CN113768499A - Blood oxygen saturation detection device, system and storage medium - Google Patents
Blood oxygen saturation detection device, system and storage medium Download PDFInfo
- Publication number
- CN113768499A CN113768499A CN202111008101.XA CN202111008101A CN113768499A CN 113768499 A CN113768499 A CN 113768499A CN 202111008101 A CN202111008101 A CN 202111008101A CN 113768499 A CN113768499 A CN 113768499A
- Authority
- CN
- China
- Prior art keywords
- blood oxygen
- pulse wave
- signal
- oxygen signal
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
- A61B5/14551—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/7257—Details of waveform analysis characterised by using transforms using Fourier transforms
Abstract
The invention discloses a blood oxygen saturation detection device, a system and a storage medium. The invention preprocesses the collected blood oxygen signal to obtain an initial blood oxygen signal; performing band-pass filtering on the initial blood oxygen signal to obtain pulse wave data; determining a blood oxygen signal peak point of the initial blood oxygen signal according to the pulse wave data; segmenting the initial blood oxygen signal according to the peak point of the blood oxygen signal to obtain a pulse wave group, and aligning the pulse wave group to obtain an aligned pulse wave group; and fusing the aligned pulse wave groups to obtain a target pulse wave, and determining the blood oxygen saturation according to the target pulse wave. The invention obtains the target pulse wave by carrying out the processing of segmentation, alignment, fusion and the like on the initial blood oxygen signal, and determines the blood oxygen saturation according to the target pulse wave.
Description
Technical Field
The invention relates to the technical field of oxyhemoglobin saturation detection, in particular to a device and a system for detecting oxyhemoglobin saturation and a storage medium.
Background
The blood oxygen saturation (SaO2) reflects the oxygen content level in blood, is an important index for judging the oxygen supply state of a human body, can effectively judge whether the functions of a human body circulatory system and a respiratory system are normal or not through the detection of the blood oxygen saturation, and has important functions in the aspects of neonatal monitoring, sleep apnea monitoring and the like through continuous non-invasive blood oxygen saturation detection.
In the existing scheme, by calculating the form similarity of the red light receiving light intensity data and the infrared light receiving light intensity data, when the form similarity is greater than a set threshold, the motion interference is judged to occur, the motion interference is judged to be more accurate, and the time delay is smaller; and then, calculating a red light interference parameter and an infrared light interference parameter, eliminating the motion interference according to the two parameters and a preset interference reference data sequence, and calculating the blood oxygen value by using the infrared light receiving light intensity data and the red light receiving light intensity data after the motion interference is eliminated. In the prior art, when signals are integrated, the influence of abnormal signals on the calculation of the R value is not considered, and if abnormal signals exist in the middle, the R value may be interfered, so that the precision of the blood oxygen saturation index is influenced.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a device, a system and a storage medium for detecting the blood oxygen saturation, and aims to solve the technical problems of large calculation amount and low detection precision of the blood oxygen saturation detection in the prior art.
To achieve the above object, the present invention provides an oxyhemoglobin saturation detection apparatus comprising: a memory, a processor, and a blood oxygen saturation detection program stored on the memory and executable on the processor, the blood oxygen saturation detection program configured to implement the steps of:
preprocessing the acquired blood oxygen signal to obtain an initial blood oxygen signal;
performing band-pass filtering on the initial blood oxygen signal to obtain pulse wave data;
determining a blood oxygen signal peak point of the initial blood oxygen signal according to the pulse wave data;
segmenting the initial blood oxygen signal according to the blood oxygen signal peak point to obtain a pulse wave group, and aligning the pulse wave group to obtain an aligned pulse wave group;
and fusing the aligned pulse wave groups to obtain a target pulse wave, and determining the blood oxygen saturation according to the target pulse wave.
Optionally, the blood oxygen saturation detection program is configured to implement the steps of:
carrying out fast Fourier transform on the acquired blood oxygen signals to obtain a transform result;
acquiring the number of preset sampling points, and determining the signal quality index of the blood oxygen signal according to the number of the preset sampling points and the transformation result;
judging whether the signal quality index is larger than a preset quality index threshold value or not;
and when the signal quality index is larger than a preset quality index threshold value, taking the blood oxygen signal as an initial blood oxygen signal.
Optionally, the blood oxygen saturation detection program is configured to implement the steps of:
when the signal quality index is smaller than or equal to a preset quality index threshold value, acquiring a red light signal and an infrared light signal in the blood oxygen signal;
determining a noise reference signal according to the red light signal and the infrared light signal;
and carrying out self-adaptive filtering on the blood oxygen signal according to the noise reference signal to obtain a blood oxygen signal with noise eliminated, and taking the blood oxygen signal with noise eliminated as the initial blood oxygen signal.
Optionally, the blood oxygen saturation detection program is configured to implement the steps of:
determining the peak point position of the pulse wave data, and scanning the abnormal value of the peak point position;
removing abnormal peak points according to the abnormal value scanning result to obtain target peak points;
acquiring the delay time of the band-pass filter;
and determining the peak point of the blood oxygen signal of the initial blood oxygen signal according to the delay time length and the target peak point.
Optionally, the blood oxygen saturation detection program is configured to implement the steps of:
taking the blood oxygen signal peak point as a segmentation point, segmenting the initial blood oxygen signal into independent pulse wave bands, and obtaining a pulse wave group;
determining the length of a target pulse wave according to the length of the pulse waves in the pulse wave group;
and resampling the pulse waves in the pulse wave group according to the length of the target pulse wave to obtain the aligned pulse wave group.
Optionally, the blood oxygen saturation detection program is configured to implement the steps of:
removing outlier pulse waves in the aligned pulse wave groups to obtain retained pulse waves;
carrying out average processing on the reserved pulse waves to obtain target pulse waves;
and determining the blood oxygen saturation according to the target pulse wave.
Optionally, the blood oxygen saturation detection program is configured to implement the steps of:
clustering the aligned pulse wave groups through a k-means clustering algorithm to obtain a clustering result;
and determining outlier pulse waves according to the clustering result, and eliminating the outlier pulse waves to obtain retained pulse waves.
Optionally, the blood oxygen saturation detection program is configured to implement the steps of:
averaging the pulse wave groups after alignment to obtain an average pulse wave;
calculating the similarity of each pulse wave in the aligned pulse wave groups according to the average pulse wave;
and rejecting outlier pulse waves in the aligned pulse wave groups according to the similarity to obtain retained pulse waves.
Further, to achieve the above object, the present invention also provides a blood oxygen saturation detection system including: the device comprises a preprocessing module, a band-pass filtering module, a peak point determining module, an alignment module and a fusion module;
the preprocessing module is used for preprocessing the acquired blood oxygen signal to obtain an initial blood oxygen signal;
the band-pass filtering module is used for performing band-pass filtering on the initial blood oxygen signal to obtain pulse wave data;
the peak point determining module is used for determining a blood oxygen signal peak point of the initial blood oxygen signal according to the pulse wave data;
the alignment module is used for segmenting the initial blood oxygen signal according to the peak point of the blood oxygen signal to obtain a pulse wave group, and aligning the pulse wave group to obtain an aligned pulse wave group;
and the fusion module is used for fusing the aligned pulse wave groups to obtain a target pulse wave and determining the blood oxygen saturation according to the target pulse wave.
Further, in order to achieve the above object, the present invention also proposes a storage medium having stored thereon a blood oxygen saturation detection program that realizes, when executed by a processor, the steps of:
preprocessing the acquired blood oxygen signal to obtain an initial blood oxygen signal;
performing band-pass filtering on the initial blood oxygen signal to obtain pulse wave data;
determining a blood oxygen signal peak point of the initial blood oxygen signal according to the pulse wave data;
segmenting the initial blood oxygen signal according to the blood oxygen signal peak point to obtain a pulse wave group, and aligning the pulse wave group to obtain an aligned pulse wave group;
and fusing the aligned pulse wave groups to obtain a target pulse wave, and determining the blood oxygen saturation according to the target pulse wave.
The invention preprocesses the collected blood oxygen signal to obtain an initial blood oxygen signal; performing band-pass filtering on the initial blood oxygen signal to obtain pulse wave data; determining a blood oxygen signal peak point of the initial blood oxygen signal according to the pulse wave data; segmenting the initial blood oxygen signal according to the blood oxygen signal peak point to obtain a pulse wave group, and aligning the pulse wave group to obtain an aligned pulse wave group; and fusing the aligned pulse wave groups to obtain a target pulse wave, and determining the blood oxygen saturation according to the target pulse wave. The invention obtains the target pulse wave by carrying out the processing of segmentation, alignment, fusion and the like on the initial blood oxygen signal, and determines the blood oxygen saturation according to the target pulse wave.
Drawings
Fig. 1 is a schematic structural diagram of a blood oxygen saturation detection device in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a first embodiment of the blood oxygen saturation detection device according to the present invention;
FIG. 3 is a schematic flow chart of a second embodiment of the blood oxygen saturation detection device according to the present invention;
FIG. 4 is a schematic flow chart of a third embodiment of the blood oxygen saturation detection device according to the present invention;
fig. 5 is a block diagram showing the configuration of the system for measuring blood oxygen saturation level according to the first embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a blood oxygen saturation detection apparatus in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the blood oxygen saturation detection apparatus may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the blood oxygen saturation detection device and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and a blood oxygen saturation detection program.
In the blood oxygen saturation detection apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the blood oxygen saturation detection apparatus calls a blood oxygen saturation detection program stored in the memory 1005 by the processor 1001.
Referring to fig. 2, fig. 2 is a schematic flow chart of the device for detecting blood oxygen saturation according to the first embodiment of the present invention.
The embodiment of the invention provides a blood oxygen saturation detection device, which comprises: a memory, a processor, and a blood oxygen saturation detection program stored on the memory and executable on the processor, the blood oxygen saturation detection program configured to implement the steps of: in this embodiment, the blood oxygen saturation detection apparatus includes:
step S10: preprocessing the acquired blood oxygen signal to obtain an initial blood oxygen signal.
It should be noted that the blood oxygen signal may include a red light signal and an infrared light signal. The initial blood oxygen signal may be a blood oxygen signal obtained by preprocessing the blood oxygen signal, determining that the acquired blood oxygen signal satisfies a certain condition, and performing the next blood oxygen saturation detection by using the blood oxygen signal. The preprocessing of the collected blood oxygen signal may be to filter the blood oxygen signal by using a low-pass filter with a cut-off frequency of 10HZ, and then calculate the signal quality of the blood oxygen signal according to the filtered blood oxygen signal. When the signal quality of the blood oxygen signal is greater than a preset quality threshold value, the blood oxygen signal is used as the initial blood oxygen signal, when the signal quality of the blood oxygen signal is less than or equal to the preset quality threshold value, the blood oxygen signal is subjected to noise reduction and other processing, and then the blood oxygen signal is used as the initial blood oxygen signal. The preset quality threshold may be a preset signal quality threshold, and the embodiment is not limited herein.
Step S20: and performing band-pass filtering on the initial blood oxygen signal to obtain pulse wave data.
It should be noted that, the band-pass filtering on the initial blood oxygen signal may be to perform band-pass filtering on the maximum frequency f ± 0.5HZ on the blood oxygen signal, and only keep the pulse wave data, i.e. obtain the pulse wave data. The frequency band setting in the band-pass filtering may be adaptively adjusted according to the actual situation, and the embodiment is not limited herein.
Step S30: and determining the blood oxygen signal peak point of the initial blood oxygen signal according to the pulse wave data.
It should be noted that the blood oxygen signal peak point may be a position point of the highest light intensity in each pulse wave in the blood oxygen signal.
Further, in order to make the detected blood oxygen saturation more accurate, the step S30 includes: determining the peak point position of the pulse wave data, and scanning the abnormal value of the peak point position; removing abnormal peak points according to the abnormal value scanning result to obtain target peak points; acquiring the delay time of the band-pass filter; and determining the peak point of the blood oxygen signal of the initial blood oxygen signal according to the delay time length and the target peak point.
It should be noted that the peak point position may be a peak point position of each pulse wave in the pulse wave data. The target peak point may be a peak point which is reserved after all peak point positions are scanned by abnormal values and the abnormal peak points are removed. The delay duration may be the delay of the bandpass filter used.
In specific implementation, the peak point position of the obtained pulse wave data is determined, abnormal value scanning is carried out on the peak point position, and the scanning process can be that if the peak point interval is greater than 80% of an expected interval, the peak point is determined to be a normal peak point and is reserved; and if the interval of the peak points is less than or equal to 80% of the expected interval, judging the peak points to be abnormal peak points, and removing the abnormal peak points. The expected interval is obtained by dividing the sample rate of the oximetry signal by the maximum frequency of the oximetry signal. Removing abnormal peak points according to the abnormal value scanning result to obtain reserved target peak points; acquiring the delay time of the band-pass filter; and determining the peak point of the blood oxygen signal of the initial blood oxygen signal according to the delay time length and the target peak point. For example, if the target peak point is T and the delay of the band pass filter is Δ T, the blood oxygen signal peak point position T' is T + Δ T.
Step S40: and segmenting the initial blood oxygen signal according to the blood oxygen signal peak point to obtain a pulse wave group, and aligning the pulse wave group to obtain an aligned pulse wave group.
It should be noted that the pulse wave group may be a pulse wave obtained by segmenting the initial blood oxygen signal according to the blood oxygen signal peak point. The aligned pulse wave group may be obtained by resampling each pulse wave in the pulse wave group to the same pulse wave length according to the length of the pulse wave in the pulse wave group. The lengths of the pulse waves in the pulse wave group are made equal.
Further, in order to make the detected blood oxygen saturation more accurate, the step S40 includes: taking the blood oxygen signal peak point as a segmentation point, segmenting the initial blood oxygen signal into independent pulse wave bands, and obtaining a pulse wave group; determining the length of a target pulse wave according to the length of the pulse waves in the pulse wave group; and resampling the pulse waves in the pulse wave group according to the length of the target pulse wave to obtain the aligned pulse wave group.
It should be noted that, the blood oxygen signal peak point is taken as a segmentation point, and the segmentation of the initial blood oxygen signal into individual pulse wave bands may be performed by respectively taking each blood oxygen signal peak point as a segmentation point and segmenting the blood oxygen signal into individual pulse wave bands. The target pulse wavelength may be a length corresponding to a pulse wave having the longest pulse wave length in the pulse wave group. The resampling the pulse waves in the pulse wave group according to the target pulse wave length may be sampling the lengths of the pulse waves in the pulse wave group to the target pulse wave length.
In an implementation, for example, if the peak point of the blood oxygen signal is T ', the blood oxygen signal is divided into len (T ') -1 individual pulse wave bands by using each T ' as a dividing point, so as to obtain pulse wave groups. And removing the head pulse wave and the tail pulse wave which are possibly incomplete to prevent the interference introduced to the subsequent calculation due to the incomplete head pulse wave and the tail pulse wave, and determining the length of the pulse wave with the longest pulse wave length in the pulse wave group, namely the length of the target pulse wave. Sampling the lengths of the pulse waves in the pulse wave group to the target pulse wave length. And obtaining the aligned pulse wave groups.
Step S50: and fusing the aligned pulse wave groups to obtain a target pulse wave, and determining the blood oxygen saturation according to the target pulse wave.
The target pulse wave may be a pulse wave obtained by fusing all the pulse waves in the pulse wave group. The fusing of the aligned pulse wave groups may be fusing the pulse wave groups by a direct averaging method. Alternatively, the outlier pulse waves in the pulse wave group may be removed first and then averaged, which is not limited herein.
It should be understood that the blood oxygen signal includes a red light signal and an infrared light signal, and the target pulse waves include a red light target pulse wave and an infrared light target pulse wave. The above steps S10 to S50 are performed on both the red light signal and the infrared light signal in the collected blood oxygen signal, so as to obtain a red light target pulse wave and an infrared light target pulse wave. Determining the blood oxygen saturation level according to the target pulse wave may be to calculate an R value and a blood oxygen saturation value according to the red target pulse wave and the infrared target pulse wave based on a well-known blood oxygen calculation method, which is not limited herein.
In a specific implementation, for example, there are two pulse waves a and B in the pulse wave group, and fusing the pulse waves a and B by a direct averaging method may be to calculate light intensity values a1 and B1 of the pulse waves a and B at the same time point, calculate an average value of a1 and B1, take the average value as the light intensity value of the fused target pulse wave at the time point, and perform the above operations for each time point on the pulse waves a and B to obtain the target pulse wave. And respectively executing the steps on the red light signal and the infrared light signal in the acquired blood oxygen signals to obtain a red light target pulse wave and an infrared light target pulse wave, and calculating an R value and a blood oxygen saturation value according to the red light target pulse wave and the infrared light target pulse wave based on a known blood oxygen calculation method.
The embodiment preprocesses the collected blood oxygen signal to obtain an initial blood oxygen signal; performing band-pass filtering on the initial blood oxygen signal to obtain pulse wave data; determining a blood oxygen signal peak point of the initial blood oxygen signal according to the pulse wave data; segmenting the initial blood oxygen signal according to the blood oxygen signal peak point to obtain a pulse wave group, and aligning the pulse wave group to obtain an aligned pulse wave group; and fusing the aligned pulse wave groups to obtain a target pulse wave, and determining the blood oxygen saturation according to the target pulse wave. In the embodiment, the target pulse wave is obtained by segmenting, aligning, fusing and the like the initial blood oxygen signal, and the blood oxygen saturation is determined according to the target pulse wave.
Referring to fig. 3, fig. 3 is a schematic flow chart of a second embodiment of the blood oxygen saturation detection device of the present invention.
Based on the first embodiment described above, in the present embodiment, the step S10 includes:
step S101: and carrying out fast Fourier transform on the acquired blood oxygen signals to obtain a transform result.
It should be noted that, performing a fast fourier transform on the acquired blood oxygen signal may be converting the blood oxygen signal into a frequency domain by the fast fourier transform.
Step S102: and acquiring the number of preset sampling points, and determining the signal quality index of the blood oxygen signal according to the number of the preset sampling points and the transformation result.
It should be noted that the preset number of sampling points may be a preset number of sampling points. The transformation result may be the corresponding amplitude of each sample point and the amplitude at the maximum frequency after the fft. The determining the signal quality index of the blood oxygen signal according to the number of the preset sampling points and the transformation result may be calculating the signal quality index of the blood oxygen signal according to the number of the preset sampling points and the transformation result by the following formula:
wherein FQSI is the signal quality index, NnThe amplitude corresponding to the nth sampling point; n is the number of sampling points in the blood oxygen signal, and typical values are 1024, 2048, 4096 and the like; and S is the amplitude at the maximum frequency after the fast Fourier transform.
Step S103: and judging whether the signal quality index is larger than a preset quality index threshold value or not.
It should be noted that the preset quality index threshold may be a preset quality index value. May be 0.25, etc. The setting can be customized according to the actual scene, and the setting is not performed in the embodiment.
Step S104: and when the signal quality index is larger than a preset quality index threshold value, taking the blood oxygen signal as an initial blood oxygen signal.
It should be understood that, in the present embodiment, the quality index of the blood oxygen signal is obtained by quality detection of the blood oxygen signal, and the blood oxygen signal is directly used as the initial blood oxygen signal only when the signal quality index is greater than the preset quality index threshold. And then the calculation of the blood oxygen saturation is carried out.
Further, in order to make the result of the blood oxygen saturation detection more accurate, the step S103 is followed by the step of: when the signal quality index is smaller than or equal to a preset quality index threshold value, acquiring a red light signal and an infrared light signal in the blood oxygen signal; determining a noise reference signal according to the red light signal and the infrared light signal; and carrying out self-adaptive filtering on the blood oxygen signal according to the noise reference signal to obtain a blood oxygen signal with noise eliminated, and taking the blood oxygen signal with noise eliminated as the initial blood oxygen signal.
It should be noted that, determining the noise reference signal according to the red light signal and the infrared light signal may be determining an alternating current signal according to the red light signal and the infrared light signal, performing a difference on the alternating current signal to obtain a noise reference signal, and then performing adaptive filtering on the blood oxygen signal by using the noise reference signal to obtain the blood oxygen signal with the noise removed. And taking the blood oxygen signal after the noise elimination as the initial blood oxygen signal.
The embodiment performs fast Fourier transform on the acquired blood oxygen signal to obtain a transform result; acquiring the number of preset sampling points, and determining the signal quality index of the blood oxygen signal according to the number of the preset sampling points and the transformation result; judging whether the signal quality index is larger than a preset quality index threshold value or not; and when the signal quality index is larger than a preset quality index threshold value, taking the blood oxygen signal as an initial blood oxygen signal. In this embodiment, the quality index of the blood oxygen signal is obtained by detecting the quality of the blood oxygen signal, and the blood oxygen signal is directly used as the initial blood oxygen signal only when the signal quality index is greater than the preset quality index threshold. And then the calculation of the blood oxygen saturation is carried out. When the signal quality index is less than or equal to the preset quality index threshold, noise elimination is required to be performed first, and then the blood oxygen saturation is calculated according to the blood oxygen signal, so that the detection precision of the blood oxygen saturation is improved.
Referring to fig. 4, fig. 4 is a schematic flow chart of a third embodiment of the blood oxygen saturation detection device of the present invention.
Based on the foregoing embodiments, in this embodiment, the step S50 includes:
step S501: and rejecting outlier pulse waves in the aligned pulse wave group to obtain retained pulse waves.
The outlier pulse wave may be a pulse wave having a large difference from an average pulse wave of the pulse wave groups, and the remaining pulse wave may be a pulse wave obtained by removing the outlier pulse wave from the aligned pulse wave groups. The average pulse wave may be a pulse wave obtained by averaging the pulse waves in the pulse wave group.
Further, in order to make the result of the blood oxygen saturation detection more accurate, the step S501 may include: clustering the aligned pulse wave groups through a k-means clustering algorithm to obtain a clustering result; and determining outlier pulse waves according to the clustering result, and eliminating the outlier pulse waves to obtain retained pulse waves.
In the specific implementation, the pulse waves can be divided into two categories by a k-means clustering algorithm (Euclidean distance, cosine distance and the like can be used for distance measurement), the category with less pulse waves is defined as outlier pulse waves, and the pulse waves of the category are removed to obtain the retained pulse waves.
The step S501 may further include: averaging the pulse wave groups after alignment to obtain an average pulse wave; calculating the similarity of each pulse wave in the aligned pulse wave groups according to the average pulse wave; and rejecting outlier pulse waves in the aligned pulse wave groups according to the similarity to obtain retained pulse waves.
The calculating of the similarity of each pulse wave in the aligned pulse wave groups from the average pulse wave may be calculating the similarity of each pulse wave in the aligned pulse wave groups and the average pulse wave. The removing of the outlier pulse waves in the aligned pulse wave groups according to the similarity may be to define the pulse waves with the similarity smaller than a preset similarity threshold as the outlier pulse waves and remove the outlier pulse waves, where the preset similarity threshold may be a threshold set in advance according to information such as the number of the pulse waves, and may be adaptively adjusted according to an actual scene, and this embodiment is not limited herein.
Step S502: and carrying out average processing on the retained pulse waves to obtain target pulse waves.
The averaging process for the remaining pulse wave may be to calculate an average pulse wave corresponding to the remaining pulse wave according to the remaining pulse wave, and use the average pulse wave as the target pulse wave.
Step S503: and determining the blood oxygen saturation according to the target pulse wave.
It should be noted that, the determining of the blood oxygen saturation level according to the target pulse wave may be calculating an R value and a blood oxygen saturation value according to a red target pulse wave and an infrared target pulse wave in the target pulse wave based on a known blood oxygen calculation method, and an appropriate calculation method may be selected according to an actual scene, which is not limited herein.
In the embodiment, outlier pulse waves in the aligned pulse wave group are removed to obtain reserved pulse waves; carrying out average processing on the reserved pulse waves to obtain target pulse waves; and determining the blood oxygen saturation according to the target pulse wave. In the embodiment, the retained pulse waves are obtained by removing outlier pulse waves in the aligned pulse wave groups; and averaging the retained pulse waves to obtain the target pulse waves. Further, the blood oxygen saturation calculated according to the target pulse wave is more accurate.
Referring to fig. 5, fig. 5 is a block diagram of the first embodiment of the blood oxygen saturation detection system of the present invention.
As shown in fig. 5, the system for detecting blood oxygen saturation according to the embodiment of the present invention includes: the system comprises a preprocessing module 10, a band-pass filtering module 20, a peak point determining module 30, an alignment module 40 and a fusion module 50;
the preprocessing module 10 is configured to preprocess the acquired blood oxygen signal to obtain an initial blood oxygen signal;
the band-pass filtering module 20 is configured to perform band-pass filtering on the initial blood oxygen signal to obtain pulse wave data;
the peak point determining module 30 is configured to determine a blood oxygen signal peak point of the initial blood oxygen signal according to the pulse wave data;
the aligning module 40 is configured to segment the initial blood oxygen signal according to the peak point of the blood oxygen signal to obtain a pulse wave group, and align the pulse wave group to obtain an aligned pulse wave group;
the fusion module 50 is configured to fuse the aligned pulse wave groups to obtain a target pulse wave, and determine the blood oxygen saturation level according to the target pulse wave.
The embodiment preprocesses the collected blood oxygen signal to obtain an initial blood oxygen signal; performing band-pass filtering on the initial blood oxygen signal to obtain pulse wave data; determining a blood oxygen signal peak point of the initial blood oxygen signal according to the pulse wave data; segmenting the initial blood oxygen signal according to the blood oxygen signal peak point to obtain a pulse wave group, and aligning the pulse wave group to obtain an aligned pulse wave group; and fusing the aligned pulse wave groups to obtain a target pulse wave, and determining the blood oxygen saturation according to the target pulse wave. In the embodiment, the target pulse wave is obtained by segmenting, aligning, fusing and the like the initial blood oxygen signal, and the blood oxygen saturation is determined according to the target pulse wave.
It should be noted that the above-described work flows are only exemplary, and do not limit the scope of the present invention, and in practical applications, a person skilled in the art may select some or all of them to achieve the purpose of the solution of the embodiment according to actual needs, and the present invention is not limited herein.
In addition, the technical details that are not described in detail in this embodiment may refer to the parameter operation method provided in any embodiment of the present invention, and are not described herein again.
A second embodiment of the system for detecting blood oxygen saturation of the present invention is proposed based on the above first embodiment of the system for detecting blood oxygen saturation of the present invention.
In this embodiment, the preprocessing module 10 is further configured to perform fast fourier transform on the acquired blood oxygen signal to obtain a transform result; acquiring the number of preset sampling points, and determining the signal quality index of the blood oxygen signal according to the number of the preset sampling points and the transformation result; judging whether the signal quality index is larger than a preset quality index threshold value or not; and when the signal quality index is larger than a preset quality index threshold value, taking the blood oxygen signal as an initial blood oxygen signal.
Further, the preprocessing module 10 is further configured to obtain a red light signal and an infrared light signal in the blood oxygen signal when the signal quality index is less than or equal to a preset quality index threshold; determining a noise reference signal according to the red light signal and the infrared light signal; and carrying out self-adaptive filtering on the blood oxygen signal according to the noise reference signal to obtain a blood oxygen signal with noise eliminated, and taking the blood oxygen signal with noise eliminated as the initial blood oxygen signal.
Further, the peak point determining module 30 is further configured to determine a peak point position of the pulse wave data, and perform abnormal value scanning on the peak point position; removing abnormal peak points according to the abnormal value scanning result to obtain target peak points; acquiring the delay time of the band-pass filter; and determining the peak point of the blood oxygen signal of the initial blood oxygen signal according to the delay time length and the target peak point.
Further, the aligning module 40 is further configured to segment the initial blood oxygen signal into individual pulse wave bands by using the peak point of the blood oxygen signal as a segmentation point, so as to obtain pulse wave groups; determining the length of a target pulse wave according to the length of the pulse waves in the pulse wave group; and resampling the pulse waves in the pulse wave group according to the length of the target pulse wave to obtain the aligned pulse wave group.
Further, the fusion module 50 is further configured to remove outlier pulse waves in the aligned pulse wave groups to obtain retained pulse waves; carrying out average processing on the reserved pulse waves to obtain target pulse waves; and determining the blood oxygen saturation according to the target pulse wave.
Further, the fusion module 50 is further configured to cluster the aligned pulse wave groups by using a k-means clustering algorithm to obtain a clustering result; and determining outlier pulse waves according to the clustering result, and eliminating the outlier pulse waves to obtain retained pulse waves.
Further, the fusion module 50 is further configured to average the aligned pulse wave groups to obtain an average pulse wave; calculating the similarity of each pulse wave in the aligned pulse wave groups according to the average pulse wave; and rejecting outlier pulse waves in the aligned pulse wave groups according to the similarity to obtain retained pulse waves.
Other embodiments or specific implementations of the system for detecting blood oxygen saturation of the present invention can refer to the above embodiments of the method, and are not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., a rom/ram, a magnetic disk, an optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. An oxyhemoglobin saturation detection apparatus, characterized by comprising: a memory, a processor, and a blood oxygen saturation detection program stored on the memory and executable on the processor, the blood oxygen saturation detection program configured to implement the steps of:
preprocessing the acquired blood oxygen signal to obtain an initial blood oxygen signal;
performing band-pass filtering on the initial blood oxygen signal to obtain pulse wave data;
determining a blood oxygen signal peak point of the initial blood oxygen signal according to the pulse wave data;
segmenting the initial blood oxygen signal according to the blood oxygen signal peak point to obtain a pulse wave group, and aligning the pulse wave group to obtain an aligned pulse wave group;
and fusing the aligned pulse wave groups to obtain a target pulse wave, and determining the blood oxygen saturation according to the target pulse wave.
2. The blood oxygen saturation detection device according to claim 1, wherein said blood oxygen saturation detection program is configured to realize the steps of:
carrying out fast Fourier transform on the acquired blood oxygen signals to obtain a transform result;
acquiring the number of preset sampling points, and determining the signal quality index of the blood oxygen signal according to the number of the preset sampling points and the transformation result;
judging whether the signal quality index is larger than a preset quality index threshold value or not;
and when the signal quality index is larger than a preset quality index threshold value, taking the blood oxygen signal as an initial blood oxygen signal.
3. The blood oxygen saturation detection device according to claim 2, wherein said blood oxygen saturation detection program is configured to realize the steps of:
when the signal quality index is smaller than or equal to a preset quality index threshold value, acquiring a red light signal and an infrared light signal in the blood oxygen signal;
determining a noise reference signal according to the red light signal and the infrared light signal;
and carrying out self-adaptive filtering on the blood oxygen signal according to the noise reference signal to obtain a blood oxygen signal with noise eliminated, and taking the blood oxygen signal with noise eliminated as the initial blood oxygen signal.
4. The blood oxygen saturation detection device according to claim 1, wherein said blood oxygen saturation detection program is configured to realize the steps of:
determining the peak point position of the pulse wave data, and scanning the abnormal value of the peak point position;
removing abnormal peak points according to the abnormal value scanning result to obtain target peak points;
acquiring the delay time of the band-pass filter;
and determining the peak point of the blood oxygen signal of the initial blood oxygen signal according to the delay time length and the target peak point.
5. The blood oxygen saturation detection device according to claim 1, wherein said blood oxygen saturation detection program is configured to realize the steps of:
taking the blood oxygen signal peak point as a segmentation point, segmenting the initial blood oxygen signal into independent pulse wave bands, and obtaining a pulse wave group;
determining the length of a target pulse wave according to the length of the pulse waves in the pulse wave group;
and resampling the pulse waves in the pulse wave group according to the length of the target pulse wave to obtain the aligned pulse wave group.
6. The blood oxygen saturation detection device according to claim 1, wherein said blood oxygen saturation detection program is configured to realize the steps of:
removing outlier pulse waves in the aligned pulse wave groups to obtain retained pulse waves;
carrying out average processing on the reserved pulse waves to obtain target pulse waves;
and determining the blood oxygen saturation according to the target pulse wave.
7. The blood oxygen saturation detection device according to claim 1, wherein said blood oxygen saturation detection program is configured to realize the steps of:
clustering the aligned pulse wave groups through a k-means clustering algorithm to obtain a clustering result;
and determining outlier pulse waves according to the clustering result, and eliminating the outlier pulse waves to obtain retained pulse waves.
8. The blood oxygen saturation detection device according to claim 1, wherein said blood oxygen saturation detection program is configured to realize the steps of:
averaging the pulse wave groups after alignment to obtain an average pulse wave;
calculating the similarity of each pulse wave in the aligned pulse wave groups according to the average pulse wave;
and rejecting outlier pulse waves in the aligned pulse wave groups according to the similarity to obtain retained pulse waves.
9. An oximetry system, comprising: the device comprises a preprocessing module, a band-pass filtering module, a peak point determining module, an alignment module and a fusion module;
the preprocessing module is used for preprocessing the acquired blood oxygen signal to obtain an initial blood oxygen signal;
the band-pass filtering module is used for performing band-pass filtering on the initial blood oxygen signal to obtain pulse wave data;
the peak point determining module is used for determining a blood oxygen signal peak point of the initial blood oxygen signal according to the pulse wave data;
the alignment module is used for segmenting the initial blood oxygen signal according to the peak point of the blood oxygen signal to obtain a pulse wave group, and aligning the pulse wave group to obtain an aligned pulse wave group;
and the fusion module is used for fusing the aligned pulse wave groups to obtain a target pulse wave and determining the blood oxygen saturation according to the target pulse wave.
10. A storage medium having stored thereon an oxyhemoglobin saturation detection program that when executed by a processor implements the steps of:
preprocessing the acquired blood oxygen signal to obtain an initial blood oxygen signal;
performing band-pass filtering on the initial blood oxygen signal to obtain pulse wave data;
determining a blood oxygen signal peak point of the initial blood oxygen signal according to the pulse wave data;
segmenting the initial blood oxygen signal according to the blood oxygen signal peak point to obtain a pulse wave group, and aligning the pulse wave group to obtain an aligned pulse wave group;
and fusing the aligned pulse wave groups to obtain a target pulse wave, and determining the blood oxygen saturation according to the target pulse wave.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111008101.XA CN113768499A (en) | 2021-08-30 | 2021-08-30 | Blood oxygen saturation detection device, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111008101.XA CN113768499A (en) | 2021-08-30 | 2021-08-30 | Blood oxygen saturation detection device, system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113768499A true CN113768499A (en) | 2021-12-10 |
Family
ID=78840096
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111008101.XA Pending CN113768499A (en) | 2021-08-30 | 2021-08-30 | Blood oxygen saturation detection device, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113768499A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140187883A1 (en) * | 2012-12-28 | 2014-07-03 | Covidient LP | Systems and methods for ensemble averaging in pulse oximetry |
| CN104684459A (en) * | 2012-08-01 | 2015-06-03 | 皇家飞利浦有限公司 | A method and system to identify motion artifacts and improve reliability of measurements and alarms in photoplethysmographic measurements |
| US20160220188A1 (en) * | 2015-01-29 | 2016-08-04 | Ki H. Chon | Motion and noise artifact detection and reconstruction algorithms for photoplethysmogram and equivalent signals |
| CN110753515A (en) * | 2017-05-18 | 2020-02-04 | 普瑞温迪克斯有限责任公司 | Reliable acquisition of photoplethysmographic data |
-
2021
- 2021-08-30 CN CN202111008101.XA patent/CN113768499A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104684459A (en) * | 2012-08-01 | 2015-06-03 | 皇家飞利浦有限公司 | A method and system to identify motion artifacts and improve reliability of measurements and alarms in photoplethysmographic measurements |
| US20140187883A1 (en) * | 2012-12-28 | 2014-07-03 | Covidient LP | Systems and methods for ensemble averaging in pulse oximetry |
| US20160220188A1 (en) * | 2015-01-29 | 2016-08-04 | Ki H. Chon | Motion and noise artifact detection and reconstruction algorithms for photoplethysmogram and equivalent signals |
| CN110753515A (en) * | 2017-05-18 | 2020-02-04 | 普瑞温迪克斯有限责任公司 | Reliable acquisition of photoplethysmographic data |
Non-Patent Citations (2)
| Title |
|---|
| GARCIA-LOPEZ I, IMTIAZ SA, RODRIGUEZ-VILLEGAS E.: "Characterization Study of Neck Photoplethysmography.", ANNU INT CONF IEEE ENG MED BIOL SOC * |
| 张浩: "基于光电容积脉搏波的血氧饱和度算法研究", 硕士电子期刊, pages 22 - 29 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10304267B2 (en) | Systems, apparatus, and methods for continuous authentication | |
| EP2351524B1 (en) | Drowsiness determining device and program | |
| EP3087915A1 (en) | Method and system for noise cleaning of photoplethysmogram signals for estimating blood pressure | |
| EP2777485B1 (en) | Signal processor, signal processing method, and signal processing program | |
| EP2124185A1 (en) | Hair image display method and display device | |
| CN105205464A (en) | Fingerprint identification method, fingerprint identification device and terminal | |
| CN108324271B (en) | Electrocardiosignal identification method and system and electrocardiosignal monitoring equipment | |
| CN110547783A (en) | non-contact heart rate detection method, system, equipment and storage medium | |
| CN107233103B (en) | High-speed rail dispatcher fatigue state evaluation method and system | |
| CN109843158A (en) | Judge the whether effective method and device of pulse wave | |
| EP2975844B1 (en) | Image processing device, image processing method, and program | |
| CN111513701A (en) | Heart rate detection method and device, computer equipment and readable storage medium | |
| Rasoulzadeh et al. | A comparative stationarity analysis of EEG signals | |
| CN105796115A (en) | Blood oxygen measurement method and system | |
| CN113768499A (en) | Blood oxygen saturation detection device, system and storage medium | |
| KR101957019B1 (en) | ECG Template Detection Method of Wearable Device for Personal Authentication | |
| JP5365632B2 (en) | Authentication apparatus and authentication method | |
| CN116778758A (en) | Unmanned aerial vehicle remote control signal identification method, device, equipment and medium based on time-frequency diagram | |
| CN110584662A (en) | Self-imposed disease risk quantification method and device based on electroencephalogram information and storage medium | |
| CN113331824B (en) | Blink judgment method and device based on laser measurement | |
| CN107392099B (en) | Method and device for extracting hair detail information and terminal equipment | |
| CN110313902B (en) | Blood volume change pulse signal processing method and related device | |
| CN111685730B (en) | Non-contact physiological parameter detection method, system, terminal equipment and storage medium | |
| CN110151182B (en) | Apnea type identification method and device | |
| CN110647870B (en) | Method for calculating approximate entropy of resting state fMRI data based on sliding window |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |