Sleep hypopnea syndrome monitoring device and storage medium

Abstract

The invention provides a sleep hypopnea syndrome monitoring device and a storage medium, and relates to the technical field of sleep monitoring. The device comprises an electrocardio measurement assembly used for collecting an electrocardio signal of a user; the processor is used for determining a plurality of hypopnea characteristic index values based on the electrocardiosignals, determining airflow difference value characteristics based on the hypopnea characteristic index values and determining hypopnea monitoring results based on the airflow difference value characteristics. According to the invention, the operand of the processor can be reduced, so that the monitoring efficiency of the sleep hypopnea syndrome is improved, and the power consumption of the processor is reduced, so that equipment with relatively low electric quantity or operand such as wearable equipment can comprise the processor, and whether a user is in a sleep hypopnea state or not can be monitored in real time; and the timeliness and efficiency of sleep hypopnea syndrome monitoring are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of sleep monitoring, and in particular to a sleep hypoventilation syndrome monitoring device and a storage medium. Background Art

[0002] Sleep Apnea Hypopnea Syndrome (SAHS) refers to a sleep breathing disorder in which apnea or hypopnea occurs repeatedly during sleep due to various reasons. Repeated nocturnal hypoxia and hypercapnia caused by apnea may lead to complications such as hypertension, coronary heart disease, diabetes and cerebrovascular disease. Therefore, SAHS is a potentially fatal sleep breathing disorder, and timely and effective monitoring of SAHS is of great significance.

[0003] At present, the method for identifying sleep hypoventilation mainly collects the user's ECG signal, and then transmits the ECG signal to other systems or servers for detecting sleep hypoventilation, so as to analyze it in the system or server using the sleep hypoventilation algorithm model. However, during the transmission of the ECG signal, there may be network delays or network failures, resulting in the inability to monitor in real time whether the user is in a state of sleep hypoventilation. In addition, the currently commonly used algorithm model usually uses a classification model trained by machine learning to distinguish events of sleep apnea syndrome, which has a large amount of calculations and will result in low efficiency in identifying sleep hypoventilation. Summary of the invention

[0004] The invention provides a sleep hypoventilation syndrome monitoring device and a storage medium, which are used to solve the defects of poor real-time performance, large amount of calculation and low efficiency of sleep hypoventilation monitoring in the prior art.

[0005] The present invention provides a sleep hypoventilation syndrome monitoring device, comprising:

[0006] An electrocardiogram measurement component, used to collect the user's electrocardiogram signal;

[0007] The processor is used to determine a plurality of hypoventilation characteristic index values ​​based on the electrocardiogram signal, determine an airflow difference characteristic based on the plurality of hypoventilation characteristic index values, and determine a hypoventilation monitoring result based on the airflow difference characteristic.

[0008] According to a sleep hypopnea syndrome monitoring device provided by the present invention, the determining of a plurality of hypopnea characteristic index values ​​based on the electrocardiogram signal comprises:

[0009] Filtering the electrocardiogram signal to obtain a target electrocardiogram signal;

[0010] Dividing the target ECG signal to obtain a plurality of ECG signal segments;

[0011] The hypoventilation characteristic index value corresponding to each of the plurality of electrocardiogram signal segments is determined.

[0012] According to a sleep hypopnea syndrome monitoring device provided by the present invention, the step of determining the hypopnea characteristic index value corresponding to each of the plurality of electrocardiogram signal segments comprises:

[0013] respectively determining the signal means of the plurality of electrocardiogram signal segments;

[0014] Based on the mean values ​​of each signal, the hypoventilation characteristic index values ​​corresponding to the plurality of ECG signal segments are calculated respectively.

[0015] According to a sleep hypopnea syndrome monitoring device provided by the present invention, filtering the electrocardiogram signal to obtain a target electrocardiogram signal includes:

[0016] Determining a baseline value of each signal data point in the electrocardiogram signal;

[0017] Based on the baseline value, performing baseline filtering on the electrocardiogram signal to obtain a filtered electrocardiogram signal;

[0018] The filtered ECG signal is subjected to high-frequency noise reduction processing to obtain the target ECG signal.

[0019] According to a sleep hypopnea syndrome monitoring device provided by the present invention, the high-frequency noise reduction processing is performed on the filtered ECG signal to obtain the target ECG signal, including:

[0020] According to a preset time window length, sliding selection is performed in the filtered ECG signal to obtain a plurality of signal data point sequences;

[0021] respectively determining the signal data point means corresponding to all the signal data points in the plurality of signal data point sequences;

[0022] Based on the mean value of the signal data points, noise reduction processing is performed on each signal data point in the filtered ECG signal to obtain the target ECG signal.

[0023] According to a sleep hypopnea syndrome monitoring device provided by the present invention, the airflow difference feature is determined based on the plurality of hypopnea characteristic index values, including:

[0024] A first characteristic index sequence and a second characteristic index sequence are selected from the plurality of hypopnea characteristic index values; wherein the hypopnea characteristic index value in the first characteristic index sequence is greater than the hypopnea characteristic index value in the second characteristic index sequence;

[0025] The airflow difference feature is calculated based on the first feature index sequence and the second feature index sequence.

[0026] According to a sleep hypopnea syndrome monitoring device provided by the present invention, the airflow difference feature is calculated based on the first characteristic index sequence and the second characteristic index sequence, including:

[0027] Determine a first airflow characteristic mean of all hypopnea characteristic index values ​​in the first characteristic index sequence;

[0028] Determine a second airflow characteristic mean of all hypopnea characteristic index values ​​in the second characteristic index sequence;

[0029] The airflow difference feature is calculated based on the first airflow feature mean and the second airflow feature mean.

[0030] According to a sleep hypopnea syndrome monitoring device provided by the present invention, the first characteristic index sequence and the second characteristic index sequence are selected from the plurality of hypopnea characteristic index values, comprising:

[0031] Sorting the plurality of hypopnea characteristic index values ​​to obtain a sorting result;

[0032] According to the sorting result, the first characteristic index sequence and the second characteristic index sequence are selected according to a preset selection ratio.

[0033] According to a sleep hypopnea syndrome monitoring device provided by the present invention, the determining of the hypopnea monitoring result based on the airflow difference feature includes:

[0034] If the airflow difference characteristic is greater than a preset airflow threshold, it is determined that the hypopnea monitoring result is that the user is in a normal sleeping state;

[0035] If the airflow difference characteristic is less than or equal to a preset airflow threshold, it is determined that the hypoventilation monitoring result is that the user is in a sleep hypoventilation state.

[0036] According to a sleep hypopnea syndrome monitoring device provided by the present invention, if the airflow difference feature is greater than a preset airflow threshold, determining that the hypopnea monitoring result is that the user is in a normal sleep state includes:

[0037] If the airflow difference characteristic is greater than a preset airflow threshold, and the airflow difference characteristic is less than an abnormal airflow threshold, it is determined that the hypoventilation monitoring result is that the user is in a normal sleeping state;

[0038] The determining of the hypopnea monitoring result based on the airflow difference feature further includes:

[0039] If the airflow difference characteristic is greater than or equal to the abnormal airflow threshold, the hypopnea monitoring result is determined to be an abnormal result;

[0040] Wherein, the abnormal airflow threshold is greater than the preset airflow threshold.

[0041] According to a sleep hypopnea syndrome monitoring device provided by the present invention, the sleep hypopnea syndrome monitoring device is a wearable device.

[0042] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed, the method executed by the processor in any one of the above items is implemented.

[0043] The sleep hypoventilation syndrome monitoring device and storage medium provided by the present invention include an electrocardiogram measurement component for collecting the user's electrocardiogram signal, so that the processor can determine a number of hypoventilation characteristic index values ​​based on the electrocardiogram signal, and determine the airflow difference characteristics based on the several hypoventilation characteristic index values, and finally determine the hypoventilation monitoring result based on the airflow difference characteristics. Through the above-mentioned method, the processor only needs to perform the above-mentioned simple data processing to determine the hypoventilation monitoring result. Compared with the prior art of hypoventilation detection through an algorithm model, the present invention can reduce the amount of calculation of the processor, thereby improving the monitoring efficiency of sleep hypoventilation syndrome, and reducing the power consumption of the processor, so that a device with low power or calculation amount such as a wearable device can include the processor. In other words, the sleep hypoventilation syndrome monitoring method executed by the above-mentioned processor can be executed on a device with low power or calculation amount such as a wearable device, thereby ensuring that it can monitor in real time whether the user is in a sleep hypoventilation state, and improve the timeliness and efficiency of sleep hypoventilation syndrome monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 A schematic diagram of the structure of the sleep hypoventilation syndrome monitoring device provided by the present invention;

[0046] Figure 2 One of the flowcharts of the method executed by the processor provided by the present invention;

[0047] Figure 3 A second flowchart diagram of a method executed by a processor provided by the present invention;

[0048] Figure 4 This is a schematic structural diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not 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.

[0050] Sleep Apnea Hypopnea Syndrome (SAHS) refers to a sleep-related respiratory disorder characterized by repeated apnea or hypopnea during sleep due to various reasons. Sleep hypopnea is defined as a decrease in nasal and oral airflow greater than or equal to 30%, which lasts for greater than or equal to 10 seconds, and is accompanied by a decrease in oxygen saturation greater than or equal to 3%, or an event of awakening.

[0051] SAHS is a common chronic sleep-related breathing disorder. Untreated SAHS patients have a significantly increased risk of cardiovascular disease, stroke, cognitive dysfunction and cancer, and their mortality rate is 2-3 times that of the general population. Due to the lack of sufficient sleep laboratories or experts, the scarcity of polysomnography (PSG) in the laboratory and the high cost of diagnosis, SAHS has become a disease with low public awareness, and a large number of potential SAHS patients have not been diagnosed and treated in time. In addition, recurrent nocturnal hypoxia and hypercapnia caused by apnea or sleep hypoventilation may lead to complications such as hypertension, coronary heart disease, diabetes and cerebrovascular disease. Therefore, SAHS is a potentially fatal sleep breathing disorder, and timely and effective monitoring of SAHS is of great significance.

[0052] At present, the method for identifying sleep hypoventilation mainly collects the user's ECG signal, and then transmits the ECG signal to other systems or servers for detecting sleep hypoventilation, so as to analyze it in the system or server using the sleep hypoventilation algorithm model. However, during the transmission of the ECG signal, there may be network delays or network failures, resulting in the inability to monitor in real time whether the user is in a state of sleep hypoventilation. In addition, the currently commonly used algorithm model usually uses a classification model trained by machine learning to distinguish events of sleep apnea syndrome, which has a large amount of calculations and will result in low efficiency in identifying sleep hypoventilation.

[0053] In view of the above problems, the present invention proposes the following embodiments. Figure 1 The structure diagram of the sleep hypoventilation syndrome monitoring device provided by the present invention is as follows: Figure 1 As shown, the sleep hypopnea syndrome monitoring device includes: an electrocardiogram measurement component 110 and a processor 120.

[0054] The ECG measurement component is used to collect the user's ECG signal.

[0055] Here, the ECG signal is a bioelectric signal generated when the user's heart moves. In one embodiment, the ECG signal is a single-lead ECG signal, and correspondingly, the ECG measurement component is a single-lead ECG measurement component.

[0056] In one embodiment, the sampling frequency of the ECG signal is within a preset frequency range, which can be set according to actual needs. For example, the preset frequency range is 100 data points per second to 500 data points per second, that is, the preset frequency range is 100 Hz to 500 Hz.

[0057] The processor is used to determine a plurality of hypoventilation characteristic index values ​​based on the electrocardiogram signal, determine an airflow difference characteristic based on the plurality of hypoventilation characteristic index values, and determine a hypoventilation monitoring result based on the airflow difference characteristic.

[0058] Here, the processor may execute a sleep hypopnea syndrome monitoring method. Figure 2 One of the flowcharts of the method executed by the processor provided by the present invention is as follows: Figure 2 As shown, the method includes:

[0059] Step 210: determining a plurality of hypopnea characteristic index values ​​based on the electrocardiogram signal.

[0060] Here, the hypoventilation characteristic index value is used to characterize the characteristics related to sleep hypoventilation, that is, to characterize the respiratory intensity, and further, it is used to characterize the degree of sleep hypoventilation. The hypoventilation characteristic index value may include but is not limited to at least one of the following: the signal mean of the electrocardiogram signal, the root mean square value of the electrocardiogram signal, the power spectrum density of the electrocardiogram signal, etc.

[0061] In some embodiments, the ECG signal is divided to obtain a plurality of ECG signal segments; and a hypoventilation characteristic index value corresponding to each of the plurality of ECG signal segments is determined.

[0062] In one embodiment, according to the preset first time window length, sliding selection is performed in the ECG signal to obtain a plurality of ECG signal segments. Each ECG signal segment includes a plurality of signal data points. In other words, according to the preset first time window length, a plurality of ECG signal segments are obtained by segmenting the ECG signal one by one, that is, one ECG signal segment is intercepted from the ECG signal per the first time window length, that is, the time length of each ECG signal segment is the first time window length.

[0063] The length of the first time window is within a first time range, and the first time range can be set according to actual needs, for example, the first time range is 1 second to 3 seconds.

[0064] In one embodiment, based on the signal mean value of each ECG signal segment, the hypopnea characteristic index value corresponding to each ECG signal segment is calculated.

[0065] The signal mean of any ECG signal segment is the mean of all signal data points in the ECG signal segment. For ease of understanding, the calculation formula of the signal mean is as follows:

[0066]

[0067] In the formula, S i,avg is the average value of all signal data points in the ith ECG signal segment among several ECG signal segments; N is the number of all signal data points in the ith ECG signal segment; S i [n] is the nth signal data point in the i-th ECG signal segment.

[0068] Exemplarily, if the hypoventilation characteristic index value is a root mean square value, then the hypoventilation characteristic index value corresponding to any ECG signal segment is the root mean square value of all signal data points in the ECG signal segment. For ease of understanding, the calculation formula of the hypoventilation characteristic index value is as follows:

[0069]

[0070] In the formula, Hindex i [n] is the RMS value of all signal data points in the ith ECG signal segment among the ECG signal segments; N is the number of all signal data points in the ith ECG signal segment; S i [n] is the nth signal data point in the i-th ECG signal segment, S i,avg is the average value of all signal data points in the i-th ECG signal segment among several ECG signal segments.

[0071] It should be noted that when sleep apnea occurs, blood oxygen decreases, and airflow drops sharply, the hypoventilation characteristic index value will also decrease synchronously. The change in breathing intensity, that is, the change in nasal airflow, will reflect the change in lung impedance, and then cause the change in the root mean square or power spectrum density of the AC signal in the ECG signal. Therefore, the hypoventilation characteristic index value can be used as a simple and convenient respiratory detection feature.

[0072] Step 220: determining an airflow difference characteristic based on the plurality of hypopnea characteristic index values.

[0073] It should be noted that a large number of experiments have shown that the airflow change value is closely related to features such as respiratory ventilation and blood oxygen saturation. For example, during the period of sleep apnea, respiratory ventilation generally decreases by more than 30%, and blood oxygen saturation generally decreases by 5% to 20%. Based on this, the airflow difference feature can be used to characterize the decrease in respiratory ventilation and blood oxygen saturation.

[0074] Specifically, a first characteristic index sequence and a second characteristic index sequence are determined from a plurality of hypopnea characteristic index values; and an airflow difference characteristic is determined based on the first characteristic index sequence and the second characteristic index sequence.

[0075] In a specific embodiment, a linear operation or a proportional operation is performed on the first characteristic index sequence and the second characteristic index sequence to obtain the airflow difference characteristic. The linear operation may include but is not limited to: linear addition and linear subtraction, etc. The proportional operation is to determine the ratio of the two.

[0076] Step 230: Determine a hypopnea monitoring result based on the airflow difference characteristic.

[0077] Here, the hypoventilation monitoring result may include but is not limited to: the user is in a normal sleep state, the user is in a sleep hypoventilation state, and the like.

[0078] Specifically, based on the comparison result of the airflow difference feature and the preset airflow threshold, the hypopnea monitoring result is determined. The number of the preset airflow thresholds can be 1, 2, or more. The preset airflow threshold can be set according to actual needs, and the embodiment of the present invention does not specifically limit this.

[0079] The sleep hypoventilation syndrome monitoring device provided by the embodiment of the present invention includes an electrocardiogram measurement component for collecting the user's electrocardiogram signal, so that the processor can determine a number of hypoventilation characteristic index values ​​based on the electrocardiogram signal, and determine the airflow difference characteristics based on the number of hypoventilation characteristic index values, and finally determine the hypoventilation monitoring result based on the airflow difference characteristics. Through the above method, the processor only needs to perform the above simple data processing to determine the hypoventilation monitoring result. Compared with the prior art of hypoventilation detection through an algorithm model, the embodiment of the present invention can reduce the amount of calculation of the processor, thereby improving the monitoring efficiency of sleep hypoventilation syndrome, and reducing the power consumption of the processor, so that wearable devices and other devices with low power or calculation can include the processor. In other words, the sleep hypoventilation syndrome monitoring method executed by the above processor can be executed on wearable devices and other devices with low power or calculation, thereby ensuring that it can monitor in real time whether the user is in a sleep hypoventilation state, and improve the timeliness and efficiency of sleep hypoventilation syndrome monitoring.

[0080] Based on the above embodiments, Figure 3 The second flowchart of the method executed by the processor provided by the present invention is as follows: Figure 3 As shown, the above step 210 includes:

[0081] Step 211, filtering the ECG signal to obtain a target ECG signal.

[0082] Here, the target ECG signal is a high-quality ECG signal, thereby improving the accuracy of the hypoventilation characteristic index value, and further improving the accuracy of the hypoventilation monitoring result.

[0083] Here, the filtering process may include but is not limited to at least one of the following: filtering process, noise reduction process, etc. In one embodiment, the filtering process may be baseline filtering, and further, the baseline filtering may be median filtering.

[0084] In some embodiments, a baseline value of each data point in the ECG signal is determined; based on the baseline value, the ECG signal is subjected to baseline filtering to obtain a target ECG signal.

[0085] Here, the baseline value may include but is not limited to: the median value of each data point in the ECG signal, the average value of each data point in the ECG signal, the root mean square value of each data point in the ECG signal, and the like.

[0086] In a specific embodiment, a target data point to be filtered in the ECG signal is determined; based on the target data point, a target data point sequence is selected from each data point in the ECG signal; and the median of the target data point sequence is determined as the baseline value of the target data point.

[0087] The number of data points in the target data point sequence can be determined according to the sliding window length, and the sliding window length can be set according to actual needs. For example, the sliding window length is 101, that is, the number of data points in the target data point sequence is 101. Based on this, the median of the target data point sequence is the 51st data point in the sorted target data point sequence. For ease of understanding, assuming that the target data point sequence is {X[n], X[n+1], X[n+2], ..., X[n+100]}, the baseline value of the target data point sequence is X[n+50].

[0088] It should be noted that the baseline value is the drift baseline of the ECG signal, and the sliding window length of 101 points is selected to effectively suppress the low-frequency baseline drift.

[0089] In one embodiment, the length of the sliding window is 0.1 to 1.5 times the sampling frequency of the ECG signal.

[0090] Specifically, the target ECG signal is determined based on the difference between each data point in the ECG signal and the corresponding baseline value. Exemplarily, the calculation formula of the target ECG signal is as follows:

[0091] Y[n]=X[n]-Q[n];

[0092] Where Y[n] is the nth data point in the target ECG signal, X[n] is the nth data point in the ECG signal, and Q[n] is the baseline value corresponding to the nth data point in the target ECG signal.

[0093] It can be understood that based on the difference between each data point in the ECG signal and the corresponding baseline value, the baseline value can be removed to obtain a stable target ECG signal, thereby facilitating subsequent extraction of the hypoventilation characteristic index value, thereby improving the accuracy of the hypoventilation characteristic index value.

[0094] In some other embodiments, the ECG signal is subjected to noise reduction processing to obtain the target ECG signal. Further, the ECG signal is subjected to high frequency noise reduction processing to obtain the target ECG signal.

[0095] In one embodiment, the high frequency noise reduction process uses a sliding average method, and the time window length of the sliding average method can be 0.02 times to 0.1 times the sampling frequency of the electrocardiogram signal.

[0096] Specifically, according to a preset time window length, sliding selection is performed in the ECG signal to obtain a plurality of signal data point sequences; the signal data point mean corresponding to all signal data points in each signal data point sequence is determined; based on the signal data point mean corresponding to all signal data points in each signal data point sequence, each signal data point in the ECG signal is subjected to noise reduction processing to obtain a target ECG signal.

[0097] For ease of understanding, the calculation formula for high-frequency noise reduction processing is as follows:

[0098]

[0099] Where Y[n] is the nth data point in the target ECG signal, X[n] is the nth data point in the ECG signal, and L is the sliding average window length. For example, if the sliding average window length L is 3, the calculation formula for high-frequency noise reduction processing is as follows:

[0100]

[0101] It can be understood that by performing noise reduction processing on each signal data point in the ECG signal, a stable target ECG signal can be obtained, thereby facilitating the subsequent extraction of the hypoventilation characteristic index value, thereby improving the accuracy of the hypoventilation characteristic index value, and playing a key role in the resolution of sleep hypoventilation monitoring.

[0102] Step 212, dividing the target ECG signal to obtain a plurality of ECG signal segments.

[0103] In a specific embodiment, according to the preset first time window length, a sliding selection is performed in the target ECG signal to obtain a plurality of ECG signal segments. Each ECG signal segment includes a plurality of signal data points. In other words, according to the preset first time window length, a plurality of ECG signal segments are obtained by segmenting the target ECG signal one by one, that is, one ECG signal segment is intercepted from the target ECG signal per the first time window length, that is, the time length of each ECG signal segment is the first time window length.

[0104] The length of the first time window is within a first time range, and the first time range can be set according to actual needs, for example, the first time range is 1 second to 3 seconds.

[0105] For ease of understanding, assuming that the length of the first time window is 2 seconds, a number of ECG signal segments are obtained from the target ECG signal one by one, that is, an ECG signal segment is intercepted from the target ECG signal every 2 seconds, that is, the time length of each ECG signal segment is 2 seconds.

[0106] Step 213: determine the hypoventilation characteristic index value corresponding to each of the plurality of electrocardiogram signal segments.

[0107] Here, the hypopnea characteristic index value may include but is not limited to at least one of the following: a signal mean value of the electrocardiogram signal, a root mean square value of the electrocardiogram signal, a power spectrum density of the electrocardiogram signal, and the like.

[0108] The sleep hypoventilation syndrome monitoring device provided in the embodiment of the present invention can obtain a stable target ECG signal by filtering the ECG signal, thereby facilitating the subsequent extraction of a hypoventilation characteristic index value, thereby improving the accuracy of the hypoventilation characteristic index value, thereby improving the accuracy of the hypoventilation monitoring results, and ultimately improving the monitoring accuracy of sleep hypoventilation.

[0109] Based on any of the above embodiments, the above step 213 includes:

[0110] respectively determining the signal means of the plurality of electrocardiogram signal segments;

[0111] Based on the mean values ​​of each signal, the hypoventilation characteristic index values ​​corresponding to the plurality of ECG signal segments are calculated respectively.

[0112] Here, the signal mean of any ECG signal segment is the mean of all signal data points in the ECG signal segment. For ease of understanding, the calculation formula for the signal mean is as follows:

[0113]

[0114] In the formula, S i,avg is the average value of all signal data points in the ith ECG signal segment among several ECG signal segments; N is the number of all signal data points in the ith ECG signal segment; S i [n] is the nth signal data point in the i-th ECG signal segment.

[0115] It should be noted that, if the length of the first time window is 2 seconds and the sampling frequency of the ECG signal is 100 data points per second, the number N of all signal data points in the i-th ECG signal segment is 200.

[0116] In a specific embodiment, if the hypoventilation characteristic index value is a root mean square value, then the hypoventilation characteristic index value corresponding to any ECG signal segment is the root mean square value of all signal data points in the ECG signal segment. For ease of understanding, the calculation formula of the hypoventilation characteristic index value is as follows:

[0117]

[0118] In the formula, Hindex i [n] is the RMS value of all signal data points in the ith ECG signal segment among the ECG signal segments; N is the number of all signal data points in the ith ECG signal segment; S i [n] is the nth signal data point in the i-th ECG signal segment, S i,avg is the average value of all signal data points in the i-th ECG signal segment among several ECG signal segments.

[0119] The sleep hypoventilation syndrome monitoring device provided in the embodiment of the present invention can accurately calculate the hypoventilation characteristic index value corresponding to each ECG signal segment based on the signal mean of each ECG signal segment, thereby improving the accuracy of the hypoventilation characteristic index value, and then improving the accuracy of the hypoventilation monitoring results, and ultimately improving the monitoring accuracy of sleep hypoventilation.

[0120] Based on any of the above embodiments, the above step 211 includes:

[0121] Determining a baseline value of each signal data point in the electrocardiogram signal;

[0122] Based on the baseline value, performing baseline filtering on the electrocardiogram signal to obtain a filtered electrocardiogram signal;

[0123] The filtered ECG signal is subjected to high-frequency noise reduction processing to obtain the target ECG signal.

[0124] It should be noted that the ECG signal is obtained by sampling based on a sampling frequency, so the ECG signal includes a plurality of signal data points, and the number of the signal data points is determined according to the sampling frequency and the sampling duration.

[0125] Here, the baseline value may include but is not limited to: the median value of each signal data point in the ECG signal, the average value of each signal data point in the ECG signal, the root mean square value of each signal data point in the ECG signal, and the like.

[0126] In a specific embodiment, a target signal data point to be filtered in the ECG signal is determined; based on the target signal data point, a target data point sequence is selected from each signal data point in the ECG signal; and the median of the target data point sequence is determined as the baseline value of the target signal data point.

[0127] The number of signal data points in the target data point sequence can be determined according to the sliding window length, and the sliding window length can be set according to actual needs. For example, the sliding window length is 101, that is, the number of signal data points in the target data point sequence is 101. Based on this, the median of the target data point sequence is the 51st signal data point in the sorted target data point sequence. For ease of understanding, assuming that the target data point sequence is {X[n], X[n+1], X[n+2], ..., X[n+100]}, the baseline value of the target data point sequence is X[n+50].

[0128] It should be noted that the baseline value is the drift baseline of the ECG signal, and the sliding window length of 101 points is selected to effectively suppress the low-frequency baseline drift.

[0129] In one embodiment, the length of the sliding window is 0.1 to 1.5 times the sampling frequency of the ECG signal.

[0130] Specifically, the baseline filtering process is as follows: based on the difference between each signal data point in the ECG signal and the corresponding baseline value, a filtered ECG signal is determined. Exemplarily, the calculation formula of the filtered ECG signal is as follows:

[0131] Z[n]=X[n]-Q[n];

[0132] Where Z[n] is the nth signal data point in the filtered ECG signal, X[n] is the nth signal data point in the ECG signal, and Q[n] is the baseline value corresponding to the nth signal data point in the filtered ECG signal. Z[n] is the signal data point obtained by splitting X[n] after median filtering.

[0133] It can be understood that based on the difference between each signal data point in the ECG signal and the corresponding baseline value, the baseline value can be removed to obtain a stable filtered ECG signal, thereby facilitating the subsequent extraction of the hypoventilation characteristic index value, thereby improving the accuracy of the hypoventilation characteristic index value.

[0134] In one embodiment, the high frequency noise reduction process uses a sliding average method, and the time window length of the sliding average method can be 0.02 times to 0.1 times the sampling frequency of the electrocardiogram signal.

[0135] The sleep hypoventilation syndrome monitoring device provided in the embodiment of the present invention provides support for filtering processing of ECG signals in the above-mentioned manner. Based on the baseline value of each signal data point in the ECG signal, the ECG signal is baseline filtered to obtain a filtered ECG signal, and then the filtered ECG signal is subjected to high-frequency noise reduction processing to obtain a stable target ECG signal, thereby facilitating subsequent extraction of a hypoventilation characteristic index value, thereby improving the accuracy of the hypoventilation characteristic index value, thereby improving the accuracy of the hypoventilation monitoring results, and ultimately improving the monitoring accuracy of sleep hypoventilation.

[0136] Based on any of the above embodiments, the step of performing high frequency noise reduction processing on the filtered ECG signal to obtain the target ECG signal includes:

[0137] According to a preset time window length, sliding selection is performed in the filtered ECG signal to obtain a plurality of signal data point sequences;

[0138] respectively determining the signal data point means corresponding to all the signal data points in the plurality of signal data point sequences;

[0139] Based on the mean value of the signal data points, noise reduction processing is performed on each signal data point in the filtered ECG signal to obtain the target ECG signal.

[0140] Here, the time window length can be set according to actual needs. In one embodiment, the time window length can be 0.02 times to 0.1 times the sampling frequency of the electrocardiogram signal.

[0141] Here, the signal data point mean may be the average value of all signal data points, or the weighted average value of all signal data points, or other types of means.

[0142] Specifically, the mean value of each signal data point can be directly determined as the target ECG signal, or the mean value of each signal data point can be further processed to obtain the target ECG signal. It can be understood that this process is high-frequency noise reduction processing.

[0143] For ease of understanding, the calculation formula for high-frequency noise reduction processing is as follows:

[0144]

[0145] Where Y[n] is the nth signal data point in the target ECG signal, Z[n] is the nth signal data point in the filtered ECG signal, and L is the time window length. For example, if the time window length L is 3, the calculation formula for high-frequency noise reduction processing is as follows:

[0146]

[0147] The sleep hypoventilation syndrome monitoring device provided by the embodiment of the present invention performs sliding selection in the filtered ECG signal according to the pre-set time window length to obtain a plurality of signal data point sequences; determines the signal data point mean corresponding to all signal data points in each signal data point sequence; and performs noise reduction processing on each signal data point in the filtered ECG signal based on the mean of each signal data point to obtain a target ECG signal. Through the above method, support is provided for the high-frequency noise reduction processing method, and noise reduction processing is performed on each signal data point in the filtered ECG signal to obtain a stable target ECG signal, thereby facilitating the subsequent extraction of the hypoventilation characteristic index value, thereby improving the accuracy of the hypoventilation characteristic index value, thereby improving the accuracy of the hypoventilation monitoring results, and ultimately improving the monitoring accuracy of sleep hypoventilation.

[0148] Based on any of the above embodiments, the above step 220 includes:

[0149] A first characteristic index sequence and a second characteristic index sequence are selected from the plurality of hypopnea characteristic index values; wherein the hypopnea characteristic index value in the first characteristic index sequence is greater than the hypopnea characteristic index value in the second characteristic index sequence;

[0150] The airflow difference feature is calculated based on the first feature index sequence and the second feature index sequence.

[0151] It should be noted that a large number of experiments have shown that the airflow change value is closely related to features such as respiratory ventilation and blood oxygen saturation. For example, during the period of sleep apnea, respiratory ventilation generally decreases by more than 30%, and blood oxygen saturation generally decreases by 5% to 20%. Based on this, the airflow difference feature can be used to characterize the decrease in respiratory ventilation and blood oxygen saturation.

[0152] Here, the first characteristic index sequence includes a plurality of hypopnea characteristic index values, and the second characteristic index sequence includes a plurality of hypopnea characteristic index values; the number of hypopnea characteristic index values ​​in the first characteristic index sequence and the second characteristic index sequence may be the same or different.

[0153] Specifically, the high airflow feature is determined based on the first characteristic index sequence, and the low airflow feature is determined based on the second characteristic index sequence; based on the high airflow feature and the low airflow feature, the airflow difference feature is calculated.

[0154] In a specific embodiment, a linear operation or a proportional operation is performed on the high airflow feature and the low airflow feature to obtain an airflow difference feature. The linear operation may include but is not limited to: linear addition and linear subtraction, etc. The proportional operation is to determine the ratio of the two.

[0155] The sleep hypoventilation syndrome monitoring device provided in the embodiment of the present invention first selects a first characteristic index sequence and a second characteristic index sequence from a plurality of hypoventilation characteristic index values, and the hypoventilation characteristic index value in the first characteristic index sequence is greater than the hypoventilation characteristic index value in the second characteristic index sequence, that is, a larger hypoventilation characteristic index value and a smaller hypoventilation characteristic index value are obtained by division, and then the airflow difference feature is better calculated to improve the accuracy of the airflow difference feature, thereby improving the accuracy of the hypoventilation monitoring results, and ultimately improving the monitoring accuracy of sleep hypoventilation.

[0156] Based on any of the above embodiments, the step of calculating the airflow difference feature according to the first characteristic index sequence and the second characteristic index sequence includes:

[0157] Determine a first airflow characteristic mean of all hypopnea characteristic index values ​​in the first characteristic index sequence;

[0158] Determine a second airflow characteristic mean of all hypopnea characteristic index values ​​in the second characteristic index sequence;

[0159] The airflow difference feature is calculated based on the first airflow feature mean and the second airflow feature mean.

[0160] Here, the first airflow characteristic mean may be the average value of all hypoventilation characteristic index values, or the weighted average value of all hypoventilation characteristic index values, or other forms of means. The second airflow characteristic mean may be the average value of all hypoventilation characteristic index values, or the weighted average value of all hypoventilation characteristic index values, or other forms of means.

[0161] Specifically, the high airflow feature is determined based on the mean of the first airflow feature, and the low airflow feature is determined based on the mean of the second airflow feature; based on the high airflow feature and the low airflow feature, the airflow difference feature is calculated. The first airflow feature mean can be directly used as the high airflow feature, or the first airflow feature mean can be further processed to obtain the high airflow feature. The second airflow feature mean can be directly used as the low airflow feature, or the second airflow feature mean can be further processed to obtain the low airflow feature.

[0162] In some embodiments, a linear operation or a proportional operation is performed on the high airflow feature and the low airflow feature to obtain an airflow difference feature. The linear operation may include but is not limited to: linear addition and linear subtraction, etc. The proportional operation is to determine the ratio of the two.

[0163] In one embodiment, the absolute difference between the high airflow feature and the low airflow feature is used as the airflow difference feature. Exemplarily, the calculation formula of the airflow difference feature is as follows:

[0164] Diff H1 =|HAVG-LAVG|;

[0165] In the formula, Diff H1 It is the airflow difference characteristic, HAVG is the high airflow characteristic, and LAVG is the low airflow characteristic.

[0166] The sleep hypoventilation syndrome monitoring device provided in an embodiment of the present invention calculates the airflow difference feature based on the first airflow characteristic mean of all hypoventilation characteristic index values ​​in the first characteristic index sequence and the second airflow characteristic mean of all hypoventilation characteristic index values ​​in the second characteristic index sequence, thereby providing support for the calculation of the airflow difference feature and improving the accuracy of the airflow difference feature calculation, thereby improving the accuracy of the hypoventilation monitoring results and ultimately improving the monitoring accuracy of sleep hypoventilation.

[0167] Based on any of the above embodiments, the step of selecting a first characteristic index sequence and a second characteristic index sequence from the plurality of hypopnea characteristic index values ​​comprises:

[0168] Sorting the plurality of hypopnea characteristic index values ​​to obtain a sorting result;

[0169] According to the sorting result, the first characteristic index sequence and the second characteristic index sequence are selected according to a preset selection ratio.

[0170] Specifically, a plurality of hypopnea characteristic index values ​​are sorted according to the magnitude of the hypopnea characteristic index values ​​to obtain a sorting result, wherein the sorting method may be an ascending method or a descending method, which is not specifically limited in the embodiment of the present invention.

[0171] Here, the selection ratio can be limited according to actual needs, and the selection ratios corresponding to the first characteristic index sequence and the second characteristic index sequence can be the same or different. For example, the selection ratio corresponding to the first characteristic index sequence can be 10%, and the selection ratio corresponding to the second characteristic index sequence can be 10%.

[0172] Specifically, according to the sorting result, the first characteristic index sequence and the second characteristic index sequence are selected according to the preset selection ratio and the preset selection position. The selection position can be set according to actual needs. For example, the first characteristic index sequence can come from the first 10% of the descending set, or from the last 10% of the ascending set; the second characteristic index sequence can come from the first 10% of the ascending set, or from the last 10% of the descending set.

[0173] In one embodiment, a plurality of hypopnea characteristic index values ​​are collected based on a preset second time window length. Further, based on the second time window length and the first time window length, a plurality of hypopnea characteristic index values ​​are collected. The second time window length can be set according to actual needs, and the second time window length can be 30 seconds to 120 seconds.

[0174] For ease of understanding, a specific embodiment is used for illustration. According to the second time window length T2, a number of hypoventilation characteristic index values ​​Hindex are collected, and the number of hypoventilation characteristic index values ​​form a first feature set H1. Assuming that the second time window length T2 is 60 seconds and the first time window length T1 is 2 seconds, in the 60-second window width, the target ECG signal is divided into ECG signal segments of 2 seconds each, so as to determine the hypoventilation characteristic index value Hindex corresponding to each ECG signal segment, that is, the hypoventilation characteristic index values ​​Hindex corresponding to a total of 30 ECG signal segments within 60 seconds are obtained. i , where Hindex i represents the hypoventilation characteristic index value corresponding to the i-th ECG signal segment. The first feature set H1 is as follows:

[0175] H1={Hindex1,Hindex2,…,Hindex 30}.

[0176] Afterwards, the first feature set H1 is sorted in descending order to obtain a second feature set HS. The second feature set HS is as follows:

[0177] H2={Hindex 1′ ,Hindex 2′ ,…,Hindex 30′};

[0178] Among them, Hindex 1′ >Hindex 2′ >…>Hindex 30′ .

[0179] Afterwards, the first characteristic index sequence and the second characteristic index sequence are selected according to the preset selection ratio. Exemplarily, the first characteristic index sequence is as follows:

[0180] {Hindex 2′ ,Hindex 3′ ,Hindex 4′ ,Hindex 5′ ,Hindex 6′};

[0181] The second characteristic index sequence is as follows:

[0182] {Hindex 25′ ,Hindex 26′ ,Hindex 27′ ,Hindex 28′ ,Hindex 29′}.

[0183] Afterwards, the high airflow feature is determined based on the first airflow feature mean of the first feature index sequence, and the low airflow feature is determined based on the second airflow feature mean of the second feature index sequence. The calculation formula of the high airflow feature HAVG is as follows:

[0184]

[0185] The calculation formula of the low airflow characteristic LAVG is as follows:

[0186]

[0187] Finally, the airflow difference feature is calculated based on the high airflow feature and the low airflow feature.

[0188] The sleep hypoventilation syndrome monitoring device provided in the embodiment of the present invention sorts a plurality of hypoventilation characteristic index values ​​to obtain a sorting result; based on the sorting result, a first characteristic index sequence and a second characteristic index sequence are selected according to a preset selection ratio, thereby providing support for the selection of the first characteristic index sequence and the second characteristic index sequence, and furthermore, better calculating the airflow difference feature to improve the accuracy of the airflow difference feature, thereby improving the accuracy of the hypoventilation monitoring result, and ultimately improving the monitoring accuracy of sleep hypoventilation.

[0189] Based on any of the above embodiments, the above step 230 includes:

[0190] If the airflow difference characteristic is greater than a preset airflow threshold, it is determined that the hypopnea monitoring result is that the user is in a normal sleeping state;

[0191] If the airflow difference characteristic is less than or equal to a preset airflow threshold, it is determined that the hypoventilation monitoring result is that the user is in a sleep hypoventilation state.

[0192] Here, the preset airflow threshold can be set according to actual needs. In one embodiment, a 30% decrease in ventilation in the international sleep standard, accompanied by a 3% decrease in blood oxygen saturation, is used as a reference label for sleep hypoventilation, and the optimal preset airflow threshold is determined based on the ROC (Receiver Operating Characteristic) curve. Specifically, the airflow difference feature is used as the judgment feature of sleep hypoventilation, and the preset airflow threshold is continuously changed to obtain the optimal preset airflow threshold. For example, when the preset airflow threshold is 0.2, the sensitivity can reach 98.8%, the specificity can reach 86.4%, and the area under the ROC curve (AUC) can reach 0.969.

[0193] In one embodiment, if the airflow difference characteristic is greater than a preset airflow threshold and the airflow difference characteristic is less than an abnormal airflow threshold, then the hypopnea monitoring result is determined to be that the user is in a normal sleep state, wherein the abnormal airflow threshold is greater than the preset airflow threshold.

[0194] Furthermore, if the airflow difference feature is greater than or equal to the abnormal airflow threshold, it is determined that the hypoventilation monitoring result may be an abnormal result, that is, it is determined that the user may have a large change in sleeping posture and generate movement noise.

[0195] It can be understood that by jointly judging the hypoventilation monitoring results by presetting the airflow threshold and the abnormal airflow threshold, the accuracy of the hypoventilation monitoring results can be improved, thereby improving the accuracy of sleep hypoventilation monitoring.

[0196] The sleep hypoventilation syndrome monitoring device provided in the embodiment of the present invention determines the hypoventilation monitoring result based on the comparison result of the preset airflow threshold and the airflow difference characteristic, thereby improving the accuracy of the hypoventilation monitoring result and ultimately improving the monitoring accuracy of sleep hypoventilation.

[0197] Based on any of the above embodiments, if the airflow difference feature is greater than a preset airflow threshold, determining that the hypopnea monitoring result is that the user is in a normal sleeping state includes:

[0198] If the airflow difference characteristic is greater than a preset airflow threshold, and the airflow difference characteristic is less than an abnormal airflow threshold, it is determined that the hypoventilation monitoring result indicates that the user is in a normal sleeping state.

[0199] Here, the abnormal airflow threshold is greater than a preset airflow threshold, and the abnormal airflow threshold can be set according to actual needs.

[0200] Accordingly, determining the hypopnea monitoring result based on the airflow difference feature further includes:

[0201] If the airflow difference characteristic is greater than or equal to the abnormal airflow threshold, the hypopnea monitoring result is determined to be an abnormal result.

[0202] The sleep hypoventilation syndrome monitoring device provided in the embodiment of the present invention can improve the accuracy of the hypoventilation monitoring results by jointly judging the hypoventilation monitoring results through a preset airflow threshold and an abnormal airflow threshold, thereby improving the monitoring accuracy of sleep hypoventilation; at the same time, if the airflow difference feature is greater than or equal to the abnormal airflow threshold, the hypoventilation monitoring result is judged to be an abnormal result, thereby avoiding the possibility that the user may have a large change in sleeping posture and generate movement noise, and still judging that the user is in a normal sleeping state, thereby further improving the monitoring accuracy of sleep hypoventilation.

[0203] Based on any of the above embodiments, the sleep hypopnea syndrome monitoring device is a wearable device.

[0204] Here, the wearable device may include but is not limited to at least one of the following: a smart watch, a smart bracelet, a wristband device, a smart ring, etc.

[0205] It should be noted that using wearable devices such as smart watches and smart bracelets to monitor health is becoming a new lifestyle. Hundreds of millions of wearable devices such as smart watches are used every day, and the number is increasing dramatically. Since sleep is a key determinant of personal health and happiness, sleep monitoring is one of the most popular features of such wearable devices.

[0206] The sleep hypoventilation syndrome monitoring device provided in the embodiment of the present invention can be a wearable device, thereby ensuring that it can monitor in real time whether the user is in a sleep hypoventilation state, improve the timeliness and efficiency of sleep hypoventilation syndrome monitoring, and improve the convenience of sleep hypoventilation syndrome monitoring.

[0207] In actual application scenarios, the use of low-cost and easy-to-use wearable devices to diagnose and screen SAHS at home and evaluate the treatment effect will greatly contribute to public health. One of the most critical technologies for monitoring SAHS with wearable devices is the SAHS monitoring method. Based on the above embodiments, the sleep period can be monitored based on the hypoventilation characteristic index value and airflow difference characteristics of the ECG signal, which can effectively determine whether a hypoventilation event occurs or not, with very high accuracy; and the hypoventilation characteristic index value and airflow difference characteristics used in this application have a computing complexity of O(n), which is lower than the computing power required by machine learning or deep learning, wavelet analysis, etc., which is lower than the computing power required by machine learning or deep learning, wavelet analysis, etc. 2 ), this application has the characteristics of low cost and low power consumption, and at the same time has high-precision sleep hypopnea detection capabilities, which is suitable for use in wearable devices. In other words, the method executed by the processor in this application can make full use of the convenient characteristics of wearable devices, and use lower computing power and electricity in the process of dynamic ECG monitoring of sleep breathing, and efficiently analyze and screen standard hypopnea events in sleep breathing. It can be used as one of the key parameters for sleep quality assessment, which is of great help to the implementation of ECG home health detection scenarios and optimization of sleep quality-related industry scenarios.

[0208] Based on the above embodiments, this application proposes to judge the intensity and duration of breathing based on the characteristics of the electrocardiogram, and then accurately and efficiently perform low ventilation monitoring and identification with low power consumption, which helps to develop quality indicators of sleep breathing on smart health wearable devices, and becomes a very useful function on health wearable devices. In other words, based on the low ventilation characteristic index value in the electrocardiogram signal, this application can effectively observe the change of the total impedance of the heart and lungs due to the intensity of breathing, and then change the change value of the total energy of the electrocardiogram signal exchange, and then mark the low ventilation events through the airflow difference feature, with very few missed detection rates and false positives, and at the same time, it also has the characteristics of low computing power and low power consumption, and has the feasibility of a wide range of clinical, health care, and home sleep health monitoring landing application scenarios.

[0209] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4As shown, the electronic device may include: a processor 120, a communication interface 410, a memory 420 and a communication bus 430, wherein the processor 120, the communication interface 410 and the memory 420 communicate with each other through the communication bus 430. The processor 120 may call the logic instructions in the memory 420 to execute a sleep hypoventilation syndrome monitoring method, the method comprising: determining a plurality of hypoventilation characteristic index values ​​based on the electrocardiogram signal; determining an airflow difference characteristic based on the plurality of hypoventilation characteristic index values; and determining a hypoventilation monitoring result based on the airflow difference characteristic.

[0210] In addition, the logic instructions in the above-mentioned memory 420 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0211] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the sleep hypoventilation syndrome monitoring method provided by the above-mentioned methods, and the method includes: determining a number of hypoventilation characteristic index values ​​based on the electrocardiogram signal; determining an airflow difference characteristic based on the number of hypoventilation characteristic index values; and determining a hypoventilation monitoring result based on the airflow difference characteristic.

[0212] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed, implements the method executed by the processor in each of the above-mentioned devices, the method comprising: determining a number of hypoventilation characteristic index values ​​based on the electrocardiogram signal; determining an airflow difference characteristic based on the number of hypoventilation characteristic index values; and determining a hypoventilation monitoring result based on the airflow difference characteristic.

[0213] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0214] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0215] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A sleep hypopnea syndrome monitoring device, characterized in that: include: An electrocardiogram measurement component, used to collect the user's electrocardiogram signal; The processor is used to determine a plurality of hypoventilation characteristic index values ​​based on the electrocardiogram signal, determine an airflow difference characteristic based on the plurality of hypoventilation characteristic index values, and determine a hypoventilation monitoring result based on the airflow difference characteristic.

2. The sleep hypopnea syndrome monitoring device according to claim 1, characterized in that: Determining a plurality of hypoventilation characteristic index values ​​based on the electrocardiogram signal comprises: Filtering the electrocardiogram signal to obtain a target electrocardiogram signal; Dividing the target ECG signal to obtain a plurality of ECG signal segments; The hypoventilation characteristic index value corresponding to each of the plurality of electrocardiogram signal segments is determined.

3. The sleep hypopnea syndrome monitoring device according to claim 2, characterized in that: The step of determining the hypoventilation characteristic index value corresponding to each of the plurality of electrocardiogram signal segments comprises: respectively determining the signal means of the plurality of electrocardiogram signal segments; Based on the mean values ​​of each signal, the hypoventilation characteristic index values ​​corresponding to the plurality of ECG signal segments are calculated respectively.

4. The sleep hypopnea syndrome monitoring device according to claim 2, characterized in that: The filtering process of the electrocardiogram signal to obtain a target electrocardiogram signal includes: Determining a baseline value of each signal data point in the electrocardiogram signal; Based on the baseline value, performing baseline filtering on the electrocardiogram signal to obtain a filtered electrocardiogram signal; The filtered ECG signal is subjected to high-frequency noise reduction processing to obtain the target ECG signal.

5. The sleep hypopnea syndrome monitoring device according to claim 4, characterized in that: The step of performing high frequency noise reduction processing on the filtered ECG signal to obtain the target ECG signal includes: According to a preset time window length, sliding selection is performed in the filtered ECG signal to obtain a plurality of signal data point sequences; respectively determining the signal data point means corresponding to all the signal data points in the plurality of signal data point sequences; Based on the mean value of the signal data points, noise reduction processing is performed on each signal data point in the filtered ECG signal to obtain the target ECG signal.

6. The sleep hypoventilation syndrome monitoring device according to claim 1, characterized in that: The determining of the airflow difference feature based on the plurality of hypoventilation characteristic index values ​​comprises: A first characteristic index sequence and a second characteristic index sequence are selected from the plurality of hypopnea characteristic index values; wherein the hypopnea characteristic index value in the first characteristic index sequence is greater than the hypopnea characteristic index value in the second characteristic index sequence; The airflow difference feature is calculated based on the first feature index sequence and the second feature index sequence.

7. The sleep hypopnea syndrome monitoring device according to claim 6, characterized in that: The step of calculating the airflow difference feature according to the first characteristic index sequence and the second characteristic index sequence includes: Determine a first airflow characteristic mean of all hypopnea characteristic index values ​​in the first characteristic index sequence; Determine a second airflow characteristic mean of all hypopnea characteristic index values ​​in the second characteristic index sequence; The airflow difference feature is calculated based on the first airflow feature mean and the second airflow feature mean.

8. The sleep hypopnea syndrome monitoring device according to claim 6, characterized in that: The step of selecting a first characteristic index sequence and a second characteristic index sequence from the plurality of hypopnea characteristic index values ​​comprises: Sorting the plurality of hypopnea characteristic index values ​​to obtain a sorting result; According to the sorting result, the first characteristic index sequence and the second characteristic index sequence are selected according to a preset selection ratio.

9. The sleep hypopnea syndrome monitoring device according to claim 1, characterized in that: Determining a hypopnea monitoring result based on the airflow difference feature includes: If the airflow difference characteristic is greater than a preset airflow threshold, it is determined that the hypopnea monitoring result is that the user is in a normal sleeping state; If the airflow difference characteristic is less than or equal to a preset airflow threshold, it is determined that the hypoventilation monitoring result is that the user is in a sleep hypoventilation state.

10. The sleep hypopnea syndrome monitoring device according to claim 9, characterized in that: If the airflow difference characteristic is greater than a preset airflow threshold, determining that the hypopnea monitoring result is that the user is in a normal sleeping state includes: If the airflow difference characteristic is greater than a preset airflow threshold, and the airflow difference characteristic is less than an abnormal airflow threshold, it is determined that the hypoventilation monitoring result is that the user is in a normal sleeping state; The determining of the hypopnea monitoring result based on the airflow difference feature further includes: If the airflow difference characteristic is greater than or equal to the abnormal airflow threshold, the hypopnea monitoring result is determined to be an abnormal result; Wherein, the abnormal airflow threshold is greater than the preset airflow threshold.

11. The sleep hypopnea syndrome monitoring device according to any one of claims 1 to 10, characterized in that: The sleep hypoventilation syndrome monitoring device is a wearable device.

12. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the method executed by the processor as claimed in any one of claims 1 to 10 is implemented.

Images