A hypoxic load calculation method, system and medium based on finger pulse oximeter

Abstract

The present invention relates to a method, system, and medium for calculating hypoxic load based on a pulse oximeter. The method comprises: obtaining a raw oxygen saturation signal; dividing the raw oxygen saturation signal into multiple signal segments; selecting a baseline for each signal segment, defining the curve below the baseline in the signal segment as the oxygen depletion curve; defining oxygen depletion events; eliminating artifacts associated with oxygen depletion events, calculating and summarizing the area of ​​each oxygen depletion event in each signal segment after artifact elimination, and obtaining the hypoxic load based on the summarized hypoxic areas. The system and medium are used to implement the above method. Compared with existing technologies, the present invention simplifies hypoxic load calculation and accurately calculates hypoxic load in various situations.

Description

Technical Field

[0001] The present invention relates to the technical field of sleep respiratory medicine, and in particular to a hypoxia load calculation method, system and medium thereof based on a finger pulse oximeter. Background Art

[0002] Obstructive sleep apnea (OSA) has become a global health problem and is characterized by recurrent partial or complete collapse of the upper airway, leading to intermittent nocturnal hypoxia and sleep fragmentation.

[0003] OSA is an independent risk factor for cardiovascular and cerebrovascular diseases, cognitive dysfunction, and metabolic disorders. Currently, the apnea-hypopnea index (AHI) is a commonly used indicator for diagnosing OSA and assessing its severity. However, the AHI has significant limitations. It only counts the average number of apnea and hypopnea events per hour, but fails to fully reflect key factors such as the duration of airway restriction and the severity of hypoxia. Therefore, it cannot fully assess the health risks posed by OSA.

[0004] To address these technical issues, a new OSA-specific hypoxic load indicator was proposed. This indicator is based on the ratio of the area between the oxygen depletion curve caused by respiratory events (apnea or hypopnea) and the baseline to total sleep time. It aims to more accurately reflect the frequency, duration, and severity of hypoxemia associated with OSA, without being affected by hypoxia caused by other factors. Studies have shown that hypoxic load has demonstrated good predictive value in community and clinical cohorts over the past three years, and its increase is significantly associated with the risk of fatal and non-fatal cardiovascular events. However, the calculation of the above-mentioned hypoxic load requires polysomnography (PSG), which has the following disadvantages: 1) The examination cost is high, and the installation of multiple electrodes and sensors may interfere with the patient's sleep, especially for patients with mild symptoms. The examination results may be inaccurate due to discomfort, and the discomfort may cause a first-night effect. One night's examination may affect the results due to lack of adaptation and cannot represent the patient's usual sleep status; 2) The technical requirements are high, and the analysis of PSG requires professional technicians; 3) The monitoring and analysis process of PSG is time-consuming and requires more manpower and material resources; 4) The calculation of hypoxic load based on PSG requires more data types, and the calculation process is complicated. Chinese patent application CN117045243A discloses a method for calculating the hypoxic load of polysomnography. Although it eliminates errors caused by subject movement by eliminating erroneous values, it cannot avoid other shortcomings of PSG. Although the detection algorithm accuracy is improved to a certain extent by setting the basis for oxygen depletion event detection and changing the area calculation method of the traditional oxygen depletion event detection algorithm, its calculation process is relatively complicated, and the oxygen depletion event and its corresponding baseline are determined by respiratory events, which is not conducive to calculating the hypoxic load when the subject experiences continuous oxygen depletion and cannot recover to the baseline, and the calculation accuracy in this case cannot be guaranteed.

[0005] Therefore, providing a method that can simplify the calculation of hypoxic load and accurately calculate the hypoxic load in various situations is a technical problem that needs to be solved. Summary of the Invention

[0006] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and provide a method, system and medium for calculating hypoxia load based on a pulse oximeter.

[0007] The purpose of the present invention can be achieved by the following technical solutions:

[0008] According to a first aspect of the present invention, a method for calculating hypoxia load based on a pulse oximeter is provided, the method comprising:

[0009] Obtaining pulse oximeter monitoring data and extracting a raw oxygen saturation signal therefrom, wherein the raw oxygen saturation signal has time as the horizontal axis and blood oxygen saturation as the vertical axis;

[0010] Traverse the original oxygen saturation signal from the time start point to the time end point, and use the point where the blood oxygen saturation value first decreases as the left boundary point of the current signal segment. Using the left boundary point as the starting point, find the first maximum blood oxygen saturation value that appears within the preset time as the right boundary point of the current signal segment. Repeat the above process until the entire original oxygen saturation signal is divided into multiple signal segments;

[0011] For each signal segment, select the smaller value point between its left boundary point and right boundary point, draw a straight line parallel to the horizontal axis through the smaller value point as the baseline of the signal segment, and define the curve below the baseline in the signal segment as the oxygen depletion curve;

[0012] Obtaining the intersection of each oxygen depletion curve and the corresponding baseline, and using two adjacent intersection points as the start and end points of an oxygen depletion event, wherein the signal segment includes at least one oxygen depletion event;

[0013] Artifacts of hypoxia events were excluded, and the area of ​​each hypoxia event in each signal segment after artifact exclusion was calculated and summarized. The hypoxia load was obtained based on the summarized hypoxia area.

[0014] As a preferred technical solution, the method for eliminating artifacts in each signal segment is as follows: eliminating artifacts whose difference between the lowest blood oxygen saturation value and the baseline between two adjacent intersections is not greater than a preset value; eliminating artifacts whose oxygen depletion duration does not exceed a preset duration, and the oxygen depletion duration is determined based on the starting and end points of the oxygen depletion event; and eliminating artifacts whose lowest blood oxygen saturation value is less than a preset percentage.

[0015] As a preferred technical solution, the preset value is 1%, the preset duration is 1 second, and the preset percentage is 40%.

[0016] As a preferred technical solution, the method for calculating the area of ​​each oxygen depletion event is:

[0017]

[0018] S n represents the area of ​​the nth oxygen depletion event, represents the starting point of the nth oxygen depletion event, Indicates the end point of the nth oxygen depletion event, baseline n represents the baseline corresponding to the nth oxygen depletion event, represents the oxygen reduction curve corresponding to the nth oxygen reduction event, t represents the time of the oxygen reduction event and n represents the oxygen depletion event number and n∈[1,N], where N represents the total number of oxygen depletion events.

[0019] As a preferred technical solution, the method for obtaining low oxygen load is:

[0020]

[0021] HBoxi represents the hypoxic load value, N represents the total number of hypoxia events, n represents the hypoxia event number and n∈[1,N], S n represents the area of ​​the nth oxygen reduction event, t 总 Indicates the duration of the raw oxygen saturation signal.

[0022] According to a second aspect of the present invention, a hypoxia load calculation system based on a finger pulse oximeter is provided, comprising:

[0023] Oxygen saturation signal acquisition module: used to obtain the pulse oximeter monitoring data and extract the original oxygen saturation signal from it. The original oxygen saturation signal has time as the horizontal axis and blood oxygen saturation as the vertical axis;

[0024] The signal segmentation module is used to traverse the original oxygen saturation signal from the time start point to the time end point, and use the point where the blood oxygen saturation value first decreases as the left boundary point of the current signal segment. Starting from the left boundary point, it searches for the first maximum blood oxygen saturation value that appears within a preset time as the right boundary point of the current signal segment. The above process is repeated until the entire original oxygen saturation signal is divided into multiple signal segments.

[0025] Oxygen reduction curve acquisition module: For each signal segment, select the smaller value point between its left boundary point and its right boundary point, draw a straight line parallel to the horizontal axis through the smaller value point as the baseline of the signal segment, and define the curve below the baseline in the signal segment as the oxygen reduction curve;

[0026] An oxygen depletion event determination module is configured to obtain the intersection of each oxygen depletion curve and the corresponding baseline, and use two adjacent intersection points as the start and end points of the oxygen depletion event, wherein the signal segment includes at least one oxygen depletion event;

[0027] Artifact elimination module: used to eliminate artifacts caused by oxygen depletion events;

[0028] Hypoxia load calculation module: used to calculate and summarize the area of ​​each oxygen depletion event in each signal segment after excluding artifacts, and obtain the hypoxia load based on the summarized hypoxia area.

[0029] According to a third aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method described above is implemented.

[0030] Compared with the prior art, the present invention has the following advantages:

[0031] 1) Compared with the existing technology that requires PSG monitoring data, the present invention only needs the oxygen saturation signal obtained by the finger pulse oximeter to calculate the hypoxic load. This not only eliminates the negative impact of the subject's non-adaptation to PSG, making the obtained data more accurate, but also simplifies the calculation process of hypoxic load. In addition, directly determining the baseline of oxygen depletion events through the oxygen saturation signal is more intuitive than the existing technology;

[0032] 2) The present invention's calculation of hypoxic load is no longer limited to determining each individual hypoxia event, but rather calculates the area below the baseline within the left and right boundaries of the signal segment. This is especially true for a patient with severe OSA, whose hypoxia may be continuous and unable to return to baseline. The calculation method of the present invention can effectively avoid underestimation of the hypoxic load of such patients due to determining individual hypoxia events. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 is a flow chart of the method of the present invention;

[0034] Figure 2 Schematic diagram of the hypoxic load calculation method of the present invention;

[0035] Figure 3 This is a diagram illustrating an example of oxygen depletion event detection according to the present invention;

[0036] Figure 4 This is a diagram of the calculation results of the present invention. DETAILED DESCRIPTION

[0037] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0038] Example 1

[0039] In the existing technology, the calculation of hypoxic load requires polysomnography (PSG), but the cost of PSG examination is high. For patients, installing multiple electrodes and sensors may interfere with their sleep, especially for patients with mild symptoms. The examination results may be inaccurate due to discomfort. This discomfort may also cause a first-night effect, so that the results of one night's examination may be affected by the lack of adaptation and cannot represent the patient's usual sleep state.

[0040] With the rapid development of wearable devices, more and more smart devices include oxygen saturation monitoring. Using only oxygen saturation-related parameters has shown certain advantages in the initial screening of OSA. Therefore, this embodiment proposes a hypoxia load calculation method based solely on a pulse oximeter. Combined with wearable devices, it can initially realize the identification of OSA risk groups, use the pulse oximetry waveform characteristics to detect oxygen depletion events, and perform calculations based on their morphological characteristics.

[0041] Specifically, a flow chart of a method for calculating hypoxia load based on a pulse oximeter is as follows: Figure 1 As shown, the following steps are included in detail:

[0042] S1. Obtain pulse oximeter monitoring data and extract an original oxygen saturation signal therefrom, wherein the original oxygen saturation signal has time as the horizontal axis and blood oxygen saturation as the vertical axis.

[0043] S2. Divide the entire original oxygen saturation signal into multiple signal segments based on the left and right boundary points. The specific steps are as follows:

[0044] Traverse the original oxygen saturation signal from the time start point to the time end point, and take the point where the blood oxygen saturation value first decreases as the left boundary point of the current signal segment. Starting from the left boundary point, find the maximum blood oxygen saturation value that appears for the first time within 100 seconds as the right boundary point of the current signal segment. Repeat the process of step S2 until the entire original oxygen saturation signal is divided into multiple signal segments. Take one of the information segments as an example. Figure 2 shown.

[0045] S3. Select the baseline for each signal segment and define the oxygen depletion curve based on the baseline. The specific steps are as follows:

[0046] For each signal segment, select the smaller value point between its left boundary point and right boundary point, draw a straight line parallel to the horizontal axis through the smaller value point as the baseline of the signal segment, and define the curve below the baseline in the signal segment as the oxygen reduction curve.

[0047] S4. Define the oxygen depletion event and its start and end points based on the oxygen depletion curve. The specific steps are as follows:

[0048] Obtain the intersection of each oxygen reduction curve and the corresponding baseline, and use the two adjacent intersections as the starting and ending points of the oxygen reduction event. The signal segment includes at least one oxygen reduction event, such as Figure 2 As shown, and are the starting points of the nth oxygen reduction event and the n+1th oxygen reduction event, respectively. and are the endpoints of the nth oxygen depletion event and the n+1th oxygen depletion event, respectively.

[0049] S5. Eliminate artifacts of hypoxia events, calculate the area of ​​hypoxia events, and calculate the hypoxic load based on the area of ​​hypoxia events. The detailed steps include:

[0050] S51. Eliminate artifacts where the difference between the lowest blood oxygen saturation value and the baseline between two adjacent intersection points is no more than 1%.

[0051] S52, exclude oxygen reduction duration, i.e. The difference does not exceed 1s artifact.

[0052] S53. Eliminate artifacts with a minimum blood oxygen saturation value of less than 40%, such as signal abnormalities caused by loosening or falling off of the finger pulse oximeter.

[0053] S54. Calculate the area of ​​each oxygen reduction event, which is expressed as:

[0054]

[0055] S n represents the area of ​​the nth oxygen depletion event, represents the starting point of the nth oxygen depletion event, Indicates the end point of the nth oxygen depletion event, baseline n represents the baseline corresponding to the nth oxygen depletion event, represents the oxygen reduction curve corresponding to the nth oxygen reduction event, t represents the time of the oxygen reduction event and n represents the oxygen depletion event number and n∈[1,N], where N represents the total number of oxygen depletion events.

[0056] S55. Summarize the area of ​​each oxygen depletion event and add it to the total monitoring time to obtain the hypoxic load, which is expressed as:

[0057]

[0058] HBoxi represents the hypoxic load value, N represents the total number of hypoxia events, n represents the hypoxia event number and n∈[1,N], S n represents the area of ​​the nth oxygen reduction event, t 总 Indicates the duration of the raw oxygen saturation signal.

[0059] In order to verify the feasibility of the above method, the following explanation is made:

[0060] 1) Figure 3 This is the oxygen depletion event detection effect of a certain subject at a certain moment. The dotted box in the figure indicates that the subject has an oxygen depletion event in which oxygen cannot be restored to the baseline. When using this embodiment to calculate the hypoxic load of the subject, the two parts before and after the dotted box are combined into one oxygen depletion event to calculate the shaded area below the baseline, where the baseline is the solid line segment in the figure.

[0061] However, when calculating the oxygen depletion event area of ​​the subject, the prior art divides the two shadows before and after the dotted box into two independent oxygen depletion events, and calculates the shadow areas below the baselines of the two independent oxygen depletion events respectively. The baseline corresponding to this method is the dotted line segment in the figure, while the baseline divided by the method adopted in the present invention corresponds to the line segment corresponding to the thick solid line in the figure.

[0062] It can be seen that the calculation results of the method provided in this embodiment when the oxygen depletion of the subject cannot be restored to the baseline can more truly reflect the subject's hypoxic load value than the existing technology method, and will not cause the problem of underestimation of the hypoxic load of such subjects.

[0063] 2) Simultaneously, the above method was used to calculate the hypoxic load of a large number of subjects and the apnea-hypopnea index (AHI value) obtained based on PSG, and a correlation diagram was drawn with the hypoxic load calculated by this method as the vertical axis and the apnea-hypopnea index (AHI value) obtained based on PSG as the horizontal axis, as shown in FIG. Figure 4 shown.

[0064] Among them, R represents the correlation coefficient, and the closer its value is to 1, the better the correlation between the two; P represents the statistical significance of the correlation, and the closer its value is to 0, the more significant the correlation is. Figure 4 It can be seen that the correlation coefficient between the calculated value of this method and the clinical indicator AHI value is 0.81, which is close to 1, and the P value is less than 0.001 and is approximately equal to 0. That is, the hypoxic load result calculated by the method provided in this embodiment has a strong correlation with the AHI result, indicating that the calculation result of the present invention is accurate and feasible.

[0065] Example 2

[0066] The above is an introduction to the method embodiment. The following further illustrates the solution of the present invention through a system embodiment.

[0067] A hypoxia load calculation system based on a finger pulse oximeter, comprising:

[0068] Oxygen saturation signal acquisition module: used to obtain the pulse oximeter monitoring data and extract the original oxygen saturation signal from it. The original oxygen saturation signal has time as the horizontal axis and blood oxygen saturation as the vertical axis.

[0069] Signal segment division module: used to traverse the original oxygen saturation signal from the time start point to the time end point, take the point where the blood oxygen saturation value first decreases as the left boundary point of the current signal segment, and use the left boundary point as the starting point to find the maximum blood oxygen saturation value that first appears within the preset time as the right boundary point of the current signal segment. Repeat the above process until the entire original oxygen saturation signal is divided into multiple signal segments.

[0070] Oxygen reduction curve acquisition module: For each signal segment, select the smaller value point between its left boundary point and right boundary point, draw a straight line parallel to the horizontal axis through the smaller value point as the baseline of the signal segment, and define the curve below the baseline in the signal segment as the oxygen reduction curve.

[0071] Oxygen depletion event determination module: used to obtain the intersection of each oxygen depletion curve and the corresponding baseline, and use two adjacent intersection points as the starting point and end point of the oxygen depletion event. Each signal segment includes at least one oxygen depletion event.

[0072] Artifact elimination module: used to eliminate artifacts caused by oxygen depletion events.

[0073] Hypoxia load calculation module: used to calculate and summarize the area of ​​each oxygen depletion event in each signal segment after excluding artifacts, and obtain the hypoxia load based on the summarized hypoxia area.

[0074] The system of the present invention also includes a central processing unit (CPU), which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) or loaded from a storage unit into a random access memory (RAM). In the RAM, various programs and data required for device operation can also be stored. The CPU, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0075] Many components in a device are connected to the I / O interface, including: input units, such as a keyboard and mouse; output units, such as various types of displays and speakers; storage units, such as magnetic disks and optical disks; and communication units, such as network cards, modems, and wireless communication transceivers. The communication unit allows the device to exchange information / data with other devices via computer networks such as the Internet and / or various telecommunication networks.

[0076] The processing unit performs the various methods and processes described above, such as methods S1 to S5. For example, in some embodiments, methods S1 to S5 can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit. In some embodiments, part or all of the computer program can be loaded and / or installed on the device via a ROM and / or a communication unit. When the computer program is loaded into the RAM and executed by the CPU, one or more steps of methods S1 to S5 described above can be performed. Alternatively, in other embodiments, the CPU can be configured to execute methods S1 to S5 by any other appropriate means (for example, by means of firmware).

[0077] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0078] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0079] In the context of the present invention, machine-readable medium can be a tangible medium that can contain or store a program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0080] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A method for calculating hypoxia load based on a finger pulse oximeter, characterized in that: The method includes: Obtaining pulse oximeter monitoring data and extracting a raw oxygen saturation signal therefrom, wherein the raw oxygen saturation signal has time as the horizontal axis and blood oxygen saturation as the vertical axis; Traverse the original oxygen saturation signal from the time start point to the time end point, and use the point where the blood oxygen saturation value first decreases as the left boundary point of the current signal segment. Using the left boundary point as the starting point, find the first maximum blood oxygen saturation value that appears within the preset time as the right boundary point of the current signal segment. Repeat the above process until the entire original oxygen saturation signal is divided into multiple signal segments; For each signal segment, select the smaller value point between its left boundary point and right boundary point, draw a straight line parallel to the horizontal axis through the smaller value point as the baseline of the signal segment, and define the curve below the baseline in the signal segment as the oxygen depletion curve; Obtaining the intersection of each oxygen depletion curve and the corresponding baseline, and using two adjacent intersection points as the start and end points of an oxygen depletion event, wherein the signal segment includes at least one oxygen depletion event; Eliminate artifacts of hypoxia events, calculate the area of ​​each hypoxia event in each signal segment after excluding artifacts, and summarize them. Obtain hypoxia burden based on the summarized hypoxia area. The method for eliminating artifacts of oxygen depletion events is as follows: eliminating artifacts where the difference between the lowest blood oxygen saturation value and the baseline between two adjacent intersections is not greater than a preset value; eliminating artifacts where the duration of oxygen depletion does not exceed a preset duration, where the duration of oxygen depletion is determined based on the start and end points of the oxygen depletion event; and eliminating artifacts where the lowest blood oxygen saturation value is less than a preset percentage.

2. The method for calculating hypoxia load based on a finger pulse oximeter according to claim 1, characterized in that: The preset value is 1%, the preset duration is 1 second, and the preset percentage is 40%.

3. The method for calculating hypoxia load based on a finger pulse oximeter according to claim 1, characterized in that: The method for calculating the area of ​​each oxygen depletion event is: ， represents the area of ​​the nth oxygen depletion event, represents the starting point of the nth oxygen depletion event, represents the end point of the nth oxygen depletion event, represents the baseline corresponding to the nth oxygen depletion event, represents the oxygen reduction curve corresponding to the nth oxygen reduction event, t represents the time of the oxygen reduction event and , n represents the oxygen depletion event number and , N represents the total number of oxygen depletion events.

4. The method for calculating hypoxia load based on finger pulse oximeter according to claim 1, characterized in that: The method for obtaining low oxygen load is: ， represents the hypoxic load value, N represents the total number of hypoxic events, n represents the hypoxic event number and , represents the area of ​​the nth oxygen reduction event, Indicates the duration of the raw oxygen saturation signal.

5. A hypoxia load calculation system based on a finger pulse oximeter, characterized in that: include: Oxygen saturation signal acquisition module: used to obtain the pulse oximeter monitoring data and extract the original oxygen saturation signal from it. The original oxygen saturation signal has time as the horizontal axis and blood oxygen saturation as the vertical axis; The signal segmentation module is used to traverse the original oxygen saturation signal from the time start point to the time end point, and use the point where the blood oxygen saturation value first decreases as the left boundary point of the current signal segment. Starting from the left boundary point, it searches for the first maximum blood oxygen saturation value that appears within a preset time as the right boundary point of the current signal segment. The above process is repeated until the entire original oxygen saturation signal is divided into multiple signal segments. Oxygen reduction curve acquisition module: For each signal segment, select the smaller value point between its left boundary point and its right boundary point, draw a straight line parallel to the horizontal axis through the smaller value point as the baseline of the signal segment, and define the curve below the baseline in the signal segment as the oxygen reduction curve; An oxygen depletion event determination module is configured to obtain the intersection of each oxygen depletion curve and the corresponding baseline, and use two adjacent intersection points as the start and end points of the oxygen depletion event, wherein the signal segment includes at least one oxygen depletion event; Artifact elimination module: used to eliminate artifacts caused by oxygen depletion events; Hypoxia load calculation module: used to calculate and summarize the area of ​​each oxygen depletion event in each signal segment after excluding artifacts, and obtain the hypoxia load based on the summarized hypoxia area; The method for excluding artifacts of oxygen depletion events is as follows: excluding artifacts where the difference between the lowest blood oxygen saturation value and the baseline between two adjacent intersections is no more than 1%; excluding artifacts where the duration of oxygen depletion does not exceed 1 second; and excluding artifacts where the lowest blood oxygen saturation value is less than 40%.

6. A hypoxia load calculation system based on a finger pulse oximeter according to claim 5, characterized in that: The method for calculating the area of ​​each oxygen depletion event is: ， represents the area of ​​the nth oxygen depletion event, represents the starting point of the nth oxygen depletion event, represents the end point of n oxygen depletion events, represents the baseline corresponding to the nth oxygen depletion event, represents the oxygen reduction curve corresponding to the nth oxygen reduction event, t represents the time of the oxygen reduction event and , n represents the oxygen depletion event number and , N represents the total number of oxygen depletion events.

7. The hypoxia load calculation system based on finger pulse oximeter according to claim 5, characterized in that: The method for obtaining low oxygen load is: ， represents the hypoxic load value, N represents the total number of hypoxic events, n represents the hypoxic event number and , represents the area of ​​the nth oxygen reduction event, Indicates the duration of the raw oxygen saturation signal.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images