were obtained by reconstructing the data based on leakage characterization and invalid segment results. First, an apparent analysis was performed on each respiratory waveform segment to determine the inspiratory time window for each respiratory cycle. Then, combined with an individualized pressure-volume conversion factor, the pressure integral value of each respiratory cycle was converted into apparent respiratory volume. Taking a stable respiratory segment from this treatment as an example, the apparent respiratory volumes for three consecutive respiratory cycles were 92 ml, 96 ml, and 94 ml, respectively; the corresponding dynamic leakage coefficients were 0.08, 0.09, and 0.07, respectively, and all were marked as valid segments. Therefore, the reconstructed data... The effective respiratory volumes after these intervals were 85 ml, 87 ml, and 87 ml, respectively. Taking a respiratory cycle during the crying phase as an example, the apparent respiratory volume corresponding to this cycle was 101 ml, and the dynamic leakage coefficient was 0.18. However, this cycle had been marked as an invalid segment, so after invalid screening, the effective respiratory volume corresponding to this cycle was recorded as 0 ml. After summarizing the entire treatment process, the cumulative apparent respiratory volume was 15.84 liters, the cumulative effective respiratory volume was 12.96 liters, and the respiratory volume deviation was 2.88 liters, thus forming the effective respiratory volume monitoring results for this treatment.

[0146] Based on the effective respiratory volume monitoring results, a real-time assessment was conducted. First, window statistics were performed to obtain statistical results such as the cumulative apparent respiratory volume, cumulative effective respiratory volume, respiratory volume deviation, percentage of ineffective segments, and window leakage level during the treatment process. Then, quantitative analysis was performed to obtain the effective nebulization utilization rate, rolling minute effective ventilation, and short-term change indicators. Taking the overall assessment results of this treatment as an example, the effective nebulization utilization rate was 81.8%, and the percentage of ineffective segments was 12.2%. During the crying and head-turning phases of the child, the effective respiratory volume decreased significantly in the corresponding rolling assessment results, and the window leakage level increased. The quantitative assessment indicators corresponding to this treatment were then compared with the assessment threshold table corresponding to this age group. Finally, the pre- and post-treatment phases were classified as stable, the head-turning phase as requiring adjustment, and the crying phase as abnormal. Finally, the cumulative apparent respiratory volume, cumulative effective respiratory volume, respiratory volume deviation, percentage of ineffective segments, effective nebulization utilization rate, rolling minute effective ventilation, short-term change indicators, window leakage level, and assessment status results were recorded as real-time assessment results.

[0147] After treatment, respiratory waveform segments under stable conditions are extracted from the treatment and written into a stable respiratory segment set; respiratory waveform segments corresponding to the intermediate-level leakage stage are written into a leakage segment set; invalid respiratory waveform segments corresponding to the crying and breath-holding stages are written into an invalid segment set; combined with the patient's previous two historical treatment records, the individualized pressure-volume conversion coefficient, invalid segment discrimination threshold, and leakage discrimination boundary are updated according to the parameter update method in Example 2, and the update results are recorded as a new version of the adaptive monitoring parameter set; the updated adaptive monitoring parameter set is called to further match the monitoring results in subsequent treatments with the individual characteristics of the patient.

[0148] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely preferred examples and are not intended to limit the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

[0149] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0150] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0151] It is understood that the relevant features in the above methods and apparatus can be referenced interchangeably. Furthermore, the terms "first," "second," etc., in the above embodiments are used to distinguish between embodiments and do not represent the superiority or inferiority of any particular embodiment.

[0152] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0153] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, this invention is not directed to any particular programming language. It should be understood that the contents of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the invention.

[0154] In addition, the memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0155] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0156] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0157] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0158] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0159] In a typical configuration, an electronic device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0160] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0161] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by electronic devices. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0162] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0163] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0164] It should be noted that although the operations of the method of this application are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. On the contrary, the steps depicted in the flowchart can be performed in a different order. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0165] It should be understood that when the terms "first," "second," "third," and "fourth," etc., are used in the claims, specification, and drawings of this application, they are used only to distinguish different objects and not to describe a specific order. The terms "comprising" and "including" as used in the specification and claims of this application indicate the presence of the described features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or collections thereof.

[0166] It should also be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application. As used in this specification and claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this specification and claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations.

[0167] Although the embodiments of this application are described above, the content is merely an example adopted for the purpose of facilitating understanding of this application and is not intended to limit the scope and application scenarios of this application. Any person skilled in the art described in this application may make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in this application, but the scope of patent protection of this application shall still be determined by the scope defined in the appended claims.

Claims

1. A method for real-time monitoring of respiratory volume in a medical nebulizer, characterized in that, include: Data from the nebulization treatment process is collected to obtain a raw monitoring data set, which includes a driving reference signal and a mixed monitoring signal. The hybrid monitoring signal is decoupled by frequency band using the driving reference signal as a constraint to obtain the atomization correlation component, which includes a carrier component and a breathing component. Leakage analysis is performed based on the carrier components to obtain leakage characterization results; Invalid segment results are obtained by identifying invalid respiratory components. Effective reconstruction is performed using the leakage characterization results and the invalid segment results as constraints to obtain effective respiratory volume monitoring results; Based on the effective respiratory volume monitoring results, a real-time evaluation is obtained.

2. The method according to claim 1, characterized in that, The hybrid monitoring signal is decoupled in the frequency band using the driving reference signal as a constraint to obtain atomization-related components, including: Drive analysis is performed based on the drive reference signal to obtain the drive reference frequency band; Using the driving reference frequency band as a reference, the frequency band of the mixed monitoring signal is extracted to obtain the carrier component and the breathing component; The carrier component and the breathing component are recorded as nebulization-related components.

3. The method according to claim 1, characterized in that, Leakage analysis is performed based on the carrier component to obtain leakage characterization results, including: The attenuation is obtained by comparing and analyzing the carrier component with the driving reference signal; Leakage characterization calculations are performed based on the attenuation situation to obtain leakage characterization results.

4. The method according to claim 3, characterized in that, Leakage characterization calculations based on attenuation include: The attenuation is calculated based on the carrier amplitude parameter set within the current time window to obtain the dynamic leakage coefficient corresponding to the current time window; A preset leakage detection interval is used to match the dynamic leakage coefficient with the leakage detection interval and determine the leakage status marker corresponding to the current time window. The dynamic leakage coefficient and leakage status label are recorded together as the leakage characterization result.

5. The method according to claim 1, characterized in that, Invalid segment identification is performed based on the respiratory components to obtain invalid segment results, including: Respiratory waveform segments are obtained by periodically dividing the respiratory components. Waveform analysis was performed on respiratory waveform segments to obtain disturbance characterization information; Invalid segments are obtained by marking respiratory components with invalid information based on perturbation characterization information.

6. The method according to claim 1, characterized in that, Effective reconstruction is performed using the leakage characterization results and the invalid fragment results as constraints to obtain effective respiratory volume monitoring results, including: Apparent respiratory volume is obtained by performing an apparent analysis based on respiratory waveform segments. The apparent respiratory volume was corrected for leakage using the leakage characterization results as a constraint, and the leakage correction results were obtained. Invalid fragment results were used as constraints to screen out invalid leakage correction results, thus obtaining valid respiratory volume monitoring results.

7. The method according to claim 6, characterized in that, Apparent respiratory volume is obtained by performing an apparent analysis based on respiratory waveform segments, including: Set up the test environment to perform basic coefficient calibration and calculate the basic pressure-volume conversion coefficient table; Individualized pressure-volume conversion factors are obtained by making individual adjustments based on the basic pressure-volume conversion factor table. Extracting inspiratory time windows and changes in respiratory pressure based on respiratory waveform segments; The pressure integral value is obtained by integrating the change in respiratory pressure. Apparent respiratory rate is calculated based on individualized pressure-volume conversion factor and pressure integral value.

8. The method according to claim 1, characterized in that, Based on the effective respiratory volume monitoring results, a real-time evaluation is obtained, including: Window statistics are performed based on the effective respiratory volume monitoring results to obtain the respiratory volume statistics; Based on the respiratory volume statistics, a process quantitative analysis was performed to obtain quantitative evaluation indicators; The status is determined based on quantitative evaluation indicators to obtain the evaluation status result; By summarizing respiratory volume statistics, quantitative assessment indicators, and assessment status results, real-time assessment results are obtained.

9. The method according to claim 1, characterized in that, After obtaining the real-time evaluation results, the method further includes: Parameters are updated based on real-time assessment results to adapt to the long-term nature of nebulization therapy. Personalized analysis of the real-time assessment results yields an adaptive parameter set for optimizing subsequent treatment outcomes. Specific steps include: The real-time evaluation results are collected to form an individualized write-back sample set; Key monitoring parameters are updated based on individualized write-back sample sets to generate an adaptive monitoring parameter set; An adaptive monitoring parameter set is used in subsequent treatments to optimize the treatment outcome.

10. A real-time monitoring system for respiratory volume of a medical nebulizer, characterized in that, include: Nebulization acquisition module: used to acquire data during nebulization treatment to obtain a raw monitoring data set, which includes a driving reference signal and a mixed monitoring signal; Data decoupling module: used to perform frequency band decoupling on the hybrid monitoring signal with the driving reference signal as a constraint to obtain atomization-related components, the atomization-related components including carrier components and breathing components; Disturbance identification module: used to perform leakage analysis on the carrier component and obtain leakage characterization results; Invalid segment results are obtained by identifying invalid respiratory components. Effective reconstruction module: used to perform effective reconstruction based on the leakage characterization results and the invalid segment results to obtain effective respiratory volume monitoring results; Real-time assessment module: used to monitor and assess the effective respiratory volume monitoring results to obtain real-time assessment results.

Images