Method and device for evaluating respiratory function based on continuous electrocardiogram recording
By receiving and analyzing continuous ECG signals, combining heart rate deceleration force detection technology, evaluating data comparison between bedtime and sleep time periods, the problem of inaccurate evaluation of respiratory function in the existing technology is solved, and efficient and accurate respiratory function is achieved Evaluate.
Patent Information
- Application Number
- CN202311787265.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-22
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2043-12-22
AI Technical Summary
The lack of clinical trial support for existing smart wearable devices when evaluating respiratory function, resulting in unreliable evaluation results and requiring detailed testing by professional medical institutions, which are inefficient and cost-effective.
By receiving continuous electrocardiogram signals, calculating RR interval data and heart rate data, obtaining power spectrum data based on time-domain-frequency domain conversion, and combining heart rate deceleration force detection technology, determining the data comparison between bedtime and sleep time periods, realizing the breathing function Assessment.
The efficiency and accuracy of respiratory function evaluation are improved, and the accuracy and universality of evaluation results are ensured through the comparison of total frequency domain power and extremely low frequency values.
Smart Images

Figure CN117598709B_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present invention relate to the technical field of electrocardiogram signals, and in particular to a method and device for analyzing respiratory function based on continuous electrocardiogram recording. Background Art
[0002] Some existing smart wearables can collect the human body's ECG signals and conduct health assessments on the wearer based on the ECG signals. The assessment content includes but is not limited to heart rate changes, sleep quality, respiratory function, etc. However, due to the lack of clinical trials, such evaluation results can only be used as a reference in a sense and cannot be truly tailored to the user.
[0003] If you want a reliable evaluation of your respiratory function, you need to go to a professional medical institution for detailed testing, and then have professionals judge whether your respiratory function is abnormal based on the test report and experience. This method is generally expensive and requires a long stay in the hospital for data collection, so it is relatively inefficient. Summary of the invention
[0004] In order to overcome the shortcomings of the prior art, the purpose of the embodiments of the present invention is to provide a method and device for evaluating respiratory function analysis based on continuous electrocardiogram recording, which realizes respiratory function evaluation and improves efficiency based on data comparison between the pre-sleep time period and the sleep time period.
[0005] To solve the above problems, the first aspect of the embodiment of the present invention discloses a method for analyzing respiratory function based on continuous electrocardiogram recording, comprising:
[0006] Receiving continuous electrocardiogram signals, and calculating RR interval data and heart rate data based on the continuous electrocardiogram signals;
[0007] Determine a bedtime period according to the heart rate data, wherein the duration of the bedtime period is a first preset duration;
[0008] Perform time domain-frequency domain conversion based on the RR interval data to obtain power spectrum data, where the power spectrum data is frequency domain data corresponding to the RR interval data, and determine power spectrum data of the pre-sleep time period and the sleep time period, which are recorded as first power spectrum data and second power spectrum data, respectively;
[0009] Using the heart rate deceleration force detection technology, the heart rate deceleration force data and the heart rate acceleration force data corresponding to the RR interval data are obtained; the heart rate deceleration force data and the heart rate acceleration force data of the pre-sleep time period are determined, which are recorded as the first heart rate deceleration force and the first heart rate acceleration force, respectively; the heart rate deceleration force data and the heart rate acceleration force data of the sleep time period are determined, which are recorded as the second heart rate deceleration force and the second heart rate acceleration force, respectively;
[0010] Respiratory function evaluation is performed based on the first power spectrum data, the first heart rate deceleration force, the second power spectrum data and the second heart rate deceleration force.
[0011] As a preferred embodiment, in a first aspect of the embodiment of the present invention, determining the bedtime period according to the heart rate data includes:
[0012] Determine the initial sleep period based on the heart rate changes before and after sleep;
[0013] Determining a critical time point according to the heart rate change during the initial sleep period;
[0014] Taking the critical time point as the end point, the first preset time length is selected forward as the bedtime period.
[0015] As a preferred embodiment, in the first aspect of the embodiment of the present invention, determining the initial sleep time period according to the heart rate change pattern before and after sleep includes:
[0016] Divide the bedtime period into m first preset sub-time segments, and the duration of each first preset sub-time segment is equal;
[0017] The heart rate data is divided into the first preset sub-time segments to obtain a plurality of heart rate sub-data, wherein the duration of each heart rate sub-data is equal to the duration of the first preset sub-time segment;
[0018] Get the average heart rate difference corresponding to each heart rate sub-data, and the calculation formula is:
[0019] ΔH i =H i -H i+1
[0020] Where ΔH i is the average heart rate difference of the ith heart rate sub-data, H i is the average heart rate of the ith heart rate sub-data, H i+1 is the average heart rate of the i+1th heart rate sub-data;
[0021] Select all heart rate sub-data whose average heart rate difference is greater than or equal to zero, and record them as target heart rate sub-data;
[0022] Taking the target heart rate sub-data as the starting point, calculate the sum of the average heart rate differences of m consecutive heart rate sub-data:
[0023]
[0024] Where ΔH j is the average heart rate difference of the jth heart rate sub-data, and ΔH j ≥0; ΔHn jis the sum of the average heart rate differences corresponding to the j-th heart rate sub-data, which is greater than or equal to the first preset threshold;
[0025] The continuous m heart rate sub-data corresponding to the maximum value in the sum of the average heart rate differences are marked as initial sleep heart rate data, and the time period corresponding to the initial sleep heart rate data is recorded as the initial sleep time period.
[0026] As a preferred embodiment, in the first aspect of the embodiment of the present invention, determining the critical time point according to the heart rate change in the initial sleep period includes:
[0027] The initial sleep onset heart rate data is divided into n initial sleep onset heart rate subsegments, and the average heart rate difference of each initial sleep onset heart rate subsegment is calculated. The time of the target initial sleep onset heart rate subsegment is used as the critical time point. The average heart rate difference of the target initial sleep onset heart rate subsegment is the maximum value of the average heart rate differences of all initial sleep onset heart rate subsegments:
[0028]
[0029] Among them, ΔHr max is the maximum value of the average heart rate difference of all the heart rate sub-segments at the beginning of sleep, which is greater than or equal to the second preset threshold, ΔH k is the average heart rate of the kth early sleep heart rate subsegment, ΔH k+1 is the average heart rate of the k+1th early sleep heart rate subsegment.
[0030] As a preferred embodiment, in a first aspect of the embodiment of the present invention, the respiratory function evaluation is performed based on the first power spectrum data, the first heart rate deceleration force, the second power spectrum data and the second heart rate deceleration force, including:
[0031] Divide the sleep time period into a plurality of sleep time sub-segments, determine the second power spectrum data, the second heart rate deceleration force and the second heart rate acceleration force of each sleep time sub-segment, and record them as the second sub-power spectrum data, the second sub-heart rate deceleration force and the second sub-heart rate acceleration force, respectively;
[0032] Calculate the total power and the extremely low frequency value of the first power spectrum data, recorded as the first total power and the first extremely low frequency value, calculate the total power and the extremely low frequency value of the second sub-power spectrum data corresponding to the target sleep time sub-segment, recorded as the second total power and the second extremely low frequency value;
[0033] Calculate the ratio of the second total power to the first total power, and the ratio of the second extremely low frequency value to the first extremely low frequency value, and record them as the first ratio and the second ratio respectively;
[0034] If the first ratio is not within a third preset threshold range, and the second ratio is not within a fourth preset threshold range, the target sleep time subsegment is marked as a suspected abnormal breathing segment;
[0035] Calculating a ratio of the second sub-heart rate deceleration force to the first heart rate deceleration force of the suspected abnormal breathing segment, recording the ratio as a third ratio, and if the third ratio is not within a fifth preset threshold range, marking the suspected abnormal breathing segment as an abnormal breathing segment;
[0036] Respiratory function is evaluated based on the number of abnormal breathing segments.
[0037] As a preferred embodiment, in the first aspect of the embodiment of the present invention, the respiratory function is evaluated according to the number of abnormal breathing segments, including:
[0038] Determine the number of breathing abnormality segments in the second preset duration, and determine the number of breathing abnormalities according to the relationship between the second preset duration and the sleep time sub-segments:
[0039]
[0040] Wherein, P1 is the number of abnormal breathing, T1 is the second preset duration, T2 is the duration of the sleep time sub-segment, and N1 is the number of abnormal breathing segments in the second preset duration;
[0041] Determine the number of abnormal breathing segments in the sleep time period, and determine the abnormal breathing index based on the relationship between the sleep time period and the sleep time sub-segments:
[0042]
[0043] Among them, P2 is the abnormal breathing index, T0 is the duration of the sleep period, and N2 is the number of abnormal breathing segments in the sleep period;
[0044] The respiratory function is evaluated according to the abnormal breathing number and / or the abnormal breathing index.
[0045] As a preferred embodiment, in the first aspect of the embodiment of the present invention, the respiratory function evaluation is performed according to the abnormal breathing number and / or the abnormal breathing index, including:
[0046] When the number of abnormal breathing is greater than a sixth preset threshold, or / and the abnormal breathing index is greater than a seventh preset threshold, the respiratory function corresponding to the continuous electrocardiogram signal is abnormal.
[0047] A second aspect of an embodiment of the present invention discloses a respiratory function analysis device based on continuous electrocardiogram recording, comprising:
[0048] A receiving unit, configured to receive a continuous electrocardiogram signal and calculate RR interval data and heart rate data based on the continuous electrocardiogram signal;
[0049] a determining unit, configured to determine a pre-sleep time period according to the heart rate data, wherein the duration of the pre-sleep time period is a first preset duration;
[0050] A conversion unit, configured to perform a time domain-frequency domain conversion based on the RR interval data to obtain power spectrum data, wherein the power spectrum data is the frequency domain data corresponding to the RR interval data, and determine the power spectrum data of the pre-sleep time period and the sleep time period, which are recorded as first power spectrum data and second power spectrum data, respectively;
[0051] an acquisition unit, configured to acquire the heart rate deceleration force data and the heart rate acceleration force data corresponding to the RR interval data by using the heart rate deceleration force detection technology; determine the heart rate deceleration force data and the heart rate acceleration force data in the pre-sleep time period, recorded as the first heart rate deceleration force and the first heart rate acceleration force, respectively, and determine the heart rate deceleration force data and the heart rate acceleration force data in the sleep time period, recorded as the second heart rate deceleration force and the second heart rate acceleration force, respectively;
[0052] An evaluation unit is used to evaluate respiratory function based on the first power spectrum data, the first heart rate deceleration force, the second power spectrum data and the second heart rate deceleration force.
[0053] A third aspect of an embodiment of the present invention discloses an electronic device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the computer program, the steps of the method for analyzing respiratory function assessment based on continuous electrocardiogram recording disclosed in the first aspect of the embodiment of the present invention are implemented.
[0054] A fourth aspect of an embodiment of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the steps of the respiratory function analysis method based on continuous electrocardiogram recording disclosed in the first aspect of the embodiment of the present invention.
[0055] A fifth aspect of an embodiment of the present invention discloses a computer program product. When the computer program product is run on a computer, the computer is enabled to execute the steps of the method for analyzing respiratory function assessment based on continuous electrocardiogram recording disclosed in the first aspect of the embodiment of the present invention.
[0056] A sixth aspect of an embodiment of the present invention discloses an application publishing platform, which is used to publish a computer program product. When the computer program product runs on a computer, the computer executes the steps of the respiratory function analysis method based on continuous electrocardiogram recording disclosed in the first aspect of the embodiment of the present invention.
[0057] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:
[0058] 1. The embodiment of the present invention compares the ECG signal data during the sleep period and the pre-sleep period to evaluate the respiratory function and improve the evaluation efficiency;
[0059] 2. In the process of respiratory function evaluation, the accuracy and universality of the evaluation results can be guaranteed by comparing the total power in the frequency domain, the extremely low frequency value in the frequency domain, and the heart rate deceleration force. BRIEF DESCRIPTION OF THE DRAWINGS
[0060] Figure 1 It is a flowchart of a method for analyzing respiratory function based on continuous electrocardiogram recording provided in the first embodiment of the present invention;
[0061] Figure 2 is a schematic diagram of RRI data provided by an embodiment of the present invention;
[0062] Figure 3 is a schematic diagram of continuous RR interval data provided by an embodiment of the present invention;
[0063] Figure 4 is a schematic diagram of continuous heart rate data provided by an embodiment of the present invention;
[0064] Figure 5 is a schematic diagram of a process for obtaining a bedtime period provided by an embodiment of the present invention;
[0065] Figure 6 is a schematic diagram of an average heart rate difference provided by an embodiment of the present invention;
[0066] Figure 7 is a schematic diagram of the process of obtaining the initial sleep time period provided by an embodiment of the present invention;
[0067] Figure 8 is a schematic diagram of the average heart rate difference in the initial sleep period provided by an embodiment of the present invention;
[0068] Fig. 9 is a schematic diagram of continuous ECG RR interval data provided by an embodiment of the present invention;
[0069] Fig.10 yes Fig. 9 The corresponding frequency domain power spectrum;
[0070] Fig.11 It is a schematic diagram of ECG frequency domain variable data of multiple 5-minute sleep periods provided by an embodiment of the present invention;
[0071] Fig.12 It is a schematic diagram of continuous ECG RR interval data and its corresponding power spectrum during a 60-minute target sleep period provided by an embodiment of the present invention;
[0072] Fig.13 It is a schematic diagram of the ratio of the frequency domain power spectrum and the heart rate deceleration force ratio of the 60-minute target sleep period to the 15 minutes before going to bed and the 15 minutes after waking up provided by an embodiment of the present invention;
[0073] Fig.14 It is a structural schematic diagram of a respiratory function analysis device based on continuous electrocardiogram recording disclosed in Embodiment 2 of the present invention;
[0074] Fig.15 It is a structural schematic diagram of an electronic device disclosed in Embodiment 3 of the present invention. DETAILED DESCRIPTION
[0075] This specific implementation manner is merely an explanation of an embodiment of the present invention, and it is not a limitation of the embodiment of the present invention. After reading this specification, a person skilled in the art may make non-creative modifications to the embodiment as needed, but as long as it is within the scope of the claims of the embodiment of the present invention, it is protected by the patent law.
[0076] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. Based on the embodiments in 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 embodiments of the present invention.
[0077] The term "comprise" and any variations thereof in the specification and claims of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.
[0078] In the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.
[0079] Embodiment 1
[0080] See also Figure 1 , Figure 1FIG. 1 is a flow chart of a method for evaluating respiratory function based on continuous electrocardiogram recording disclosed in an embodiment of the present invention. Figure 1 As shown, the method for evaluating respiratory function analysis based on continuous ECG recording may include the following steps:
[0081] S110, receiving a continuous electrocardiogram signal, and calculating RR interval data and heart rate data based on the continuous electrocardiogram signal.
[0082] In a preferred embodiment of the present invention, the continuous ECG signal adopts complete nighttime dynamic ECG data (from 20:00 at night to 10:00 the next day), and the effective nighttime ECG data must exceed 3 hours, otherwise the data will be deemed invalid; the data, cardiac cycle data status, etc. are derived through the complete continuous cardiac cycle of the data.
[0083] Record the RRI data in the continuous ECG signal (the function obtained by mathematically processing the RR period sequence to obtain various characteristics of heart rate variability) such as Figure 2 express.
[0084] The acquired RRI data is converted into a complete RR interval (RR interval refers to the time limit between two R waves in the ECG signal) (marked as NN interval), thereby obtaining the RR interval data required for respiratory function evaluation. The conversion formula is as follows:
[0085] RR i =a i -a i-1
[0086] Among them, RR i is the i-th RR interval, a i is the time of the ith R wave, a i-1 is the time of the i-1th R wave. As a preferred embodiment, the sampling frequency of the ECG signal is set to 1000 Hz. The RR interval data is directly determined by using the above formula. The respiratory function evaluation result obtained is more accurate. If other sampling frequencies, such as 128 Hz, are used, they can also be converted to 1000 Hz to obtain the RR interval data:
[0087]
[0088] After the formula conversion, the RR interval data of the continuous ECG signal (i.e., the dynamic ECG data for a whole night) is obtained, and the NN interval data is marked (if the continuous ECG signal comes from the ECG, 1 small square in the ECG = 0.04s, the number of small squares between normal R peaks × 0.04 (s), which is the measured value of the NN interval) data; the obtained RR interval data can be used Figure 3 express.
[0089] According to the start time of ECG monitoring, the RR interval data are added together to mark the corresponding time point for each RR interval, and the time point corresponding to each RR interval is recorded (for example: 2023-03-09 20:11:01).
[0090] Convert all RR interval data into heart rate data (Hr). The conversion formula is as follows:
[0091]
[0092] Among them, Hr i is the heart rate data corresponding to the i-th RR interval data, recorded as the i-th heart rate data, because RR i Generally, milliseconds are used for statistics, while heart rate data is generally counted in minutes. Therefore, milliseconds need to be converted into minutes through 60*1000.
[0093] In this way, the above continuous ECG signals are converted into corresponding heart rate data, and the time point corresponding to each heart rate data is determined according to the time point corresponding to the RR interval. The continuous heart rate data is as follows: Figure 4 shown.
[0094] S120. Determine a bedtime period according to the heart rate data, wherein the duration of the bedtime period is a first preset duration.
[0095] When a person just falls asleep, their heart rate is generally relatively stable and low, usually 5-10 beats / min slower than when awake. At the same time, according to sleep patterns, the human body can generally fall asleep in about 15 minutes. Therefore, we use these two conditions to analyze the heart rate data and obtain the bedtime period.
[0096] Please refer to Figure 5 As shown, it can specifically include the following steps:
[0097] S121. Determine the initial sleep time period based on the heart rate variation pattern before and after sleep.
[0098] Since the human body can generally enter a sleep state in about 15 minutes, the first preset duration can be set to 15 minutes. The pre-sleep time period is divided into m first preset sub-time segments, and the duration of each first preset sub-time segment is equal; for example, if the first preset sub-time segment is 5 minutes, then m=3. Here, the present invention is explained and illustrated with the first preset sub-time segment being 5 minutes and the pre-sleep time period being 15 minutes.
[0099] The heart rate data is divided into the first preset sub-time segments to obtain a plurality of heart rate sub-data, and the duration of each heart rate sub-data is equal to the duration of the first preset sub-time segment. That is, taking 5 minutes as a unit, a plurality of 5-minute heart rate sub-data are obtained, and the average heart rate of each 5-minute period can be calculated.
[0100] After calculating all the 5-minute average heart rates, use the previous 5-minute average heart rate H i Subtract the average heart rate H of the next 5 minutes i+1 , get the average heart rate difference △H i :
[0101] ΔH i =H i -H i+1
[0102] Where ΔH i is the average heart rate difference of the ith heart rate sub-data, H i is the average heart rate of the ith heart rate sub-data, H i+1 is the average heart rate of the i+1th heart rate sub-data.
[0103] Select all heart rate sub-data with average heart rate difference greater than or equal to zero and record them as target heart rate sub-data. i ≥0, it indicates that the heart rate has decreased; if △H i <0; then the heart rate is marked to have increased, as shown in the schematic diagram Figure 6 shown.
[0104] If △H i <0, it means that the heart rate has increased, then these 5 minutes will be skipped and the average heart rate difference for the next 5 minutes will be determined.
[0105] Taking the target heart rate sub-data as the starting point, the sum of the average heart rate differences of m consecutive heart rate sub-data is calculated, and the calculation formula is as follows:
[0106]
[0107] Where ΔH j is the average heart rate difference of the jth heart rate sub-data, which is the target heart rate sub-data, i.e. ΔH j ≥0; ΔHn j is the sum of the average heart rate differences corresponding to the j-th heart rate sub-data, which is greater than or equal to the first preset threshold.
[0108] The specific method is:
[0109] If △H j≥0, indicating that the heart rate has dropped. The corresponding heart rate sub-data can be used as the target heart rate sub-data. Then, the target heart rate sub-data is used as the starting point, together with the next two consecutive 5-minute periods (15 minutes) as a processing unit, and the average heart rate differences of these three 5-minute periods are added together. If the sum ΔHn j <0, then skip these 5 minutes and enter the processing unit corresponding to the next target heart rate sub-data.
[0110] If △H j ≥0, and ΔHn j >0, it means that the overall heart rate in the processing unit is decreasing, please refer to Figure 7 As shown, there may be the following situations:
[0111] ① If the three 5-minute average heart rates of the processing unit are continuously decreasing, add the three 5-minute average heart rate differences to obtain the sum of the maximum average heart rate difference of the processing unit, and determine ΔHn j Is it greater than or equal to a first preset threshold (the first preset threshold can be set as needed, for example, it can be set to 5. It can be understood that ΔHn j When the heart rate sub-data is greater than or equal to the first preset threshold, it must be greater than 0), if so, the processing unit is marked as suspected early stage heart rate data of falling asleep, otherwise, the processing unit corresponding to the next target heart rate sub-data is entered;
[0112] ② If the first two average heart rate differences decrease and the third one increases, then add the three 5-minute average heart rate differences (where the third average heart rate difference is a negative value) to obtain the sum of the maximum average heart rate difference of the processing unit and determine ΔHn j whether it is greater than or equal to a first preset threshold value, if so, marking the processing unit as suspected early stage of falling asleep heart rate data, otherwise, entering the processing unit corresponding to the next target heart rate sub-data;
[0113] ③ If the first average heart rate difference decreases, the second increases, and the third decreases, then add the three 5-minute average heart rate differences (where the second average heart rate difference is a negative value) to obtain the sum of the maximum average heart rate difference of the processing unit, and determine ΔHn j Is it greater than or equal to the first preset threshold? If so, the processing unit is marked as suspected early stage heart rate data of falling asleep; otherwise, the processing unit corresponding to the next target heart rate sub-data is entered.
[0114] Other cases: If the first average heart rate difference decreases, the second increases, and the third also increases, the three 5-minute average heart rate differences can be added together (where the second and third average heart rate differences are both negative values) to obtain the sum of the maximum average heart rate differences of the processing unit, and determine ΔHn jWhether it is greater than or equal to the first preset threshold, of course, in this case, it is highly likely that the user has not entered sleep mode, and the result may be discarded directly.
[0115] The above suspected initial sleep heart rate data are counted, and the suspected initial sleep heart rate data corresponding to the maximum value in the sum of the corresponding average heart rate differences in the suspected initial sleep heart rate data is marked as the initial sleep heart rate data, and the time period corresponding to the initial sleep heart rate data is recorded as the initial sleep time period. If there are two or more maximum values in the sum of the average heart rate differences, the earliest time period of the suspected initial sleep heart rate data is taken as the initial sleep time period.
[0116] S122: Determine a critical time point according to the heart rate change during the initial sleep period.
[0117] After obtaining the initial heart rate data of falling asleep, divide the initial heart rate data of falling asleep into n initial heart rate sub-segments (for example, each minute is regarded as an initial heart rate sub-segment of falling asleep, and when the duration corresponding to the initial heart rate data of falling asleep is 15 minutes, n=15), and calculate the average heart rate difference of each initial heart rate sub-segment of falling asleep, please refer to Figure 8 shown.
[0118] The time of the target initial sleep heart rate subsegment is taken as the critical time point, and the average heart rate difference of the target initial sleep heart rate subsegment is the maximum value among the average heart rate differences of all initial sleep heart rate subsegments (if there are multiple maximum values among the average heart rate differences of all initial sleep heart rate subsegments, the earliest time of the initial sleep heart rate subsegment is taken as the critical time point):
[0119]
[0120] Among them, ΔHr max is the maximum value of the average heart rate difference of all the heart rate sub-segments at the beginning of sleep, which is greater than or equal to the second preset threshold, ΔH k is the average heart rate of the kth early sleep heart rate subsegment, ΔH k+1 is the average heart rate of the k+1th early sleep heart rate subsegment.
[0121] S123, taking the critical time point as the end point, selecting a first preset time length forward as the bedtime period.
[0122] According to the critical time point obtained above (for example, 2023-03-09 22:11:00, accurate to the minute), the 15 minutes before the critical time point is recorded as the 15 minutes before bedtime, that is, the bedtime time period.
[0123] S130. Perform time domain-frequency domain conversion based on the RR interval data to obtain power spectrum data, the power spectrum data being the frequency domain data corresponding to the RR interval data, and determine the power spectrum data of the pre-sleep time period and the sleep time period, which are recorded as the first power spectrum data and the second power spectrum data, respectively. Utilize the heart rate deceleration force detection technology to obtain the heart rate deceleration force data and the heart rate acceleration force data corresponding to the RR interval data; determine the heart rate deceleration force data and the heart rate acceleration force data of the pre-sleep time period, which are recorded as the first heart rate deceleration force and the first heart rate acceleration force, respectively; determine the heart rate deceleration force data and the heart rate acceleration force data of the sleep time period, which are recorded as the second heart rate deceleration force and the second heart rate acceleration force, respectively.
[0124] Before performing other operations, the required operation algorithms are encapsulated to facilitate subsequent operations; the operation methods we currently need are ECG frequency domain analysis method and heart rate deceleration force analysis.
[0125] Determine the time period required for frequency domain analysis, and obtain the NN (normal RR interval) interval data of the required operation time period; obtain a complete continuous NN interval sequence and mark the operation sequence.
[0126] After obtaining the correct number of NN intervals, the data is converted from time domain to frequency domain. Here, the fast Fourier formula is used to achieve this. The fast Fourier formula is:
[0127]
[0128] Fourier transform assumes that a periodic function (signal) contains multiple frequency components. Any function (signal) f(t) can be synthesized by adding multiple periodic functions (basis functions) (f(t) is a periodic function, which is the NN interval data here). The function f(t) in the time domain is transformed into F(ω) in the frequency domain through Fourier transform, where ω is the frequency, F(ω) is the image function, f(t) is the original function, and e -iωt A complex function is a function with complex numbers as independent and dependent variables. e is the base of the natural logarithm, i is the imaginary unit, and ω is the frequency. The typical use of the Fourier transform is to decompose a signal into a frequency spectrum - showing the amplitude corresponding to the frequency.
[0129] Fast Fourier Transform (FFT) is a fast algorithm for discrete Fourier transform. It is obtained by improving the discrete Fourier transform algorithm based on the odd, even, imaginary, and real characteristics of discrete Fourier transform. The application of discrete Fourier transform in computer systems is very effective. The FFT algorithm is generated based on the different methods of decomposing and selecting sequences.
[0130] FFT is a fast algorithm for discrete Fourier transform, which can transform a signal into the frequency domain. Some signals are difficult to see any features in the time domain, so they need to be transformed into the frequency domain. This is why some signal analysis uses FFT transformation. FFT can extract the spectrum of a signal, which is often used in spectrum analysis. An analog signal becomes a digital signal after being sampled by ADC. The sampled digital signal can be transformed by FFT. After N sampling points, N points of FFT can be obtained. In order to facilitate FFT calculation, N is usually taken as an integer power of 2. Then the result after FFT is a complex number of N points. Each point corresponds to a frequency point. The modulus value of this point is the amplitude characteristic at this frequency value. Assuming that the peak value of the original signal is A, the modulus value of each point of the FFT result is N / 2 times A. The first point is the DC component, and its modulus value is N times the DC component. And the phase of each point is the phase of the signal at that frequency.
[0131] Get the NN interval data for the corresponding time period (such as Fig. 9 After that, according to the fast Fourier transform (FFT) algorithm, the corresponding power spectrum data is obtained, as shown in Fig.10 shown.
[0132] According to the power spectrum operation rules, the total power TP (0-0.4HZ), ultra-low frequency power (0-0.003HZ), extremely low frequency power (0.003HZ-0.04HZ), low frequency power (0.04HZ-0.15HZ), and high frequency power (0.15HZ-0.4HZ) are calculated and counted by frequency segmentation to obtain the total power, extremely low frequency, low frequency, high frequency, low-high frequency ratio and other values of the ECG data in the target time period, and the data is output and returned with each time period as a label.
[0133] For the power spectrum data of the pre-sleep time period, the ECG data of 15 minutes before sleep can be obtained according to the interpretation and calculation method of the 15-minute pre-sleep time period, and the RR interval data of three 5-minute continuous ECGs can be obtained. The frequency domain analysis method is used to calculate this data.
[0134] According to the frequency domain analysis method, the frequency domain variable value of the ECG time period 15 minutes before going to bed (before going to bed time period) can be obtained, which is recorded as the first power spectrum data. It includes the ECG frequency domain total power TP 15 minutes before going to bed (recorded as the first total power), the ECG frequency domain very low frequency VLF 15 minutes before going to bed (recorded as the first very low frequency value), the ECG frequency domain low frequency LF 15 minutes before going to bed (recorded as the first low frequency value), the ECG frequency domain high frequency HF 15 minutes before going to bed (recorded as the first high frequency value) and the ECG frequency domain low-high frequency ratio LHF 15 minutes before going to bed (recorded as the first low-high frequency ratio), and the time period and variable values are stored for secondary calculation.
[0135] Similarly, after knowing the time of falling asleep (i.e., the critical time point) and the time of waking up clearly, a sleep time period is obtained, and now the electrocardiogram data of the sleep time period is calculated.
[0136] Here, the sleep time period is divided into a plurality of sleep time sub-segments (for example, each sleep time sub-segment may be 5 minutes), and the power spectrum data of each sleep time sub-segment is determined and recorded as the second sub-power spectrum data.
[0137] Starting from the critical time point, every 5 minutes is taken as a basic operation unit, and the non-NN interval data within each 5 minutes are selected. If the non-NN interval data reaches one-third of the RR data of this 5 minutes, the data of this 5 minutes are marked as a unit with more arrhythmias.
[0138] The NN interval data of each 5-minute basic time unit is obtained in turn, and the frequency domain analysis method is called to obtain the frequency domain variable values of the ECG time periods corresponding to all 5 minutes, which are recorded as the second sub-power spectrum data; it includes each 5-minute ECG frequency domain total power TP (recorded as the second sub-total power), each 5-minute ECG frequency domain very low frequency VLF (recorded as the second sub-very low frequency value), each 5-minute ECG frequency domain low frequency LF (recorded as the second sub-low frequency value), each 5-minute ECG frequency domain high frequency HF (recorded as the second sub-high frequency value) and each 5-minute ECG frequency domain low-high frequency ratio LHF (recorded as the second sub-low-high frequency ratio), and the time periods and variable values are stored for secondary calculations. The calculation mode is as follows: Fig.11 shown.
[0139] After calculating the ECG frequency domain variable data of all sleep time subsegments throughout the night, we have also calculated the frequency domain variables of the data before bedtime. We will calculate the following new variables: ⑴Total power ratio (TP_RATIO): the ratio of the total power TP in the ECG frequency domain of the current sleep time subsegment to the total power TP in the ECG frequency domain of the time period before bedtime, recorded as the first ratio; ⑵Very low frequency ratio (VLF_RATIO): the ratio of the very low frequency VLF in the ECG frequency domain of the current sleep time subsegment to the very low frequency VLF in the ECG frequency domain of the time period before bedtime, recorded as the second ratio; ⑶Low-high frequency ratio (LHF_RATIO): the ratio of the low-high frequency ratio LHF in the ECG frequency domain of the current sleep time subsegment to the low-high frequency ratio LHF in the ECG frequency domain of the time period before bedtime.
[0140] Determine the time period in which the heart rate deceleration force needs to be calculated, obtain the number of continuous RR interval sequences in the target time period, and use the heart rate deceleration force detection technology to calculate the heart rate deceleration force.
[0141] The deceleration capacity of rate (DC) is a new technology for detecting autonomic nervous tension that was discovered and proposed by Professor Georg Schmidt of the Munich Heart Center in Germany in recent years. The formula is:
[0142] DC=[X(0)+X(1)-X(-1)-X(-2)]×1 / 4
[0143] Among them, X(0) is the average value of the RR interval of the center point, X(1) is the average value of the RR interval after the center point, X(-1) is the average value of the RR interval before the center point, and X(-2) is the average value of the RR intervals before the center point.
[0144] According to the calculation, the heart rate deceleration force (DC) and heart rate acceleration force (AC) values of the ECG data are obtained and outputted back.
[0145] When the RR interval data of the target cardiac cycle is greater than the RR interval data of the previous cardiac cycle, the heart rate deceleration force calculated by the heart rate deceleration force detection technology is the heart rate deceleration force. When the RR interval data of the target cardiac cycle is less than the RR interval data of the previous cardiac cycle, the heart rate acceleration force calculated by the heart rate deceleration force detection technology is the heart rate acceleration force.
[0146] By putting the RR interval data of the pre-sleep time period into the heart rate deceleration force technical algorithm, we can obtain the ECG heart rate deceleration force DC and the ECG heart rate acceleration force AC of the pre-sleep time period, which are recorded as the first heart rate deceleration force and the first heart rate acceleration force respectively. The time period and variable values are stored for secondary calculations.
[0147] By putting the RR interval data of each sleep time sub-segment into the heart rate deceleration force technical algorithm, we can obtain the ECG heart rate deceleration force DC of the sleep time sub-segment and the ECG heart rate acceleration force AC of the sleep time sub-segment, which are respectively recorded as the second sub-heart rate deceleration force and the second sub-heart rate acceleration force. The time period and variable values are stored for secondary calculation.
[0148] After obtaining the first heart rate deceleration force and the first heart rate acceleration force as well as the second sub-heart rate deceleration force and the second sub-heart rate acceleration force, the two can be compared to obtain a new variable DC ratio (DC_RATIO): the ratio of the second sub-heart rate deceleration force to the first heart rate deceleration force, recorded as the third ratio.
[0149] S150. Evaluate respiratory function based on the first power spectrum data, the first heart rate deceleration force, the second power spectrum data, and the second heart rate deceleration force.
[0150] During the entire sleep period, we stipulate that valid data must reach 3 hours to be a complete data case. Based on the experience in medical research, we use the second preset time, such as 60 minutes of ECG data for calculation, and the data results can have a certain reference value. Currently, 5 minutes is used as a sleep time sub-segment, so the method of forming a 60-minute calculation period is as follows:
[0151] ① The starting point is to take each sleep time sub-segment as the starting point, and form the starting points of multiple 60-minute time periods in chronological order; ② After having the starting point, use this starting point for 12 consecutive 5-minute periods to form a new 60-minute time period; ③ In the process of forming 60 minutes in sequence, when the last 5 minutes of the 60-minute time period intersects with the 15-minute time period after waking up, the combination is completed, and the 60-minute time period with the intersection is removed.
[0152] After obtaining the list of all 60-minute time periods (starting point-ending point) throughout the night, obtain the ECG continuous NN interval data (RR interval with state N) of the 60-minute target time period in turn; and input the data into the packaged frequency domain analysis method for calculation to obtain the frequency domain variable values of the 60-minute target time period, including the ECG frequency domain total power TP, frequency domain very low frequency VLF, frequency domain low frequency LF, frequency domain high frequency HF, and frequency domain low-high frequency ratio LHF of the 60-minute target time period. And save the start time point, end time point, frequency domain variable value, etc. of this 60-minute time period for subsequent secondary calculations, such as Fig.12 shown.
[0153] Calculate the ECG heart rate deceleration force in a 60-minute time period and obtain the ECG continuous RR interval data in the 60-minute target time period; input the data into the packaged heart rate deceleration force technology to obtain the corresponding heart rate deceleration force DC and heart rate acceleration force AC in the 60-minute time period in turn, and store them for secondary calculation.
[0154] After calculating the ECG frequency domain variables and heart rate deceleration and acceleration data for all 60-minute target time periods throughout the night, we calculated the maximum value of the total ECG frequency domain power TP for the 60-minute target time period, recorded as TPmax, and obtained the start and end time points of the 60-minute target time period in the entire case, and obtained the corresponding frequency domain variable data (very low frequency VLF, low frequency LF, high frequency HF, low high frequency ratio LHF) and heart rate deceleration and acceleration of the corresponding time period. This hour was identified as the time period with the most work power in the sleep period of this case, that is, the target time period, and the target time period was statistically marked as TARGERT-TIMEmax. At the same time, we also obtain the frequency domain variables of the data in the 15-minute time period before going to bed and variables such as heart rate deceleration force. Through ratio operation, we will calculate the following new variables: ⑴Total power ratio (T_TP_RATIO): the ratio of the total power TP in the ECG frequency domain in the target time period to the total power TP in the ECG frequency domain 15 minutes before going to bed; ⑵Very low frequency ratio (T_VLF_RATIO): the ratio of the very low frequency VLF in the ECG frequency domain in the target time period to the very low frequency VLF in the ECG frequency domain 15 minutes before going to bed; ⑶Low-high frequency ratio (T_LHF_RATIO): the ratio of the low-high frequency ratio LHF in the ECG frequency domain in the target time period to the low-high frequency ratio LHF in the ECG frequency domain 15 minutes before going to bed; ⑷Heart rate deceleration force ratio (T_DC_RATIO): the ratio of the heart rate deceleration force in the target time period to the heart rate deceleration force in the 15 minutes before going to bed. After completing the above operations, the start and end time points of the target time period, the frequency domain variable values, the heart rate deceleration force values, and the variable ratios are marked and stored in the database to facilitate data export and statistics. Fig.13 shown.
[0155] After knowing the time of falling asleep and waking up clearly, the sleep period of the whole night is obtained, and the ECG data of the sleep period of the whole night is calculated to obtain the continuous RR interval data and the corresponding cardiac cycle state of the sleep period at night, and the NN interval data sequence is extracted; (1) The NN interval data is input into the packaged frequency domain analysis method for calculation to obtain the ECG frequency domain total power TP, frequency domain very low frequency VLF, frequency domain low frequency LF, frequency domain high frequency HF, and frequency domain low-high frequency ratio LHF of the sleep period. (2) The RR interval data is input into the packaged heart rate deceleration force technology to obtain the heart rate deceleration force DC and heart rate acceleration force AC of the sleep period; the frequency domain variable results and heart rate deceleration force results output by the algorithm are stored in the database.
[0156] From the stored data of all 5-minute ECG frequency domain variables of all basic calculation units in the calculated sleep time period, extract all TP ratios (the ratio of the total ECG frequency domain power TP in the 5-minute period to the total ECG frequency domain power TP in the 15 minutes before sleep) and very low frequency ratios (the ratio of the very low frequency VLF in the ECG frequency domain in the 5-minute period to the very low frequency VLF in the ECG frequency domain in the 15 minutes before sleep), judge the breathing abnormality in this 5-minute period, record it as a suspected breathing abnormality segment, and mark it.
[0157] Specifically, a ratio of the second total power to the first total power and a ratio of the second extremely low frequency value to the first extremely low frequency value are calculated and recorded as a first ratio and a second ratio, respectively.
[0158] If the first ratio is not within the third preset threshold range, and the second ratio is not within the fourth preset threshold range, the target sleep time subsegment is marked as a suspected breathing abnormality segment. The third preset threshold range and the fourth preset threshold range can be set according to the actual situation of different groups of people or individuals.
[0159] Then, the ratio of the second sub-heart rate deceleration force to the first heart rate deceleration force of the suspected abnormal breathing segment is calculated and recorded as the third ratio. If the third ratio is not within the fifth preset threshold range, the suspected abnormal breathing segment is marked as an abnormal breathing segment. The fifth preset threshold range can also be set according to the actual situation of different groups of people or individuals.
[0160] Determine the number of breathing abnormality segments in the second preset duration, and determine the number of breathing abnormalities according to the relationship between the second preset duration and the sleep time sub-segments:
[0161]
[0162] Among them, P1 is the number of abnormal breathing, T1 is the second preset duration, T2 is the duration of the sleep time sub-segment, and N1 is the number of abnormal breathing segments in the second preset duration.
[0163] Get the start and end time of the target time period (second preset duration) of the sleep time period in the case, and sequentially obtain the number of 12 5-minute abnormal breathing segments within the 60-minute target time period, recorded as N1 times, and calculate the index of the number of abnormal ECG breathing segments in the current target time period in this target time period, recorded as the abnormal breathing number. After conversion, the data obtained is N1 / 12 (times / minute) = 5*N1 (times / hour).
[0164] Determine the number of abnormal breathing segments in the sleep time period, and determine the abnormal breathing index based on the relationship between the sleep time period and the sleep time sub-segments:
[0165]
[0166] Among them, P2 is the abnormal breathing index, T0 is the duration of the sleep period, and N2 is the number of abnormal breathing segments in the sleep period.
[0167] The start and end time points of the sleep time period are obtained in the previous calculation steps, and based on this, all data variables of the basic calculation unit of 5 minutes within the sleep time period can be obtained. The number of 5-minute data is recorded as M, and the number of abnormal breathing segments is read from it, recorded as N2 times, so as to convert the index of ECG and respiratory abnormalities in the sleep time period, N2 / M (times / minute) = N2*60 / M (times / hour).
[0168] The respiratory function can be evaluated based on the abnormal breathing number and / or the abnormal breathing index. For example, when the abnormal breathing number is greater than the sixth preset threshold, or / and the abnormal breathing index is greater than the seventh preset threshold, it can be determined that the continuous ECG signal corresponds to an abnormal respiratory function of the human body.
[0169] Embodiment 2
[0170] See also Fig.14 , Fig.14 Schematic diagram of a device for analyzing respiratory function based on continuous electrocardiogram recording disclosed in an embodiment of the present invention. Fig.14 As shown, the respiratory function analysis device based on continuous electrocardiogram recording includes:
[0171] The receiving unit 210 is used to receive a continuous electrocardiogram signal and calculate RR interval data and heart rate data based on the continuous electrocardiogram signal;
[0172] A determination unit 220, configured to determine a pre-sleep time period according to the heart rate data, wherein the duration of the pre-sleep time period is a first preset duration;
[0173] A conversion unit 230 is used to perform a time domain-frequency domain conversion based on the RR interval data to obtain power spectrum data, where the power spectrum data is the frequency domain data corresponding to the RR interval data, and determine the power spectrum data of the pre-sleep time period and the sleep time period, which are recorded as first power spectrum data and second power spectrum data respectively;
[0174] The acquisition unit 240 is used to acquire the heart rate deceleration force data and the heart rate acceleration force data corresponding to the RR interval data by using the heart rate deceleration force detection technology; determine the heart rate deceleration force data and the heart rate acceleration force data in the pre-sleep time period, which are recorded as the first heart rate deceleration force and the first heart rate acceleration force, respectively; determine the heart rate deceleration force data and the heart rate acceleration force data in the sleep time period, which are recorded as the second heart rate deceleration force and the second heart rate acceleration force, respectively;
[0175] The evaluation unit 250 is used to evaluate the respiratory function based on the first power spectrum data, the first heart rate deceleration force, the second power spectrum data and the second heart rate deceleration force.
[0176] Embodiment 3
[0177] See also Fig.15 , Fig.15 A schematic diagram of an electronic device that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of the present invention described herein or / and claimed.
[0178] like Fig.15 As shown, the electronic device includes at least one processor 310, and a memory connected to the at least one processor 310, such as a ROM (read-only memory) 320, a RAM (random access memory) 330, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 310 can perform various appropriate actions and processes according to the computer program stored in the ROM 320 or the computer program loaded from the storage unit 380 to the random access memory RAM 330. In the RAM 330, various programs and data required for the operation of the electronic device can also be stored. The processor 310, the ROM 320, and the RAM 330 are connected to each other via a bus 340. An I / O (input / output) interface 350 is also connected to the bus 340.
[0179] A number of components in the electronic device are connected to the I / O interface 350, including: an input unit 360, such as a keyboard, a mouse, etc.; an output unit 370, such as various types of displays, speakers, etc.; a storage unit 380, such as a disk, an optical disk, etc.; and a communication unit 390, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 390 allows the electronic device to exchange information / data with other devices through a computer network such as the Internet or / and various telecommunication networks.
[0180] The processor 310 may be a variety of general or / and special processing components with processing and computing capabilities. Some examples of the processor 310 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 310 performs one or more steps of a method for evaluating respiratory function based on continuous electrocardiogram recording described in the first embodiment above.
[0181] In some embodiments, a method for analyzing respiratory function based on continuous ECG recording can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 380. In some embodiments, part or all of the computer program can be loaded into or / and installed on an electronic device via ROM 320 and / or communication unit 390. When the computer program is loaded into RAM 330 and executed by processor 310, one or more steps of a method for analyzing respiratory function based on continuous ECG recording described in the first embodiment above can be executed. Alternatively, in other embodiments, processor 310 can be configured to execute a method for analyzing respiratory function based on continuous ECG recording by any other appropriate means (e.g., by means of firmware).
[0182] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, or / and combinations thereof. These various embodiments may include: being implemented in one or more computer programs that can be executed or / and interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0183] The computer programs for implementing the methods of the embodiments of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart or / and the block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0184] In the context of an embodiment of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0185] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).
[0186] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0187] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.
[0188] The above is a detailed introduction to a method and device for analyzing respiratory function based on continuous electrocardiogram recording disclosed in the present invention. Specific examples are used in this article 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 those 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 method for evaluating respiratory function based on continuous electrocardiogram recording. It is characterized in that It includes: Receiving continuous electrocardiogram signals, and calculating RR interval data and heart rate data based on the continuous electrocardiogram signals; Determine a bedtime period according to the heart rate data, wherein the duration of the bedtime period is a first preset duration; Perform time domain-frequency domain conversion based on the RR interval data to obtain power spectrum data, where the power spectrum data is frequency domain data corresponding to the RR interval data, and determine power spectrum data of the pre-sleep time period and the sleep time period, which are recorded as first power spectrum data and second power spectrum data, respectively; Using heart rate deceleration force detection technology, obtaining heart rate deceleration force data and heart rate acceleration force data corresponding to the RR interval data; Determine the heart rate deceleration force data and the heart rate acceleration force data in the pre-sleep time period, record them as the first heart rate deceleration force and the first heart rate acceleration force, determine the heart rate deceleration force data and the heart rate acceleration force data in the sleep time period, record them as the second heart rate deceleration force and the second heart rate acceleration force, respectively; Perform respiratory function evaluation based on the first power spectrum data, the first heart rate deceleration force, the second power spectrum data, and the second heart rate deceleration force; Determining a bedtime period according to the heart rate data includes: Determine the initial sleep period based on the heart rate changes before and after sleep; Determining a critical time point according to the heart rate change during the initial sleep period; Taking the critical time point as the end point, selecting the first preset time length forward as the bedtime period; Determine the initial sleep period based on the heart rate changes before and after sleep, including: Divide the bedtime period into m first preset sub-time segments, and the duration of each first preset sub-time segment is equal; The heart rate data is divided into the first preset sub-time segments to obtain a plurality of heart rate sub-data, wherein the duration of each heart rate sub-data is equal to the duration of the first preset sub-time segment; Get the average heart rate difference corresponding to each heart rate sub-data, and the calculation formula is: ΔH i =H i -H i+1 Where ΔH i is the average heart rate difference of the ith heart rate sub-data, H i is the average heart rate of the ith heart rate sub-data, H i+1 is the average heart rate of the i+1th heart rate sub-data; Select all heart rate sub-data whose average heart rate difference is greater than or equal to zero, and record them as target heart rate sub-data; Taking the target heart rate sub-data as the starting point, calculate the sum of the average heart rate differences of m consecutive heart rate sub-data: Where ΔH j is the average heart rate difference of the jth heart rate sub-data, and ΔH j ≥0; ΔHn j is the sum of the average heart rate differences corresponding to the j-th heart rate sub-data, which is greater than or equal to the first preset threshold; Marking the continuous m heart rate sub-data corresponding to the maximum value in the sum of the average heart rate differences as initial sleep heart rate data, and recording the time period corresponding to the initial sleep heart rate data as the initial sleep time period; Determining the critical time point according to the heart rate change during the initial sleep period includes: The initial sleep onset heart rate data is divided into n initial sleep onset heart rate subsegments, and the average heart rate difference of each initial sleep onset heart rate subsegment is calculated. The time of the target initial sleep onset heart rate subsegment is used as the critical time point. The average heart rate difference of the target initial sleep onset heart rate subsegment is the maximum value of the average heart rate differences of all initial sleep onset heart rate subsegments: Among them, ΔHr max is the maximum value of the average heart rate difference of all the heart rate sub-segments at the beginning of sleep, which is greater than or equal to the second preset threshold, ΔH k is the average heart rate of the kth early sleep heart rate subsegment, ΔH k+1 is the average heart rate of the k+1th early sleep heart rate subsegment.
2. The method for analyzing respiratory function based on continuous electrocardiogram recording according to claim 1, It is characterized in that The respiratory function is evaluated based on the first power spectrum data, the first heart rate deceleration force, the second power spectrum data, and the second heart rate deceleration force, including: Divide the sleep time period into a plurality of sleep time sub-segments, determine the second power spectrum data, the second heart rate deceleration force and the second heart rate acceleration force of each sleep time sub-segment, and record them as the second sub-power spectrum data, the second sub-heart rate deceleration force and the second sub-heart rate acceleration force, respectively; Calculate the total power and the extremely low frequency value of the first power spectrum data, recorded as the first total power and the first extremely low frequency value, calculate the total power and the extremely low frequency value of the second sub-power spectrum data corresponding to the target sleep time sub-segment, recorded as the second total power and the second extremely low frequency value; Calculate the ratio of the second total power to the first total power, and the ratio of the second extremely low frequency value to the first extremely low frequency value, and record them as the first ratio and the second ratio respectively; If the first ratio is not within a third preset threshold range, and the second ratio is not within a fourth preset threshold range, the target sleep time subsegment is marked as a suspected abnormal breathing segment; Calculating a ratio of the second sub-heart rate deceleration force to the first heart rate deceleration force of the suspected abnormal breathing segment, recording the ratio as a third ratio, and if the third ratio is not within a fifth preset threshold range, marking the suspected abnormal breathing segment as an abnormal breathing segment; Respiratory function is evaluated based on the number of abnormal breathing segments.
3. The method for analyzing respiratory function based on continuous electrocardiogram recording according to claim 2, It is characterized in that Respiratory function evaluation is performed based on the number of abnormal breathing segments, including: Determine the number of breathing abnormality segments in the second preset duration, and determine the number of breathing abnormalities according to the relationship between the second preset duration and the sleep time sub-segments: Among them, P 1 is the number of abnormal breathing, T 1 is the second preset duration, T 2 is the duration of the sleep time sub-segment, N 1 is the number of abnormal breathing segments in the second preset time length; Determine the number of abnormal breathing segments in the sleep time period, and determine the abnormal breathing index based on the relationship between the sleep time period and the sleep time sub-segments: Among them, P 2 is the respiratory abnormality index, T 0 is the duration of the sleep period, N 2 The number of abnormal breathing segments during the sleep period; The respiratory function is evaluated according to the abnormal breathing number and / or the abnormal breathing index.
4. The method for analyzing respiratory function based on continuous electrocardiogram recording according to claim 3, It is characterized in that The respiratory function is evaluated according to the abnormal breathing number and / or the abnormal breathing index, including: When the number of abnormal breathing is greater than a sixth preset threshold, or / and the abnormal breathing index is greater than a seventh preset threshold, the respiratory function corresponding to the continuous electrocardiogram signal is abnormal.
5. A respiratory function analysis device based on continuous electrocardiogram recording, It is characterized in that It includes: A receiving unit, configured to receive a continuous electrocardiogram signal and calculate RR interval data and heart rate data based on the continuous electrocardiogram signal; a determining unit, configured to determine a pre-sleep time period according to the heart rate data, wherein the duration of the pre-sleep time period is a first preset duration; A conversion unit, configured to perform a time domain-frequency domain conversion based on the RR interval data to obtain power spectrum data, wherein the power spectrum data is the frequency domain data corresponding to the RR interval data, and determine the power spectrum data of the pre-sleep time period and the sleep time period, which are recorded as first power spectrum data and second power spectrum data, respectively; an acquisition unit, configured to acquire the heart rate deceleration force data and the heart rate acceleration force data corresponding to the RR interval data by using a heart rate deceleration force detection technology; Determine the heart rate deceleration force data and the heart rate acceleration force data in the pre-sleep time period, record them as the first heart rate deceleration force and the first heart rate acceleration force, determine the heart rate deceleration force data and the heart rate acceleration force data in the sleep time period, record them as the second heart rate deceleration force and the second heart rate acceleration force, respectively; An evaluation unit, configured to evaluate respiratory function based on the first power spectrum data, the first heart rate deceleration force, the second power spectrum data, and the second heart rate deceleration force; Identify units, including: Determine the initial sleep period based on the heart rate changes before and after sleep; Determining a critical time point according to the heart rate change during the initial sleep period; Taking the critical time point as the end point, selecting the first preset time length forward as the bedtime period; Determine the initial sleep period based on the heart rate changes before and after sleep, including: Divide the bedtime period into m first preset sub-time segments, and the duration of each first preset sub-time segment is equal; The heart rate data is divided into the first preset sub-time segments to obtain a plurality of heart rate sub-data, wherein the duration of each heart rate sub-data is equal to the duration of the first preset sub-time segment; Get the average heart rate difference corresponding to each heart rate sub-data, and the calculation formula is: ΔH i =H i -H i+1 Where ΔH i is the average heart rate difference of the ith heart rate sub-data, H i is the average heart rate of the ith heart rate sub-data, H i+1 is the average heart rate of the i+1th heart rate sub-data; Select all heart rate sub-data whose average heart rate difference is greater than or equal to zero, and record them as target heart rate sub-data; Taking the target heart rate sub-data as the starting point, calculate the sum of the average heart rate differences of m consecutive heart rate sub-data: Where ΔH j is the average heart rate difference of the jth heart rate sub-data, and ΔH j ≥0; ΔHn j is the sum of the average heart rate differences corresponding to the j-th heart rate sub-data, which is greater than or equal to the first preset threshold; Marking the continuous m heart rate sub-data corresponding to the maximum value in the sum of the average heart rate differences as initial sleep heart rate data, and recording the time period corresponding to the initial sleep heart rate data as the initial sleep time period; Determining the critical time point according to the heart rate change during the initial sleep period includes: The initial sleep onset heart rate data is divided into n initial sleep onset heart rate subsegments, and the average heart rate difference of each initial sleep onset heart rate subsegment is calculated. The time of the target initial sleep onset heart rate subsegment is used as the critical time point. The average heart rate difference of the target initial sleep onset heart rate subsegment is the maximum value of the average heart rate differences of all initial sleep onset heart rate subsegments: Among them, ΔHr max is the maximum value of the average heart rate difference of all the heart rate sub-segments at the beginning of sleep, which is greater than or equal to the second preset threshold, ΔH k is the average heart rate of the kth early sleep heart rate subsegment, ΔH k+1 is the average heart rate of the k+1th early sleep heart rate subsegment.
6. An electronic device, It is characterized in that It comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein when the processor executes the computer program, the steps of the method for analyzing respiratory function assessment based on continuous electrocardiogram recording as described in any one of claims 1 to 4 are implemented.
7. A computer-readable storage medium, It is characterized in that It stores a computer program, wherein the computer program enables the computer to execute the steps of the method for evaluating respiratory function based on continuous electrocardiogram recording as described in any one of claims 1 to 4.
