Method for diagnosing obstructive sleep apnea hypopnea syndrome

Abstract

The invention discloses a method for diagnosing obstructive sleep apnea hypopnea syndrome, and relates to the technical field of medical diagnos.The method comprises the steps that an airflow curve and an oxyhemoglobin saturation curve of a patient during sleep are collected, all respiratory events are traversed and retrieved from the airflow curve, and according to the occurrence time of each respiratory event, all the respiratory events are determined; finding out a corresponding search window from the blood oxygen saturation curve, calculating the area of the search window of each apnea event, accumulating the areas of all closed areas to obtain an area sum, dividing the area sum by the total sleep time to obtain an index value of the sleep apnea specific hypoxia load, and determining the sleep apnea specific hypoxia load based on the index value and an index threshold value. Obtaining the symptom level of apnea of the patient; the method has the advantages of simple and convenient indexes, rapidness and high accuracy, and can be well applied to screening and diagnosis of the obstructive sleep apnea hypopnea syndrome.

Description

Technical Field

[0001] The invention relates to the technical field of medical diagnosis, in particular to a method for diagnosing obstructive sleep apnea hypopnea syndrome. Background Art

[0002] Obstructive sleep apnea-hypopnea syndrome (OSA) is a common chronic sleep disorder characterized by frequent upper airway obstruction, decreased respiratory rate, intermittent hypoxia, and repeated awakenings during sleep. Despite improvements in diagnostic techniques, the rate of missed diagnosis remains high. Polysomnography (PSG) is often used as the standard method for diagnosing OSA, but the technique is time-consuming, laborious, and expensive. Early practical diagnostic models used minimum oxygen saturation and other parameters, such as lipid accumulation product levels and triglyceride-glucose index, combined with age, sex, body mass index, neck waist circumference, glucose, insulin, and apolipoprotein B levels to establish an OSA diagnostic model; the STOP-BANG questionnaire (SBQ) can identify undiagnosed OSA and can be applied in clinical practice. However, the sensitivity and specificity of the above diagnostic methods are low. In addition, the results of diagnosing OSA in adults using only questionnaires and other tools are not accurate. Therefore, more effective tools are urgently needed to provide diagnostic methods with higher sensitivity and specificity.

[0003] A patent application with publication number CN108778118A discloses a sleep apnea monitoring system, which monitors the user's sleep state by utilizing the user's biological signals of the tested parts and impedance tomography information of the biological tissue characteristics. The system can be produced as a portable device, so that measurements can be performed at home in a natural sleep state. However, this method requires the generation of impedance tomography information, and the processing process is relatively cumbersome.

[0004] To this end, the present invention provides a method for diagnosing obstructive sleep apnea-hypopnea syndrome. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a method for diagnosing obstructive sleep apnea hypopnea syndrome, which has the advantages of simple indicators, rapidity and high accuracy, and can be well applied to the screening and diagnosis of OSA.

[0006] To achieve the above object, a method for diagnosing obstructive sleep apnea hypopnea syndrome is proposed, comprising the following steps:

[0007] Step 1: Collect the patient's airflow curve and blood oxygen saturation curve during sleep;

[0008] Step 2: Traverse and retrieve all respiratory events from the airflow curve;

[0009] Step 3: Find the corresponding search window from the blood oxygen saturation curve according to the time when each respiratory event occurs;

[0010] Step 4: Calculate the area of ​​the search window corresponding to each apnea event, accumulate the areas of all closed areas, and obtain the area sum;

[0011] Step 5: Divide the area sum by the total sleep time to obtain the index value of sleep apnea-specific hypoxia load;

[0012] Step 6: Pre-set indicator thresholds for each symptom level, and obtain the symptom level of the patient's apnea based on the indicator value and the indicator threshold;

[0013] Among them, the abbreviation of sleep apnea-specific hypoxic burden is SASHB, which is the abbreviation of sleep apnea-specific hypoxic burden;

[0014] The airflow curve refers to a curve obtained by connecting the real-time airflow volume generated by the patient's breathing in a sleeping state in chronological order, wherein the horizontal axis of the airflow curve is time and the vertical axis is airflow volume;

[0015] The blood oxygen saturation curve refers to a curve obtained by connecting the real-time blood oxygen saturation of the patient in a sleeping state in chronological order, wherein the horizontal axis of the blood oxygen saturation curve is time and the vertical axis is blood oxygen saturation;

[0016] The step of traversing and retrieving all respiratory events from the airflow curve comprises the following steps:

[0017] Step 11: For each second in the airflow curve, the maximum value of the airflow magnitude before that second in the airflow curve is taken as the maximum value of the airflow magnitude in that second;

[0018] Step 12: Traverse the airflow curve second by second until the airflow size is lower than the corresponding maximum airflow value, and take the time point when the airflow size is multiplied by the preset ratio threshold as the event start time. Continue traversing after the event start time until the airflow size is higher than the corresponding maximum airflow value again, and take the time point when the airflow size is multiplied by the preset ratio threshold as the event end time.

[0019] If the duration from the event start time to the event end time is greater than the preset duration threshold, the time period from the event start time to the event end time is called a respiratory event; otherwise, execute step 13;

[0020] Step 13: Starting from the event end time of step 12, restart the traversal and repeat step 12 until all respiratory events are found;

[0021] The method of finding the corresponding search window from the blood oxygen saturation curve according to the time when each respiratory event occurs is:

[0022] Starting from the initial time of each respiratory event, the blood oxygen saturation curve is traversed, and the first time node where the blood oxygen saturation decreases is obtained as the search initial time, and the blood oxygen saturation corresponding to the search initial time is used as the baseline level. A horizontal line parallel to the horizontal axis is drawn at the position where the vertical axis is the baseline level as the baseline;

[0023] Continue to traverse the blood oxygen saturation curve from the initial search time until the blood oxygen saturation returns to the baseline level, and use the current time point as the search end time;

[0024] The closed interval formed by the curve segment from the search initial time to the search end time of the blood oxygen saturation curve and the baseline is used as the search window;

[0025] The area and symbol is S, then S can be expressed as: S = ∑ i s i , where i is the number of the respiratory event, s i is the area of ​​the search window corresponding to the i-th respiratory event;

[0026] Since the unit of the area of ​​each search window can be expressed as min×%, where min is the unit of the bottom of the search window (the search window can be approximately regarded as a triangle, and the horizontal axis is the bottom), and % is the unit of the height of the search window (i.e., the unit of SPO2), and the unit of the total sleep time can be expressed as h, therefore, the unit of the sleep apnea-specific hypoxia load SASHB is %min / h;

[0027] The symptom levels include none, mild, moderate, and severe.

[0028] The method further comprises:

[0029] According to the pre-calibrated response time difference between apnea and decreased blood oxygen saturation, the search window is shifted to obtain an updated search window, wherein the starting point and the end point of the updated search window are shifted to the left by the length of the response time difference;

[0030] Aligning the updated search window with the time interval of the apnea event in the airflow curve based on the highest point of the curve;

[0031] The aligned updated search window and the time interval of the apnea event in the airflow curve are compared, and the unaligned parts of the two are removed to obtain a final search window, and the search window is replaced by the final search window to obtain the index value of the sleep apnea-specific hypoxia load again.

[0032] The method further comprises:

[0033] The response time difference between apnea and oxygen desaturation was calculated by comparing the time point when the apnea event started or ended with the time point when the oxygen saturation began to decrease or recover.

[0034] An electronic device is proposed, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0035] The processor executes the above-mentioned method for diagnosing obstructive sleep apnea-hypopnea syndrome by calling the computer program stored in the memory.

[0036] A computer-readable storage medium is provided, on which a rewritable computer program is stored;

[0037] When the computer program is executed on a computer device, the computer device is caused to execute the above-mentioned method for diagnosing obstructive sleep apnea-hypopnea syndrome.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] The present invention obtains SASHB (sleep apnea-specific hypoxia burden) by counting the total area of ​​a search window formed by a blood oxygen saturation curve when all apnea or hypopnea events occur during a patient's sleep, and then dividing the total area by the statistical time; the obtained SASHB has high accuracy, and the SASHB is highly correlated with the apnea-hypopnea index and the oxygen saturation index, which indicates that SASHB has high clinical application value. Compared with the traditional diagnostic method for obstructive sleep apnea-hypopnea syndrome, SASHB is simple, fast and highly accurate, and can be well applied to the screening and diagnosis of obstructive sleep apnea-hypopnea syndrome. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a flow chart of a method for diagnosing obstructive sleep apnea hypopnea syndrome in Example 1 of the present invention;

[0041] Figure 2 Schematic diagram of the principle of calculating the index value of sleep apnea-specific hypoxia burden (SASHB);

[0042] Figure 3 This is the ROC curve diagram comparing SASHB with other indicators for the diagnosis and severity classification of OSA. DETAILED DESCRIPTION

[0043] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Example 1

[0045] like Figure 1 A method for diagnosing obstructive sleep apnea hypopnea syndrome comprises the following steps:

[0046] Step 1: Collect the patient's airflow curve and blood oxygen saturation curve during sleep;

[0047] Step 2: Traverse and retrieve all respiratory events from the airflow curve;

[0048] Step 3: Find the corresponding search window from the blood oxygen saturation curve according to the time when each respiratory event occurs;

[0049] Step 4: Calculate the area of ​​the search window for each apnea event, accumulate the areas of all closed areas, and obtain the area sum;

[0050] Step 5: Divide the area sum by the total sleep time to obtain the index value of sleep apnea-specific hypoxia load;

[0051] Step 6: Pre-set indicator thresholds for each symptom level, and obtain the symptom level of the patient's apnea based on the indicator value and the indicator threshold;

[0052] It should be noted that the sleep apnea-specific hypoxic burden is abbreviated as SASHB, which is the abbreviation of sleep apnea-specific hypoxic burden. For the sake of convenience, all SASHBs mentioned below are abbreviations of sleep apnea-specific hypoxic burden.

[0053] The airflow curve refers to a curve obtained by connecting the real-time airflow volume generated by the patient's breathing in a sleeping state in chronological order, wherein the horizontal axis of the airflow curve is time and the vertical axis is airflow volume; it can be understood that the real-time airflow volume can be collected in real time by a respiratory airflow sensor;

[0054] The blood oxygen saturation curve refers to a curve obtained by connecting the real-time blood oxygen saturation of the patient in a sleeping state in chronological order, wherein the horizontal axis of the blood oxygen saturation curve is time and the vertical axis is blood oxygen saturation; it can be understood that the real-time blood oxygen saturation (SPO2) can be collected in real time by a smart wearable device;

[0055] like Figure 2The schematic diagram of the principle of calculating the index value of sleep apnea-specific hypoxia burden (SASHB) shown in the figure, the curve in part A of the figure is the airflow curve, the horizontal axis is time (unit: second), the vertical axis is the airflow size, the airflow greater than 0 indicates exhalation, and the airflow less than 0 indicates inhalation; the curve in part B is the blood oxygen saturation curve, the horizontal axis is time, and the vertical axis is blood oxygen saturation;

[0056] Furthermore, the step of traversing and retrieving all respiratory events from the airflow curve includes the following steps:

[0057] Step 11: For each second in the airflow curve, the maximum value of the airflow magnitude before that second in the airflow curve is taken as the maximum value of the airflow magnitude in that second;

[0058] Step 12: Traverse the airflow curve second by second until the airflow size is lower than the corresponding maximum airflow value, and take the time point when the airflow size is multiplied by the preset ratio threshold as the event start time. Continue traversing after the event start time until the airflow size is higher than the corresponding maximum airflow value again, and take the time point when the airflow size is multiplied by the preset ratio threshold as the event end time.

[0059] If the duration from the event start time to the event end time is greater than the preset duration threshold, the time period from the event start time to the event end time is called a respiratory event; otherwise, execute step 13;

[0060] It should be noted that an apnea event is defined as a decrease in airflow amplitude ≥90% and a duration ≥10s; a hypopnea event is defined as a decrease in airflow amplitude ≥30% and a duration ≥10s, accompanied by a decrease in SPO2 ≥3% or accompanied by micro-awakening. Therefore, generally, the ratio threshold is set to 90% and the duration threshold is set to 10 seconds.

[0061] Step 13: Starting from the event end time of step 12, restart the traversal and repeat step 12 until all respiratory events are found;

[0062] An example is Figure 2 As shown in the respiratory event in the curve of part A, in this respiratory event, it can be considered that the patient's ventilation drops sharply for a period of time and the duration is more than 10 seconds, thus an apnea event or a hypopnea event occurs;

[0063] Furthermore, the method of finding the corresponding search window from the blood oxygen saturation curve according to the time when each respiratory event occurs is:

[0064] When a respiratory event occurs, the oxygen inhaled before the patient's blood oxygen saturation is suspended is not consumed in time, so there will not be a significant drop immediately. Therefore, there is a time difference between the drop in blood oxygen saturation and the occurrence of a respiratory event.

[0065] Starting from the initial time of each respiratory event, the blood oxygen saturation curve is traversed, and the first time node where the blood oxygen saturation decreases is obtained as the search initial time, and the blood oxygen saturation corresponding to the search initial time is used as the baseline level. A horizontal line parallel to the horizontal axis is drawn at the position where the vertical axis is the baseline level as the baseline;

[0066] Continue to traverse the blood oxygen saturation curve from the initial search time until the blood oxygen saturation returns to the baseline level, and use the current time point as the search end time;

[0067] The closed interval formed by the curve segment from the search initial time to the search end time of the blood oxygen saturation curve and the baseline is used as the search window;

[0068] It can be understood that due to intermittent hypoxia during apnea and hypopnea events, SPO2 decreases, and when the respiratory event ends, the SPO2 trend returns to normal, forming a "similar triangle" with the descending and ascending trend lines and the baseline. Figure 2 As shown in the curve diagram of part B in the figure, the baseline level of the search window in the figure is the blood oxygen saturation at the initial time of the search, and the curve of the descending process and the curve of the subsequent ascending process and the baseline together form a "similar triangle";

[0069] Furthermore, the method of calculating the area of ​​the search window for each apnea event may be an integral calculation or calculation using calculation software such as MATLAB, which will not be described in detail in this application;

[0070] Preferably, the area and symbol are S, then S can be expressed as: S = ∑ i si, where i is the number of the respiratory event and si is the area of ​​the search window for the i-th respiratory event;

[0071] Because the unit of the area of ​​each search window can be expressed as min×%, where min is the unit of the bottom of the search window (the search window can be approximately regarded as a triangle, and the horizontal axis is the bottom), and % is the unit of the height of the search window (i.e., the unit of SPO2), and the unit of total sleep time can be expressed as h, therefore, the unit of the sleep apnea-specific hypoxia load is %min / h; an example is: there are 8 minutes in each hour of sleep, when the SPO2 decreases by 5% compared to the baseline, the SASHB index value that can be calculated is: 5%×8(min / h)=40%min / h.

[0072] Preferably, the symptom levels include none, mild, moderate and severe; through a large amount of experimental data verification, the threshold values ​​of the indexes for each symptom level setting can be set to: 0, 19.64, 40.96 and 69.40, that is, the SASHB index value is asymptomatic when it is 0-19.64, mild when it is 19.64-40.96, moderate when it is 40.96-69.40, and severe when it is above 69.40;

[0073] In an optional embodiment, the method further comprises:

[0074] According to the pre-calibrated response time difference between apnea and decreased blood oxygen saturation, the search window is shifted to obtain an updated search window, wherein the starting point and the end point of the updated search window are shifted to the left by the length of the response time difference;

[0075] Aligning the updated search window with the time interval of the apnea event in the airflow curve based on the highest point of the curve;

[0076] The aligned updated search window and the time interval of the apnea event in the airflow curve are compared, and the unaligned parts of the two are removed to obtain a final search window, and the search window is replaced by the final search window to obtain the index value of the sleep apnea-specific hypoxia load again.

[0077] In this way, in this embodiment, the update search window can be aligned with the time interval of the apnea event in the airflow curve based on the highest point of the curve, thereby avoiding the error caused by the delay between apnea and the decrease of blood oxygen concentration.

[0078] In an optional embodiment, the method further comprises:

[0079] The response time difference between apnea and oxygen desaturation was calculated by comparing the time point when the apnea event started or ended with the time point when the oxygen saturation began to decrease or recover.

[0080] It should be further explained that in order to verify the effectiveness of the sleep apnea-specific hypoxia load proposed in this application, this application also provides the following experimental data for verification:

[0081] 1. Research subjects

[0082] Patients with suspected obstructive sleep apnea who visited the sleep center of the same hospital from January 2019 to July 2021 constituted the experimental cohort, and patients with unrelated obstructive sleep apnea admitted from August 2021 to July 2024 served as the validation cohort;

[0083] A total of 2303 subjects were included, including 1200 in the experimental group (no OSA: 344; mild OSA: 225; moderate OSA: 237; severe OSA: 394) and 1103 in the validation group (no OSA: 309; mild OSA: 223; moderate OSA: 214; severe OSA: 357).

[0084] Table 1 is a table of clinical characteristics of the subjects, including various clinical and physiological characteristics of each patient in the experimental group and the validation group;

[0085] Table 1 Clinical characteristics of the subjects

[0086]

[0087]

[0088] 1. Inclusion criteria:

[0089] 1) Aged 18 or above;

[0090] 2) Obvious snoring;

[0091] 3) Subjects who signed the informed consent.

[0092] 2. Exclusion criteria:

[0093] 1) Previous treatment for obstructive sleep apnea;

[0094] 2) Chronic diseases, such as chronic kidney disease, mental illness, or hyperparathyroidism;

[0095] 3) Mental disorder or malignant tumor;

[0096] 4) Under 18 years old;

[0097] 5) receiving systemic steroid therapy or hormone replacement therapy;

[0098] 6) missing clinical data;

[0099] 7) Patients with sleep disorders other than OSA, such as upper airway resistance syndrome, restless legs syndrome, or narcolepsy, were also excluded.

[0100] 3. Other comparative indicators of comparative experiments:

[0101] Neck circumference NC, waist circumference WC and hip circumference HC, neck-to-height ratio NHR, waist-to-hip ratio WHR, Epworth Sleepiness Scale ESS, minimum blood oxygen saturation LSPO2 and average blood oxygen saturation MSPO2, awakening reaction index ArI and oxygen saturation index ODI.

[0102] 4. Experimental setup:

[0103] All-night sleep data is recorded by two commonly used standardized PSG systems (Alice-5, Alice-6). Relevant sleep parameters are calculated by technicians in this field. Apnea is defined as a complete cessation of airflow for at least 10 seconds; hypopnea is defined as a 30% decrease in airflow for more than 10 seconds, or a decrease of less than 30%, but accompanied by a decrease in SPO2 of at least 3%, or micro-arousal. The apnea-hypopnea index (AHI) refers to the number of apnea and hypopnea events per hour of sleep. None, mild, moderate and severe OSA are defined as AHI<5, 5≤AHI<15, 15≤AHI<30 and AHI≥30.

[0104] 5. Research methods:

[0105] A model for predicting OSA was established for SASHB and other indicators by logistic regression in the experimental group and validated by drawing receiver operating characteristic curves (ROC) in the validation group.

[0106] 6. Statistical analysis methods:

[0107] All statistical analyses were performed using SPSS version 26.0 or MATLAB. Continuous variables with normal distribution were expressed as mean ± standard deviation, and skewed data were expressed as median (interquartile range). Categorical variables were expressed as percentages. Pearson's test was used to test the correlation between variables and SASHB. Receiver operating characteristic (ROC) curves were drawn to explore the accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), positive and negative likelihood ratios of SASHB and other indicators in the diagnosis and severity classification of OSA. P value < 0.05 reflected statistically significant differences.

[0108] 7. Experimental results:

[0109] Pearson correlation analysis obtained in the validation group showed that SASHB was significantly correlated with anthropometric indices such as neck circumference NC (r = 0.374, P < 0.001), neck circumference to height ratio NHR (r = 0.347, P < 0.001), waist circumference WC (r = 0.386, P < 0.001), hip circumference HC (r = 0.284, P < 0.001), AHI (r = 0.823, P < 0.001), and minimum blood oxygen saturation LSPO2 (r = -0. 636, P<0.001), mean blood oxygen saturation MSPO2 (r=-0.548, P<0.001), the proportion of arterial oxygen saturation <90% time to total sleep time (r=0.697, P<0.001); arousal response index (ArI) (r=0.304, P<0.001); oxygen saturation index (ODI) (r=0.805, P<0.001); ESS score (r=0.212, P<0.001). The strongest positive correlation was found between SASHB and AHI (r=0.823, P<0.001).

[0110] like Figure 3 As shown in the figure, the ROC curves of the comparison of SASHB and other indicators for the diagnosis and severity classification of OSA are shown in the figure. The four curves are the ROC curves of the prediction accuracy of SASHB and other comparative indicators in the population without OSA, mild OSA, moderate OSA and severe OSA; Table 2 is based on Figure 3 The more specific ROC curve analysis results of each indicator analyzed;

[0111] Table 2 ROC curve analysis results of single variable in the validation group for predicting OSA

[0112]

[0113]

[0114] from Figure 3As can be seen in Table 2, when the area under the ROC curve of the best cutoff point of each indicator was compared with the area of ​​SASHB, SASHB was the most accurate in both the experimental group and the validation group. In the former group, SASHB distinguished OSA from non-OSA status with a sensitivity / specificity of 89.5 / 87.7% (AUC: 0.948, 95%, CI 0.934-0.962). In the validation group (AUC: 0.931, 95%, CI 0.913-0.949), the sensitivity / specificity reached 85.7 / 90.1%. Next, we explored whether SASHB could predict mild, moderate, and severe OSA. The subjects in the validation group were divided into mild OSA (SASHB1=19.64), moderate OSA (SASHB=40.96), and severe OSA (SASHB=69.40). The diagnostic limits of OSA are mild (AUC: 0.878, 0.847-0.908), moderate (AUC: 0.938, 0.912-0.965) and severe (AUC: 0.959, 0.942-0.976).

[0115] 8. Experimental conclusion

[0116] SASHB had the highest accuracy, followed by sleep indicators related to blood oxygen; anthropometric indicators (NC, NHR, WC, HC, and WHR) performed poorly. SASHB distinguished OSA from non-OSA subjects and predicted the severity of OSA. SASHB was superior to the commonly used physical indicators of neck circumference NC, waist circumference WC, and hip circumference HC, minimum blood oxygen saturation LSPO2, and mean blood oxygen saturation MSPO2. SASHB was highly correlated with the apnea-hypopnea index and oxygen saturation index, indicating that SASHB has a high clinical value. In particular, the participants in the cohort had a lower degree of obesity {body mass index BMI: 25.6 (23.4-27.8)}, a relatively high mean pulse oxygen saturation MSPO2 {96 (94-96)}, and a lower proportion of arterial oxygen saturation <90% of the time to total sleep time {0.56 (0.02-4.50)}. Therefore, SASHB is a more sensitive marker of hypoxemia in non-obese, non-severely desaturated OSA patients than previously used hypoxemia parameters such as ODI and the proportion of total sleep time with arterial oxygen saturation <90% (CT90).

[0117] SASHB is superior to ordinary indicators in the effective diagnosis and classification of OSA in patients. If the algorithm for calculating SASHB is embedded in a portable oximeter (type 3 or 4 sleep device), this work will be friendly to the screening of suspected OSA patients, because this process can save medical expenses and save patients from the inconvenience of testing.

[0118] Example 2

[0119] The present application also provides an electronic device. The electronic device may include one or more processors and one or more memories. The memories store computer-readable codes, and when the computer-readable codes are executed by the one or more processors, the method for diagnosing obstructive sleep apnea-hypopnea syndrome as described above may be executed.

[0120] The method or device according to the embodiment of the present application can also be implemented with the help of the architecture of the electronic device disclosed in the present application. The electronic device may include a bus, one or more CPUs, ROM, RAM, a communication port connected to a network, an input / output component, a hard disk, etc. A storage device in the electronic device, such as a ROM or a hard disk, can store a method for diagnosing obstructive sleep apnea hypopnea syndrome provided in the present application.

[0121] Furthermore, the electronic device may also include a user interface. Of course, the architecture disclosed in this application is only exemplary, and when implementing different devices, one or more components in the electronic device disclosed in this application may be omitted according to actual needs.

[0122] Example 3

[0123] A computer-readable storage medium according to an embodiment of the present application. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by the processor, the method for diagnosing obstructive sleep apnea-hypopnea syndrome according to the embodiment of the present application can be executed. The computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0124] In addition, according to the implementation of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, the non-transitory machine-readable storage medium stores machine-readable instructions, the machine-readable instructions can be run by a processor to execute instructions corresponding to the method steps provided by the present application, and when the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0125] The methods, apparatuses, and devices of the present application may be implemented in many ways. For example, the methods, apparatuses, and devices of the present application may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present application are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present application may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers recording media storing programs for executing the method according to the present application.

[0126] In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0127] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0128] The above preset parameters or preset thresholds are all set by technicians in this field according to actual conditions or obtained through large-scale data simulation.

[0129] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for diagnosing obstructive sleep apnea hypopnea syndrome, characterized in that: The following steps are involved: Step 1: Collect the patient's airflow curve and blood oxygen saturation curve during sleep; Step 2: Traverse and retrieve all respiratory events from the airflow curve; Step 3: Find the corresponding search window from the blood oxygen saturation curve according to the time when each respiratory event occurs; Step 4: Calculate the area of ​​the search window for each apnea event, accumulate the areas of all closed areas, and obtain the area sum; Step 5: Divide the area sum by the total sleep time to obtain the index value of sleep apnea-specific hypoxia load; Step 6: Pre-set indicator thresholds for each symptom level, and obtain the patient's apnea symptom level based on the indicator value and the indicator threshold.

2. A method for diagnosing obstructive sleep apnea hypopnea syndrome according to claim 1, characterized in that: The step of traversing and retrieving all respiratory events from the airflow curve comprises the following steps: Step 11: For each second in the airflow curve, the maximum value of the airflow magnitude before that second in the airflow curve is taken as the maximum value of the airflow magnitude in that second; Step 12: Traverse the airflow curve second by second until the airflow size is lower than the corresponding maximum airflow value, and take the time point when the airflow size is multiplied by the preset ratio threshold as the event start time. Continue traversing after the event start time until the airflow size is higher than the corresponding maximum airflow value again, and take the time point when the airflow size is multiplied by the preset ratio threshold as the event end time. If the duration from the event start time to the event end time is greater than the preset duration threshold, the time period from the event start time to the event end time is called a respiratory event; otherwise, execute step 13; Step 13: Starting from the event end time of step 12, restart the traversal and repeat step 12 until all respiratory events are found.

3. A method for diagnosing obstructive sleep apnea hypopnea syndrome according to claim 2, characterized in that: The method of finding the corresponding search window from the blood oxygen saturation curve according to the time when each respiratory event occurs is: Starting from the initial time of each respiratory event, the blood oxygen saturation curve is traversed, and the first time node where the blood oxygen saturation decreases is obtained as the search initial time, and the blood oxygen saturation corresponding to the search initial time is used as the baseline level; Continue to traverse the blood oxygen saturation curve from the initial search time until the blood oxygen saturation returns to the baseline level, and use the current time point as the search end time; The closed interval formed by the curve segment from the search initial time to the search end time of the blood oxygen saturation curve and the baseline is used as the search window.

4. A method for diagnosing obstructive sleep apnea hypopnea syndrome according to claim 3, characterized in that: The baseline is constructed as follows: Draw a horizontal line parallel to the horizontal axis at the position where the vertical axis is the baseline as the baseline.

5. A method for diagnosing obstructive sleep apnea hypopnea syndrome according to claim 4, characterized in that: The airflow curve refers to a curve obtained by connecting the real-time airflow volume generated by the breathing of the patient in a sleeping state in chronological order, and the horizontal axis of the airflow curve is time, and the vertical axis is the airflow volume.

6. A method for diagnosing obstructive sleep apnea hypopnea syndrome according to claim 5, characterized in that: The blood oxygen saturation curve refers to a curve obtained by connecting the real-time blood oxygen saturation of the patient in a sleeping state in chronological order. The horizontal axis of the blood oxygen saturation curve is time, and the vertical axis is blood oxygen saturation.

7. A method for diagnosing obstructive sleep apnea hypopnea syndrome according to claim 5, characterized in that: The method further comprises: According to the pre-calibrated response time difference between apnea and decreased blood oxygen saturation, the search window is shifted to obtain an updated search window, wherein the starting point and the end point of the updated search window are shifted to the left by the length of the response time difference; Aligning the updated search window with the time interval of the apnea event in the airflow curve based on the highest point of the curve; The aligned updated search window and the time interval of the apnea event in the airflow curve are compared, and the unaligned parts of the two are removed to obtain a final search window, and the search window is replaced by the final search window to obtain the index value of the sleep apnea-specific hypoxia load again.

8. The method for diagnosing obstructive sleep apnea hypopnea syndrome according to claim 7, characterized in that: The method further comprises: The response time difference between apnea and oxygen desaturation was calculated by comparing the time point when the apnea event started or ended with the time point when the oxygen saturation began to decrease or recover.

9. An electronic device, characterized in that: include: A processor and a memory, wherein: The memory stores a computer program that can be called by the processor; The processor executes the method for diagnosing obstructive sleep apnea-hypopnea syndrome according to any one of claims 1 to 8 in the background by calling the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: A rewritable computer program is stored thereon; When the computer program is executed on a computer device, the computer device is enabled to execute the method for diagnosing obstructive sleep apnea-hypopnea syndrome according to any one of claims 1 to 8 in the background.

Images