Respiratory event type determination device and method, equipment and medium

Abstract

The invention discloses a respiratory event type determination device and method, equipment and a medium, and relates to the technical field of respiratory event type determination, and the device comprises a data preprocessing module which is used for preprocessing a collected respiratory wave data sequence, and obtaining a normalized target respiratory wave data sequence; the breathing mode determining module is used for judging the breathing mode of each breathing section based on the breathing parameters corresponding to each breathing section and the breathing mode judging conditions; the event proportion calculation module is used for combining a plurality of continuous breathing sections of the same breathing mode to generate a breathing event, and calculating a corresponding time proportion based on a time difference between an event starting point and an event ending point corresponding to the acquired breathing event and the total breathing time; and the event type judgment module is used for comparing a first size relationship between the time proportion and a preset time proportion threshold value, and judging the breathing event type of the breathing event based on a comparison result. The breathing section is determined through the breathing parameters, and breathing events can be marked more easily.

Description

Technical Field

[0001] The present invention relates to the technical field of respiratory event type determination, and in particular to a respiratory event type determination device, method, equipment and medium. Background Art

[0002] At present, a variety of sleep breathing monitoring instruments can be used to monitor the sleep process, thereby helping users to know whether there is sleep apnea disorder during sleep. Commonly used sleep breathing monitoring methods include using a polysomnography monitor to analyze and diagnose obstructive sleep apnea by wearing a nasal cannula, and using finger photoelectric volume pulse wave or other non-contact methods to indirectly detect sleep breathing. Such indirect detection methods have low accuracy and cannot meet the needs of hospital detection and diagnosis.

[0003] When using a polysomnography monitor for monitoring, the existing methods for determining the type of apnea events have the following problems: in the technology of using respiratory flow signals to determine apnea events, the information extraction and subsequent processing contained in a single respiratory flow signal are not sufficient, resulting in low accuracy in determining apnea events; and in the technology of using the variance of short-term and long-term respiratory flow signals to determine apnea events, it is necessary to store the variance information of the respiratory flow signal for a long period of time at each moment, and the algorithm is very complex and not easy to implement.

[0004] In summary, how to accurately determine the type of respiratory event based on the respiratory flow signal of any time period, improve the accuracy of event marking of respiratory wave signals, and achieve event marking without recording respiratory flow signals for a long period of time are technical problems to be solved in this field. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide a respiratory event type determination device, method, equipment and medium, which can accurately determine the respiratory event type based on the respiratory flow signal of any period, improve the accuracy of event marking of respiratory wave signals, and can also mark events without recording respiratory flow signals for a long period of time. The specific scheme is as follows:

[0006] In a first aspect, the present application discloses a respiratory event type determination device, comprising:

[0007] A data preprocessing module is used to preprocess the collected respiratory wave data sequence to obtain a normalized target respiratory wave data sequence;

[0008] A breathing mode determination module, used to determine the breathing mode of each breathing segment based on the starting point, ending point, amplitude value, stable value and breathing mode determination conditions corresponding to each breathing segment;

[0009] An event proportion calculation module is used to merge multiple continuous breathing segments corresponding to the same breathing mode to generate corresponding breathing events, and calculate the event start point and event end point of the breathing event corresponding to each breathing event, so as to calculate the time proportion corresponding to each breathing event based on the time difference between the event start point and the event end point and the total breathing time;

[0010] The event type determination module is used to compare the first size relationship between each time proportion and a preset time proportion threshold, and determine the respiratory event type to which the respiratory event belongs based on the comparison result.

[0011] Optionally, the data preprocessing module includes:

[0012] A data filtering unit, used for performing high-pass filtering and low-pass filtering on the collected respiratory wave data sequence to obtain a filtered first respiratory wave data sequence and a maximum value point, a minimum value point and an average value point of the first respiratory wave data sequence;

[0013] a threshold calculation unit, configured to respectively set an upper threshold ratio and a lower threshold ratio based on the maximum value point, the minimum value point and the average value point, so as to calculate an upper threshold and a lower threshold of the first respiratory wave data sequence based on the maximum value point, the minimum value point, the gain value, the upper threshold ratio and the lower threshold ratio;

[0014] A data normalization unit is used to calculate and normalize the first respiratory wave sequence according to the first respiratory wave data sequence, the upper threshold, the lower threshold, the size relationship between the first respiratory wave data sequence and the upper threshold as a first calculation condition, and the size relationship between the first respiratory wave data sequence and the lower threshold as a second calculation condition to obtain a target respiratory wave data sequence.

[0015] Optionally, the breathing mode determination module includes:

[0016] A breathing segment determination submodule, used to traverse the target breathing wave data sequence, screen the index points used to determine the breathing segments, and segmentally determine the breathing mode of the target breathing wave data sequence based on the index points to obtain the inhalation segment, the exhalation segment, the slow breathing segment, and the start point, end point and amplitude value of each breathing segment;

[0017] The stability value calculation submodule is used to calculate the inhalation segment breathing stability line and / or the exhalation segment breathing stability line based on the corresponding amplitude values ​​of the inhalation segment and / or the exhalation segment, and determine the corresponding inhalation segment breathing stability value and / or the exhalation segment breathing stability value based on the inhalation segment breathing stability line and / or the exhalation segment breathing stability line.

[0018] Optionally, the respiratory event type determination device further includes:

[0019] The first sequence definition unit is used to define an inhalation segment sequence, an exhalation segment sequence, and a slow breathing segment sequence, and respectively set the start point parameters, end point parameters, and amplitude values ​​of the inhalation segment sequence, the exhalation segment sequence, and the slow breathing segment sequence;

[0020] a second sequence definition unit, configured to define an initial upper baseline sequence and an initial lower baseline sequence and a data analysis window of a preset time period, traverse the target respiratory wave data sequence using the data analysis window, and calculate a first average value of the target respiratory wave data sequence greater than zero, so as to determine an initial upper baseline sequence value based on the first average value; and calculate a second average value of the target respiratory wave data sequence less than zero, so as to determine an initial lower baseline sequence value based on the second average value;

[0021] The third sequence definition unit is used to define a new upper baseline sequence and a new lower baseline sequence, and use the new upper baseline sequence to traverse and linearly interpolate the initial upper baseline sequence value according to the number of sampling points corresponding to the preset time period to obtain a new upper baseline sequence value; use the new lower baseline sequence to traverse and linearly interpolate the initial lower baseline sequence value according to the number of sampling points corresponding to the preset time period to obtain a new lower baseline sequence value.

[0022] Optionally, the breathing segment determination submodule includes:

[0023] An index point determination unit is used to traverse all sampling points of the target respiratory wave data sequence, and set the current sampling point as the index point during the traversal process, and compare the second size relationship between the sequence value of the index point and the new upper baseline sequence value; if the second size relationship is that the sequence value of the index point is greater than the new upper baseline sequence value, then set the index point as the index point starting point, and based on the index starting point, traverse forward and / or backward in sequence to find other index points for determining the respiratory segment;

[0024] The breathing segment determination unit is used to segmentally determine the breathing mode of the target breathing wave data sequence based on all index points to obtain the inhalation segment, the exhalation segment, the slow breathing segment, and the start point, the end point and the amplitude value of each breathing segment.

[0025] Optionally, the stable value calculation submodule includes:

[0026] The stable value calculation unit is used to set a stable value analysis window, calculate the coefficient of variation of the amplitude value in the time period of half the stable value analysis window before and after the sampling point in the inhalation segment and / or the exhalation segment, if the coefficient of variation is less than a preset coefficient of variation threshold, then the average amplitude in the stable value analysis window is used as the inhalation segment breathing stable value and / or the exhalation segment breathing stable value; if the coefficient of variation is greater than or equal to the preset coefficient of variation threshold, then the last inhalation segment stable value and / or exhalation segment stable value is used as the inhalation segment breathing stable value and / or exhalation segment breathing stable value.

[0027] The respiratory event type determination device further includes:

[0028] An index calculation unit is used to obtain the total number of apnea events, the total number of hypopnea events, and the total number of hours of sleep duration; and determine the sleep apnea-hypopnea index based on the ratio index of the sum of the total number of apnea events and the total number of hypopnea events to the total number of hours of sleep duration.

[0029] In a second aspect, the present application discloses a method for determining a respiratory event type, comprising:

[0030] Preprocessing the collected respiratory wave data sequence to obtain a normalized target respiratory wave data sequence;

[0031] Determine the breathing mode of each breathing segment based on the starting point, ending point, amplitude value, stable value and breathing mode determination condition corresponding to each breathing segment;

[0032] Merging multiple continuous breathing segments corresponding to the same breathing mode to generate corresponding breathing events, and calculating the event start point and event end point of the breathing event corresponding to each breathing event, so as to calculate the time proportion corresponding to each breathing event based on the time difference between the event start point and the event end point and the total breathing time;

[0033] The first magnitude relationship between each time proportion and a preset time proportion threshold is compared, and the respiratory event type to which the respiratory event belongs is determined based on the comparison result.

[0034] In a third aspect, the present application discloses an electronic device, comprising:

[0035] Memory, used to store computer programs;

[0036] The processor is used to execute the computer program to implement the steps of the respiratory event type determination method disclosed above.

[0037] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the steps of the respiratory event type determination method disclosed above are implemented.

[0038] It can be seen that the present application discloses a device for determining the type of respiratory event, including: a data preprocessing module, which is used to preprocess the collected respiratory wave data sequence to obtain a normalized target respiratory wave data sequence; a respiratory mode determination module, which is used to determine the respiratory mode of each respiratory segment based on the start point, end point, amplitude value, stability value and respiratory mode determination condition corresponding to each respiratory segment; an event proportion calculation module, which is used to merge multiple continuous respiratory segments corresponding to the same respiratory mode, generate corresponding respiratory events, and calculate the event start point and event end point of the respiratory event corresponding to each respiratory event, so as to calculate the time proportion corresponding to each respiratory event based on the time difference between the event start point and the event end point and the total respiratory time; an event type judgment module, which is used to compare the first size relationship between each time proportion and a preset time ratio threshold, and determine the respiratory event type to which the respiratory event belongs based on the comparison result. It can be seen that by analyzing the collected target respiratory wave data sequence in segments, and determining the starting point, ending point, amplitude value and stable value corresponding to each respiratory segment, and then judging the respiratory mode of each respiratory segment according to the set respiratory mode judgment conditions, the continuous respiratory segments corresponding to the same respiratory mode are further merged to form corresponding respiratory wave events, and then the event type of each respiratory wave event is judged by the preset threshold value for each respiratory wave event. The respiratory segment is determined by determining the above four parameters, which makes it easier to mark the respiratory event. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0040] Figure 1 This is a schematic diagram of the structure of a respiratory event type determination device disclosed in this application;

[0041] Figure 2 This is a schematic diagram of the structure of a specific respiratory event type determination device disclosed in this application;

[0042] Figure 3 A schematic diagram for searching and determining each index point in a normal exhalation segment disclosed in the present application;

[0043] Figure 4A flow chart of a method for determining a respiratory event type disclosed in the present application;

[0044] Figure 5 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only 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 making creative work are within the scope of protection of the present invention.

[0046] At present, a variety of sleep breathing monitoring instruments can be used to monitor the sleep process, thereby helping users to know whether there is sleep apnea disorder during sleep. Commonly used sleep breathing monitoring methods include using a polysomnography monitor to analyze and diagnose obstructive sleep apnea by wearing a nasal cannula, and using finger photoelectric volume pulse wave or other non-contact methods to indirectly detect sleep breathing. Such indirect detection methods have low accuracy and cannot meet the needs of hospital detection and diagnosis.

[0047] When using a polysomnography monitor for monitoring, the existing methods for determining the type of apnea events have the following problems: in the technology of using respiratory flow signals to determine apnea events, the information extraction and subsequent processing contained in a single respiratory flow signal are not sufficient, resulting in low accuracy in determining apnea events; and in the technology of using the variance of short-term and long-term respiratory flow signals to determine apnea events, it is necessary to store the variance information of the respiratory flow signal for a long period of time at each moment, and the algorithm is very complex and not easy to implement.

[0048] To this end, the present application provides a respiratory event type determination scheme, which can achieve accurate determination of the respiratory event type based on the respiratory flow signal of any time period, improve the accuracy of event marking of respiratory wave signals, and achieve event marking without recording respiratory flow signals for a long period of time.

[0049] Reference Figure 1 As shown, an embodiment of the present invention discloses a respiratory event type determination device, comprising:

[0050] The data preprocessing module 11 is used to preprocess the collected respiratory wave data sequence to obtain a normalized target respiratory wave data sequence;

[0051] A breathing mode determination module 12, for determining the breathing mode of each breathing segment based on the start point, end point, amplitude value, stability value and breathing mode determination condition corresponding to each breathing segment;

[0052] An event proportion calculation module 13 is used to merge multiple continuous breathing segments corresponding to the same breathing mode to generate corresponding breathing events, and calculate the event start point and event end point of the breathing event corresponding to each breathing event, so as to calculate the time proportion corresponding to each breathing event based on the time difference between the event start point and the event end point and the total breathing time;

[0053] The event type determination module 14 is used to compare a first size relationship between each time proportion and a preset time proportion threshold, and determine the respiratory event type to which the respiratory event belongs based on the comparison result.

[0054] The data preprocessing module 11 includes:

[0055] A data filtering unit, used for performing high-pass filtering and low-pass filtering on the collected respiratory wave data sequence to obtain a filtered first respiratory wave data sequence and a maximum value point, a minimum value point and an average value point of the first respiratory wave data sequence;

[0056] a threshold calculation unit, configured to respectively set an upper threshold ratio and a lower threshold ratio based on the maximum value point, the minimum value point and the average value point, so as to calculate an upper threshold and a lower threshold of the first respiratory wave data sequence based on the maximum value point, the minimum value point, the gain value, the upper threshold ratio and the lower threshold ratio;

[0057] A data normalization unit is used to calculate and normalize the first respiratory wave sequence according to the first respiratory wave data sequence, the upper threshold, the lower threshold, the size relationship between the first respiratory wave data sequence and the upper threshold as a first calculation condition, and the size relationship between the first respiratory wave data sequence and the lower threshold as a second calculation condition to obtain a target respiratory wave data sequence.

[0058] The respiratory event type determination device further includes:

[0059] An index calculation unit is used to obtain the total number of apnea events, the total number of hypopnea events, and the total number of hours of sleep duration; and determine the sleep apnea-hypopnea index based on the ratio index of the sum of the total number of apnea events and the total number of hypopnea events to the total number of hours of sleep duration.

[0060] It can be understood that the data preprocessing module 11 preprocesses the collected respiratory wave data sequence to remove oscillation interference and useless and messy respiratory wave data sequence, and then normalizes the filtered respiratory wave data sequence to obtain the target respiratory wave data sequence. Among them, in the data preprocessing module 11, the data filtering unit specifically performs a filtering processing operation. Specifically, the data filtering unit performs high-pass filtering at a preset high-pass cutoff frequency on the collected respiratory wave data sequence, and also performs low-pass filtering at a preset low-pass cutoff frequency to obtain a respiratory wave data sequence between the two cutoff frequencies. For example: using Butterworth (Butterworth filter) to perform IIR filtering on the respiratory wave data sequence, wherein the low-pass cutoff frequency is 1.1 Hz, that is, filtering out useless respiratory wave data sequences greater than 1.1 Hz; performing IIR filtering on the respiratory wave data sequence, wherein the high-pass cutoff frequency is 0.1 Hz, that is, filtering out useless respiratory wave data sequences less than 0.1 Hz. In this way, a first respiratory wave data sequence flowdata that has been filtered is obtained, that is, a respiratory wave data sequence between 0.1 Hz and 1 Hz, and then the maximum value point maxval and the minimum value point minval of the first respiratory wave data sequence flowdata are obtained, and the average value point avgval is further obtained based on the first respiratory wave data sequence.

[0061] The threshold value calculation unit in the data preprocessing module 11 is used to further determine the upper threshold value and the lower threshold value of the first respiratory wave data sequence, wherein the process of determining the upper and lower threshold values ​​of the first respiratory wave data sequence is as follows: define the initial gain value agg = 1.0; if the difference between the maximum value point maxval and the minimum value point minval of the first respiratory wave data sequence flowdata is less than 100, it is considered that the data has no respiratory signal and the analysis ends. If the difference between the maximum values ​​amp1 exceeds 100, the gain value agg is set according to the following table.

[0062] Table 1

[0063] The difference between the maximum and minimum values ​​amp1 Gain value agg amp1<100 0 amp1>5000 0.3 amp1>4000 0.4 amp1>3000 0.5 amp1>2000 0.6 amp1>1000 0.7 amp1>500 0.8 100<amp1<500 1

[0064] Set the upper threshold ratio value f1 and the lower threshold ratio value f2 of the first respiratory wave data sequence flowdata; wherein f1 and f2 are calculated as follows:

[0065] f1=(maxval-avgval)(maxval-minval);

[0066] f2=(avgval-minval)(maxval-minval);

[0067] Furthermore, an upper threshold ratio value threshold1 and a lower threshold ratio value threshold2 are defined.

[0068] If f1>0.9, set threshold1=0.3, threshold2=1;

[0069] If f1>0.8, set threshold1=0.4, threshold2=1;

[0070] If f1>0.7, set threshold1=0.5, threshold2=1;

[0071] If f1>0.6, set threshold1=0.6, threshold2=1;

[0072] If f1>0.5, set threshold1=1, threshold2=1;

[0073] If f1>0.4, set threshold1=1, threshold2=0.6;

[0074] If f1>0.3, set threshold1=1, threshold2=0.5;

[0075] If f1>0.2, set threshold1=1, threshold2=0.4;

[0076] If f1>0.1, set threshold1=1, threshold2=0.3;

[0077] Correspondingly, the upper threshold of the first respiratory wave data sequence is p1, and the lower threshold is p2. Then the formulas for determining the upper threshold and the lower threshold are as follows:

[0078] p1=avgval+threshold1×agg×(maxval-avgval);

[0079] p2=avgval-threshold2×agg×(avgval-minval);

[0080] After calculating the upper and lower thresholds of the first respiratory wave data sequence, the second respiratory wave data sequence is defined as Data[i]. The calculation formula of Data[i] is as follows:

[0081] Traverse the first respiratory wave data sequence flowdata. If the value flowdata[i] is greater than the upper threshold p1, the calculation formula of Data[i] is as follows:

[0082]

[0083] Traverse the first respiratory wave data sequence flowdata. If the value flowdata[i] is less than the lower threshold p2, the calculation formula of Data[i] is as follows:

[0084]

[0085] Based on the calculated second respiratory wave data sequence Data[i], the maximum value maxval2 and the minimum value minval2 of the second respiratory wave data sequence Data[i] are further obtained, and the data Data[i] is normalized to [-50,50]

[0086] The normalized calculation formula is as follows:

[0087] Data[i]=100×Data[i](maxval2-minval2);

[0088] The normalized Data[i] is the target respiratory wave data sequence.

[0089] After the target respiratory wave data sequence is obtained by processing the respiratory wave data sequence through the data preprocessing module 11, each respiratory segment and the four respiratory parameters corresponding to each respiratory segment, namely the starting point, the ending point, the amplitude value and the stable value, are searched through the respiratory mode determination module 12. After the respiratory parameters corresponding to each respiratory segment are found, the respiratory mode of each respiratory segment is determined. The respiratory modes may include: exhalation, inhalation and slow breathing.

[0090] The event proportion calculation module 13 is used to merge multiple continuous breathing segments corresponding to the same breathing mode. For example, when the target respiratory wave data sequence is divided into 8 breathing segments, it is found that the breathing modes of the first to third breathing segments are all inhalation according to the breathing mode. Then, when the breathing segments are merged, the three breathing segments from the first to the third breathing segments are merged together, and then the event start point and event end point of the merged breathing segment are determined. Specifically, the conditions for determining the event start point and the event end point are as follows: determine whether the amplitude value of the currently merged breathing segment meets the low ventilation threshold condition. If so, mark the start point of the breathing segment as the event start point of the respiratory event, and traverse each of the above breathing segments until the amplitude values ​​of a preset number of breathing segments do not meet the low ventilation threshold condition, and the end point of the last breathing segment is greater than the end time point of the preset breathing time + 2 seconds, it is determined that the respiratory events are ended in sequence, and the event end point is updated. Calculate the time difference between the event start point and the event end point, traverse and calculate the time difference of the breathing segments corresponding to the different breathing event type conditions of the entire target breathing data sequence, and calculate the time proportion of the total breathing time occupied by different breathing events. Specifically, the exhalation segment sequence Exppart, the inhalation segment sequence Inspart, and the slow breathing segment sequence Zeropart are rearranged one by one in sequence according to the time point of their start, and recorded as the Flow sequence.

[0091] Define the respiratory event sequence Apnea and the respiratory event sequence Hyponea. The parameters of the respiratory event sequence are the starting time point, the ending time point, and the respiratory event type, where the Apnea sequence is an apnea event sequence and the Hyponea is a hypopnea event sequence. Traverse the {Flow} sequence one by one and determine the respiratory event according to the following judgment conditions. The starting condition of the respiratory event: the amplitude value of the current respiratory segment meets the hypopnea threshold condition (lower than 0.5 times the normal respiratory amplitude value). If it meets the condition, the starting point of the segment is marked as the starting time point of the respiratory event, and the ending point of the segment is the ending position of the respiratory event. Traverse each respiratory segment sequence one by one and update the ending time point of the respiratory event. The ending condition of the respiratory event: if the amplitude values ​​of three consecutive respiratory segments (expiratory segments or inspiratory segments) in the sequence do not meet the hypopnea threshold condition, and the ending point of the third respiratory segment is greater than the ending time point of the respiratory event currently analyzed + 2 seconds, then it is determined that the search for a respiratory event is over. When the search for respiratory events is completed, the time difference totaltime from the start time point to the end time point of the respiratory event is calculated, and the total time length apneatime of the respiratory segments that meet the apnea threshold condition, the total time length hyponeatime of the respiratory segments that meet the hypopnea threshold condition, and the total time length resptime of the respiratory segments of normal breathing are calculated.

[0092] The event type judgment module 14 determines the respiratory event type to which the respiratory event belongs. Specifically, when the time proportion meets the preset time proportion threshold of a certain respiratory event type, and the time length occupied by the time difference meets the preset respiratory duration of the same respiratory event type, the type of the respiratory time is determined to be the respiratory event type, wherein the respiratory event type may specifically include: apnea type, hypopnea type, and normal breathing type. For example: if the time proportion occupied by apnea and hypopnea exceeds 0.5, that is, (apneatime+hyponeatime)totaltime>0.5 and apneatime>hyponeatime and the length of the respiratory event meets the preset duration condition, that is, the duration is at least greater than 10 seconds. If satisfied, the respiratory event type of this respiratory event is determined to be an apnea type and is included in the Apnea sequence. If the time ratio of apnea and hypopnea time exceeds 0.5, that is, (apneatime+hyponeatime)totaltime>0.5 and hyponeatime>apneatime and the length of the respiratory event meets the set conditions, that is, the duration is at least greater than 10 seconds, then the respiratory event type of this respiratory event is determined to be a hypopnea type and is included in the Hyponea sequence.

[0093] The AHI (Apnea Hypopnea Index) sleep apnea hypopnea index is calculated by the index calculation unit. The calculation formula is as follows:

[0094] AHI = (total number of apnea events + total number of hypopnea events) / number of hours of sleep throughout the night;

[0095] The apnea-hypopnea index is further calculated and obtained through the above calculation formula. In this way, since sleep apnea is a respiratory disorder, it refers to more than 30 apneas in continuous Th sleep, each airflow cessation is more than 10s (including 10s), or the average number of hypoventilations per hour exceeds 5 times, that is, the number of respiratory disorders exceeds 5 times, thereby causing a clinical syndrome of chronic hypoxemia and hypercapnia. By briefly obtaining the apnea-hypopnea index as mentioned above, it is convenient for users with sleep breathing disorders to obtain accurately calculated AHI in the case where it is difficult for them to independently perceive the time and severity of apnea, which further facilitates timely detection of problems and timely treatment and improvement.

[0096] It can be seen that the present application discloses a device for determining the type of respiratory event, including: a data preprocessing module, which is used to preprocess the collected respiratory wave data sequence to obtain a normalized target respiratory wave data sequence; a respiratory mode determination module, which is used to determine the respiratory mode of each respiratory segment based on the start point, end point, amplitude value, stability value and respiratory mode determination condition corresponding to each respiratory segment; an event proportion calculation module, which is used to merge multiple continuous respiratory segments corresponding to the same respiratory mode, generate corresponding respiratory events, and calculate the event start point and event end point corresponding to each respiratory event, so as to calculate the time proportion corresponding to each respiratory event based on the time difference between the event start point and the event end point and the total respiratory time; an event type judgment module, which is used to compare the first size relationship between each time proportion and a preset time ratio threshold, and determine the respiratory event type to which the respiratory event belongs based on the comparison result. It can be seen that by analyzing the collected target respiratory wave data sequence in segments, and determining the starting point, ending point, amplitude value and stable value corresponding to each respiratory segment, and then judging the respiratory mode of each respiratory segment according to the set respiratory mode judgment conditions, the continuous respiratory segments corresponding to the same respiratory mode are further merged to form corresponding respiratory wave events, and then the event type of each respiratory wave event is judged by the preset threshold value for each respiratory wave event. The respiratory segment is determined by determining the above four parameters, which makes it easier to mark the respiratory event.

[0097] Reference Figure 2 As shown, the embodiment of the present invention discloses a specific respiratory event type determination device. Compared with the previous embodiment, this embodiment further illustrates and optimizes the technical solution. Specifically:

[0098] The respiratory event type determination device further includes:

[0099] The first sequence definition unit is used to define an inhalation segment sequence, an exhalation segment sequence, and a slow breathing segment sequence, and respectively set the start point parameters, end point parameters, and amplitude values ​​of the inhalation segment sequence, the exhalation segment sequence, and the slow breathing segment sequence;

[0100] a second sequence definition unit, configured to define an initial upper baseline sequence and an initial lower baseline sequence and a data analysis window of a preset time period, traverse the target respiratory wave data sequence using the data analysis window, and calculate a first average value of the target respiratory wave data sequence greater than zero, so as to determine an initial upper baseline sequence value based on the first average value; and calculate a second average value of the target respiratory wave data sequence less than zero, so as to determine an initial lower baseline sequence value based on the second average value;

[0101] The third sequence definition unit is used to define a new upper baseline sequence and a new lower baseline sequence, and use the new upper baseline sequence to traverse and linearly interpolate the initial upper baseline sequence value according to the number of sampling points corresponding to the preset time period to obtain a new upper baseline sequence value; use the new lower baseline sequence to traverse and linearly interpolate the initial lower baseline sequence value according to the number of sampling points corresponding to the preset time period to obtain a new lower baseline sequence value.

[0102] The breathing mode determination module 12 comprises:

[0103] A breathing segment determination submodule 121 is used to traverse the target breathing wave data sequence, screen the index points used to determine the breathing segments, and segmentally determine the breathing mode of the target breathing wave data sequence based on the index points to obtain the inhalation segment, the exhalation segment, the slow breathing segment, and the start point, end point and amplitude value of each breathing segment;

[0104] The stability value calculation submodule 122 is used to calculate the inhalation segment breathing stability line and / or the exhalation segment breathing stability line based on the corresponding amplitude values ​​of the inhalation segment and / or the exhalation segment, and determine the corresponding inhalation segment breathing stability value and / or the exhalation segment breathing stability value based on the inhalation segment breathing stability line and / or the exhalation segment breathing stability line.

[0105] The breathing segment determination submodule 121 includes:

[0106] An index point determination unit 1211 is used to traverse all sampling points of the target respiratory wave data sequence, and set the current sampling point as the index point during the traversal process, and compare the second size relationship between the sequence value of the index point and the new upper baseline sequence value; if the second size relationship is that the sequence value of the index point is greater than the new upper baseline sequence value, then set the index point as the index point starting point, and traverse forward and / or backward in sequence based on the index starting point to find other index points for determining the respiratory segment;

[0107] The breathing segment determination unit 1212 is used to segmentally determine the breathing mode of the target breathing wave data sequence based on all index points to obtain the inhalation segment, the exhalation segment, the slow breathing segment, and the start point, end point and amplitude value of each breathing segment.

[0108] The stability value calculation submodule 122 includes:

[0109] The stable value calculation unit 1221 is used to set a stable value analysis window, calculate the coefficient of variation of the amplitude value in the time period of half the stable value analysis window before and after the sampling point in the inhalation segment and / or the exhalation segment, if the coefficient of variation is less than a preset coefficient of variation threshold, then the average amplitude in the stable value analysis window is used as the inhalation segment breathing stable value and / or the exhalation segment breathing stable value; if the coefficient of variation is greater than or equal to the preset coefficient of variation threshold, then the last inhalation segment stable value and / or exhalation segment stable value is used as the inhalation segment breathing stable value and / or exhalation segment breathing stable value.

[0110] In this embodiment, the first sequence definition unit is used to define three breathing modes: exhalation Exp, inhalation Ins, and slow breathing Zero. Each breathing mode has four parameters, namely, the starting point, the ending point, the amplitude value, and the stable value. The exhalation segment sequence Exppart, the inhalation segment sequence Inspart, and the slow breathing segment sequence Zeropart are defined. After the first three parameters of each sequence, the starting point, the ending point, and the amplitude value are obtained, the sequence index value is incremented by 1, and each sequence is filled in sequence. The initial upper baseline sequence baselineup and the initial lower baseline sequence baselinedown are defined by the second sequence definition unit, and the 5-second target respiratory wave data sequence is set as a data analysis window. The target respiratory wave data sequence Data is traversed through each data analysis window one by one. The average meanUp of the partial values ​​greater than 0 in the data analysis window is taken, and the average meanDown of the distribution values ​​less than 0 is taken. The upper baseline baselineup(k) value is set to 0.6×meanUp, and the lower baseline value baselinedown(k) is set to 0.6×meanDown, and k is the maximum number from 0 to the data analysis window.

[0111] The third sequence definition unit is used to define a new upper baseline sequence as baseup. The sequence value is the result of linear interpolation of the baselineup sequence. The specific steps are to traverse the baselineup sequence point by point, and insert the number of Data sampling points under the 5-second data analysis window between the two points (k, k+1) of the sequence baselineup. The interpolation formula is as follows, which ensures that the number of sampling points in the baseup sequence is consistent with the number of sampling points in the Data sequence.

[0112] baseup[i]=(baselineup[k+1]-baselineup[k])(f s ×5)×(ik×f s ×5)+baselineup[k×f s ×5]

[0113] Among them, i∈(k×f s ×5, (k+1)×fs ×5), f s is the sampling rate of the Data data; at the same time, a new baseline sequence basedown is defined, and the sequence value selection method is the same as the baseup sequence.

[0114] The index point determination unit 1211 of the breathing segment determination submodule 121 is used to traverse the Data data sample by sample point, set the current index point as the index point starting point, and traverse forward based on the index point starting point to find the second index point that is initially less than the new lower baseline sequence value, and find the third index point between the index starting point and the second index point that is initially greater than the new upper baseline sequence value; based on the index point starting point, traverse backward to find the fourth index point that is initially less than the new upper baseline sequence value, based on the fourth index point, traverse backward to find the fifth index point that is initially less than the new lower baseline sequence value, and based on the fourth index point, traverse backward to find the sixth index point that is initially greater than the new upper baseline sequence value. Specifically, refer to Figure 3 As shown, set the current index point to index. If Data[index] is greater than baseup[index], set the current point to A1. Traverse forward from A1 to find the first index point that is less than the corresponding basedown, set the index point to B1, and in the interval from B1 to A1, find the first index point that is greater than the corresponding baseup, set the index point to B2. Traverse backward from A1 to find the first index point that is less than the corresponding baseup, set the index point to B3, and traverse backward from B3 to find the first index point that is less than basedown, set the index point to B4, and traverse backward from B3 to find the first index point that is greater than baseup, set the index point to B5.

[0115] The breathing segment determination unit 1212 is used to traverse the breathing segments. Specifically, after screening B1, B2, B3, B4, and B5, the data is traversed sequentially from segment B1 to B2. The point where the value is first greater than 0 is set as the start point of the expiration segment Exppart. If B5 > B4, the data is traversed sequentially from segment B3 to B4, and the point where the value is first less than 0 is set as the end point of the expiration segment Exppart. If B5 < B4, point B3 is set as the end point of the expiration segment Exppart. The expiration amplitude value of the expiration segment Exppart is defined as the maximum value between the expiration start point and the expiration end point. If B5 < B4 and the sampling point distance from B3 to B5 is greater than 1 second, then the segment [B3, B5] is set as the slow breathing segment Zeropart, and the amplitude value of this segment is the average amplitude value of [B3, B5]. If B5 > B4 and the sampling point distance of the segment [B3, B4] is greater than 1 second, then the segment [B3, B4] is set as the slow breathing segment Zeropart, and the amplitude value of this segment is the average amplitude value of [B3, B4]. If the sampling point distance of the segment [B1, B2] is greater than 1 second, then the segment [B1, B2] is set as the slow breathing segment Zeropart, and the amplitude value of this segment is the average amplitude value of [B1, B2]. A similar search method is used for the inspiration segment Inspart, and the steps performed by the above-mentioned breathing segment determination sub-module 121 are repeated.

[0116] The breathing stability value calculation unit 1221 calculates the breathing stability values of each breathing segment. Specifically, according to the amplitude values of the inspiration segment sequence Inspart and the expiration segment Exppart, the inspiration segment breathing stability line and the expiration segment breathing stability line are calculated. The specific steps are as follows: Traverse the data of the inspiration segment sequence Inspart sequentially, set the analysis window to 1 minute, and calculate the coefficient of variation of the amplitude value sequence in the inspiration segment sequence within the previous and subsequent 0.5 minutes at this sampling point. If the coefficient of variation is less than 0.6, then the average amplitude value of the inspiration segment sequence Inspart within this window is used as the fourth breathing parameter in the inspiration segment sequence Inspart: the stability value. If the coefficient of variation is greater than or equal to 0.6, then the stability value of the previous inspiration segment is taken as the stability value of the current inspiration segment. The expiration segment Expstable sequence is defined. The determination of its stability value is similar to the determination of the stability value of the inspiration segment Insstable. Analyze the expiration segment sequence Exppart. The breathing stability value of the slow breathing segment sequence Zeropart is defaulted to 100.

[0117] It can be seen that by searching for the respiratory wave, that is, by segmented analysis of the exhalation segment Exp, the inhalation segment Ins, and the slow breathing segment Zero, the first three respiratory parameters of each respiratory wave are determined, and then the stable value of the respiratory wave, that is, the fourth respiratory parameter of the respiratory wave, is further determined. Then, the final respiratory wave is determined based on the above four respiratory parameters, which makes it easier to mark respiratory events, and further judge the respiratory event by the respiratory event type judgment condition threshold, and judge whether the breathing belongs to the apnea type or the hypopnea type, which makes the judgment more accurate, and then record the results. In a simple way, the type of respiratory event can be accurately judged based on partial respiratory wave data.

[0118] Reference Figure 4 As shown, the embodiment of the present invention also discloses a method for determining the type of respiratory event, including:

[0119] Step S11: pre-processing the collected respiratory wave data sequence to obtain a normalized target respiratory wave data sequence.

[0120] In this embodiment, the collected respiratory wave data sequence is preprocessed, useless and messy respiratory wave data sequences are filtered out by a filter, and normalization is performed to obtain a target respiratory wave data sequence. It should be noted that normalization makes data analysis more targeted and the results more accurate.

[0121] Step S12: Determine the breathing mode of each breathing segment based on the starting point, ending point, amplitude value, stable value and breathing mode determination conditions corresponding to each breathing segment.

[0122] In this embodiment, each breathing segment is obtained by segmenting the target breathing wave sequence, and then the starting point, end point, amplitude value and stable value corresponding to each breathing segment are obtained, and the breathing mode of each breathing segment is determined by the breathing mode determination condition. The breathing mode may specifically include: inhalation, exhalation and slow breathing.

[0123] Step S13: Merge multiple continuous breathing segments corresponding to the same breathing mode to generate corresponding breathing events, and calculate the event start point and event end point corresponding to each breathing event, so as to calculate the time proportion corresponding to each breathing event based on the time difference between the event start point and the event end point and the total breathing time.

[0124] In this embodiment, continuous breathing segments are traversed and analyzed, and combined to generate breathing events, that is, by segmented analysis of the exhalation segment Exp, the inhalation segment Ins, and the slow breathing segment Zero, and by the above four breathing parameters, that is, the starting point, the end point, the amplitude value, and the stable value, the breathing wave is finally determined, which makes it easier to mark the breathing events. At the same time, the time proportion of each breathing event is calculated and counted.

[0125] Step S14: comparing a first size relationship between each time proportion and a preset time proportion threshold, and determining the respiratory event type to which the respiratory event belongs based on the comparison result.

[0126] In this embodiment, the time proportion of each respiratory event is judged based on the judgment condition threshold corresponding to each respiratory event type, the preset time ratio threshold and other threshold judgment conditions, and the respiratory event type described by each respiratory event is determined based on the comprehensive judgment result.

[0127] It can be seen that the present application discloses preprocessing the collected respiratory wave data sequence to obtain a normalized target respiratory wave data sequence; determining the respiratory mode of each respiratory segment based on the starting point, ending point, amplitude value, stable value and respiratory mode determination conditions corresponding to each respiratory segment; merging multiple continuous respiratory segments corresponding to the same respiratory mode to generate corresponding respiratory events, and calculating the event starting point and event ending point corresponding to each respiratory event, so as to calculate the time proportion corresponding to each respiratory event based on the time difference between the event starting point and the event ending point and the total respiratory time; comparing the first size relationship between each time proportion and the preset time ratio threshold, and determining the respiratory event type to which the respiratory event belongs based on the comparison result. It can be seen that by analyzing the collected target respiratory wave data sequence in segments, and determining the starting point, ending point, amplitude value and stable value corresponding to each respiratory segment, and then determining the respiratory mode of each respiratory segment according to the set respiratory mode determination conditions, further merging the continuous respiratory segments corresponding to the same respiratory mode to form corresponding respiratory wave events, and then determining the event type of each respiratory wave event by the preset threshold for each respiratory wave event, and determining the respiratory segment by determining the above four parameters, it is easier to mark the respiratory event.

[0128] Furthermore, the present application also discloses an electronic device. Figure 5 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0129] Figure 5 A schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the respiratory event type determination method disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0130] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0131] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0132] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0133] Among them, the operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20, so as to realize the operation and processing of the massive data 223 in the memory 22 by the processor 21, which can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program that can be used to complete the respiratory event type determination method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks. In addition to data transmitted from an external device received by the electronic device, the data 223 can also include data collected by its own input and output interface 25, etc.

[0134] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the aforementioned disclosed method for determining the type of respiratory event is implemented. The specific steps of the method may refer to the corresponding contents disclosed in the aforementioned embodiments, and will not be described in detail here.

[0135] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0136] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application. The steps of the method or algorithm described in conjunction with the embodiments disclosed herein can be directly implemented with a software module executed by a hardware or processor, or a combination of the two. The software module can be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0137] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0138] The above is a detailed introduction to a respiratory event type determination device, method, equipment and medium provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for a person skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A respiratory event type determination device, characterized in that: include: A data preprocessing module is used to preprocess the collected respiratory wave data sequence to obtain a normalized target respiratory wave data sequence; A breathing mode determination module, used to determine the breathing mode of each breathing segment based on the starting point, ending point, amplitude value, stable value and breathing mode determination conditions corresponding to each breathing segment; An event proportion calculation module is used to merge multiple continuous breathing segments corresponding to the same breathing mode to generate corresponding breathing events, and calculate the event start point and event end point corresponding to each breathing event, so as to calculate the time proportion corresponding to each breathing event based on the time difference between the event start point and the event end point and the total breathing time; The event type determination module is used to compare the first size relationship between each time proportion and a preset time proportion threshold, and determine the respiratory event type to which the respiratory event belongs based on the comparison result.

2. The respiratory event type determination device according to claim 1, characterized in that: The data preprocessing module comprises: A data filtering unit, used for performing high-pass filtering and low-pass filtering on the collected respiratory wave data sequence to obtain a filtered first respiratory wave data sequence and a maximum value point, a minimum value point and an average value point of the first respiratory wave data sequence; a threshold calculation unit, configured to respectively set an upper threshold ratio and a lower threshold ratio based on the maximum value point, the minimum value point and the average value point, so as to calculate an upper threshold and a lower threshold of the first respiratory wave data sequence based on the maximum value point, the minimum value point, the gain value, the upper threshold ratio and the lower threshold ratio; A data normalization unit is used to calculate and normalize the first respiratory wave sequence according to the first respiratory wave data sequence, the upper threshold, the lower threshold, the size relationship between the first respiratory wave data sequence and the upper threshold as a first calculation condition, and the size relationship between the first respiratory wave data sequence and the lower threshold as a second calculation condition to obtain a target respiratory wave data sequence.

3. The respiratory event type determination device according to claim 1, characterized in that: The breathing mode determination module comprises: A breathing segment determination submodule, used to traverse the target breathing wave data sequence, screen the index points used to determine the breathing segments, and segmentally determine the breathing mode of the target breathing wave data sequence based on the index points to obtain the inhalation segment, the exhalation segment, the slow breathing segment, and the start point, end point and amplitude value of each breathing segment; The stability value calculation submodule is used to calculate the inhalation segment breathing stability line and / or the exhalation segment breathing stability line based on the corresponding amplitude values ​​of the inhalation segment and / or the exhalation segment, and determine the corresponding inhalation segment breathing stability value and / or the exhalation segment breathing stability value based on the inhalation segment breathing stability line and / or the exhalation segment breathing stability line.

4. The respiratory event type determination device according to claim 3, characterized in that: The respiratory event type determination device further includes: The first sequence definition unit is used to define an inhalation segment sequence, an exhalation segment sequence, and a slow breathing segment sequence, and respectively set the start point parameters, end point parameters, and amplitude values ​​of the inhalation segment sequence, the exhalation segment sequence, and the slow breathing segment sequence; a second sequence definition unit, configured to define an initial upper baseline sequence and an initial lower baseline sequence and a data analysis window of a preset time period, traverse the target respiratory wave data sequence using the data analysis window, and calculate a first average value of the target respiratory wave data sequence greater than zero, so as to determine an initial upper baseline sequence value based on the first average value; and calculate a second average value of the target respiratory wave data sequence less than zero, so as to determine an initial lower baseline sequence value based on the second average value; The third sequence definition unit is used to define a new upper baseline sequence and a new lower baseline sequence, and use the new upper baseline sequence to traverse and linearly interpolate the initial upper baseline sequence value according to the number of sampling points corresponding to the preset time period to obtain a new upper baseline sequence value; use the new lower baseline sequence to traverse and linearly interpolate the initial lower baseline sequence value according to the number of sampling points corresponding to the preset time period to obtain a new lower baseline sequence value.

5. The respiratory event type determination device according to claim 3, characterized in that: The breathing segment determination submodule includes: An index point determination unit is used to traverse all sampling points of the target respiratory wave data sequence, and set the current sampling point as the index point during the traversal process, and compare the second size relationship between the sequence value of the index point and the new upper baseline sequence value; if the second size relationship is that the sequence value of the index point is greater than the new upper baseline sequence value, then set the index point as the index point starting point, and based on the index starting point, traverse forward and / or backward in sequence to find other index points for determining the respiratory segment; The breathing segment determination unit is used to segmentally determine the breathing mode of the target breathing wave data sequence based on all index points to obtain the inhalation segment, the exhalation segment, the slow breathing segment, and the start point, the end point and the amplitude value of each breathing segment.

6. The respiratory event type determination device according to claim 3, characterized in that: The stable value calculation submodule includes: The stable value calculation unit is used to set a stable value analysis window, calculate the coefficient of variation of the amplitude value in the time period of half the stable value analysis window before and after the sampling point in the inhalation segment and / or the exhalation segment, if the coefficient of variation is less than a preset coefficient of variation threshold, then the average amplitude in the stable value analysis window is used as the inhalation segment breathing stable value and / or the exhalation segment breathing stable value; if the coefficient of variation is greater than or equal to the preset coefficient of variation threshold, then the last inhalation segment stable value and / or exhalation segment stable value is used as the inhalation segment breathing stable value and / or exhalation segment breathing stable value.

7. The respiratory event type determination device according to any one of claims 1 to 6, characterized in that: Also includes: An index calculation unit for obtaining the total number of apnea events, the total number of hypopnea events, and the total number of hours of sleep duration; The sleep apnea-hypopnea index is determined based on a ratio of the sum of the total number of apnea events and the total number of hypopnea events to the number of hours of the total sleep duration.

8. A method for determining a respiratory event type, characterized in that: include: Preprocessing the collected respiratory wave data sequence to obtain a normalized target respiratory wave data sequence; Determine the breathing mode of each breathing segment based on the starting point, ending point, amplitude value, stable value and breathing mode determination condition corresponding to each breathing segment; Merging multiple continuous breathing segments corresponding to the same breathing mode to generate corresponding breathing events, and calculating the event start point and event end point corresponding to each breathing event, so as to calculate the time proportion corresponding to each breathing event based on the time difference between the event start point and the event end point and the total breathing time; The first magnitude relationship between each time proportion and a preset time proportion threshold is compared, and the respiratory event type to which the respiratory event belongs is determined based on the comparison result.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor is used to execute the computer program to implement the steps of the respiratory event type determination method according to claim 8.

10. A computer-readable storage medium, characterized in that: Used to store a computer program; wherein, when the computer program is executed by a processor, the steps of the respiratory event type determination method according to claim 8 are implemented.

Images