CN115836863A - Bioelectric signal processing device and method for spinal curvature screening - Google Patents
Bioelectric signal processing device and method for spinal curvature screening Download PDFInfo
- Publication number
- CN115836863A CN115836863A CN202211484692.2A CN202211484692A CN115836863A CN 115836863 A CN115836863 A CN 115836863A CN 202211484692 A CN202211484692 A CN 202211484692A CN 115836863 A CN115836863 A CN 115836863A
- Authority
- CN
- China
- Prior art keywords
- data
- signal
- screening
- bioelectrical
- mathematical model
- 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.)
- Granted
Links
- 238000012216 screening Methods 0.000 title claims abstract description 74
- 208000000875 Spinal Curvatures Diseases 0.000 title claims abstract description 46
- 238000012545 processing Methods 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000012544 monitoring process Methods 0.000 claims abstract description 51
- 238000013178 mathematical model Methods 0.000 claims abstract description 36
- 238000000605 extraction Methods 0.000 claims abstract description 26
- 230000004069 differentiation Effects 0.000 claims abstract description 10
- 210000003414 extremity Anatomy 0.000 claims description 21
- 206010039722 scoliosis Diseases 0.000 claims description 18
- 210000003141 lower extremity Anatomy 0.000 claims description 13
- 238000003672 processing method Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 8
- 201000010099 disease Diseases 0.000 claims description 6
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 6
- 238000012806 monitoring device Methods 0.000 claims description 6
- 230000008506 pathogenesis Effects 0.000 claims description 6
- 210000004247 hand Anatomy 0.000 claims description 5
- 210000000245 forearm Anatomy 0.000 claims description 4
- 230000005484 gravity Effects 0.000 claims description 4
- 210000001364 upper extremity Anatomy 0.000 claims description 4
- 210000000689 upper leg Anatomy 0.000 claims description 4
- 238000003066 decision tree Methods 0.000 claims description 3
- 230000003183 myoelectrical effect Effects 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 2
- 230000003595 spectral effect Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 13
- 239000003814 drug Substances 0.000 description 8
- 230000000694 effects Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000001914 filtration Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 238000009532 heart rate measurement Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 230000035485 pulse pressure Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 210000001367 artery Anatomy 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 210000000056 organ Anatomy 0.000 description 2
- 208000034347 Faecal incontinence Diseases 0.000 description 1
- 239000002033 PVDF binder Substances 0.000 description 1
- 208000003443 Unconsciousness Diseases 0.000 description 1
- 206010046543 Urinary incontinence Diseases 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 244000309466 calf Species 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 210000003608 fece Anatomy 0.000 description 1
- 238000001727 in vivo Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000004630 mental health Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 231100000862 numbness Toxicity 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 229920002981 polyvinylidene fluoride Polymers 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 230000004800 psychological effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 210000000278 spinal cord Anatomy 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 210000001835 viscera Anatomy 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 210000000707 wrist Anatomy 0.000 description 1
Images
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The application discloses a bioelectric signal processing device and a method for screening spinal curvature, which are characterized in that firstly, bioelectric signals of the same parts of the left side and the right side of four limbs are monitored so as to respectively obtain the monitoring data of the bioelectric signals of the left side and the right side; performing data characteristic extraction on the biological signal monitoring data on the left side and the right side to obtain biological signal characteristic data on the left side and the right side; then inputting biological characteristic difference data obtained by carrying out differentiation comparison on the biological signal characteristic data on the left side and the right side into a spine curvature screening mathematical model; and finally, screening matching parameters output according to the spine curvature screening mathematical model are used as the basis for outputting the spine curvature screening result. The bioelectricity signals of the same positions of the left side and the right side of the four limbs have different characteristics by applying the spinal curvature, so that the spinal curvature screening is performed, and the efficiency and the accuracy of the spinal curvature screening can be remarkably improved.
Description
Technical Field
The invention relates to the technical field of health examination, in particular to a bioelectric signal processing device and method for spinal curvature screening.
Background
Scoliosis, commonly known as scoliosis, is the most serious of the risks to children and adolescents because of scoliosis, the growth, development and height of children are limited, and some organs including lungs and heart may be affected. The lateral curvature of the spine gradually aggravates, and then the nerve root or the spinal cord is pressed, so that the lower limbs are weak, numb or unstable in walking, and even incontinence of urine and feces is caused. It can also cause pain in the back and waist, restricted movement or local numbness, and also can cause psychological effects, such as unconsciousness, which have great influence on the mental health of children. At the present stage, screening and detection aiming at the scoliosis are performed by experienced physical examination doctors in a touch and visual observation mode, the screening efficiency and accuracy are low, the scoliosis is relatively serious even if the screening is performed, how to realize scientific and effective early screening of the scoliosis is a key subject concerned in the technical field of physical examination at the present stage.
Disclosure of Invention
The invention mainly solves the technical problem of how to realize early screening of scoliosis based on bioelectricity signals.
According to a first aspect, there is provided in an embodiment a bioelectric signal processing apparatus for spinal curvature screening, comprising:
the bioelectrical signal monitoring unit is used for monitoring bioelectrical signals of the same parts on the left side and the right side of the four limbs so as to respectively acquire the monitoring data of the bioelectrical signals on the left side and the right side; the four limbs comprise upper limbs and lower limbs, the lower limbs comprise forearms, upper arms and hands, and the lower limbs comprise thighs, shanks and feet;
the data feature extraction unit is used for respectively extracting data features of the biological signal monitoring data on the left side and the right side in the same data feature extraction mode so as to obtain biological signal feature data on the left side and the right side; the biological signal characteristic data comprises a signal time domain characteristic and a signal frequency domain characteristic; the signal time domain features and the signal frequency domain features respectively comprise root mean square, peak-to-peak, kurtosis, skewness, mean, variance and/or center-of-gravity frequency of spectrum amplitude;
the difference data acquisition unit is used for carrying out difference comparison on the biological signal characteristic data on the left side and the right side so as to acquire biological characteristic difference data;
the matching parameter acquisition unit is used for inputting the biological characteristic difference data into a spinal curvature screening mathematical model so as to acquire screening matching parameters output by the spinal curvature screening mathematical model;
and the screening result output unit is used for outputting the spinal curvature screening result according to the screening matching parameters.
According to a second aspect, there is provided in an embodiment a method of bioelectric signal processing for spinal curvature screening, comprising:
monitoring the bioelectric signals of the same parts of the left and right opposite sides of the four limbs so as to respectively obtain the monitoring data of the bioelectric signals of the left and right sides;
respectively carrying out data feature extraction on the biological signal monitoring data on the left side and the right side in the same data feature extraction mode to obtain biological signal feature data on the left side and the right side;
performing differentiation comparison on the biological signal characteristic data on the left side and the right side to obtain biological characteristic difference data;
inputting the biological characteristic difference data into a spinal curvature screening mathematical model to obtain screening matching parameters output by the spinal curvature screening mathematical model; the screening matching parameters are used for spinal curvature screening.
According to a third aspect, an embodiment provides a computer-readable storage medium, characterized in that the medium has a program stored thereon, the program being executable by a processor to implement the bioelectric signal processing method according to the second aspect.
According to the bioelectric signal processing device of the embodiment, the bioelectric signals of the same parts of the left side and the right side of the four limbs have the difference characteristic by applying the spinal curvature, so that the spinal curvature screening is performed, and the efficiency and the accuracy of the spinal curvature screening can be remarkably improved.
Drawings
FIG. 1 is a block diagram showing the structure of a bioelectrical signal processing apparatus according to an embodiment;
FIG. 2 is a schematic diagram of a pulse monitoring device according to an embodiment;
FIG. 3 is a schematic flow chart of a bioelectric signal processing method according to an embodiment;
FIG. 4 is a graph showing a pulse-pressure curve according to an embodiment;
FIG. 5 is a diagram illustrating the filtering effect of the electrical pulse signal according to an embodiment;
FIG. 6 is a schematic diagram of a sink-float signal extraction according to an embodiment;
FIG. 7 is a diagram illustrating the result of separately extracting floating and sinking signals according to an embodiment;
fig. 8 is a diagram illustrating the results of normalization processing performed on the sink-float signals respectively according to an embodiment.
Detailed Description
The present invention will be described in further detail with reference to the following detailed description and accompanying drawings. Wherein like elements in different embodiments are numbered with like associated elements. In the following description, numerous details are set forth in order to provide a better understanding of the present application. However, those skilled in the art will readily recognize that some of the features may be omitted or replaced with other elements, materials, methods in different instances. In some instances, certain operations related to the present application have not been shown or described in this specification in order not to obscure the core of the present application with unnecessary detail, and it is not necessary for those skilled in the art to describe these operations in detail, so that they may be fully understood from the description in the specification and the general knowledge in the art.
Furthermore, the features, operations, or characteristics described in the specification may be combined in any suitable manner to form various embodiments. Also, the various steps or actions in the method descriptions may be transposed or transposed in order, as will be apparent to one of ordinary skill in the art. Thus, the various sequences in the specification and drawings are for the purpose of describing certain embodiments only and are not intended to imply a required sequence unless otherwise indicated where such sequence must be followed.
The numbering of the components as such, e.g., "first", "second", etc., is used herein only to distinguish the objects as described, and does not have any sequential or technical meaning. The term "connected" and "coupled" when used in this application, unless otherwise indicated, includes both direct and indirect connections (couplings).
In the theory of traditional Chinese medicine, the spinal curvature can be quickly diagnosed by pulse taking, and the spinal curvature can be subjected to reduction treatment through bonesetting subsequently, so that the spinal curvature has a better treatment effect. Generally, the pulse taking of traditional Chinese medicine is used for diagnosing the spinal curvature, which does not exceed one minute, and is more convenient and quicker compared with the conventional medical means (such as X-ray detection and the like). On the basis of the traditional Chinese medical treatment means, the method adopts a scientific bioelectricity signal acquisition mode and monitoring data digital statistics to realize the rapid screening of the spinal curvature.
The first embodiment is as follows:
referring to fig. 1, which is a block diagram illustrating a structure of a bioelectrical signal processing apparatus in an embodiment, the bioelectrical signal processing apparatus 1 includes a bioelectrical signal monitoring unit 10, a data feature extraction unit 20, a difference data acquisition unit 30, a matching parameter acquisition unit 40, and a screening result output unit 50. The bioelectrical signal monitoring unit 10 is configured to monitor bioelectrical signals at the same positions on the left and right opposite sides of the four limbs, so as to obtain the monitoring data of the bioelectrical signals on the left and right sides, respectively. Wherein the limbs include upper limbs and lower limbs, the lower limbs include forearms, upper arms and hands, and the lower limbs include thighs, calves and feet. The data feature extraction unit 20 is configured to perform data feature extraction on the left and right biological signal monitoring data in the same data feature extraction manner, respectively, to obtain left and right biological signal feature data. The biological signal characteristic data comprises signal time domain characteristics and signal frequency domain characteristics, and the signal time domain characteristics and the signal frequency domain characteristics respectively comprise root mean square, peak-to-peak value, kurtosis, skewness, mean value, variance and/or center of gravity frequency of frequency spectrum amplitude. The difference data acquiring unit 30 is configured to compare the biological signal characteristic data on the left and right sides in a differentiation manner to acquire biological characteristic difference data. The matching parameter acquiring unit 40 is used for inputting the biological characteristic difference data into a spinal curvature screening mathematical model to acquire the screening matching parameters output by the spinal curvature screening mathematical model. The screening result output unit 50 is used for outputting the spinal curvature screening result according to the screening matching parameters.
In one embodiment, the method for obtaining the spinal curvature screening mathematical model comprises the following steps:
firstly, monitoring bioelectric signals of the same parts of the left side and the right side of the four limbs of scoliosis patients with different types, grades and/or pathogenesis respectively to obtain sample signal monitoring data; then, respectively carrying out data feature extraction on the sample signal monitoring data on the left side and the sample signal monitoring data on the right side in the same data feature extraction mode to obtain sample signal feature data on the left side and the sample signal feature data on the right side; then, carrying out differentiation comparison on the sample signal characteristic data on the left side and the right side to obtain sample characteristic difference data; and finally, inputting the type, grade and/or pathogenesis of the scoliosis corresponding to the sample characteristic difference data into a preset training mathematical model for training by using the sample characteristic difference data sample set and the type, grade and/or pathogenesis of the scoliosis corresponding to the sample characteristic difference data as labels to obtain the scoliosis screening mathematical model.
In one embodiment, the trained mathematical model is a classification mathematical model. In one embodiment, the classification mathematical model includes an SVM, XG-Boost, and/or decision tree classifier.
Referring to fig. 2, a schematic structural connection diagram of a pulse monitoring device in an embodiment is shown, in which the bioelectrical signal monitoring unit includes a pulse monitoring device, and the pulse monitoring device 11 includes a bioelectrical signal sensor 111, a dynamic pressure applying device 112, and an electrical signal collecting device 113. The dynamic pressure applying device 112 is used for pressing the bioelectrical signal sensor 111 on the part to be monitored, and applying a pressing force to the bioelectrical signal sensor 111 according to a preset pressure change curve. The bioelectrical signal sensor 111 is used for monitoring a bioelectrical signal of a portion to be monitored, and sending the bioelectrical signal obtained by monitoring to the electric signal acquisition device 113. The electrical signal acquisition device 113 is used for converting the biological electrical signal into biological signal monitoring data.
The Pulse (Pulse) is an artery Pulse that can be touched on the body surface of a human body. Pulse taking is also called pulse feeling, which is a diagnostic method for TCM to understand the intrinsic changes of disease by pressing the arteries of a patient with hands according to the pulse condition. The pulse-taking is composed of the manifestation position (deep or shallow), rate (fast or slow), intensity (forceful or weak), rhythm (regular or not, intermittent or not) and morphology of the arterial pulse. The pulse condition is an important basis for the syndrome differentiation of traditional Chinese medicine, and has important clinical significance for distinguishing the causes of diseases, deducing the changes of the diseases, identifying the true and false of the disease conditions, judging the prognosis of the diseases and the like.
In one embodiment, the bioelectric signal monitoring unit 10 is used for monitoring bioelectric signals of the same parts of the left and right opposite sides of the four limbs when the person to be monitored stands, sits quietly and/or lies quietly. In one embodiment, the site to be monitored is placed on the meridian points of the extremities.
In an embodiment of the present application, the bioelectrical signal sensor 111 employs a T-shaped pulse sensor based on PVDF, which can realize accurate positioning during pulse measurement, and can perform pulse measurement more accurately and effectively, thereby greatly reducing measurement errors caused by myoelectric interference and displacement during the test. The T-shaped structure can convert the pulse in the vertical direction into the pulse in the horizontal direction for conduction, thereby being beneficial to the extension of the piezoelectric film, leading the piezoelectric film to play the piezoelectric effect to a greater extent and generate larger deformation, further generating electric signals with larger amplitude and effectively improving the signal-to-noise ratio of the signals. The pulse measurement is very sensitive to pressure, and the traditional Chinese medicine can accurately distinguish the health conditions of different organs according to different forces such as floating, sinking and the like. However, the pulse-taking process is easy to be in mind and is difficult to be clarified, the floating and sinking forces are still indefinite, and different individual body conditions are different, so that a uniform force index cannot be formed. In order to avoid the interference caused by the pressure, in an embodiment of the present application, the dynamic pressure applying device 112 applies a pressing force to the bioelectrical signal sensor 111 according to a preset pressure variation curve, and a pulse collecting mode under continuously varying pressure can collect more abundant information. In one embodiment, the pulse signals obtained by measurement under continuously changing pressure are subjected to subsequent analysis to form a pulse-pressure curve, a floating-middle-deep slicing algorithm is customized by combining a large amount of data analysis, wherein the middle pulse is defined as the position with the maximum pulse condition amplitude in the abandoning process, and the sinking and floating positions are the position of% d (variable value given after integer output), so that abundant floating-middle-deep pulse conditions are obtained, and the perception of the floating-middle-deep pulse of the pulse feeling of traditional Chinese medicine is simulated. Wherein d can be 0-100, and in one embodiment of the present application d is 50 according to the statistical data and the actual effect.
In the embodiment of the application, the spinal curvature is screened by adopting the difference characteristic of the bioelectric signals of the same parts of the left side and the right side of the four limbs, and the cunguanchi pulse signals of the left hand and the right hand considered in the theory of traditional Chinese medicine respectively represent the health degrees of different internal organs in vivo. According to the method, the traditional Chinese medicine clinical experience and the definition and the performance of the spinal curvature in modern medicine are combined, the sensor and the collection mode are adopted to collect the pulse at the same position of the left hand and the right hand, the signals are subjected to differential comparison, the differential characteristics are extracted, the differential characteristics are combined with the clinical diagnosis result of a doctor, data analysis is carried out, a spinal curvature screening mathematical model is obtained, and the screening process only needs to collect the waveform at the same position of the left hand and the right hand and is led into the model, so that the judgment result of whether the spinal curvature exists can be obtained.
Referring to fig. 3, a schematic flow chart of a bioelectric signal processing method in an embodiment is shown, and an embodiment of the present application further discloses a bioelectric signal processing method for spinal curvature screening, which can be applied to the bioelectric signal processing apparatus described above, and the method specifically includes:
And monitoring the bioelectric signals of the same parts on the left side and the right side of the four limbs so as to respectively obtain the monitoring data of the bioelectric signals on the left side and the right side.
And respectively carrying out data feature extraction on the biological signal monitoring data on the left side and the right side in the same data feature extraction mode to obtain the biological signal feature data on the left side and the right side.
And step 103, acquiring the biological characteristic difference data.
And performing differentiation comparison on the biological signal characteristic data of the left side and the right side to obtain biological characteristic difference data.
And 104, acquiring screening matching parameters.
The biometric difference data is input into the spinal curvature screening mathematical model as previously described to obtain screening matching parameters output by the spinal curvature screening mathematical model, wherein the screening matching parameters are used for spinal curvature screening.
In one embodiment, the bio-electrical signal comprises a myoelectric and/or pulse electrical signal, the bio-signal feature data comprises signal time-domain features and signal frequency-domain features, the signal time-domain features and the signal frequency-domain features respectively comprise a root mean square, a peak-to-peak value, a kurtosis, a skewness, a mean, a variance, and/or a center of gravity frequency of spectral amplitudes.
In order to facilitate understanding of the application of the bioelectrical signal processing method disclosed in the present application, the following description is made by way of an example of practical application.
In this embodiment, the dynamic pressure applying device includes an airbag, an electromagnetic valve and an air pump, the bioelectrical signal sensor is a T-shaped sensor, and the air pump and the signal acquisition and processing are controlled by the MCU. The T-shaped sensor is fixed at the wrist of the left hand (including but not limited to the size, the closing position and the size) through the air bag, the air pump is controlled by the MCU to pressurize the air bag, the air pump is stopped after 200mmhg is added, the air pump is closed, the electromagnetic valve is controlled to uniformly deflate the system to 20mmhg, and pulse signals in the deflation process are collected and stored. And repeating the process to collect the same position of the right hand, after the collection is finished, performing relevant preprocessing on the signals by the MCU, extracting the characteristics, sending the characteristics into the spine curvature screening mathematical model for judgment, and obtaining a screening result.
Fig. 4 is a schematic diagram of a pulse-pressure curve in an embodiment, in which a curve 2 is a pressure curve and a curve 1 is a pulse curve obtained by monitoring.
Referring to fig. 5, a schematic diagram of a filtering effect of a pulse electrical signal in an embodiment is shown, where the pulse electrical signal output by the T-shaped sensor is band-pass filtered to remove baseline wander and power frequency interference, where an upper graph in fig. 5 is before filtering and a lower graph in fig. 5 is after filtering. The parameters of the filter can be any band-pass filter with a lower limit larger than 0.1Hz, an upper limit smaller than 50Hz and a lower limit smaller than the upper limit, and a 4-order Butterworth 0.5-40Hz band-pass filter is selected in one embodiment of the application.
Referring to fig. 6, a schematic diagram of floating-sinking signal extraction in an embodiment is shown, which extracts a signal in an air release stage according to a pressure curve to realize the extraction of the floating-sinking signal, wherein "fu", "zhong", and "chen" respectively represent the extraction sections of the floating signal, the mid signal, and the sinking signal. The intercepted signal segment may be all signals within 20-200mmhg, and in one embodiment, signals within 25-180mmhg are selected.
Please refer to fig. 7, which is a schematic diagram illustrating the result of separately extracting floating, middle and sinking signals in an embodiment, wherein the floating, middle and sinking signals are sequentially from top to bottom, and pulse signals of the front and back N seconds under the pressure corresponding to floating, middle and sinking are respectively extracted and obtained.
Please refer to fig. 8, which is a schematic diagram illustrating the results of performing normalization processing on the floating and sinking signals respectively in an embodiment, wherein N is any positive integer, and the value of N is not less than 3 in an embodiment.
And extracting time-frequency domain characteristics and frequency domain characteristics of the result signals of the floating-sinking signal normalization processing, differentiating the characteristics of the left hand and the right hand, and labeling the characteristics according to the diagnosis and treatment (all the time-frequency domain characteristics can be obtained, and 11-dimensional time domain signals and 12-dimensional frequency domain signals such as the root mean square, the peak-peak value, the kurtosis, the skewness, the mean value, the variance, the center-of-gravity frequency and the like of the differential signals are selected according to experience and actual effects in the patent). And finally, the features and the corresponding labels are sent into a classifier, a model is trained (any basic classifier is adopted, and an SVM classifier is adopted according to experience and actual effect in the embodiment), as many features as possible can be extracted firstly when the features are screened, the features are sent into XGBoost to obtain the correlation between each feature and a classification result, and the key features are screened after sorting.
In the embodiment of the application, the T-shaped pulse sensor is used for solving the problems of unstable data, jitter and the like during acquisition, the signal to noise ratio is greatly improved, and stable support is provided for subsequent data analysis. In addition, in order to solve the problem of measurement interference caused by uncertain pressure, the method creatively provides the steps of collecting pulse signals under continuously changing pressure, combining a self-defined floating-sinking algorithm, slicing data to obtain rich floating-sinking signals, and facilitating subsequent analysis. Meanwhile, according to the physiological characteristics of the spine and the clinical performance after bending, pulse signals under the same positions of the left hand and the right hand are collected and subjected to differential processing, so that extra interference caused by individual difference, measurement and the like is effectively reduced. The bioelectrical signal processing method obtains the scoliosis screening result according to the differential signal characteristics, and is convenient, rapid and low in cost.
The bioelectric signal processing device disclosed by the application monitors bioelectric signals of the same parts on the left side and the right side of four limbs to respectively acquire the monitoring data of the bioelectric signals on the left side and the right side; performing data characteristic extraction on the biological signal monitoring data on the left side and the right side to obtain biological signal characteristic data on the left side and the right side; then inputting biological characteristic difference data obtained by performing differentiation comparison on the biological signal characteristic data on the left side and the right side into a spine curvature screening mathematical model; and finally, screening matching parameters output according to the spine curvature screening mathematical model are used as the basis for outputting the spine curvature screening result. The bioelectricity signals of the same parts of the left side and the right side of the four limbs have different characteristics by applying the spinal curvature to screen the spinal curvature, so that the efficiency and the accuracy of the spinal curvature screening can be remarkably improved
Those skilled in the art will appreciate that all or part of the functions of the various methods in the above embodiments may be implemented by hardware, or may be implemented by computer programs. When all or part of the functions of the above embodiments are implemented by a computer program, the program may be stored in a computer-readable storage medium, and the storage medium may include: a read only memory, a random access memory, a magnetic disk, an optical disk, a hard disk, etc., and the program is executed by a computer to realize the above functions. For example, the program may be stored in a memory of the device, and when the program in the memory is executed by the processor, all or part of the functions described above may be implemented. In addition, when all or part of the functions in the above embodiments are implemented by a computer program, the program may be stored in a storage medium such as a server, another computer, a magnetic disk, an optical disk, a flash disk, or a removable hard disk, and may be downloaded or copied to a memory of a local device, or may be version-updated in a system of the local device, and when the program in the memory is executed by a processor, all or part of the functions in the above embodiments may be implemented.
The present invention has been described in terms of specific examples, which are provided to aid understanding of the invention and are not intended to be limiting. For a person skilled in the art to which the invention pertains, several simple deductions, modifications or substitutions may be made according to the idea of the invention.
Claims (10)
1. A bioelectrical signal processing device for spinal curvature screening, comprising:
the bioelectrical signal monitoring unit is used for monitoring bioelectrical signals of the same parts on the left side and the right side of the four limbs so as to respectively acquire the monitoring data of the bioelectrical signals on the left side and the right side; the four limbs comprise upper limbs and lower limbs, the lower limbs comprise forearms, upper arms and hands, and the lower limbs comprise thighs, shanks and feet;
the data feature extraction unit is used for respectively extracting data features of the biological signal monitoring data on the left side and the right side in the same data feature extraction mode so as to obtain biological signal feature data on the left side and the right side; the biological signal characteristic data comprises a signal time domain characteristic and a signal frequency domain characteristic; the signal time domain features and the signal frequency domain features respectively comprise root mean square, peak-to-peak, kurtosis, skewness, mean, variance and/or center of gravity frequency of spectrum amplitude;
the difference data acquisition unit is used for carrying out difference comparison on the biological signal characteristic data on the left side and the right side so as to acquire biological characteristic difference data;
the matching parameter acquisition unit is used for inputting the biological characteristic difference data into a spinal curvature screening mathematical model so as to acquire screening matching parameters output by the spinal curvature screening mathematical model;
and the screening result output unit is used for outputting the spinal curvature screening result according to the screening matching parameters.
2. The bioelectrical signal processing apparatus as claimed in claim 1, wherein the method of acquiring the spinal curvature screening mathematical model comprises:
monitoring bioelectric signals of the same parts of the left side and the right side of the four limbs of scoliosis patients with different types, grades and/or pathogenesis respectively to obtain sample signal monitoring data;
respectively carrying out data feature extraction on the sample signal monitoring data on the left side and the sample signal monitoring data on the right side in the same data feature extraction mode to obtain sample signal feature data on the left side and the sample signal feature data on the right side;
performing differentiation comparison on the sample signal characteristic data on the left side and the right side to obtain sample characteristic difference data;
and inputting the sample characteristic difference data sample set and the type, grade and/or pathogenesis of the scoliosis corresponding to the sample characteristic difference data as labels into a preset training mathematical model for training so as to obtain the scoliosis screening mathematical model.
3. The bioelectrical signal processing apparatus according to claim 2, wherein the training mathematical model is a classification mathematical model; the classification mathematical model comprises an SVM, XG-Boost and/or decision tree classifier.
4. The bioelectrical signal processing device according to claim 1, wherein the bioelectrical signal monitoring unit comprises a pulse monitoring device;
the pulse monitoring device comprises a bioelectrical signal sensor, a dynamic pressure applying device and an electric signal collecting device;
the dynamic pressure applying device is used for pressing the bioelectrical signal sensor on a part to be monitored and applying pressing force to the bioelectrical signal sensor according to a preset pressure change curve;
the bioelectrical signal sensor is used for monitoring a bioelectrical signal of the part to be monitored and sending the bioelectrical signal obtained by monitoring to the electric signal acquisition device;
the electric signal acquisition device is used for converting the biological electric signals into biological signal monitoring data.
5. The bioelectrical signal processing device according to claim 4, wherein the site to be monitored is provided on meridian points of the limbs.
6. The bioelectrical signal processing device according to claim 4, wherein the bioelectrical signal monitoring unit is configured to monitor the bioelectrical signals of the same portion on the left and right opposite sides of the extremity when the person to be monitored stands, sits quietly and/or lies quietly.
7. A method of bioelectrical signal processing for spinal curvature screening, comprising:
monitoring the bioelectric signals of the same parts of the left and right opposite sides of the four limbs so as to respectively obtain the monitoring data of the bioelectric signals of the left and right sides;
respectively carrying out data feature extraction on the biological signal monitoring data on the left side and the right side in the same data feature extraction mode to obtain biological signal feature data on the left side and the right side;
performing differentiation comparison on the biological signal characteristic data on the left side and the right side to obtain biological characteristic difference data;
inputting the biological characteristic difference data into a spine curvature screening mathematical model to obtain screening matching parameters output by the spine curvature screening mathematical model; the screening matching parameters are used for spinal curvature screening.
8. The bioelectrical signal processing method as claimed in claim 7, wherein the obtaining method of the spinal curvature screening mathematical model comprises:
respectively monitoring bioelectric signals of the same parts of the left side, the right side and the opposite side of the four limbs of scoliosis patients with different types, grades and/or disease causes to obtain sample signal monitoring data;
respectively carrying out data feature extraction on the sample signal monitoring data on the left side and the sample signal monitoring data on the right side in the same data feature extraction mode to obtain sample signal feature data on the left side and the sample signal feature data on the right side;
performing differentiation comparison on the sample signal characteristic data on the left side and the right side to obtain sample characteristic difference data;
and inputting the sample characteristic difference data sample set and the type, grade and/or pathogenesis of the scoliosis corresponding to the sample characteristic difference data as labels into a preset training mathematical model for training so as to obtain the scoliosis screening mathematical model.
9. The bioelectrical signal processing method according to claim 8, wherein the training mathematical model is a classification mathematical model; the classification mathematical model comprises an SVM, an XG-Boost and/or a decision tree classifier;
the four limbs comprise upper limbs and lower limbs, the lower limbs comprise forearms, upper arms and hands, and the lower limbs comprise thighs, shanks and feet;
the bioelectric signals comprise myoelectric and/or pulse electrical signals;
the biological signal characteristic data comprises a signal time domain characteristic and a signal frequency domain characteristic; the signal time domain features and the signal frequency domain features respectively include root mean square, peak-to-peak, kurtosis, skewness, mean, variance, and/or center of gravity frequency of the spectral magnitudes.
10. A computer-readable storage medium characterized in that the medium has stored thereon a program executable by a processor to implement the bioelectrical signal processing method according to any one of claims 7 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211484692.2A CN115836863B (en) | 2022-11-24 | 2022-11-24 | Bioelectric signal processing device and method for spinal curvature screening |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211484692.2A CN115836863B (en) | 2022-11-24 | 2022-11-24 | Bioelectric signal processing device and method for spinal curvature screening |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115836863A true CN115836863A (en) | 2023-03-24 |
| CN115836863B CN115836863B (en) | 2024-06-11 |
Family
ID=85577274
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211484692.2A Active CN115836863B (en) | 2022-11-24 | 2022-11-24 | Bioelectric signal processing device and method for spinal curvature screening |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115836863B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102302646B1 (en) * | 2021-04-14 | 2021-09-15 | 지미경 | Electronic device for predicting and diagnosing scoliosis and its operating method |
| CN113397485A (en) * | 2021-05-27 | 2021-09-17 | 上海交通大学医学院附属新华医院 | Scoliosis screening method based on deep learning |
| CN114287915A (en) * | 2021-12-28 | 2022-04-08 | 深圳零动医疗科技有限公司 | Noninvasive scoliosis screening method and system based on back color image |
| CN114848012A (en) * | 2022-06-20 | 2022-08-05 | 苏州市立医院 | Scoliosis analysis auxiliary method |
| CN115337008A (en) * | 2021-12-15 | 2022-11-15 | 上海长征医院 | Human muscle and bone health analysis method and system, motion guidance method and system and storage medium |
-
2022
- 2022-11-24 CN CN202211484692.2A patent/CN115836863B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102302646B1 (en) * | 2021-04-14 | 2021-09-15 | 지미경 | Electronic device for predicting and diagnosing scoliosis and its operating method |
| CN113397485A (en) * | 2021-05-27 | 2021-09-17 | 上海交通大学医学院附属新华医院 | Scoliosis screening method based on deep learning |
| CN115337008A (en) * | 2021-12-15 | 2022-11-15 | 上海长征医院 | Human muscle and bone health analysis method and system, motion guidance method and system and storage medium |
| CN114287915A (en) * | 2021-12-28 | 2022-04-08 | 深圳零动医疗科技有限公司 | Noninvasive scoliosis screening method and system based on back color image |
| CN114848012A (en) * | 2022-06-20 | 2022-08-05 | 苏州市立医院 | Scoliosis analysis auxiliary method |
Non-Patent Citations (1)
| Title |
|---|
| 刘一涛;: "神经电生理监测在脊柱侧弯手术中的效果评价", 四川医学, no. 05, 15 May 2018 (2018-05-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115836863B (en) | 2024-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107224272A (en) | A kind of pulse-taking instrument and its detection method | |
| CN112274120B (en) | Noninvasive arteriosclerosis detection method and device based on one-way pulse wave | |
| CN112294264A (en) | Sleep staging method based on BCG and blood oxygen saturation rate | |
| CN112971797A (en) | Continuous physiological signal quality evaluation method | |
| Li et al. | The correlation study of Cun, Guan and Chi position based on wrist pulse characteristics | |
| CN112274121A (en) | Noninvasive arteriosclerosis detection method and device based on multipath pulse waves | |
| JP2000166877A (en) | Biorhythm inspecting apparatus and biorhythm inspecting method | |
| Xu et al. | Quantitative analyses of pulse images in Traditional Chinese Medicine | |
| CN117281479A (en) | Human lower limb chronic pain distinguishing method, storage medium and device based on surface electromyographic signal multi-dimensional feature fusion | |
| Sonmezocak et al. | Detection of EMG signals by neural networks using autoregression and wavelet entropy for bruxism diagnosis | |
| Phanikrishna et al. | A brief review on EEG signal pre-processing techniques for real-time brain-computer interface applications | |
| Hsu et al. | Heart rate and respiratory rate monitoring using seismocardiography | |
| Szczęsna et al. | Chaotic biomedical time signal analysis via wavelet scattering transform | |
| CN116784860B (en) | Electrocardiosignal characteristic extraction system based on morphological heart beat template clustering | |
| KR20080043545A (en) | Method for diagnosis pulse action and a portable device therfor | |
| CN104323761A (en) | Infrared thermal imaging technology-based vascular endothelial function detection device and detection method thereof | |
| CN115836863B (en) | Bioelectric signal processing device and method for spinal curvature screening | |
| Chung et al. | Exploring the conventional pulse conditions using bi-sensing pulse diagnosis instrument | |
| Hu et al. | Pulse differences and 3D pulse mapping in TPNI displacements | |
| Sareen et al. | Nadi Yantra: a robust system design to capture the signals from the radial artery for non-invasive diagnosis | |
| Kadarmandalgi et al. | Pulse diagnosis System for Nadi Pariksha using parametric and statistical analysis | |
| Majid et al. | Performance assessment of the optimum feature extraction for upper-limb stroke rehabilitation using angular separation method | |
| Sahyudi et al. | Investigation of upper limb movement for VR based post stroke rehabilitation device | |
| CN112971801A (en) | Continuous physiological signal quality evaluation device | |
| CN208129992U (en) | A kind of pulse-taking instrument |
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 | ||
| GR01 | Patent grant |