Apnea recognition method, apparatus, device, and storage medium

Abstract

The application provides an apnea identification method, device, equipment and storage medium. The method comprises the following steps: acquiring airway flow data and pipeline pressure data; wherein the airway flow data is collected by a flow sensor of a breathing machine, and the pipeline pressure data is collected by a pressure sensor of the breathing machine; determining an apnea event occurrence condition according to the airway flow data; in the case that the apnea event occurrence condition indicates that an apnea event occurs, determining airway flow data and pipeline pressure data of a pause time period corresponding to the apnea event, and determining a corresponding respiratory effort index, a pipeline pressure peak-valley difference and a tidal volume trend index; obtaining a comprehensive classification score according to the respiratory effort index, the pipeline pressure peak-valley difference and the tidal volume trend index; and identifying an apnea type of the apnea event according to the comprehensive classification score. The application can accurately identify and classify different types of apnea events.

Description

Technical Field

[0001] This application relates to the field of respiratory monitoring technology, and in particular to a method, device, equipment and storage medium for identifying sleep apnea. Background Technology

[0002] Sleep apnea is a common sleep-related breathing disorder. Based on different pathophysiological mechanisms, it is mainly divided into three types: obstructive sleep apnea (OSA), caused by physical collapse of the airway; central sleep apnea (CSA), caused by the lack of respiratory drive signals in the brain; and mixed sleep apnea (MSA), which is characterized by the initial appearance of central apnea followed by obstructive apnea.

[0003] Currently, home-use Automatic Positive Airway Pressure (APAP) ventilators are commonly used to treat sleep apnea, employing a uniform strategy for detecting and managing apnea. Specifically, existing APAP devices monitor the patient's respiratory flow. When the respiratory flow drops below 10% of the baseline level and lasts for more than 10 seconds, it is considered an apnea event. Subsequently, the device uniformly executes a pressure boosting response, gradually increasing the continuous positive airway pressure (CPAP) to mechanically open the patient's airway. However, this approach lacks the ability to accurately identify and classify different types of apnea events, making it difficult to implement different treatment strategies for different types of apnea events, resulting in generally mediocre treatment outcomes. Summary of the Invention

[0004] This application aims to propose a method, device, equipment, and storage medium for sleep apnea identification, which can accurately identify and classify different types of sleep apnea events.

[0005] The sleep apnea recognition method according to a first aspect of this application includes: Acquire airway flow data and tubing pressure data; wherein the airway flow data is acquired by the flow sensor of the ventilator, and the tubing pressure data is acquired by the pressure sensor of the ventilator; Based on the airway flow data, determine the occurrence of the apnea event; When the apnea event occurrence status indicates that an apnea event has occurred, determine the airway flow data and the tubing pressure data for the apnea period corresponding to the apnea event, and determine the corresponding respiratory effort index, tubing pressure peak-to-valley difference, and tidal volume trend index. A comprehensive classification score is obtained based on the breathing effort index, the peak-to-valley difference of the pipeline pressure, and the tidal volume trend index; Based on the comprehensive classification score, the type of apnea event is identified; wherein, the type of apnea includes obstructive apnea, central apnea, and mixed apnea.

[0006] The sleep apnea recognition device according to a second aspect of this application includes: The acquisition module is used to acquire airway flow data and tubing pressure data; wherein the airway flow data is acquired by the flow sensor of the ventilator, and the tubing pressure data is acquired by the pressure sensor of the ventilator. The pause detection module is used to determine the occurrence of a sleep apnea event based on the airway flow data. The determination module is used to determine the airway flow data and the tubing pressure data for the pause period corresponding to the apnea event when the apnea event occurrence status indicates that an apnea event has occurred, and to determine the respiratory effort index, the tubing pressure peak-to-valley difference and the tidal volume trend index. The scoring module is used to obtain a comprehensive classification score based on the breathing effort index, the peak-to-valley difference of the tubing pressure, and the tidal volume trend index. The apnea type identification module is used to identify the apnea type of the apnea event based on the comprehensive classification score; wherein the apnea type includes obstructive apnea, central apnea, and mixed apnea.

[0007] An electronic device according to a third aspect of this application includes a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the sleep apnea recognition method as described in any of the first aspects of the present application.

[0008] A computer-readable storage medium according to a fourth aspect of this application stores computer-executable instructions for performing the sleep apnea recognition method as described in the first aspect of the present application.

[0009] In this embodiment, airway flow data from the ventilator's flow sensor and tubing pressure data from the pressure sensor are collected. First, the airway flow data is used to determine if an apnea event has occurred. Once an apnea event is confirmed, the two types of data within the apnea period are extracted. Three characteristic parameters are then calculated: the respiratory effort index, the peak-to-trough difference in tubing pressure, and the tidal volume trend index. These three characteristic parameters are then combined to calculate a comprehensive classification score. Finally, based on the comprehensive classification score, the system identifies three different types of apnea: obstructive apnea, central apnea, and mixed apnea. This achieves accurate classification of different types of apnea events without requiring additional sensor equipment; the existing flow and pressure sensors on the ventilator are sufficient for accurate classification. This provides a basis for subsequent differentiated treatment strategies by the ventilator, solving the problems of inability to distinguish apnea types and poor efficacy of uniform vasopressor therapy in existing technologies. This effectively improves the targeting and efficacy of apnea treatment.

[0010] Other features and advantages of this application will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing this application. Attached Figure Description

[0011] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which: Figure 1 This is a flowchart illustrating an embodiment of the sleep apnea recognition method of this application; Figure 2 This is a schematic diagram of the hardware structure of a ventilator according to an embodiment of the sleep apnea recognition method of this application; Figure 3 This is a schematic diagram of an embodiment of the sleep apnea recognition device of this application; Figure 4 This is a schematic diagram of the hardware structure of an embodiment of the electronic device of this application. Detailed Implementation

[0012] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0013] In the description of this application, the use of terms such as "first," "second," etc., is for the purpose of distinguishing technical features only and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or the order of the technical features indicated.

[0014] In the description of this application, it should be understood that the orientation descriptions, such as up, down, etc., are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0015] In the description of this application, it should be noted that, unless otherwise explicitly defined, terms such as "setup," "installation," and "connection" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this application in conjunction with the specific content of the technical solution.

[0016] The technical solution of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are some embodiments of this application, not all embodiments.

[0017] Figure 1 This is a flowchart illustrating an embodiment of the sleep apnea recognition method of this application; Figure 2 This is a schematic diagram of the hardware structure of a ventilator according to an embodiment of the sleep apnea recognition method of this application; Figure 3 This is a schematic diagram of an embodiment of the sleep apnea recognition device of this application; Figure 4 This is a schematic diagram of the hardware structure of an embodiment of the electronic device of this application.

[0018] See below. Figure 1 The embodiments of this application will be further described below. This application proposes a method for identifying sleep apnea, which includes the following steps: Step 101: Acquire airway flow data and tubing pressure data; wherein, airway flow data is acquired by the ventilator's flow sensor, and tubing pressure data is acquired by the ventilator's pressure sensor; Step 102: Determine the occurrence of the apnea event based on the airway flow data; Step 103: When an apnea event is indicated, determine the airway flow data and tubing pressure data for the apnea period corresponding to the apnea event, and determine the corresponding respiratory effort index, tubing pressure peak-to-trough difference, and tidal volume trend index. Step 104: Obtain a comprehensive classification score based on the breathing effort index, the peak-to-valley difference in tubing pressure, and the tidal volume trend index; Step 105: Identify the type of apnea event based on the comprehensive classification score; the types of apnea include obstructive apnea, central apnea, and mixed apnea.

[0019] In this embodiment, airway flow data from the ventilator's flow sensor and tubing pressure data from the pressure sensor are collected. First, the airway flow data is used to determine if an apnea event has occurred. Once an apnea event is confirmed, the two types of data within the apnea period are extracted. Three characteristic parameters are then calculated: the respiratory effort index, the peak-to-trough difference in tubing pressure, and the tidal volume trend index. These three characteristic parameters are then combined to calculate a comprehensive classification score. Finally, based on the comprehensive classification score, the system identifies three different types of apnea: obstructive apnea, central apnea, and mixed apnea. This achieves accurate classification of different types of apnea events without requiring additional sensor equipment; the existing flow and pressure sensors on the ventilator are sufficient for accurate classification. This provides a basis for subsequent differentiated treatment strategies by the ventilator, solving the problems of inability to distinguish apnea types and poor efficacy of uniform vasopressor therapy in existing technologies. This effectively improves the targeting and efficacy of apnea treatment.

[0020] It should be noted that the hardware structure of this invention is the same as that of existing APAP devices, requiring no additional sensors or hardware modifications. It achieves precise classification of apnea types and differentiated treatment solely through deep frequency domain analysis and multi-dimensional feature fusion of signals from existing flow and pressure sensors. The hardware composition of the ventilator in this application is as follows: Figure 2 As shown, it specifically includes: The MCU is used to run the sleep apnea recognition algorithm and subsequent differentiated treatment strategies; specifically, an STM32F407 with a main frequency of 168MHz can be used. A flow sensor, used to provide high-resolution respiratory flow waveforms, is the core data source for pause type identification; specifically, an SDP810 with a soft I2C interface, such as a PC9 / PA8, and a 100Hz sampling rate can be used. Pressure sensors are used to collect tubing pressure and detect pressure oscillations caused by breathing effort; BLDC fans are used to perform differentiated treatment responses, such as boosting, maintaining, or backup ventilation; specifically, TIM8 PWM and Hall sensors can be used. The SPI Flash is used to store the individual's breathing drive baseline, preset identification parameters during the identification of apnea events, and apnea classification statistics.

[0021] In some implementations, determining the occurrence of an apnea event based on airway flow data includes: If the flow sensor detects that the respiratory flow rate has dropped below a preset percentage of the individual's respiratory drive baseline for a preset pause judgment time, an apnea event is determined to have occurred.

[0022] Specifically, an apnea event can be identified when the flow sensor detects that the respiratory flow has dropped below 10% of the individual's respiratory drive baseline for 10 seconds.

[0023] In some implementations, the corresponding respiratory effort index, peak-to-trough pressure difference in the tubing, and tidal volume trend index are determined, including: Based on airway flow data, obtain the respiratory effort energy in the respiratory effort frequency band and the cardiac oscillation energy in the cardiac oscillation frequency band, calculate the ratio of respiratory effort energy to cardiac oscillation energy, and obtain the respiratory effort index. Based on the pipeline pressure data, obtain the maximum and minimum pipeline pressures, calculate the difference between the maximum and minimum pipeline pressures, and obtain the peak-to-valley difference in pipeline pressure. Based on airway flow data, the first tidal volume of the last respiratory cycle and the second tidal volume of the last three respiratory cycles within the preset judgment period before the occurrence of the apnea event are obtained. The tidal volume difference between the second tidal volume and the first tidal volume is obtained, and the ratio of the tidal volume difference to the second tidal volume is calculated to obtain the tidal volume trend index.

[0024] In this embodiment, the respiratory effort index is used to quantify the relative intensity of the patient's respiratory effort during apnea, the peak-to-trough difference in tubing pressure reflects the amplitude of tubing pressure fluctuations caused by respiratory effort, and the tidal volume trend index characterizes the changing trend of the patient's respiratory drive before apnea occurs. These three feature parameters characterize the physiological features of apnea events from three different dimensions: frequency domain energy, time domain amplitude, and respiratory trend. This provides a multi-dimensional quantitative basis for the subsequent calculation of comprehensive classification scores, avoiding classification errors that are prone to occur with single-feature judgments and improving the accuracy of classification and identification.

[0025] The respiratory effort index obtained above is actually used for correlation analysis of cardiogenic oscillation (CO).

[0026] Understandably, during the pause, although breathing ceases, the heartbeat still generates minute flow / pressure oscillations in the airway through conduction through the chest cavity; these are cardiogenic oscillations, specifically with a frequency of 0.8–2.0 Hz and an amplitude of 0.5–5 mL / s. The frequency range corresponds to a normal adult heart rate of 48–120 bpm (0.8–2.0 Hz), which, according to the AASM Sleep Medicine Scoring Manual, can be considered the generally accepted physiological heart rate range. The amplitude range is derived from statistical measurements of the cardiogenic components of airway flow signals in clinical PSG research literature. The lower limit of the frequency (0.8 Hz) corresponds to a lower heart rate during deep sleep, while the upper limit (2.0 Hz) corresponds to a faster heart rate during wakefulness or REM sleep. The lower limit of the amplitude (0.5 mL / s) corresponds to patients with low cardiac output, while the upper limit (5 mL / s) corresponds to normal cardiac output.

[0027] During obstructive apnea, the chest wall is still making respiratory effort, and "respiratory effort oscillations" can be seen in the flow signal, superimposed on the cardiac oscillations; while during central apnea, the chest wall does not make respiratory effort, and the flow signal only contains cardiac oscillations, which are small in amplitude and high in frequency, without envelope modulation of the respiratory rate.

[0028] Specifically, regarding respiratory effort oscillations, the frequency is 0.1–0.3 Hz, and the amplitude is 5–30 mL / s. The respiratory effort frequency range corresponds to a respiratory rate of 6–18 breaths / minute, which is the normal physiological range for adult respiratory rates, also referencing the AASM standard. The amplitude of 5–30 mL / s reflects the residual flow oscillation amplitude caused by chest wall respiratory effort during obstructive apnea, even though the airway is closed. This amplitude is referenced from statistical analysis of flow signal oscillations in PSG-labeled obstructive apnea events. 5 mL / s is the minimum amplitude at which a clear respiratory effort can be detected; below this value, it is difficult to distinguish from sensor noise. 30 mL / s corresponds to the maximum effort oscillation in patients with high respiratory drive. It is understood that these values ​​are used as frequency band parameters for signal processing and can be fine-tuned according to patient characteristics during actual practice.

[0029] Therefore, the Respiratory Effort Index (REI) is defined and constrained by the following expression: ; in, This refers to the energy of the airway flow signal in the 0.1–0.3 Hz frequency band during the pause, i.e., the respiratory effort energy of the airway flow data in the respiratory effort frequency band. The REI during the pause is the energy of the flow signal in the 0.8~2.0Hz frequency band, which is the energy of cardiac oscillation in the cardiac oscillation frequency band. Generally, the REI of obstructive pause is usually greater than 3.0, that is, the energy of respiratory effort is much greater than the energy of cardiac oscillation, while the REI of central pause is usually less than 0.5, that is, there is almost no energy of respiratory effort.

[0030] The values ​​of 3.0 and 0.5 were determined based on statistical analysis of a clinical PSG annotated dataset. When the energy of the respiratory effort frequency band (0.1~0.3Hz) is more than three times that of the energy of the cardiogenic oscillation frequency band (0.8~2.0Hz), it indicates significant respiratory effort during the pause (a characteristic of obstructive apnea). This value is derived from the statistical distribution of REI values ​​in obstructive apnea events annotated by PSG experts. The median REI for obstructive apnea is approximately 5~8. Taking 3.0 as the lower bound ensures that more than 95% of obstructive apneas are correctly identified, while less than 5% of central apneas are misdiagnosed. When the energy of the respiratory effort frequency band is less than half (0.5) of the energy of the cardiogenic oscillation frequency band, it indicates that there is almost no respiratory effort during the pause (a characteristic of central apnea). Based on the statistical analysis of central apnea events annotated by PSG, the median REI for central apneas is approximately 0.1~0.3. Taking 0.5 as the upper bound covers more than 90% of central apneas. The REI range between 0.5 and 3.0 is an uncertain region, so it is necessary to combine it with other characteristics for comprehensive judgment. The above thresholds can be adjusted according to clinical validation data.

[0031] The above-mentioned difference between peak and valley pressures in the pipeline is actually a pressure fluctuation analysis.

[0032] Fluctuations in tubing pressure during pauses also reflect respiratory effort; therefore, the peak-to-trough difference in tubing pressure during pauses is also relevant. It is subject to the following expression: ; in, For maximum pipeline pressure, This is the minimum tubing pressure. It's important to note that a low-pass filter must be applied beforehand to remove cardiogenic oscillations. Generally, obstructive pauses... Typically, it's about 0.5~3.0 cmH2O, which is the pressure fluctuation caused by chest wall exertion, while central cessation... Typically, a value less than 0.2 cmH2O indicates no chest wall exertion. These thresholds can also be adjusted based on clinical validation data.

[0033] The tidal volume trend index obtained above is actually a respiratory pattern analysis before apnea. The preset judgment time period before the apnea event occurs can be 30 seconds, that is, the respiratory pattern in the 30 seconds before the apnea occurs can provide important identification information.

[0034] Therefore, the tidal volume trend index It is subject to the following expression:

[0035] in, and These are the first tidal volume of the last respiratory cycle and the second tidal volume of the last three respiratory cycles within a preset judgment period before the occurrence of the apnea event, respectively; that is, the tidal volume of the last respiratory cycle and the tidal volume of the last three respiratory cycles before the apnea. Generally, before obstructive apnea, The effect is usually small, generally less than 20%, meaning a sudden interruption of breathing, before central apnea. The tidal volume is usually large, generally greater than 30%, and exhibits a gradual decreasing pattern until it stops. Furthermore, in the case of Cheyne-Stokes respiration (CSR) type central apnea, there is generally... Greater than 50%, and the tidal volume exhibits a typical increasing-decreasing pattern.

[0036] In some implementations, a comprehensive classification score is obtained based on the breathing effort index, the peak-to-valley difference in tubing pressure, and the tidal volume trend index, and is constrained by the following expression: ; Among them, ACS is the Comprehensive Classification Score, and REI is the Respiratory Effort Index. For the peak-valley difference in pipeline pressure, The tidal volume trend index is represented by α, β, and γ, which are weighting coefficients.

[0037] In this embodiment, by normalizing the breathing effort index, the peak-to-valley difference of tubing pressure, and the tidal volume trend index, and by pre-setting weights to integrate features from different dimensions, the influence of different features on the classification results can be combined to intuitively present the type characteristics of sleep apnea events in the form of a comprehensive classification score, simplifying the subsequent type identification process.

[0038] The respiratory effort index and the peak-to-trough difference in tubing pressure are positively correlated with the comprehensive classification score (ACS), meaning that the stronger the patient's respiratory effort and the greater the pressure fluctuation, the higher the ACS value, and the more likely it is to be diagnosed as obstructive apnea. The tidal volume trend index is negatively correlated with ACS, meaning that the more obvious the downward trend in tidal volume before apnea, the lower the ACS value, and the more likely it is to be diagnosed as central apnea. Through the above weighted fusion method, the three characteristic parameters with different dimensions and physical meanings are mapped to a unified scoring scale, which facilitates the unified setting and comparison of subsequent thresholds.

[0039] The aforementioned weighting coefficients α, β, and γ are preset values, and their values ​​satisfy α + β + γ = 1. Specifically, the weighting coefficients can be determined based on statistical optimization of clinical PSG-annotated datasets. For example, hundreds of event samples labeled as pause types by PSG experts can be collected, and the optimal combination can be determined through grid search under the constraint of α + β + γ = 1, with the three-class classification accuracy as the objective function.

[0040] Specifically, the value of α ranges from 0.4 to 0.6, the value of β ranges from 0.2 to 0.4, and the value of γ ranges from 0.1 to 0.3. REI has the highest weight because frequency domain breathing effort analysis is the most reliable identification method.

[0041] In some cases, α=0.50, β=0.30, and γ=0.20.

[0042] α=0.50, meaning the respiratory effort index (REI) accounts for 50%, reflecting the dominant role of frequency domain respiratory effort analysis in identification. This is because REI directly quantifies the presence / absence of respiratory effort and is the most reliable identification indicator; β=0.30, meaning the peak-to-valley difference in tubing pressure. It accounts for 30%, serving as a temporal complementary verification of respiratory effort, and confirms the existence of respiratory effort from different physical dimensions with REI; γ=0.20, i.e., tidal volume trend index. It accounts for 20%, providing auxiliary information on apnea occurrence patterns to differentiate between sudden obstructive apnea and gradual central apnea. Understandably, the weighting coefficient can be adjusted according to different patient populations; for example, γ can be increased in heart failure patients to enhance the capture of CSR-related gradual patterns.

[0043] In some cases, That is, REI is normalized to [0, 1], and the mapping rule can be: ; Right now Normalized to [0, 1], the mapping rule can be ; Right now Normalized to [0, 1], the mapping rule can be It is understandable that the above mapping rules can also be adjusted according to the actual situation.

[0044] In some implementations, the type of apnea event is identified based on a comprehensive classification score, including: If the comprehensive classification score is greater than the first threshold, the apnea event is determined to be obstructive apnea. If the comprehensive classification score is less than the second threshold, the apnea event is determined to be central apnea. If the comprehensive classification score is less than or equal to the first threshold and greater than or equal to the second threshold, the mixed apnea judgment step is performed. The steps for determining mixed apnea include: If the respiratory effort index is greater than the third threshold throughout the pause period, the apnea event is determined to be obstructive apnea. If the respiratory effort index is below the fourth threshold throughout the pause period, the apnea event is determined to be central apnea. If the respiratory effort index is less than the fourth threshold in the first half of the pause period and greater than the third threshold in the second half of the pause period, the apnea event is determined to be a mixed apnea event. Among them, the first threshold is greater than the second threshold, and the third threshold is greater than the fourth threshold.

[0045] In this embodiment, the first threshold is used to distinguish between obstructive and non-obstructive apnea; the second threshold is used to distinguish between central and non-central apnea; the third threshold is used to determine the presence of clear respiratory effort; and the fourth threshold is used to determine the absence of respiratory effort. For mixed apnea, the threshold can be determined based on the temporal distribution characteristics of the respiratory effort index during the apnea period. Therefore, when the comprehensive classification score falls within the fuzzy region between the first and second thresholds, the temporal distribution characteristics of the respiratory effort index during the apnea period are further utilized for refined classification, thereby effectively solving the problem of insufficient classification confidence in the boundary region by a single scoring threshold and improving the recognition accuracy of mixed apnea.

[0046] The first threshold value ranges from 0.6 to 0.8, and can be 0.65; the second threshold value ranges from 0.2 to 0.4, and can be 0.3; the third threshold value ranges from 1.8 to 2.5, and can be 2; the fourth threshold value ranges from 0.4 to 0.6, and can be 0.5.

[0047] In some implementations, the type of apnea event is identified based on a comprehensive classification score, and the specific classification rules are as follows.

[0048] ; The classification intervals (ACS>0.65 / ACS<0.30 / 0.30≤ACS≤0.65) were determined based on statistical analysis and ROC curve optimization of the PSG labeled dataset. The ACS distribution was calculated from hundreds of PSG labeled pause events, and the ACS histograms and cumulative distributions of the three types of events were analyzed. The 5th percentile of the ACS value for obstructive pause events is approximately 0.65, meaning 95% of obstructive pauses have an ACS > 0.65. Using this as a threshold ensures an accuracy rate > 95% for obstructive pauses. The 90th percentile of the ACS value for central pause events is approximately 0.30, meaning 90% of central pauses have an ACS < 0.30. The middle interval [0.30, 0.65] has a width of 0.35, reflecting a conservative strategy: uncertain events are categorized into a mixed category and then reclassified by dynamic REI monitoring to avoid misclassification of obstructive / central pauses. The above thresholds can be optimized based on larger-scale data.

[0049] Subsequently, through the mixed apnea judgment steps, the mixed apnea is further determined, that is, the changes in REI are dynamically monitored during the apnea, and the specific classification rules are as follows.

[0050] ; As explained earlier, under normal circumstances, the REI of obstructive apnea is usually greater than 3.0, meaning that the energy of respiratory effort is much greater than that of cardiogenic oscillation, while the REI of central apnea is usually less than 0.5, meaning that there is almost no energy of respiratory effort. The course of mixed apnea is characterized by the initial appearance of central apnea followed by obstructive apnea.

[0051] Therefore, a REI > 2.0 throughout the pause indicates a reclassification as obstructive, meaning respiratory effort is present throughout, indicating a pure obstructive pause; a REI < 0.5 throughout the pause indicates a reclassification as central, meaning no respiratory effort is present throughout, indicating a pure central pause; a REI < 0.5 in the first half indicates no respiratory drive in the first half of the pause, reflecting the central stage characteristics of the first half of a mixed pause; a REI > 2.0 in the second half indicates significant respiratory effort, confirming the entry into the obstructive stage of the second half. It is understandable that a more lenient standard of 2.0, compared to the strict threshold of 3.0 for obstructive pauses, is used to improve the detection sensitivity of mixed pauses. Furthermore, the above thresholds can be adaptively adjusted according to actual circumstances.

[0052] In some implementations, after identifying the type of apnea event based on a comprehensive classification score, the method further includes: In the case of obstructive apnea, execute the APAP booster response; In the event of central respiratory arrest, maintain current pressure and provide backup ventilation; In the case of mixed apnea, if the respiratory effort index is less than the fourth threshold, maintain the current pressure and provide backup ventilation; if the respiratory effort index is greater than the third threshold, execute the APAP boost response.

[0053] In this implementation, differentiated treatment strategies are applied to different types of apnea: for obstructive apnea, a pressurizing device is used to open the collapsed airway and eliminate the obstruction; for central apnea, the current pressure is maintained to avoid the suppression of respiratory drive by hyperventilation, while backup ventilation is initiated to ensure the patient's ventilation safety; for mixed apnea, the treatment strategy is dynamically adjusted according to the temporal changes in the respiratory effort index—in the first half of the central phase of the apnea (respiratory effort index less than the fourth threshold), pressure is not increased and backup ventilation support is provided, and pressure is increased only when the second half enters the obstructive phase (respiratory effort index greater than the third threshold), thus achieving phased and precise treatment that matches the patient's pathophysiological state and avoiding the technical defects of traditional uniform pressure increase strategies that exacerbate the condition through hyperventilation in the central phase.

[0054] In some implementations, an APAP booster response is performed in the case of an obstructive apnea event.

[0055] In this embodiment, the cause of obstructive apnea is the collapse and closure of the soft tissue of the upper airway under negative pressure. CPAP positive pressure opens the airway through the "pneumatic splint" effect. The higher the pressure, the stronger the support. Increasing the pressure is the only correct physical therapy for obstructive apnea, and it can gradually increase the pressure until the airway reopens and breathing resumes.

[0056] The standard APAP boost response is executed as follows: ; in, For the target pressure value, This is the current pressure value. The default value for each voltage increase is 0.5 cmH2O. The pause has been in effect for a period of time. The boost interval is 5 seconds by default.

[0057] In some implementations, in the event of a central respiratory arrest, the current pressure is maintained and backup ventilation is provided.

[0058] In this embodiment, the cause of central respiratory arrest is a temporary loss of driving signals from the brain's respiratory center (not due to physical airway obstruction). Increasing CPAP pressure cannot restore the lost neural drive; instead, the high pressure further inhibits respiratory drive through two mechanisms: the Hering-Breuer reflex (pulmonary stretch reflex) and a decrease in PaCO2, forming a vicious cycle of "increased pressure, decreased PaCO2, drive inhibition, and more central respiratory arrests." Therefore, by maintaining no pressure increase and providing backup ventilation, the current pressure can be maintained to avoid further inhibition of drive. At the same time, periodic pressure support pulses maintain the minimum tidal volume to ensure blood oxygenation, breaking the vicious cycle of increased pressure. Backup ventilation prevents hypoxemia, and the respiratory center recovers spontaneously, at which point the CPAP is discontinued.

[0059] Backup ventilation strategy, as detailed below: First, the waiting period: After a pause occurs, wait... Observe for seconds to see if breathing drive recovers on its own; Second, backup trigger breathing: if Still not recovered, activate pressure support to trigger breathing: ; in, Current expiratory pressure (maintained without increasing); To provide backup pressure support, the default is 4cmH2O, which only provides sufficient support for driving tidal volume and does not increase the base pressure. The pressure rise waveform for backup breathing simulates the 0.8-second rise ramp of normal inspiration; backup breathing rate. =12 times / minute, that is, triggered once every 5 seconds.

[0060] Third, respiratory drive recovery detection: immediately exit backup ventilation when spontaneous inspiration is detected.

[0061] In some implementations, when the apnea event is a mixed apnea, if the respiratory effort index is less than a fourth threshold, the current pressure is maintained and backup ventilation is performed; if the respiratory effort index is greater than a third threshold, an APAP boost response is executed.

[0062] In this embodiment, the pathological characteristics of mixed respiratory arrest are central-first and then obstructive, meaning that respiratory drive is lost at the beginning of the arrest (central stage), followed by the recovery of drive but airway collapse (obstructive stage). If bolus pressure is increased during the central stage, the Hering-Breuer reflex will prolong the time of drive loss. At the same time, premature bolus pressure increase will lead to pressure overshoot. Therefore, a phased approach is required. The current stage is determined by real-time REI monitoring. During the central stage, a strategy of not bolus pressure and waiting for drive recovery is adopted. During the obstructive stage, a strategy of bolus pressure increase to open the airway is adopted. This can shorten the total duration of the arrest, and timely and accurate bolus pressure increase during the obstructive stage can avoid pressure overshoot caused by premature bolus pressure increase.

[0063] In some implementations, if the apnea event occurrence condition indicates that an apnea event has occurred, the process further includes: Based on airway flow data, the tidal volume of each respiratory cycle in a preset period after the pause is obtained, and envelope analysis is performed to obtain the tidal volume envelope signal. The tidal volume envelope signal is periodically detected to obtain periodic detection results; When the periodic detection results indicate that the tidal volume envelope signal is periodic and there are three consecutive tidal volume fluctuation cycles, and the duration of the tidal volume fluctuation cycle is within the preset range, and the ratio of the maximum peak-to-valley difference to the maximum peak value of the tidal volume envelope signal is greater than the fifth threshold, it is determined that Cheyne-Stokes respiration has occurred.

[0064] In this embodiment, Cheyne-Stokes respiration (CSR) is a specific respiratory disturbance caused by respiratory regulation oscillations and instability due to delayed chemoreceptor feedback caused by decreased cardiac output. It presents as a characteristic periodic respiratory pattern, characterized by a cyclical fluctuation in tidal volume, gradually increasing and then decreasing, with a period of approximately 30-90 seconds, and frequently occurs in patients with heart failure. This embodiment, by extracting the periodic characteristics of the tidal volume envelope, can accurately identify pauses in CSR, avoid unintended hypertension, provide early warning of heart failure risk, and guide timely treatment regimen adjustments.

[0065] Specifically, the extraction of the tidal volume envelope signal is as follows.

[0066] Tidal volume of each breath Perform envelope analysis: ; in, This is the tidal volume envelope signal curve. It is a low-pass filter with a cutoff frequency of 0.05Hz, retaining fluctuations with a retention period of >20 seconds.

[0067] Secondly, the tidal volume envelope signal is periodically detected as follows.

[0068] Perform autocorrelation analysis on the envelope signal: ; If the autocorrelation function is in A significant peak exists within the range of 30 to 90 seconds, i.e. Then a periodic breathing pattern was detected.

[0069] Finally, the specific conditions for CSR confirmation are as follows: ; The gradual increase / decrease ratio is the ratio of the maximum peak-to-valley difference to the maximum peak value of the tidal volume envelope signal, as detailed below: ; in, This represents the maximum tidal volume within the cycle. The minimum tidal volume within the period (or 0 at the pause); a ratio > 0.6 indicates large tidal volume fluctuations, consistent with CSR characteristics, i.e., the autocorrelation function mentioned above. The period corresponding to the tidal volume envelope signal shows a significant peak with a gradual increase / decrease ratio > 0.6. Furthermore, the aforementioned thresholds can be adaptively adjusted according to actual conditions.

[0070] In some implementations, the sleep apnea recognition method further includes: A clinical alarm is triggered when Cheyne-Stokes respiration is confirmed.

[0071] In this implementation, the pause in CSR is central, but the optimal treatment is not CPAP but ASV (Adaptive Servo-Ventilation). Therefore, timely triggering of clinical alarms can remind medical staff to adjust the ventilator treatment strategy to suit the patient's pathological state, improving treatment safety and effectiveness. In some cases, when Cheyne-Stokes respiration is confirmed, a temporary treatment strategy of maintaining the current pressure and providing backup ventilation can be adopted before switching to ASV.

[0072] In some implementations, some patients with obstructive sleep apnea may also experience treatment-emergent central apnea (CompSA) during treatment, further increasing the complexity of the condition and the difficulty of treatment.

[0073] CompSA is a side effect of CPAP treatment. When pressure rises above the patient's tolerance level, hyperventilation causes PaCO2 to drop below the apnea threshold, triggering central apnea. Simultaneously, the pulmonary stretch reflex inhibits inspiratory drive. Approximately 5–15% of CPAP patients experience CompSA at the beginning of treatment. This application also includes CompSA detection and management strategies.

[0074] Specifically, the testing conditions are as follows: ; Among them, the CSA ratio is the proportion of central timeouts to the total number of timeouts; The initial pressure at the start of treatment; the above conditions If a large number of central cessations occur when pressure has already increased significantly, then CompSA may be suspected.

[0075] In the event of suspected CompSA, the response strategy employs a pressure rollback approach, as detailed below: ; Perform a 1 cmH2O reduction at regular intervals, such as a 1 cmH2O reduction every 5 minutes, until the CSA ratio drops below 20%, while coordinating with backup ventilation to ensure respiratory safety.

[0076] In this embodiment, the pressure backoff principle involves reducing pressure to allow PaCO2 to rise above the apnea threshold, thus resuming chemically driven breathing. This embodiment can identify iatrogenic central nervous system apnea caused by excessive pressure, automatically reduce pressure to break the vicious cycle, and coordinate with backup ventilation to ensure respiratory safety during backoff.

[0077] The sleep apnea recognition method provided in this application can be executed by a sleep apnea recognition device 200. This application uses the sleep apnea recognition device 200 executing the sleep apnea recognition method as an example to illustrate the sleep apnea recognition device 200 provided in this application.

[0078] Please see Figure 3 This is a schematic diagram of the structure of a sleep apnea recognition device 200 provided in an embodiment of this application. Figure 3 As shown, the sleep apnea recognition device 200 includes: The acquisition module 201 is used to acquire airway flow data and tubing pressure data; wherein, the airway flow data is acquired by the ventilator's flow sensor, and the tubing pressure data is acquired by the ventilator's pressure sensor; The pause detection module 202 is used to determine the occurrence of a breathing apnea event based on airway flow data; The determination module 203 is used to determine the airway flow data and tubing pressure data for the pause period corresponding to the apnea event when the apnea event occurrence status indicates that an apnea event has occurred, and to determine the respiratory effort index, the peak-to-valley difference of tubing pressure and the tidal volume trend index. The scoring module 204 is used to obtain a comprehensive classification score based on the breathing effort index, the peak-to-valley difference of the tubing pressure, and the tidal volume trend index. The apnea type identification module 205 is used to identify the apnea type of the apnea event based on a comprehensive classification score; wherein the apnea types include obstructive apnea, central apnea, and mixed apnea.

[0079] In some implementations, the determining module 203 may be used to: Based on airway flow data, obtain the respiratory effort energy in the respiratory effort frequency band and the cardiac oscillation energy in the cardiac oscillation frequency band, calculate the ratio of respiratory effort energy to cardiac oscillation energy, and obtain the respiratory effort index. Based on the pipeline pressure data, obtain the maximum and minimum pipeline pressures, calculate the difference between the maximum and minimum pipeline pressures, and obtain the peak-to-valley difference in pipeline pressure. Based on airway flow data, the first tidal volume of the last respiratory cycle and the second tidal volume of the last three respiratory cycles within the preset judgment period before the occurrence of the apnea event are obtained. The tidal volume difference between the second tidal volume and the first tidal volume is obtained, and the ratio of the tidal volume difference to the second tidal volume is calculated to obtain the tidal volume trend index.

[0080] In some implementations, the scoring module 204 can be used to: obtain a comprehensive classification score based on the breathing effort index, the peak-to-valley difference in tubing pressure, and the tidal volume trend index, subject to the following expression: ; Among them, ACS is the Comprehensive Classification Score, and REI is the Respiratory Effort Index. For the peak-valley difference in pipeline pressure, The tidal volume trend index is represented by α, β, and γ, which are weighting coefficients.

[0081] In some implementations, the pause type identification module 205 can be used to: If the comprehensive classification score is greater than the first threshold, the apnea event is determined to be obstructive apnea. If the comprehensive classification score is less than the second threshold, the apnea event is determined to be central apnea. If the comprehensive classification score is less than or equal to the first threshold and greater than or equal to the second threshold, the mixed apnea judgment step is performed. The steps for determining mixed apnea include: If the respiratory effort index is greater than the third threshold throughout the pause period, the apnea event is determined to be obstructive apnea. If the respiratory effort index is below the fourth threshold throughout the pause period, the apnea event is determined to be central apnea. If the respiratory effort index is less than the fourth threshold in the first half of the pause period and greater than the third threshold in the second half of the pause period, the apnea event is determined to be a mixed apnea event. Among them, the first threshold is greater than the second threshold, and the third threshold is greater than the fourth threshold.

[0082] In some implementations, the pause type identification module 205 can be used to: In the case of obstructive apnea, execute the APAP booster response; In the event of central respiratory arrest, maintain current pressure and provide backup ventilation; In the case of mixed apnea, if the respiratory effort index is less than the fourth threshold, maintain the current pressure and provide backup ventilation; if the respiratory effort index is greater than the third threshold, execute the APAP boost response.

[0083] In some implementations, the pause type identification module 205 can be used to: Based on airway flow data, the tidal volume of each respiratory cycle in a preset period after the pause is obtained, and envelope analysis is performed to obtain the tidal volume envelope signal. The tidal volume envelope signal is periodically detected to obtain periodic detection results; When the periodic detection results indicate that the tidal volume envelope signal is periodic and there are three consecutive tidal volume fluctuation cycles, and the duration of the tidal volume fluctuation cycle is within the preset range, and the ratio of the maximum peak-to-valley difference to the maximum peak value of the tidal volume envelope signal is greater than the fifth threshold, it is determined that Cheyne-Stokes respiration has occurred.

[0084] In some implementations, the pause type identification module 205 can be used to: A clinical alarm is triggered when Cheyne-Stokes respiration is confirmed.

[0085] Since the sleep apnea recognition device 200 adopts all the technical solutions of the sleep apnea recognition method of the above embodiments, it has at least all the beneficial effects brought about by the technical solutions of the above embodiments, and will not be described in detail here.

[0086] Figure 4 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application.

[0087] This electronic device may include a processor 301 and a memory 302 storing computer program instructions.

[0088] Specifically, the processor 301 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0089] Memory 302 may include mass storage for data or instructions. For example, and not limitingly, memory 302 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 302 may include removable or non-removable (or fixed) media. Where appropriate, memory 302 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 302 is non-volatile solid-state memory.

[0090] In some embodiments, memory 302 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Thus, generally, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of this disclosure.

[0091] The processor 301 reads and executes computer program instructions stored in the memory 302 to implement any of the sleep apnea recognition methods in the above embodiments.

[0092] In one example, the electronic device may also include a communication interface 303 and a bus 310. For example, Figure 4 As shown, the processor 301, memory 302, and communication interface 303 are connected through bus 310 and complete communication with each other.

[0093] The communication interface 303 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0094] Bus 310 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 310 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0095] The electronic device can execute the apnea recognition method in the embodiments of this application, thereby achieving a combination of Figure 1 and Figure 3 The described method and apparatus for sleep apnea identification.

[0096] In addition, in conjunction with the sleep apnea recognition method in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the sleep apnea recognition methods in the above embodiments.

[0097] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0098] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0099] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0100] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in 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, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0101] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for recognizing sleep apnea, characterized in that, include: Acquire airway flow data and tubing pressure data; wherein the airway flow data is acquired by the flow sensor of the ventilator, and the tubing pressure data is acquired by the pressure sensor of the ventilator; Based on the airway flow data, determine the occurrence of the apnea event; When the apnea event occurrence status indicates that an apnea event has occurred, determine the airway flow data and the tubing pressure data for the apnea period corresponding to the apnea event, and determine the corresponding respiratory effort index, tubing pressure peak-to-valley difference, and tidal volume trend index. A comprehensive classification score is obtained based on the breathing effort index, the peak-to-valley difference of the pipeline pressure, and the tidal volume trend index; Based on the comprehensive classification score, the type of apnea event is identified; wherein, the type of apnea includes obstructive apnea, central apnea, and mixed apnea.

2. The sleep apnea recognition method according to claim 1, characterized in that, The determination of the corresponding respiratory effort index, peak-to-trough difference in tubing pressure, and tidal volume trend index includes: Based on the airway flow data, obtain the respiratory effort energy in the respiratory effort frequency band and the cardiac oscillation energy in the cardiac oscillation frequency band, calculate the ratio of the respiratory effort energy to the cardiac oscillation energy, and obtain the respiratory effort index. Based on the pipeline pressure data, the maximum pipeline pressure and the minimum pipeline pressure are obtained, and the difference between the maximum pipeline pressure and the minimum pipeline pressure is calculated to obtain the pipeline pressure peak-valley difference. Based on the airway flow data, the first tidal volume of the last respiratory cycle and the second tidal volume of the last three respiratory cycles within the preset judgment period before the occurrence of the apnea event are obtained. The tidal volume difference between the second tidal volume and the first tidal volume is obtained. The ratio of the tidal volume difference to the second tidal volume is calculated to obtain the tidal volume trend index.

3. The sleep apnea recognition method according to claim 1 or 2, characterized in that, The comprehensive classification score, derived from the breathing effort index, the peak-to-valley difference in tubing pressure, and the tidal volume trend index, is constrained by the following expression: ； Wherein, ACS is the comprehensive classification score, and REI is the respiratory effort index. The peak-to-valley difference in the pipeline pressure. The tidal volume trend index is defined as α, β, and γ, which are weighting coefficients.

4. The sleep apnea recognition method according to claim 1, characterized in that, The step of identifying the type of apnea event based on the comprehensive classification score includes: If the comprehensive classification score is greater than the first threshold, the apnea event is determined to be obstructive apnea. If the comprehensive classification score is less than the second threshold, the apnea event is determined to be central apnea. If the comprehensive classification score is less than or equal to the first threshold and greater than or equal to the second threshold, the mixed apnea judgment step is performed; The mixed apnea determination step includes: If the respiratory effort index is greater than the third threshold throughout the pause period, the apnea event is determined to be obstructive apnea. If the respiratory effort index is less than the fourth threshold throughout the pause period, the apnea event is determined to be central apnea. If the breathing effort index is less than the fourth threshold during the first half of the pause period and the breathing effort index is greater than the third threshold during the second half of the pause period, the apnea event is determined to be the mixed apnea. Wherein, the first threshold is greater than the second threshold, and the third threshold is greater than the fourth threshold.

5. The sleep apnea recognition method according to claim 4, characterized in that, After identifying the type of apnea based on the comprehensive classification score, the method further includes: In the case that the apnea event is obstructive apnea, an APAP booster response is performed; In the event that the apnea event is central apnea, maintain the current pressure and provide backup ventilation; In the case of the apnea event being the mixed apnea, if the respiratory effort index is less than the fourth threshold, the current pressure is maintained and backup ventilation is performed; if the respiratory effort index is greater than the third threshold, the APAP boost response is executed.

6. The sleep apnea recognition method according to claim 1, characterized in that, Following the indication that an apnea event has occurred in the apnea event occurrence scenario, the method further includes: Based on the airway flow data, the tidal volume of each respiratory cycle in a preset period after the pause period is obtained, and envelope analysis is performed to obtain the tidal volume envelope signal. The tidal volume envelope signal is periodically detected to obtain periodic detection results; When the periodic detection results indicate that the tidal volume envelope signal is periodic and has three consecutive tidal volume fluctuation cycles, and the duration of the tidal volume fluctuation cycle is within a preset range, and the ratio of the maximum peak-to-valley difference to the maximum peak value of the tidal volume envelope signal is greater than the fifth threshold, it is determined that Cheyne-Stokes respiration has occurred.

7. The sleep apnea recognition method according to claim 6, characterized in that, The sleep apnea recognition method further includes: A clinical alarm is triggered if the aforementioned Chen-Shi respiration is confirmed.

8. A sleep apnea recognition device, characterized in that, include: The acquisition module is used to acquire airway flow data and tubing pressure data; wherein the airway flow data is acquired by the flow sensor of the ventilator, and the tubing pressure data is acquired by the pressure sensor of the ventilator. The pause detection module is used to determine the occurrence of a sleep apnea event based on the airway flow data. The determination module is used to determine the airway flow data and the tubing pressure data for the pause period corresponding to the apnea event when the apnea event occurrence status indicates that an apnea event has occurred, and to determine the respiratory effort index, the tubing pressure peak-to-valley difference and the tidal volume trend index. The scoring module is used to obtain a comprehensive classification score based on the breathing effort index, the peak-to-valley difference of the tubing pressure, and the tidal volume trend index. The pause type identification module is used to identify the type of apnea event based on the comprehensive classification score; wherein the apnea type includes obstructive apnea, central apnea, and mixed apnea.

9. An electronic device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the sleep apnea recognition method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions for causing a computer to perform the sleep apnea recognition method as described in any one of claims 1 to 7.

Images