CN104545912A - Cardiac and pulmonary impedance measuring method and device - Google Patents
Cardiac and pulmonary impedance measuring method and device Download PDFInfo
- Publication number
- CN104545912A CN104545912A CN201510049187.9A CN201510049187A CN104545912A CN 104545912 A CN104545912 A CN 104545912A CN 201510049187 A CN201510049187 A CN 201510049187A CN 104545912 A CN104545912 A CN 104545912A
- Authority
- CN
- China
- Prior art keywords
- impedance
- cardiac
- cardiopulmonary
- module
- digital signal
- 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
- 230000000747 cardiac effect Effects 0.000 title claims abstract description 81
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000002685 pulmonary effect Effects 0.000 title abstract 8
- 238000001914 filtration Methods 0.000 claims abstract description 23
- 238000013528 artificial neural network Methods 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000006243 chemical reaction Methods 0.000 claims abstract description 10
- 238000003062 neural network model Methods 0.000 claims abstract description 9
- 230000036541 health Effects 0.000 claims abstract description 7
- 230000002612 cardiopulmonary effect Effects 0.000 claims description 70
- 210000004072 lung Anatomy 0.000 claims description 47
- 238000005259 measurement Methods 0.000 claims description 22
- 238000004088 simulation Methods 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 17
- 230000029058 respiratory gaseous exchange Effects 0.000 claims description 14
- 210000002569 neuron Anatomy 0.000 claims description 13
- 230000007935 neutral effect Effects 0.000 claims description 13
- 210000000038 chest Anatomy 0.000 claims description 12
- 238000005314 correlation function Methods 0.000 claims description 12
- 230000009467 reduction Effects 0.000 claims description 12
- 230000036391 respiratory frequency Effects 0.000 claims description 12
- 230000001537 neural effect Effects 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 9
- 230000003862 health status Effects 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 7
- 238000003745 diagnosis Methods 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 7
- 230000010247 heart contraction Effects 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 6
- 201000010099 disease Diseases 0.000 claims description 5
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 5
- 238000005086 pumping Methods 0.000 claims description 5
- 239000008280 blood Substances 0.000 claims description 3
- 210000004369 blood Anatomy 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000002847 impedance measurement Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 210000001113 umbilicus Anatomy 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 2
- 230000003247 decreasing effect Effects 0.000 abstract 1
- 238000001228 spectrum Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 208000019622 heart disease Diseases 0.000 description 3
- 210000000056 organ Anatomy 0.000 description 3
- 231100000915 pathological change Toxicity 0.000 description 3
- 230000036285 pathological change Effects 0.000 description 3
- 208000019693 Lung disease Diseases 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000036772 blood pressure Effects 0.000 description 2
- 230000036760 body temperature Effects 0.000 description 2
- 230000002526 effect on cardiovascular system Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004199 lung function Effects 0.000 description 2
- 230000035485 pulse pressure Effects 0.000 description 2
- 201000006306 Cor pulmonale Diseases 0.000 description 1
- 206010019280 Heart failures Diseases 0.000 description 1
- 208000004186 Pulmonary Heart Disease Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000009534 blood test Methods 0.000 description 1
- 210000000481 breast Anatomy 0.000 description 1
- 210000000621 bronchi Anatomy 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000003130 cardiopathic effect Effects 0.000 description 1
- 230000002802 cardiorespiratory effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 230000004217 heart function Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009325 pulmonary function Effects 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 238000004092 self-diagnosis Methods 0.000 description 1
- 230000004936 stimulating effect Effects 0.000 description 1
- 210000000115 thoracic cavity Anatomy 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves
- A61B5/053—Measuring electrical impedance or conductance of a portion of the body
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- 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
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Physiology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Cardiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Pulmonology (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
A cardiac and pulmonary impedance measuring method and device is disclosed. The method is characterized by including: entering basic information of a patient, and using the device to acquire a cardiac impedance analog signal and a pulmonary impedance analog signal of the patient; allowing an analog-digital conversion module to convert the acquired cardiac and pulmonary impedance signals into cardiac and pulmonary impedance digital signals, and filtering and denoising the digital signals; extracting feature values from the digital signals; building neural network models, entering the basic information and the extracted feature values into neural networks, training the neural networks, and determining weight values of the neural networks; classifying the trained models according to the entered feature values, and outputting corresponding health states. The cardiac and pulmonary impedance measuring method and device has the advantages that according to two types of basic information of the patient and five features extracted from the cardiac an pulmonary impedance signals, the cardiac and pulmonary health states of the patient are primarily detected, detecting is simple and fast and accurate, hospital resources are well saved, expenditure on seeing doctors is decreased for the patient, and the device is simple in structure, easy to manufacture, low in cost and convenient to use.
Description
Technical field
The present invention relates to field of medical technology, specifically relate to a kind of measuring method and device of cardiopulmonary impedance.
Background technology
Healthy most important for people of lung and these two organs of heart, once pulmonary function or cardiac pumping function generation obstacle, has serious impact to orthobiosis of people and even life.And on the other hand, these two organs are interrelated again, when having a pathological changes among them, another also can be affected more or less.Such as pulmonary heart disease, though be heart disease, be caused by the pathological changes of bronchus or lung tissue etc., both can show heart failure clinically, also can there is other sign of lung failure etc.People is the organic whole of a system, and lung and heart are again two extremely important parts, must there is interaction, even if a pathological changes also can functionally embodying at two organs all to some extent.
At present all that the examination for pulmonary disease is generally x-ray transmission or CT based on electrocardiogram, X-ray, ultrasonic, blood test etc. for cardiopathic inspection, though there is X-ray examination, for position also different.Be likely heart disease, but show the obvious reduction of lung functions, do rabat and just may cannot be checked through the cause of disease, in other words in contrast, pneumonopathy goes to check heart also without effect, and wasting manpower and material resources on the contrary, has also largely increased the weight of the medical expenses of patient.Prior art proposes a kind of state of an illness self diagnosis equipment based on nerual network technique, which depict a rectangular device, the body temperature of patient, pulse and blood pressure information can be gathered, the built-in neural network procedure of microcontroller of equipment, this program utilizes the suggestion of care specialists, in conjunction with intelligent algorithm, medical diagnosis on disease can be carried out according to the sign information of patient and state of an illness information.But this device does not carry out the collection of sign information for heart and lung functions, only acquire body temperature, pulse and blood pressure, therefore good analysis result cannot be obtained in the health status of lung and heart.
Summary of the invention
The object of the invention is to for above-mentioned existing problems and deficiency, provide a kind of measuring method and device of cardiopulmonary impedance, Electrical Bioimpedance Measurement Technology is utilized to record the cardiopulmonary impedance signal of human body, through obtaining the series of features about breathing and heart beating to the computing of impedance signal, again feature is inputted in advance for the neutral net that cardiovascular fitness state is trained, just can tentatively judge patient health state, the method is fast easy, detect accurately, and the structure of device is simple, easy to manufacture, cost is low, easy to use.
Technical scheme of the present invention is achieved in that
The measuring method of cardiopulmonary impedance of the present invention, is characterized in comprising the following steps:
S1: the essential information of input patient, and the cardiac impedance analogue signal and the lung impedance simulation signal that pass through cardiopulmonary impedance collection module acquires patient;
S2: convert the cardiac impedance analogue signal collected and lung impedance simulation signal to cardiac impedance digital signal and lung impedance digital signal by analog-to-digital conversion module, and filtering and noise reduction is carried out to digital signal;
S3: extract eigenvalue from the digital signal after filtering and noise reduction;
S4: set up neural network model, by the eigenvalue input neural network of essential information and extraction, trains neutral net, determines its weights;
S5: the model trained is classified according to the eigenvalue of input, exports corresponding health status.
Wherein, the concrete operations of above-mentioned steps S1 are as follows:
Acceptable age and chest measurement input as the essential information of patient, to distinguish the patient of Different age group and build, realize better classification results;
For gathering laying of the electrode of cardiac impedance analogue signal in cardiopulmonary impedance collection module: the intersection point getting horizontal line and anterior midline residing for the axillary fossa of left and right, wherein two voltage measurement electrodes are attached to the 2cm place, left and right of intersection point, and two galvanism electrodes are positioned at the 5cm place, left and right of intersection point;
For gathering laying of the electrode of lung impedance simulation signal in cardiopulmonary impedance collection module: get the horizontal line at 10cm place and the intersection point of anterior midline above umbilicus, wherein two voltage measurement electrodes are attached to the 2cm place, left and right of intersection point, and two galvanism electrodes are positioned at the 5cm place, left and right of intersection point.
In above-mentioned steps S2, the concrete operations of filtering and noise reduction are carried out to digital signal as follows:
Carry out bandpass filtering to cardiac impedance digital signal, its passband is 1Hz ~ 30Hz, to remove major part interference; Carry out bandpass filtering to lung impedance digital signal, its passband is 0.01Hz ~ 1Hz, to remove the interference irrelevant with breath signal.
The concrete operations of above-mentioned steps S3 are as follows:
S31: calculate respiratory frequency;
First to lung impedance digital signal R
ldifferentiate, obtains the derivative of lung impedance digital signal
, because the derivative at each crest place of lung impedance digital signal is 0, if then at moment t, meet original signal R simultaneously
lt () is greater than a certain threshold value M
1, and derivative
equal 0, then can judge the crest of moment t place as lung impedance digital signal, calculate in one minute and have N
1individual crest, then respiratory frequency is BR=N
1/ 60Hz;
S32: calculate heart rate;
First to cardiac impedance digital signal R
hdifferentiate, obtains the derivative of cardiac impedance digital signal
, because the derivative at each crest place of cardiac impedance digital signal is 0, if then at moment t, meet original signal R simultaneously
ht () is greater than a certain threshold value M
2, and derivative
equal 0, then can judge the crest of moment t place as cardiac impedance digital signal, calculate in one minute and have N
2individual crest, then heart rate is HR=N
2/ 60Hz;
S33: calculate tidal volume per minute;
Namely lung impedance variation reflects the air-breathing of human body and the process of the lung volume change caused of exhaling, and therefore obtains tidal volume by lung impedance, first calculates the integration of one minute lung impedance digital signal:
Correction function k is obtained by contrasting with standard tidal volume detector
1, then the tidal volume per minute after correcting is:
S34: calculate cardiac output per minute;
Cardiac impedance change reflects the process of the Thorax volume mechanical periodicity that the cardiac pumping of human body causes, and therefore indirectly obtains cardiac output by cardiac impedance measurement; It is as follows that cardiac output calculates formula:
Wherein
represent blood resistivity, meansigma methods is 150
;
lit is the distance between two measurement electrode;
represent the peak value on impedance differential map;
t z represent ejection time, the i.e. width of differential map crest;
z 0 represent basal impedance, the cardiac impedance namely before heart output;
hRnamely the heart rate calculated before;
Then the cardiac output by measuring with standard thermodilution method contrasts and obtains correction coefficient k
2, then the cardiac output per minute after correcting is:
S35: the crest frequency calculating the cross-spectral density of two impedance digital signals;
First calculate the cross-correlation function of two impedance digital signals, cross-spectral density is the Fourier transformation of cross-correlation function:
Be calculating discrete series above
with
the formula of cross-correlation function, wherein N is the length of sequence; Again Fourier transform is carried out to cross-correlation function and can obtain cross-spectral density:
Try to achieve the later frequency that just can find corresponding to power maximum of cross-spectral density, i.e. crest frequency
.
The concrete operations of above-mentioned steps S4 are as follows:
S41: first set up a neural network model, comprises an input layer, a hidden layer and an output layer, and input layer contains 7 input blocks, for inputting 2 essential informations and 5 eigenvalues extracted of patient; Hidden layer neural unit number determines optimal value J by training; Output layer only has a neural unit, for the classification results of output network;
S42: the cardiopulmonary impedance signal gathering the patient made a definite diagnosis, eigenvalue is inputted network train, the least mean-square error arranging network is 0, namely the Output rusults ensureing network is completely the same with the standard results made a definite diagnosis, the error of each sample is 0, if error is not 0, returns amendment network weight;
Input matrix X is by weight matrix W
1weighting is input to hidden layer, and hidden layer calculates, and obtain the output of each neural unit of hidden layer, computing formula is as follows:
Wherein
represent
the output of individual hidden layer neuron;
for transfer function;
represent
individual input;
represent the
individual hidden layer neuron and
the weights that individual input is corresponding;
represent this neuronic threshold value, this neuron reaching threshold criteria just can be activated, and produces corresponding output;
Output layer neuron in conjunction with each neuronic Output rusults of hidden layer, by weights W
2produce final network after weighting and export Y; When training network with great amount of samples training, the actual disease type Ys of Y and patient contrasts by network, and error function is chosen for target and exports Ys and the actual squared difference sum exporting Y, that is:
Work as error
when not being 0, network progressively revises weights W according to error-reduction principle
1and W
2, obtain amended result, then the value of error of calculation function, be not that the words of 0 continue to revise weights again, until error function result is 0, namely complete training.
The measuring device of cardiopulmonary impedance of the present invention, be characterized in comprising a host computer and a slave computer, wherein said host computer comprises the display module for pointing out input patient's essential information and output patient health state, for inputting the input module of the essential information of patient, for controlling the main control module that host computer each several part works in order, cardiopulmonary impedance digital signal for sending slave computer carries out filtering reduction interference and improves the pretreatment module of the signal to noise ratio of signal, the computing module of the eigenvalue of a series of needs is obtained for carrying out series of computation to the signal after pretreatment, for storing the memory module of the cardiopulmonary impedance digital signal that slave computer transmits, for receiving the wireless transport module of the cardiopulmonary impedance digital signal that slave computer transmits and the neural network module for classifying to the eigenvalue of input, described main control module is control centre, first control inputs module and display module work after startup, prompting user inputs the essential information of patient, and this essential information is stored in memory module, then the cardiopulmonary impedance digital signal from slave computer is received by wireless transport module, by pretreatment module, filtering is carried out to the cardiopulmonary impedance digital signal received and remove interference, calculate with computing module thereupon, obtain the series of features value of breathing and heart beating, these eigenvalues comprise respiratory frequency, heart rate, tidal volume per minute, cardiac output per minute, the crest frequency of the cross-spectral density between two impedance digital signals, finally the essential information that user inputs is inputted the neural network module trained together with the eigenvalue of extraction, and the corresponding health status obtained exports from display module by neural network module, described slave computer comprises the main control module worked in order for controlling slave computer each several part, for giving slave computer normal power supply and the power module of battery saving mode can being entered when not working, for gathering the cardiopulmonary impedance collection module of the cardiopulmonary impedance simulation signal of patient, for the cardiopulmonary collected impedance simulation signal being converted to the analog-to-digital conversion module of cardiopulmonary impedance digital signal, for cardiopulmonary impedance digital signal being sent to the wireless transport module of host computer, wherein said cardiopulmonary impedance collection module is by the cardiac impedance acquisition module of the cardiac impedance analogue signal for gathering patient and form for the lung impedance collection module of the lung impedance simulation signal gathering patient, containing the constant-current source applying constant current to galvanism electrode in described power module.
The present invention compared with prior art, has following beneficial effect:
1, in conjunction with cardiac impedance signal and lung impedance signal, extract the crest frequency of the cross-spectral density of respiratory frequency, heart rate, tidal volume per minute, cardiac output per minute and two kinds of impedance signals, can to the whether normal principium identification of cardio-pulmonary function, fast and simple, the saving of medical treatment cost is contributed to;
2, utilize bio-electrical impedance measuring apparatus acquired signal, from impedance signal, extract the characteristic parameter about breathing and heart beating, to human-body safety noinvasive, without any side effect;
3, neutral net has good learning capacity, by the training of great amount of samples to neutral net, obtains optimum neural unit number and corresponding network weight, improves the accuracy of result.
Below in conjunction with accompanying drawing, the present invention is further illustrated.
Accompanying drawing explanation
Fig. 1 is the schematic diagram of neural network training of the present invention.
Fig. 2 is electrode riding position schematic diagram of the present invention.
Fig. 3 is the structural representation of neutral net of the present invention.
Fig. 4 is the block diagram of measuring device of the present invention.
Fig. 5 is use schematic flow sheet of the present invention.
Detailed description of the invention
The measuring method of cardiopulmonary impedance of the present invention, comprises the following steps:
S1: the essential information of input patient, and use the cardiopulmonary impedance collection module in measuring device to put the breathing of Real-time Collection patient and the impedance information in thoracic cavity, to obtain cardiac impedance analogue signal and the lung impedance simulation signal of patient;
S2: convert by analog-to-digital conversion module the cardiopulmonary impedance simulation signal collected to cardiopulmonary impedance digital signal, and filtering and noise reduction is carried out to cardiopulmonary impedance digital signal;
S3: extract eigenvalue from the cardiopulmonary impedance digital signal after filtering and noise reduction;
S4: set up neural network model, by the eigenvalue input neural network of the essential information of patient and extraction, trains neutral net, determines its weights;
S5: the neural network model trained is classified according to the eigenvalue of input, exports the corresponding health status of patient.
Wherein, in above-mentioned steps S1, being acceptable age and chest measurement inputs as the essential information of patient, to distinguish the patient of Different age group and build, realizes better classification results.And to choose age and chest measurement as the essential information input of patient be consider that the signal that the people of all ages and classes and chest measurement collects has larger difference certainly, also avoid the essential information of patient to make the input number of neutral net much become more complicated too much simultaneously.
The present invention, after starting drive, first inputs the essential information of patient, comprises the age and breast encloses; Then Electrical Bioimpedance Measurement Technology is utilized to record the cardiopulmonary impedance simulation signal of human body; Then carry out pretreatment to signal, pretreated method first converts cardiopulmonary impedance simulation signal to cardiopulmonary impedance digital signal by analog-to-digital conversion module, then carries out filtering and noise reduction to digital signal; Digital signal after pretreated can obtain the series of features about breathing and heart beating by computing, and these features comprise breathing rate and tidal volume, heart rate and cardiac output, and the crest frequency of the crosspower spectrum of two kinds of impedance signals; Set up neural network model afterwards, by the feature input neural network of essential information and extraction, neutral net is trained, determines its weights; Model training well gets final product practical application later, and the eigenvalue according to input is classified, and exports the corresponding health status of patient.
As shown in Figure 1, primary signal comprises age and the chest measurement of input, and the cardiopulmonary impedance signal gathered.From lung impedance signal, calculate breathing rate and tidal volume, from cardiac impedance signal, calculate heart rate and cardiac output, and obtain crosspower spectrum in conjunction with two impedance signals, and then calculate its crest frequency.
The crest frequency of breathing rate, tidal volume, heart rate, cardiac output, crosspower spectrum, age input neural network together with chest measurement is trained, improves the accuracy of network.During training, Output rusults and objective result contrast by network, Error Feedback are gone back and carry out the adjustment of weights, namely having trained until reach aimed at precision.Afterwards can by Application of Neural Network in reality.
As shown in Figure 2, the electrode measuring lung impedance simulation signal is laid: get the horizontal line at 10cm place and the intersection point of anterior midline above umbilicus, two voltage measurement electrodes are attached to the 2cm place, left and right of intersection point, and two galvanism electrodes are positioned at the 5cm place, left and right of intersection point.
The electrode measuring cardiac impedance analogue signal is laid: the intersection point getting horizontal line and anterior midline residing for the axillary fossa of left and right, two voltage measurement electrodes are attached to the 2cm place, left and right of intersection point, and two galvanism electrodes are positioned at the 5cm place, left and right of intersection point.
By two acquisition modules, certain electric current I is applied to corresponding stimulating electrode, detects the voltage of corresponding measurement electrode, can resistance value be obtained:
。
Above-mentioned steps S2 is the pretreatment to signal, and its concrete operations are as follows:
S21: cardiopulmonary impedance simulation signal is converted to cardiopulmonary impedance digital signal, to facilitate subsequent treatment by analog-to-digital conversion module;
S22: bandpass filtering is carried out to cardiac impedance digital signal, its passband is 1Hz ~ 30Hz, can remove major part interference like this, obtain the cardiac impedance variable signal preferably caused by cardiac pumping; Carry out bandpass filtering to lung impedance digital signal, its passband is 0.01Hz ~ 1Hz, to remove the interference irrelevant with breath signal.
Above-mentioned steps S3 extracts characteristic parameter from through pretreated cardiopulmonary impedance digital signal, comprises the crest frequency of the cross-spectral density between respiratory frequency, heart rate, tidal volume per minute, cardiac output per minute, two signals.Its concrete operations are as follows:
S31: calculate respiratory frequency.Impedance signal waveform can be similar to regards sinusoidal periodic signal as.First to lung impedance digital signal R
ldifferentiate, obtains the derivative of respiratory impedance
.Because the derivative at each crest place of lung impedance digital signal is 0, if then at moment t, meet original signal R simultaneously
lt () is greater than a certain threshold value M
1, and derivative
equal 0, then can judge the crest of moment t place as impedance signal.Calculate in one minute and have N
1individual crest, then respiratory frequency is BR=N
1/ 60Hz;
S32: calculate heart rate.Similar with calculating respiratory frequency, first to cardiac impedance digital signal R
hdifferentiate, obtains the derivative of cardiac impedance signal
.The derivative at each crest place of cardiac impedance digital signal is 0, if then at moment t, meets original signal R simultaneously
ht () is greater than a certain threshold value M
2, and derivative
equal 0, then can judge the crest of moment t place as impedance signal.Calculate in one minute and have N
2individual crest, then heart rate is HR=N
2/ 60Hz;
S33: calculate tidal volume per minute.Namely lung impedance variation reflects the air-breathing of human body and the process of the lung volume change caused of exhaling, and therefore obtains tidal volume by impedance.First calculate the integration of one minute impedance signal:
Correction function k is obtained by contrasting with standard tidal volume detector
1, then the tidal volume per minute after correcting is:
S34: calculate cardiac output per minute.Cardiac impedance change reflects the process of the Thorax volume mechanical periodicity that the cardiac pumping of human body causes, and therefore indirectly obtains cardiac output by impedance measurement.It is as follows that cardiac output calculates formula:
Wherein
represent blood resistivity, meansigma methods is 150
;
it is the distance between two measurement electrode;
represent the peak value on impedance differential map;
represent ejection time, the i.e. width of differential map crest;
represent basal impedance, the cardiac impedance namely before heart output;
namely the heart rate calculated before;
Then the cardiac output by measuring with standard thermodilution method contrasts and obtains correction coefficient k
2, then the cardiac output per minute after correcting is:
S35: the crest frequency calculating the cross-spectral density of two impedance signals.First calculate the cross-correlation function of two impedance signals, cross-spectral density is the Fourier transformation of cross-correlation function:
Be calculating discrete series above
with
the formula of cross-correlation function.Wherein N is the length of sequence.Again Fourier transform is carried out to cross-correlation function and can obtain cross-spectral density:
Try to achieve the later frequency that just can find corresponding to power maximum of cross-spectral density, i.e. crest frequency
.
The concrete operations of above-mentioned steps S4 are as follows:
S41: first set up a neural network model, comprise an input layer, a hidden layer and an output layer, input layer contains 7 input blocks, for inputting 2 essential informations and 5 features extracted of patient; Hidden layer neural unit number determines optimal value J by training; Output layer only has a neural unit, the classification results of output network;
S42: the cardiopulmonary impedance signal gathering the patient made a definite diagnosis, feature is inputted network train, the least mean-square error arranging network is 0, namely the Output rusults ensureing network is completely the same with the standard results made a definite diagnosis, the error of each sample is 0, if error is not 0, returns amendment network weight;
As shown in Figure 3, specific as follows:
Input layer has 7 neural units, in order to 5 features of 2 essential informations and extraction that input patient, comprises the crest frequency of crosspower spectrum of breathing rate, heart rate, tidal volume, cardiac output and two impedances;
Note is input as matrix X, exports as Y.Input matrix X is by weight matrix W
1weighting is input to hidden layer, and hidden layer calculates, and obtain the output of each neural unit of hidden layer, computing formula is as follows:
Wherein
represent
the output of individual hidden layer neuron;
for transfer function;
represent
individual input;
represent the
individual hidden layer neuron and
the weights that individual input is corresponding;
represent this neuronic threshold value, this neuron of standard reaching threshold value just can be activated, and produces corresponding output;
Output layer only has a neuron.This neuron in conjunction with each neuronic Output rusults of hidden layer, by weights W
2produce final network after weighting and export Y.When training network with great amount of samples training, the actual disease type Ys of Y and patient contrasts by network, and error function is chosen for target and exports Ys and the actual squared difference sum exporting Y, that is:
Work as error
when not being 0, network progressively revises weights W according to error-reduction principle
1and W
2, obtain amended result, then the value of error of calculation function, be not that the words of 0 continue to revise weights again, until error function result is 0, namely complete training.
Above-mentioned steps S5 is the model utilizing step S4 to train, and carries out preliminary analysis to the cardiovascular fitness state of patient.The age of input patient and chest measurement, then gather impedance information.After series of computation process, 7 input pointers are input to neutral net by control system, obtain the Output rusults of health status.
As shown in Figure 4, the measuring device of cardiopulmonary impedance of the present invention, comprises host computer and slave computer two parts,
First disposed slave computer, particularly, slave computer comprises:
Cardiopulmonary impedance collection mould, this cardiopulmonary impedance collection mould is made up of cardiac impedance acquisition module and lung impedance collection module, for gathering cardiac impedance analogue signal and the lung impedance simulation signal of patient;
Power module, for ensureing the normal work of slave computer, containing constant-current source, this constant-current source is used for applying constant electric current to two groups of galvanism electrodes;
Analog-to-digital conversion module, for being converted to cardiopulmonary impedance digital signal by the cardiopulmonary collected impedance simulation signal;
Wireless transport module, for sending to host computer by cardiopulmonary impedance digital signal;
Main control module, this module is the maincenter of slave computer, controls slave computer each several part and works without any confusion;
Dispose host computer again, particularly, host computer comprises:
Display module, for pointing out input patient's essential information and exporting patient health state;
Input module, for inputting the essential information of patient;
Main control module, works in order for controlling host computer each several part;
Pretreatment module, carries out filtering for the cardiopulmonary impedance digital signal sent slave computer, to reduce interference, thus improves the signal to noise ratio of signal;
Computing module, obtain the eigenvalue of a series of needs for carrying out series of computation to the signal after pretreatment, these eigenvalues comprise the crest frequency of the cross-spectral density between respiratory frequency, heart rate, tidal volume per minute, cardiac output per minute, two impedance digital signals;
Memory module, for storing the cardiopulmonary impedance digital signal that slave computer transmits;
Wireless transport module, for receiving the cardiopulmonary impedance digital signal that slave computer transmits;
Neural network module, for classifying to the eigenvalue of input;
In this host computer, its main control module is control centre, first control inputs module and display module work after startup, prompting user inputs the essential information of patient, and this essential information is stored in memory module, then the cardiopulmonary impedance digital signal from slave computer is received by wireless transport module, by pretreatment module, filtering is carried out to the cardiopulmonary impedance digital signal received and remove interference, calculate with computing module thereupon, obtain the series of features value of breathing and heart beating, finally the essential information that user inputs is inputted the neural network module trained together with the eigenvalue of extraction, and the corresponding health status obtained exports from display module by neural network module, inform user.
As shown in Figure 5, after starting drive, first input the essential information of patient and age and chest measurement, and preserve, this information is also finally a part for neutral net input;
Start to gather cardiac impedance signal and lung impedance signal after having inputted, and respectively analog digital conversion and Filtering Processing are carried out to two groups of signals, obtain the impedance signal desired by us;
Next step is exactly extract feature from the signal after process, comprises breathing rate and tidal volume, heart rate and cardiac output, and the crest frequency of crosspower spectrum;
Finally patient's essential information that the first step inputs is inputted the neutral net trained together with the feature of extraction, just can obtain the result of Preliminary detection, healthy or unhealthy.
The present invention is the cardiopulmonary impedance signal utilizing Electrical Bioimpedance Measurement Technology to record human body, through obtaining the series of features about breathing and heart beating to the computing of impedance signal, these features comprise breathing rate and tidal volume, heart rate and cardiac output, and the crest frequency of the crosspower spectrum of two impedances, again feature is inputted neutral net trained for heart and lung diseases in advance together with the essential information of patient, whether just tentatively can judge the health of patient's cardiorespiratory system, thus made contribution for patient's later stage treats more accurately, so not only save medical resource, the spending of the patient also saved.
The present invention is described by embodiment, but the present invention is not construed as limiting, with reference to description of the invention, other changes of the disclosed embodiments, as the professional person for this area easily expects, such change should belong within the scope of the claims in the present invention restriction.
Claims (6)
1. a measuring method for cardiopulmonary impedance, is characterized in that comprising the following steps:
S1: the essential information of input patient, and the cardiac impedance analogue signal and the lung impedance simulation signal that pass through cardiopulmonary impedance collection module acquires patient;
S2: convert the cardiac impedance analogue signal collected and lung impedance simulation signal to cardiac impedance digital signal and lung impedance digital signal by analog-to-digital conversion module, and filtering and noise reduction is carried out to digital signal;
S3: extract eigenvalue from the digital signal after filtering and noise reduction;
S4: set up neural network model, by the eigenvalue input neural network of essential information and extraction, trains neutral net, determines its weights;
S5: the model trained is classified according to the eigenvalue of input, exports corresponding health status.
2. the measuring method of cardiopulmonary impedance according to claim 1, is characterized in that the concrete operations of above-mentioned steps S1 are as follows:
Acceptable age and chest measurement input as the essential information of patient, to distinguish the patient of Different age group and build, realize better classification results;
For gathering laying of the electrode of cardiac impedance analogue signal in cardiopulmonary impedance collection module: the intersection point getting horizontal line and anterior midline residing for the axillary fossa of left and right, wherein two voltage measurement electrodes are attached to the 2cm place, left and right of intersection point, and two galvanism electrodes are positioned at the 5cm place, left and right of intersection point;
For gathering laying of the electrode of lung impedance simulation signal in cardiopulmonary impedance collection module: get the horizontal line at 10cm place and the intersection point of anterior midline above umbilicus, wherein two voltage measurement electrodes are attached to the 2cm place, left and right of intersection point, and two galvanism electrodes are positioned at the 5cm place, left and right of intersection point.
3. the measuring method of cardiopulmonary impedance according to claim 1, is characterized in that carrying out the concrete operations of filtering and noise reduction to digital signal in above-mentioned steps S2 as follows:
Carry out bandpass filtering to cardiac impedance digital signal, its passband is 1Hz ~ 30Hz, to remove major part interference; Carry out bandpass filtering to lung impedance digital signal, its passband is 0.01Hz ~ 1Hz, to remove the interference irrelevant with breath signal.
4. the measuring method of cardiopulmonary impedance according to claim 1, is characterized in that the concrete operations of above-mentioned steps S3 are as follows:
S31: calculate respiratory frequency;
First to lung impedance digital signal R
ldifferentiate, obtains the derivative of lung impedance digital signal
, because the derivative at each crest place of lung impedance digital signal is 0, if then at moment t, meet original signal R simultaneously
lt () is greater than a certain threshold value M
1, and derivative
equal 0, then can judge the crest of moment t place as lung impedance digital signal, calculate in one minute and have N
1individual crest, then respiratory frequency is BR=N
1/ 60Hz;
S32: calculate heart rate;
First to cardiac impedance digital signal R
hdifferentiate, obtains the derivative of cardiac impedance digital signal
, because the derivative at each crest place of cardiac impedance digital signal is 0, if then at moment t, meet original signal R simultaneously
ht () is greater than a certain threshold value M
2, and derivative
equal 0, then can judge the crest of moment t place as cardiac impedance digital signal, calculate in one minute and have N
2individual crest, then heart rate is HR=N
2/ 60Hz;
S33: calculate tidal volume per minute;
Namely lung impedance variation reflects the air-breathing of human body and the process of the lung volume change caused of exhaling, and therefore obtains tidal volume by lung impedance, first calculates the integration of one minute lung impedance digital signal:
Correction function k is obtained by contrasting with standard tidal volume detector
1, then the tidal volume per minute after correcting is:
S34: calculate cardiac output per minute;
Cardiac impedance change reflects the process of the Thorax volume mechanical periodicity that the cardiac pumping of human body causes, and therefore indirectly obtains cardiac output by cardiac impedance measurement; It is as follows that cardiac output calculates formula:
Wherein
represent blood resistivity, meansigma methods is 150
;
lit is the distance between two measurement electrode;
represent the peak value on impedance differential map;
t z represent ejection time, the i.e. width of differential map crest;
z 0 represent basal impedance, the cardiac impedance namely before heart output;
hRnamely the heart rate calculated before;
Then the cardiac output by measuring with standard thermodilution method contrasts and obtains correction coefficient k
2, then the cardiac output per minute after correcting is:
S35: the crest frequency calculating the cross-spectral density of two impedance digital signals;
First calculate the cross-correlation function of two impedance digital signals, cross-spectral density is the Fourier transformation of cross-correlation function:
Be calculating discrete series above
with
the formula of cross-correlation function, wherein N is the length of sequence; Again Fourier transform is carried out to cross-correlation function and can obtain cross-spectral density:
Try to achieve the later frequency that just can find corresponding to power maximum of cross-spectral density, i.e. crest frequency
.
5. the measuring method of cardiopulmonary impedance according to claim 1, is characterized in that the concrete operations of above-mentioned steps S4 are as follows:
S41: first set up a neural network model, comprises an input layer, a hidden layer and an output layer, and input layer contains 7 input blocks, for inputting 2 essential informations and 5 eigenvalues extracted of patient; Hidden layer neural unit number determines optimal value J by training; Output layer only has a neural unit, for the classification results of output network;
S42: the cardiopulmonary impedance signal gathering the patient made a definite diagnosis, eigenvalue is inputted network train, the least mean-square error arranging network is 0, namely the Output rusults ensureing network is completely the same with the standard results made a definite diagnosis, the error of each sample is 0, if error is not 0, returns amendment network weight;
Input matrix X is by weight matrix W
1weighting is input to hidden layer, and hidden layer calculates, and obtain the output of each neural unit of hidden layer, computing formula is as follows:
Wherein
represent
the output of individual hidden layer neuron;
for transfer function;
represent
individual input;
represent the
individual hidden layer neuron and
the weights that individual input is corresponding;
represent this neuronic threshold value, this neuron reaching threshold criteria just can be activated, and produces corresponding output;
Output layer neuron in conjunction with each neuronic Output rusults of hidden layer, by weights W
2produce final network after weighting and export Y; When training network with great amount of samples training, the actual disease type Ys of Y and patient contrasts by network, and error function is chosen for target and exports Ys and the actual squared difference sum exporting Y, that is:
Work as error
when not being 0, network progressively revises weights W according to error-reduction principle
1and W
2, obtain amended result, then the value of error of calculation function, be not that the words of 0 continue to revise weights again, until error function result is 0, namely complete training.
6. the measuring device of a cardiopulmonary impedance, this measuring device is used in the measuring method of cardiopulmonary impedance described in above-mentioned arbitrary claim, it is characterized in that comprising a host computer and a slave computer, wherein said host computer comprises the display module for pointing out input patient's essential information and output patient health state, for inputting the input module of the essential information of patient, for controlling the main control module that host computer each several part works in order, cardiopulmonary impedance digital signal for sending slave computer carries out filtering reduction interference and improves the pretreatment module of the signal to noise ratio of signal, the computing module of the eigenvalue of a series of needs is obtained for carrying out series of computation to the signal after pretreatment, for storing the memory module of the cardiopulmonary impedance digital signal that slave computer transmits, for receiving the wireless transport module of the cardiopulmonary impedance digital signal that slave computer transmits and the neural network module for classifying to the eigenvalue of input, described main control module is control centre, first control inputs module and display module work after startup, prompting user inputs the essential information of patient, and this essential information is stored in memory module, then the cardiopulmonary impedance digital signal from slave computer is received by wireless transport module, by pretreatment module, filtering is carried out to the cardiopulmonary impedance digital signal received and remove interference, calculate with computing module thereupon, obtain the series of features value of breathing and heart beating, these eigenvalues comprise respiratory frequency, heart rate, tidal volume per minute, cardiac output per minute, the crest frequency of the cross-spectral density between two impedance digital signals, finally the essential information that user inputs is inputted the neural network module trained together with the eigenvalue of extraction, and the corresponding health status obtained exports from display module by neural network module, described slave computer comprises the main control module worked in order for controlling slave computer each several part, for giving slave computer normal power supply and the power module of battery saving mode can being entered when not working, for gathering the cardiopulmonary impedance collection module of the cardiopulmonary impedance simulation signal of patient, for the cardiopulmonary collected impedance simulation signal being converted to the analog-to-digital conversion module of cardiopulmonary impedance digital signal, for cardiopulmonary impedance digital signal being sent to the wireless transport module of host computer, wherein said cardiopulmonary impedance collection module is by the cardiac impedance acquisition module of the cardiac impedance analogue signal for gathering patient and form for the lung impedance collection module of the lung impedance simulation signal gathering patient, containing the constant-current source applying constant current to galvanism electrode in described power module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510049187.9A CN104545912B (en) | 2015-01-31 | 2015-01-31 | The measuring method and device of a kind of cardiopulmonary impedance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510049187.9A CN104545912B (en) | 2015-01-31 | 2015-01-31 | The measuring method and device of a kind of cardiopulmonary impedance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104545912A true CN104545912A (en) | 2015-04-29 |
| CN104545912B CN104545912B (en) | 2017-06-16 |
Family
ID=53063768
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510049187.9A Active CN104545912B (en) | 2015-01-31 | 2015-01-31 | The measuring method and device of a kind of cardiopulmonary impedance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104545912B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105030215A (en) * | 2015-07-08 | 2015-11-11 | 北京大学 | Cardiac impedance signal analysis device |
| CN106137182A (en) * | 2016-07-27 | 2016-11-23 | 复旦大学 | The frequency domain correlation analysis method of cardiac mapping signal |
| CN109381187A (en) * | 2017-08-02 | 2019-02-26 | 德尔格制造股份两合公司 | For determining the device and method of difference characteristic number based on EIT- data |
| CN109452936A (en) * | 2018-12-15 | 2019-03-12 | 浙江大学台州研究院 | Breathing and heart stroke combined monitoring equipment |
| CN109767844A (en) * | 2018-12-28 | 2019-05-17 | 郑州大学第一附属医院 | Target tumor intervention therapeutic agent and preparation method thereof and intelligent checking system |
| CN109984742A (en) * | 2019-04-22 | 2019-07-09 | 深圳大学 | Cardiac impedance signal processing system and method |
| CN110013245A (en) * | 2019-04-30 | 2019-07-16 | 中山大学孙逸仙纪念医院 | A kind of wearable device cardiopulmonary data acquisition testing system capable of automatic alarm |
| CN110123306A (en) * | 2019-04-30 | 2019-08-16 | 中山大学孙逸仙纪念医院 | A kind of cardiopulmonary data acquisition testing system based on wearable device |
| CN110151182A (en) * | 2019-04-04 | 2019-08-23 | 深圳创达云睿智能科技有限公司 | A kind of apnea kind identification method and equipment |
| CN112244853A (en) * | 2020-10-26 | 2021-01-22 | 生物岛实验室 | Edge computing node manufacturing method and edge computing node |
| CN112932684A (en) * | 2021-04-06 | 2021-06-11 | 江苏百宁盈创医疗科技有限公司 | Nerve monitoring device based on human body impedance detection |
| CN113368403A (en) * | 2021-06-24 | 2021-09-10 | 深圳市恒康泰医疗科技有限公司 | Intelligent physiotherapy system capable of improving cardio-pulmonary function |
| CN115590497A (en) * | 2022-07-29 | 2023-01-13 | 重庆大学（Cn） | Lung ventilation dysfunction disease diagnosis system based on gas-electricity synchronous measurement |
| CN115624333A (en) * | 2022-09-29 | 2023-01-20 | 武汉远光瑞康科技有限公司 | Human body electrical impedance signal acquisition system and working method thereof |
| US20230109043A1 (en) * | 2018-07-18 | 2023-04-06 | SCA Robotics | Methods of implementing an artificial intelligence based imaging platform for precision medical treatment predictive modeling platforms |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012104490A1 (en) * | 2011-02-03 | 2012-08-09 | Tty-Säätiö | A method for decomposition of a composite signal consisting of oscillatory waveforms and a modulating signal |
| US20140046205A1 (en) * | 2002-07-03 | 2014-02-13 | Tel Aviv University Future Technology Development L.P. | Apparatus and method for estimating stroke volume of the heart using bio-impedance techniques |
| WO2014060938A1 (en) * | 2012-10-16 | 2014-04-24 | Night-Sense, Ltd | Comfortable and personalized monitoring device, system, and method for detecting physiological health risks |
-
2015
- 2015-01-31 CN CN201510049187.9A patent/CN104545912B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140046205A1 (en) * | 2002-07-03 | 2014-02-13 | Tel Aviv University Future Technology Development L.P. | Apparatus and method for estimating stroke volume of the heart using bio-impedance techniques |
| WO2012104490A1 (en) * | 2011-02-03 | 2012-08-09 | Tty-Säätiö | A method for decomposition of a composite signal consisting of oscillatory waveforms and a modulating signal |
| WO2014060938A1 (en) * | 2012-10-16 | 2014-04-24 | Night-Sense, Ltd | Comfortable and personalized monitoring device, system, and method for detecting physiological health risks |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105030215A (en) * | 2015-07-08 | 2015-11-11 | 北京大学 | Cardiac impedance signal analysis device |
| CN106137182B (en) * | 2016-07-27 | 2019-11-12 | 复旦大学 | The frequency domain correlation analysis method of cardiac mapping signal |
| CN106137182A (en) * | 2016-07-27 | 2016-11-23 | 复旦大学 | The frequency domain correlation analysis method of cardiac mapping signal |
| CN109381187A (en) * | 2017-08-02 | 2019-02-26 | 德尔格制造股份两合公司 | For determining the device and method of difference characteristic number based on EIT- data |
| US20230109043A1 (en) * | 2018-07-18 | 2023-04-06 | SCA Robotics | Methods of implementing an artificial intelligence based imaging platform for precision medical treatment predictive modeling platforms |
| US11848105B2 (en) * | 2018-07-18 | 2023-12-19 | SCA Robotics | Methods of implementing an artificial intelligence based imaging platform for precision medical treatment predictive modeling platforms |
| CN109452936A (en) * | 2018-12-15 | 2019-03-12 | 浙江大学台州研究院 | Breathing and heart stroke combined monitoring equipment |
| CN109767844A (en) * | 2018-12-28 | 2019-05-17 | 郑州大学第一附属医院 | Target tumor intervention therapeutic agent and preparation method thereof and intelligent checking system |
| CN110151182A (en) * | 2019-04-04 | 2019-08-23 | 深圳创达云睿智能科技有限公司 | A kind of apnea kind identification method and equipment |
| CN110151182B (en) * | 2019-04-04 | 2022-04-19 | 深圳创达云睿智能科技有限公司 | Apnea type identification method and device |
| CN109984742A (en) * | 2019-04-22 | 2019-07-09 | 深圳大学 | Cardiac impedance signal processing system and method |
| CN110123306A (en) * | 2019-04-30 | 2019-08-16 | 中山大学孙逸仙纪念医院 | A kind of cardiopulmonary data acquisition testing system based on wearable device |
| CN110013245A (en) * | 2019-04-30 | 2019-07-16 | 中山大学孙逸仙纪念医院 | A kind of wearable device cardiopulmonary data acquisition testing system capable of automatic alarm |
| CN112244853A (en) * | 2020-10-26 | 2021-01-22 | 生物岛实验室 | Edge computing node manufacturing method and edge computing node |
| CN112244853B (en) * | 2020-10-26 | 2022-05-13 | 生物岛实验室 | Edge computing node manufacturing method and edge computing node |
| CN112932684A (en) * | 2021-04-06 | 2021-06-11 | 江苏百宁盈创医疗科技有限公司 | Nerve monitoring device based on human body impedance detection |
| CN113368403B (en) * | 2021-06-24 | 2022-01-04 | 深圳市恒康泰医疗科技有限公司 | Intelligent physiotherapy system capable of improving cardio-pulmonary function |
| CN113368403A (en) * | 2021-06-24 | 2021-09-10 | 深圳市恒康泰医疗科技有限公司 | Intelligent physiotherapy system capable of improving cardio-pulmonary function |
| CN115590497A (en) * | 2022-07-29 | 2023-01-13 | 重庆大学（Cn） | Lung ventilation dysfunction disease diagnosis system based on gas-electricity synchronous measurement |
| CN115624333A (en) * | 2022-09-29 | 2023-01-20 | 武汉远光瑞康科技有限公司 | Human body electrical impedance signal acquisition system and working method thereof |
| CN115624333B (en) * | 2022-09-29 | 2024-03-15 | 武汉远光瑞康科技有限公司 | Human body electrical impedance signal acquisition system and working method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104545912B (en) | 2017-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104545912A (en) | Cardiac and pulmonary impedance measuring method and device | |
| CN103038772B (en) | Predict the system and device of the viability of patient | |
| US20190295729A1 (en) | Universal non-invasive blood glucose estimation method based on time series analysis | |
| CN103957862B (en) | Impedance measuring devices and methods for emergency cardiovascular care | |
| CN107714023A (en) | Static ecg analysis method and apparatus based on artificial intelligence self study | |
| CN103070683B (en) | Sleep breathing mode identification method and device based on bioelectrical impedance | |
| CN107832737A (en) | Electrocardiogram interference identification method based on artificial intelligence | |
| CN106901705A (en) | A kind of unaware human Body Physiology Multi-parameter harvester and acquisition method and application | |
| CN106236503B (en) | The wearable exoskeleton system of the electrically driven (operated) upper limb of flesh and control method | |
| CN100577097C (en) | Method for masuring metabolism of human for one day and heat quantity valve needed by human for biologic action | |
| CN103598886B (en) | Based on the method for dynamic urine volume in the long-pending urine process of model compensation method monitoring | |
| CN107480637B (en) | Heart failure based on heart sound feature method by stages | |
| CN113317794B (en) | Vital sign analysis method and system | |
| CN114376564A (en) | Sleep staging method, system, device and medium based on cardiac shock signal | |
| CN111887858B (en) | Ballistocardiogram signal heart rate estimation method based on cross-modal mapping | |
| CN111317600A (en) | Artificial limb control method, device, system, equipment and storage medium | |
| CN102551699A (en) | Non-invasive cardiac output determination system | |
| CN113160921A (en) | Construction method and application of digital human cardiovascular system based on hemodynamics | |
| CN102670190A (en) | Heart rate variability nonlinear characteristic-based automatic diagnosis method for congestive heart failure | |
| CN106768245A (en) | A kind of fat scale intelligent Matching user method | |
| CN106725376A (en) | Sign detection method and device | |
| Roy et al. | On-device reliability assessment and prediction of missing photoplethysmographic data using deep neural networks | |
| CN106388825A (en) | Respiration rate extraction method and device thereof | |
| CN104605850A (en) | Real-time monitoring device and method for bladder urine volume based on electrical impedance tomography imaging technology | |
| CN110200619A (en) | It is a kind of to establish major cardiovascular disease risks Early-warning Model method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |