CN114191788A - Individualized respiratory motion pattern reconstruction training system and use method thereof - Google Patents

Abstract

The application discloses individualized respiratory motion pattern rebuilds training system, it includes: the device comprises a physiological parameter sensor unit, a respiration reconstruction unit and a guide signal display unit; the respiratory reconstruction unit is implemented by a computer configured to include: the device comprises a physiological parameter receiving module, a guide signal module and a respiratory goodness of fit calculating module; the physiological parameter sensor unit is worn on a subject to measure a respiratory signal of the subject; the physiological parameter receiving module is configured to receive a respiratory signal from the physiological parameter sensor unit; the guiding signal module is configured to drive the guiding signal display unit, thereby outputting a guiding signal to the subject so that the subject performs respiratory motion according to the guiding signal; the respiratory goodness of fit calculation module is configured to calculate goodness of fit between the respiratory signal received by the physiological parameter receiving module and the guide signal when the user makes respiratory movement under the guidance of the guide signal.

Description

Individualized respiratory motion pattern reconstruction training system and use method thereof

Technical Field

The present application relates to a respiratory reconstruction technique, and more particularly, to an individualized respiratory motion pattern reconstruction training system and a method for using the same.

Background

According to the statistics of death causes of ten main diseases in part of cities and the first ten rural areas in 2006, respiratory diseases (excluding lung cancer) account for the fourth (13.1%) and the third (16.4%) of death causes in cities and rural areas. In recent years, due to the influence of physical and chemical factors, biological factors, population aging and other factors caused by industrial economic development, air pollution, smoking and the like, respiratory diseases, particularly chronic respiratory diseases represented by chronic obstructive pulmonary diseases (chronic obstructive pulmonary diseases for short, including chronic bronchitis, emphysema and pulmonary heart disease), asthma and the like, have obviously increased morbidity and mortality, wherein the morbidity of the chronic obstructive pulmonary diseases of 40-year-old and above people reaches 13.6 percent, the total number of sick people is nearly 1 hundred million, and more than 3000 million asthma patients. In addition, chronic respiratory diseases have long course and repeated attacks, which seriously affect the health and life quality of patients.

Chronic respiratory diseases often result in abnormal breathing patterns, including chest, abdomen, shoulder and shallow breathing, with various abnormal breathing patterns. Therefore, the reconstruction of the normal breathing movement pattern, especially the deep and slow abdominal breathing, is very important for the rehabilitation of patients with chronic respiratory diseases. For example, the breathing of a patient with chronic obstructive pulmonary disease is characterized by incomplete reversible airflow limitation, the patient often becomes increasingly severe, the breathing action is completed mainly through chest breathing and even shoulder breathing, the breathing is short, the inhaled gas is mainly concentrated on the middle upper part of the lung, alveoli at the lower part of the lung are difficult to fill and cannot inhale a large amount of fresh air, and oxygen deficiency, carbon dioxide retention and the like are caused, so that the lung function is further damaged; through carrying out breathing mode reconstruction training to the patient of chronic obstructive pulmonary disease, impel the patient to take exercise abdominal respiration, enlarge vital capacity, make the thorax obtain furthest's expansion, the alveolus of lung lower part can stretch out and draw back, can effectively improve patient's pulmonary function system, shortens the course of disease, improves quality of life.

At present, no effective auxiliary tool and method are available for reconstruction of respiratory motion modes of doctors and patients, the respiratory motion modes usually stay in a mode of dictation or personal education, and objective indexes for training level and effect assessment are unavailable.

Disclosure of Invention

In view of the above problems, the present application aims to propose an individualized respiratory motion pattern reconstruction training system and a method of using the same, which is capable of giving an objective evaluation to the respiratory motion training of a subject; the present application also aims to propose an individualized respiratory motion pattern reconstruction training system and a method of use thereof, which is individualized for the training performed by the subject; the present application is also directed to an individualized respiratory motion pattern reconstruction training system and a method of using the same, which can analyze the contribution ratio of the respiration of each pattern in the respiratory motion of a subject in the whole respiratory motion, and provide information feedback for reconstructing a healthy respiratory motion pattern.

The individualized respiratory motion pattern reconstruction training system of the present application, comprising: the device comprises a physiological parameter sensor unit, a respiration reconstruction unit and a guide signal display unit; the respiratory reconstruction unit is implemented by a computer configured to include: the device comprises a physiological parameter receiving module, a guide signal module and a respiratory goodness of fit calculating module;

the physiological parameter sensor unit is worn on a subject to measure a respiratory signal of the subject;

the physiological parameter receiving module is configured to receive a respiratory signal from the physiological parameter sensor unit;

the guiding signal module is configured to drive the guiding signal display unit, thereby outputting a guiding signal to the subject so that the subject performs respiratory motion according to the guiding signal;

the respiratory goodness of fit calculation module is configured to calculate goodness of fit between the respiratory signal received by the physiological parameter receiving module and the guide signal when the user makes respiratory movement under the guidance of the guide signal.

Preferably, the breathing reconstruction unit further comprises: a baseline data module;

the baseline data module is configured to obtain breathing mode baseline data according to the breathing signals received by the physiological parameter receiving module during the resting spontaneous breathing of a predetermined time length before the subject performs breathing mode training;

the guidance signal module outputs a guidance signal based on the breathing pattern baseline data.

Preferably, the respiratory goodness of fit calculation module calculates at least one of a tidal volume curve goodness of fit, a thoraco-abdominal respiratory curve goodness of fit, and a respiratory rate goodness of fit:

wherein, the calculation of the goodness of fit of the tidal volume curve is as follows:

1) the respiratory waveform was fitted with the following interpolation function:

in [ a, b ]]N +1 points a ≦ x are given₀<x₁<…<x_nB, f (x) is [ a, b ]]Function of (a), function s (x; a)₀,...,a_n) The fit is as follows: s (x)_i；a₀,...,a_n)＝f(x_i),i＝0,1,…,n；

Wherein s (x) is f (x) in [ a, b ]]If s (x) is related to the parameter a₀,a₁,...,a_nIs a linear relationship, i.e.:

s(x)＝a₀s₀(x)+a₁s₁(x)+…+a_ns_n(x)

s (x) is a polynomial interpolation function;

2) calculating tidal volume curve waveform through thoracoabdominal respiratory wave: VT ═ K × RC + M × AB;

3) setting a curve tolerance range: range ═ 0.05 (maxS-minS);

wherein: range is the tolerance Range;

maxS, setting the wave peak value of the respiratory wave;

minS, setting the trough value of the respiratory wave;

4) setting a window to be 5s, and calculating the number N of each sampling point of the tidal volume waveform within the tolerance range within 5 s;

5) calculating the goodness of fit: G-N100/A

Wherein: g is goodness of fit, N is the number of sampling points within the tolerance range of 5s, and A is the number of all sampling points within 5 s;

wherein the content of the first and second substances,

[ a, b ]: intercepting respiratory signals of a-b time periods on a thoracic and abdominal respiratory curve;

f (x): a discrete function over the thoraco-abdominal breathing curve [ a, b ] time segment;

s (x): f (x) an interpolation function over [ a, b ];

VT: tidal volume;

m, K: fitting coefficients of thoracic and abdominal respiratory signals;

RC, AB: thoracic and abdominal respiration signals;

range: a tolerance range;

maxS, setting the wave peak value of the respiratory wave;

minS, setting the trough value of the respiratory wave;

g: tidal volume goodness of fit;

n: the number of sampling points within the tolerance range of 5 s;

a: the number of all sampling points in 5 s;

the goodness of fit of the thoraco-abdominal breathing curve is calculated as follows:

1) fitting C, A for the relevant thoracoabdominal respiration waveforms by setting the respiration rate and the thoracoabdominal respiration contribution ratio;

2) the actual thoracic and abdominal respiration wave forms are ch and ab;

3) setting the tolerance range of the thoraco-abdominal curve: crange, Arange

Crange＝±0.05(maxC-minC)

Arange＝±0.05(maxA-minA)

4) Setting a window to be 5s, and calculating the thoracoabdominal respiration waveform goodness of fit within 5s, wherein GC and GA are respectively

GC＝Nc*100/Ac；

GA＝Na*100/Aa；

Nc, Na: the number of sampling points of the chest respiration signal and the abdomen respiration signal within the tolerance range of 5 s;

ac. Aa: the number of all sampling points of the chest respiration signal and the abdomen respiration signal within 5 s;

5) calculating the final goodness of fit: g ═ 2 (GC + GA);

wherein the content of the first and second substances,

C. a: fitting thoracic and abdominal respiration waveforms;

ch. ab: actual thoracic and abdominal respiration waveforms;

crange, Arange: tolerance ranges of thoracic and abdominal curves;

maxC, minC: setting the wave peak value and the wave valley value of the chest respiratory wave signal;

maxA, minA: the peak value and the valley value of the set abdominal respiration signal;

GC. GA: the respiratory waveform goodness of fit of the chest and the abdomen;

nc, Na: the number of sampling points of the chest respiration signal and the abdomen respiration signal within the tolerance range of 5 s;

ac. Aa: the number of all sampling points of the chest respiration signal and the abdomen respiration signal within 5 s;

g: the respiratory signal goodness of fit;

the respiratory rate goodness of fit is calculated as follows:

the goodness of fit is calculated by G ═ a × 100/N, where,

g is goodness of fit;

a is the number of breaths with the respiratory rate difference less than 3;

n is the actual number of breaths.

Preferably, the guidance signal module generates the guidance signal based on the set training duration, inspiration time, expiration time, and breath-hold time.

Preferably, the training duration, the inspiration time, the expiration time and the breath holding time are set by an operator.

Preferably, the training duration, the inspiration time, the expiration time and the breath holding time are set according to the breathing pattern baseline data obtained by the baseline data module.

Preferably, the breathing reconstruction unit further comprises: a breathing pattern recognition module;

the breathing pattern recognition module is configured to calculate the chest-abdomen breathing contribution ratio of the subject in the breathing exercise training process according to the breathing signals of the chest and the abdomen of the subject received by the physiological parameter receiving module.

Preferably, the guidance signal module outputs a corresponding guidance signal according to a parameter set by an operator.

The method of using the individualized respiratory motion pattern reconstruction training system as described above of the present application, comprising:

receiving a respiratory signal from a physiological parameter sensor unit worn by a subject through a physiological parameter receiving module;

driving a guide signal display unit through a guide signal module, thereby outputting a guide signal to the subject so that the subject performs a respiratory motion in accordance with the guide signal;

calculating the goodness of fit between the respiratory signal received by the physiological parameter receiving module and the guide signal when the user makes respiratory movement under the guide of the guide signal through a respiratory goodness of fit calculation module, wherein the goodness of fit comprises at least one of the goodness of fit of a tidal volume curve, the goodness of fit of a thoraco-abdominal respiratory curve and the goodness of fit of a respiratory rate;

wherein, the calculation of the goodness of fit of the tidal volume curve is as follows:

1) the respiratory waveform was fitted with the following interpolation function:

in [ a, b ]]N +1 points a ≦ x are given₀<x₁<…<x_nB, f (x) is [ a, b ]]Function of (a), function s (x; a)₀,...,a_n) The fit is as follows: s (x)_i；a₀,...,a_n)＝f(x_i),i＝0,1,…,n；

Wherein s (x) is f (x) in [ a, b ]]If s (x) is related to the parameter a₀,a₁,...,a_nIs a linear relationship, i.e.:

s(x)＝a₀s₀(x)+a₁s₁(x)+…+a_ns_n(x)

s (x) is a polynomial interpolation function;

2) calculating tidal volume curve waveform through thoracoabdominal respiratory wave: VT ═ K × RC + M × AB;

3) setting a curve tolerance range: range ═ 0.05 (maxS-minS);

wherein: range is the tolerance Range;

maxS, setting the wave peak value of the respiratory wave;

minS, setting the trough value of the respiratory wave;

4) setting a window to be 5s, and calculating the number N of each sampling point of the tidal volume waveform within the tolerance range within 5 s;

5) calculating the goodness of fit: G-N100/A

Wherein: g is goodness of fit, N is the number of sampling points within the tolerance range of 5s, and A is the number of all sampling points within 5 s;

wherein the content of the first and second substances,

[ a, b ]: intercepting respiratory signals of a-b time periods on a thoracic and abdominal respiratory curve;

f (x): a discrete function over the thoraco-abdominal breathing curve [ a, b ] time segment;

s (x): f (x) an interpolation function over [ a, b ];

VT: tidal volume;

m, K: fitting coefficients of thoracic and abdominal respiratory signals;

RC, AB: thoracic and abdominal respiration signals;

range: a tolerance range;

maxS, setting the wave peak value of the respiratory wave;

minS, setting the trough value of the respiratory wave;

g: tidal volume goodness of fit;

n: the number of sampling points within the tolerance range of 5 s;

a: the number of all sampling points in 5 s;

the goodness of fit of the thoraco-abdominal breathing curve is calculated as follows:

1) fitting C, A for the relevant thoracoabdominal respiration waveforms by setting the respiration rate and the thoracoabdominal respiration contribution ratio;

2) the actual thoracic and abdominal respiration wave forms are ch and ab;

3) setting the tolerance range of the thoraco-abdominal curve: crange, Arange

Crange＝±0.05(maxC-minC)

Arange＝±0.05(maxA-minA)

4) Setting a window to be 5s, and calculating the thoracoabdominal respiration waveform goodness of fit within 5s, wherein GC and GA are respectively

GC＝Nc*100/Ac；

GA＝Na*100/Aa；

Nc, Na: the number of sampling points of the chest respiration signal and the abdomen respiration signal within the tolerance range of 5 s;

ac. Aa: the number of all sampling points of the chest respiration signal and the abdomen respiration signal within 5 s;

5) calculating the final goodness of fit: g ═ 2 (GC + GA);

wherein the content of the first and second substances,

C. a: fitting thoracic and abdominal respiration waveforms;

ch. ab: actual thoracic and abdominal respiration waveforms;

crange, Arange: tolerance ranges of thoracic and abdominal curves;

maxC, minC: setting the wave peak value and the wave valley value of the chest respiratory wave signal;

maxA, minA: the peak value and the valley value of the set abdominal respiration signal;

GC. GA: the respiratory waveform goodness of fit of the chest and the abdomen;

nc, Na: the number of sampling points of the chest respiration signal and the abdomen respiration signal within the tolerance range of 5 s;

ac. Aa: the number of all sampling points of the chest respiration signal and the abdomen respiration signal within 5 s;

g: the respiratory signal goodness of fit;

the respiratory rate goodness of fit is calculated as follows:

the goodness of fit is calculated by G ═ a × 100/N, where,

g is goodness of fit;

a is the number of breaths with the respiratory rate difference less than 3;

n is the actual number of breaths.

Preferably, the breathing reconstruction unit further comprises: a baseline data module;

acquiring breathing mode baseline data by configuring a breathing signal received by a physiological parameter receiving module according to a predetermined length of rest spontaneous breathing before a subject performs breathing mode training through a baseline data module;

the guiding signal module generates a guiding signal based on the set training time, the set inspiration time, the set expiration time and the set breath holding time;

the breathing pattern recognition module is configured to calculate the chest-abdomen breathing contribution ratio of the subject in the breathing exercise training process according to the breathing signals of the chest and the abdomen of the subject received by the physiological parameter receiving module.

The individualized respiratory motion mode reconstruction training device and the individualized respiratory motion mode reconstruction training method can objectively compare the coincidence degree of actual respiration and guided respiration, and provide objective evaluation indexes for training; the individualized breathing movement pattern reconstruction training device and the method thereof set training parameters based on the condition of a subject; the individualized respiratory motion mode reconstruction training device and the individualized respiratory motion mode reconstruction training method can quantitatively analyze the total proportion of the breath of each mode in the whole breath and provide feedback information for reconstructing healthy breath.

Drawings

FIG. 1 is a schematic diagram of a breathing pattern training presentation;

FIG. 2 is a schematic diagram of the following degree of the actual respiratory signal and the respiratory signal set by the expert;

FIG. 3 is a diagram of the thoraco-abdominal respiration waveform and the thoraco-abdominal respiration contribution ratio;

FIG. 4 is a schematic diagram showing the variation trend of heart rate and blood oxygen saturation;

FIG. 5 is a breathing pattern assessment interface;

FIG. 6 is a schematic diagram of a training interface for reconstructing a breathing mode in an expert mode;

FIG. 7 is a schematic diagram of a breathing mode reconstruction training interface in a normal mode;

FIG. 8 is a diagram of an expert mode reconstruction training report;

FIG. 9 is a diagram illustrating a common mode reconstruction training report;

FIG. 10 is a wearable device for physiological parameter measurement in breathing pattern training;

FIG. 11 is a block diagram of the construction of the breath reconstruction unit of the individualized breath motion pattern reconstruction training system of the present application;

FIGS. 12-14 are schematic views of tidal volume following degree;

FIGS. 15-17 are graphs showing the goodness of fit of the breathing curve;

fig. 18-20 are schematic views of respiratory rate goodness of fit.

Detailed Description

Hereinafter, the individualized breathing exercise pattern reconstruction training device and the method thereof according to the present application will be described in detail with reference to the accompanying drawings.

The respiration reconstruction unit in the individualized respiration motion pattern reconstruction training system is realized by a computer or a tablet computer, and the computer or the tablet computer is subjected to program configuration, so that the computer or the computer comprises: the device comprises a physiological parameter receiving module, a guide signal module, a respiratory goodness of fit calculation module, a baseline data module and a respiratory pattern recognition module. In other words, by executing the corresponding program, the computer or the tablet computer correspondingly realizes the functions of the physiological parameter receiving module, the guidance signal module, the respiratory goodness of fit calculating module, the baseline data module and the respiratory pattern recognition module.

The physiological parameter receiving module is configured to receive a respiratory signal from a physiological parameter sensor worn by the subject; the guidance signal module is configured to output a guidance signal to the subject to cause the subject to perform respiratory motion in accordance with the guidance signal; the respiratory goodness of fit calculation module is configured to calculate goodness of fit between the respiratory signal received by the physiological parameter receiving module and the guide signal when the user makes respiratory movement under the guidance of the guide signal. The baseline data module is configured to obtain breathing mode baseline data according to the breathing signals received by the physiological parameter receiving module during the resting spontaneous breathing of a predetermined time length before the subject performs breathing mode training; the guidance signal module outputs a guidance signal based on the breathing pattern baseline data. The breathing pattern recognition module is configured to calculate the chest-abdomen breathing contribution ratio of the subject in the breathing exercise training process according to the breathing signals of the chest and the abdomen of the subject received by the physiological parameter receiving module.

The physiological parameter sensor unit is realized by a wearable physiological parameter monitoring terminal, and can monitor the chest and abdomen breathing movement and physiological parameters such as heart rate, blood oxygen and the like; the wearable physiological parameter monitoring terminal wirelessly transmits data to the PDA or the large screen, and displays the chest and abdomen respiration motion curve, the respiration mode related information and the cardiovascular system parameter change information on the large screen in real time. The large screen is provided with a respiratory motion guide curve for guiding the subject to perform respiratory motion training.

The wearable physiological parameter monitoring terminal is characterized in that a respiration induction plethysmography sensor is arranged at the chest and abdomen part to obtain a chest and abdomen real respiration motion curve, and tidal volume is obtained through calibration; electrocardio and blood oxygen saturation are measured through an electrocardio and blood oxygen wristwatch.

The guide signal display unit may be implemented by a display, a projector, or the like.

Before respiratory reconstruction training, the subject breathes for 1-2 minutes in a resting autonomous manner, breathing mode baseline data of the subject are obtained, wherein the breathing mode baseline data comprise breathing rate, inspiration and expiration time, thoracoabdominal breathing contribution ratio and the like, and the breathing mode is evaluated through the breathing mode baseline data, so that auxiliary decision support information is provided for guiding a patient to carry out respiratory mode reconstruction training by a doctor.

After the breathing pattern evaluation is completed, the doctor sets individualized breathing reconstruction training patterns of the patient, including an expert pattern and a common pattern. The method comprises the steps of setting a target breathing rate, inspiration time, expiration time and the like, then generating a guide curve or graph on a guide signal unit based on the set target breathing mode, and realizing reconstruction training of the breathing mode of a subject through interactive guide.

Expert mode

Firstly, after the respiratory mode is evaluated, a doctor sets target respiratory parameters including parameters such as training time, inspiration time, expiration time, breath holding time, respiratory rate, respiratory ratio and the like, and the respiratory mode is deeply quantized;

an interactive breathing guidance interface for visual and/or auditory guidance;

the presentation mode is as follows: including trapezoidal and round balls, and can be switched according to personal preference. The trapezoidal presentation mode is as follows: the length of the side of the trapezoid is correspondingly changed according to the relative value of the set parameter, and when respiratory training is carried out, the moving point moves along the trapezoid track; the sphere presenting mode is as follows: according to the parameter setting, the size of the initial value of the sphere is determined according to the value of the setting parameter (inspiration time/expiration time), and is changed correspondingly; when breathing in, the radius of the ball is gradually increased and is expanded from the circle 2 to the circle 1, when breathing out, the radius is reduced from the circle 1 to the circle 2, and when holding breath, the size of the ball is not changed. As shown in fig. 1

The respiratory pattern reconstruction training guidance method comprises the following steps: and carrying out breathing training according to the voice prompt.

The trapezoid presenting way is as follows: the moving point is at the starting point of the trapezoid, when the voice prompts 'inhale', the moving point moves along the track, and the patient performs inhale; when the moving point moves to the position 1, the patient stops inhaling, and the voice prompts 'breath holding' and makes breath holding action; when the moving point moves to the position 2, the voice prompts 'expiration', and the patient starts to do expiration action; when the moving point moves to the position 3, the patient stops breathing, the voice prompts 'breath holding', after the breath holding action is finished, a breathing cycle is completed, the moving point returns to the starting point, and the action is repeated to carry out breathing training;

the sphere presenting mode: taking the initial value of the ball size as the expiration time as an example, when the voice prompts 'inspiration', the patient does inspiration movement, the radius of the ball gradually expands and changes from the circle 2 to the circle 1; the voice prompts 'breath holding', the radius of the sphere is not changed and not changed; after the breath holding action is finished, the voice prompts 'expiration', the radius of the ball is gradually reduced and changes from the circle 1 to the circle 2, then the voice prompts 'breath holding', the radius of the ball is unchanged and unchanged, and a breathing cycle is completed.

The index of the goodness of fit is provided,

comprises tidal volume curve goodness of fit, thoraco-abdominal respiration curve goodness of fit and respiration rate goodness of fit;

tidal volume curve goodness of fit

1) The respiratory waveform was fitted with the following interpolation function:

in [ a, b ]]Is given aboven +1 points a is less than or equal to x₀<x₁<…<x_nB, f (x) is [ a, b ]]Function of (a), function s (x; a)₀,...,a_n) The fit is as follows: s (x)_i；a₀,...,a_n)＝f(x_i),i＝0,1,…,n

Wherein s (x) is f (x) in [ a, b ]]If s (x) with respect to the parameter a₀,a₁,...,a_nIs a linear relationship between the first and second components,

namely:

s(x)＝a₀s₀(x)+a₁s₁(x)+…+a_ns_n(x)

s (x) is a polynomial interpolation function.

2) Calculating tidal volume curve waveform through thoracoabdominal respiratory wave: VT-K RC + M AB

3) Setting a curve tolerance range: range ═ 0.05(maxS-minS)

Wherein: range is the tolerance Range;

MaxS, setting the wave peak value of the respiratory wave

minS setting the trough value of the respiratory wave

4) Setting a window to be 5s, and calculating the number N of each sampling point of the tidal volume waveform within the tolerance range within 5 s;

5) calculating the goodness of fit: G-N100/A

Wherein: g is goodness of fit, N is the number of sampling points within the tolerance range of 5s, and A is the number of all sampling points within 5 s.

And (3) related parameters:

a. b: intercepting respiratory signals of a-b time periods on a thoracic and abdominal respiratory curve;

f (x): a discrete function over the thoraco-abdominal breathing curve [ a, b ] time segment;

s (x): f (x) an interpolation function over [ a, b ];

VT: tidal volume;

m, K: fitting coefficients of thoracic and abdominal respiratory signals;

RC, AB: thoracic and abdominal respiration signals;

range: a tolerance range;

MaxS, setting the wave peak value of the respiratory wave

minS setting the trough value of the respiratory wave

G: tidal volume goodness of fit;

n: the number of sampling points within the tolerance range of 5 s;

a: the number of all sampling points in 5 s.

Chest-abdomen respiration curve goodness of fit

1) Fitting C, A for the relevant thoracoabdominal respiration waveforms by setting the respiration rate and the thoracoabdominal respiration contribution ratio;

2) the actual thoracic and abdominal respiration wave forms are ch and ab;

3) setting the tolerance range of the thoraco-abdominal curve: crange, Arange

Crange＝±0.05(maxC-minC)

Arange＝±0.05(maxA-minA)

4) Setting a window to be 5s, and calculating the thoracoabdominal respiration waveform goodness of fit within 5s, wherein GC and GA are respectively

GC＝Nc*100/Ac

GA＝Na*100/Aa

Nc, Na: number of sampling points of chest respiration signal and abdomen respiration signal within 5s tolerance range

Ac. Aa: number of all sampling points of 5s internal chest respiration signal and abdominal respiration signal

5) Calculating the final goodness of fit: g ═ 2 (GC + GA).)

And (3) related parameters:

C. a: fitting thoracic and abdominal respiration waveforms;

ch. ab: actual thoracic and abdominal respiration waveforms;

crange, Arange: tolerance ranges of thoracic and abdominal curves;

maxC, minC: setting the wave peak value and the wave valley value of the chest respiratory wave signal;

maxA, minA: the peak value and the valley value of the set abdominal respiration signal;

GC. GA: the respiratory waveform goodness of fit of the chest and the abdomen;

nc, Na: number of sampling points of chest respiration signal and abdomen respiration signal within 5s tolerance range

Ac. Aa: number of all sampling points of 5s internal chest respiration signal and abdominal respiration signal

G: respiratory signal goodness of fit

Respiratory rate goodness of fit

The goodness of fit is calculated by G ═ a × 100/N, where,

g is goodness of fit;

a is the number of breaths with the respiratory rate difference less than 3;

n is the actual number of breaths.

And synchronously displaying the respiration oscillogram and the waveform coincidence degree parameter of the actual respiration and the respiration set by an expert on a guide signal display unit, such as a PDA or a screen, and quantitatively displaying the following degree of the respiration of the patient in real time. The actual respiration signal follows the respiration signal set by the expert as shown in fig. 2. Wherein the actual breathing curve is obtained by fitting a thoracoabdominal breathing curve.

Based on the actually measured tidal volume, the tidal volume calibration is carried out by adopting a least square method according to a formula (2), chest and abdomen respiration signal fitting coefficients are obtained, the chest and abdomen respiration contribution ratio is calculated according to the chest and abdomen respiration signal fitting coefficients, and the doctor further judges the participation degree of the abdominal respiration movement of the subject according to the above, and based on the index, the subject is further guided to strengthen the abdominal respiration participation degree, and the transition from shoulder respiration and chest respiration to abdominal respiration is gradually guided to achieve a better training effect.

VT＝K*RC+M*AB (2)

r＝K*RC/(M*AB) (3)

VT: tidal volume

K: fitting coefficient of chest respiration signal

M: fitting coefficient of abdominal respiration signal

RC: chest respiration signal

AB: abdominal respiration signal

r: chest-abdomen respiration contribution ratio

And the chest-abdomen respiration motion curve and the chest-abdomen respiration contribution ratio are drawn on the PDA or the screen in real time, so that the chest-abdomen respiration motion curve and the chest-abdomen respiration contribution ratio can be visually fed back to a doctor and a subject, and the follow-up condition and the training effect can be conveniently observed by the doctor and the subject, as shown in fig. 3.

And the heart rate and the change trend of the blood oxygen saturation are displayed in real time, and doctors and patients can visually see the change of the physiological parameters of the heart and the lung in the respiratory reconstruction process, so that the confidence is further enhanced, as shown in fig. 4.

Ninthly, calculating HRV components and RSA components based on the heart rate change, and displaying the HRV components and the RSA components for doctors and patients to further enhance the confidence.

Common mode

In a common mode, a patient can set breathing parameters by himself to perform breathing mode reconstruction training.

Setting breathing parameters: the device comprises inspiration time, expiration time, training duration, respiration rate, breathing ratio and the like, and can meet the requirement of simple setting of parameters by nurses;

interactive breathing guidance: the method comprises the steps of presenting interactive breathing guidance, voice guidance and character demonstration guidance in real time, wherein the three guidance methods are matched with each other, so that the patient can be guided more clearly and accurately in the aspects of vision and/or hearing;

presentation mode: the same as the expert mode;

and fourthly, displaying parameters such as the actual respiration and respiration goodness of fit data, the actual respiration rate, the effective training time, the actual breathing ratio and the like set by the expert in real time. After the training is finished, the training effect is scored according to the goodness of fit data, and the training enthusiasm of the patient is mobilized to obtain a higher score.

In the normal mode, the system can also adaptively adjust the guiding breathing mode according to the actual breathing training result of the patient, as shown in table 1.

Table 1: adaptive adjustment of breathing patterns

By adaptively adjusting the breathing mode, a proper breathing training mode can be automatically selected for the patient according to the actual breathing condition of the patient, and the defect that the breathing mode set by the patient is possibly not suitable for the patient to carry out breathing training is overcome.

The wearable physiological parameter monitoring terminal comprises a vest, wherein breathing belts are arranged on the chest and the abdomen respectively, surround the chest and the abdomen for a circle and are used for collecting breathing signals; the blood oxygen wristwatch is worn on the wrist and used for monitoring the blood oxygen saturation; the data acquisition unit is connected with the vest, and is internally provided with an electrocardio sensor for monitoring electrocardiosignals and storing respiration signals, electrocardiosignals and oxyhemoglobin saturation signals, as shown in fig. 10

1. Tidal volume calibration

And (3) taking the tidal volume collected by the flowmeter as a golden standard, carrying out tidal volume calibration on the collected thoracic and abdominal respiration signals by adopting a least square method to obtain thoracic and abdominal fitting coefficients, and obtaining the thoracic and abdominal tidal volume based on the thoracic and abdominal fitting coefficients so as to obtain the thoracic and abdominal respiration contribution ratio.

The tidal volume range of the chest and abdomen: and calculating the tidal volume of the chest and abdomen through the formula (2) and the formula (3) according to the fitting coefficient.

VT_Rc＝K×RC (2)

VT_AB＝M×AB (3)

VT_RC: amplitude of tidal volume of chest

VT_AB: amplitude of abdominal tidal volume

② the chest-abdomen respiration contribution ratio: the thoracoabdominal respiration contribution ratio is calculated by equation (4).

r＝VT_RC/VT_AB (4)

r: chest-abdomen respiration contribution ratio

2. Baseline determination

Before respiratory reconstruction training, the patient breathes for 1-2 minutes in a resting autonomous manner, respiratory mode testing is carried out, respiratory mode baseline data of the subject are obtained, wherein the respiratory mode baseline data comprise heart rate, respiratory rate, inspiration and expiration time, thoraco-abdominal respiration contribution ratio and the like, respiratory mode evaluation is carried out through the respiratory mode baseline data, and auxiliary decision support information is provided for guiding the patient to carry out respiratory mode reconstruction training by a doctor. The breathing pattern assessment interface is shown in figure 5.

3. Personalized interactive guidance

And after the respiratory mode evaluation is finished, entering an individualized interactive guide interface to guide the patient to carry out respiratory mode reconstruction training. The individualized interactive guidance comprises an expert mode and a common mode, and in the expert mode, a doctor or a nurse sets respiratory parameters to guide a patient to carry out respiratory mode reconstruction training; in the normal mode, the patient can set breathing parameters according to the self condition, and the system can automatically select a proper breathing training mode for the patient according to the baseline data.

Expert mode

The interface for guiding the patient in the expert mode for breathing pattern reconstruction training is shown in fig. 6.

Setting target breathing parameters including parameters such as training duration, inspiration time, expiration time, breath holding time and the like by a doctor, and deeply quantifying a breathing mode;

an interactive breathing guidance interface for visual and/or auditory guidance;

presentation mode: including trapezoidal and round balls, and can be switched according to personal preference.

And fourthly, guiding the patient to carry out the respiratory mode reconstruction training in a trapezoidal presentation mode.

The specific guiding method comprises the following steps: the moving point is at the starting point of the trapezoid, when the voice prompts 'inhale', the moving point moves along the track, and the patient performs inhale; when the moving point moves to the position 1, the patient stops inhaling, and the voice prompts 'breath holding' and makes breath holding action; when the moving point moves to the position 2, the voice prompts 'expiration', and the patient starts to do expiration action; when the moving point moves to the position 3, the patient stops breathing, the voice prompts 'breath holding', after the breath holding action is finished, a breathing cycle is completed, the moving point returns to the starting point, and the action is repeated to carry out breathing training;

and fifthly, synchronously displaying the respiration oscillogram and the waveform coincidence degree parameter set by the expert and the actual respiration and the expert by the respiration mode reconstruction training interface in the expert mode, and quantitatively displaying the following degree of the respiration of the patient in real time. The parameters for respiratory training are set by the expert: for example, the inspiration time is 5.0s, the breath holding time is 1.0s, the expiration time is 5.0s, and the breath holding time is 0.5s, so that 1 breathing cycle is completed. And (4) carrying out respiratory training on the patient according to the set parameters, and evaluating the goodness of fit. Tidal volume following degrees are shown in fig. 12-14. The fit of the breathing curve is shown in fig. 15-17. The respiratory rate goodness of fit is shown in fig. 18-20.

And sixthly, drawing a thoraco-abdominal respiration motion curve and a thoraco-abdominal respiration contribution ratio in real time by a respiration mode reconstruction training interface in an expert mode, and visually feeding back the curve to a doctor and a testee, so that the doctor and the testee can observe following conditions and training effects conveniently, and guide and correct the patient to perform respiratory training in time.

And the variation trend of the heart rate and the blood oxygen saturation is displayed in real time, so that doctors and patients can visually see the variation of the physiological parameters of the heart and the lung in the respiratory reconstruction process, and the confidence is further enhanced.

Common mode

The breathing pattern reconstruction training interface in normal mode is shown in fig. 7.

In a common mode, a patient can set breathing parameters by himself or by a nurse to perform breathing mode reconstruction training.

Setting breathing parameters: the device comprises inspiration time, expiration time, training duration, respiration rate, breathing ratio and the like, and can meet the requirement of simple setting of parameters by nurses;

interactive breathing guidance: the method comprises the steps of presenting interactive breathing guidance, voice guidance and character demonstration guidance in real time, wherein the three guidance methods are matched with each other, so that the patient can be guided more clearly and accurately in the aspects of vision and/or hearing;

presentation mode: including trapezoidal and round balls, and can be switched according to personal preference.

And fourthly, explaining the respiratory mode reconstruction training of the patient under an expert mode in a spherical presentation mode, wherein the coincidence degree of the respiratory signal waveform is not considered in the spherical presentation mode.

The specific guiding method comprises the following steps: and carrying out breathing training according to the breathing training guide diagram of the character in the voice prompt or the interactive interface. When the voice prompts 'suction', a person in the interface performs suction action, displays the character of 'suction and suction' and an arrow pointing to the nostril, and simultaneously prompts the character of 'suction and abdominal bulge' by slowly bulging the abdomen of the person, and the radius of the sphere is gradually increased; when the voice prompts 'breath holding', the characters in the interface do breath holding actions to display the 'breath holding' word, the arrow disappears, the abdomen does not change, the 'breath holding abdomen does not move' word is displayed, and the size of the ball does not change; when the voice prompts 'expiration', a person in the interface performs expiration action, an arrow opposite to the direction of an inspiration arrow is displayed, the abdomen of the person slowly contracts at the same time, the character of 'contraction of the abdomen during expiration' is prompted, and the radius of the sphere gradually becomes smaller; the person in the interface holds the breath by voice, arrows at nostrils disappear, the character of holding the breath is displayed, the abdomen does not change, the size of the ball does not change, and a breathing cycle is completed. When the voice prompts 'inspiration' again, the person in the interface performs the inspiration action as above, the same prompting word is displayed, and meanwhile, the change of the ball is the same as the change of the 'inspiration', and the training of the next breathing cycle is started.

Under the common mode, the system can also adaptively adjust the respiratory training guiding mode according to the actual respiratory training result of the patient, and can automatically select a proper respiratory training mode for the patient according to the actual respiratory condition of the patient by adaptively adjusting the respiratory mode, thereby making up the defect that the respiratory mode set by the patient is possibly not suitable for the patient to perform respiratory training.

Example 1

1. Expert mode respiratory mode training: sheet XX, woman, height: 159cm, body weight: 66kg, age: COPD patients, wear physiological parameter monitoring terminal according to fig. 10, then set breathing training parameters at PDA interface, including: the wearable device is turned on after the parameters are set, and the PDA interface is displayed as shown in figure 5. Under the prompting of voice (auditory sense) and interactive guidance schematic diagram (visual sense), the respiratory mode reconstruction training is carried out according to the set respiratory training parameters, the terminal interface displays the respiratory oscillogram set by the expert, the thoracic and abdominal respiratory waveforms and the contribution ratio, the heart rate and blood oxygen trend graph in real time, the goodness of fit between the actual respiration of the subject and the respiratory waveform set by the expert, the thoracic and abdominal respiratory contribution ratio parameter, the heart rate value and the blood oxygen value can be observed in real time, the respiratory training condition of the subject is known, and after the training is finished, a report is given to explain the respiratory training condition. The report includes a training summary of blood oxygen saturation and a pre-and post-training comparison of values of blood oxygen, heart rate, respiratory rate, tidal volume, a trend graph of blood oxygen, heart rate, respiratory rate, thoracic breathing, abdominal breathing contribution, as shown in fig. 8. Through the breathing training, the abdominal breathing contribution ratio is gradually increased, so that the cardiopulmonary respiration function of the patient can be improved.

Example 2

A normal mode: the subject was a Cao in the normal mode, and was trained for breathing mode reconstruction, wearing a physiological parameter monitoring terminal according to fig. 10, and entering a PDA interface as shown in fig. 7. Setting breathing training parameters such as inspiration time, expiration time, training duration and the like, after the wearable equipment is started, carrying out breathing mode reconstruction training under the guidance of voice (hearing) and a figure demonstration dynamic graph (vision), wherein when the voice prompts 'inspiration', a figure in an interface performs inspiration action, displays a 'inspiration and inspiration' character and an arrow pointing to a nostril, and simultaneously, the abdomen of the figure is slowly swollen to prompt the 'inspiration abdomen swollen' character, and the radius of a ball is gradually increased; when the voice prompts 'breath holding', the characters in the interface do breath holding actions to display the 'breath holding' word, the arrow disappears, the abdomen does not change, the 'breath holding abdomen does not move' word is displayed, and the size of the ball does not change; when the voice prompts 'expiration', a person in the interface performs expiration action, an arrow opposite to the direction of an inspiration arrow is displayed, the abdomen of the person slowly contracts at the same time, the character of 'contraction of the abdomen during expiration' is prompted, and the radius of the sphere gradually becomes smaller; the person in the interface holds the breath by voice, arrows at nostrils disappear, the character of holding the breath is displayed, the abdomen does not change, the size of the ball does not change, and a breathing cycle is completed. When the voice prompts 'inspiration' again, the person in the interface performs the inspiration action as above, the same prompting word is displayed, and meanwhile, the change of the ball is the same as the change of the 'inspiration', and the training of the next breathing cycle is started. After the breathing training is finished, a report is given, and the report pattern is shown in fig. 9.

The advantages of the invention are as follows:

1. the breathing pattern reconstruction training includes an expert pattern and a normal pattern. In the expert mode, the patient can carry out interactive breathing training under the guidance of a voice guidance and presentation mode, and meanwhile, a doctor can set breathing guidance parameters in real time according with the training condition of the patient and check the change condition of other physiological parameters of the patient in real time; in a common mode, a patient carries out interactive breathing training according to a voice prompt and presentation mode, can carry out training according to an expert prescription and can also carry out basic breathing training under the guidance of a nurse;

2. the guiding of the breathing training of the patient in the aspects of vision and hearing can be realized no matter in the expert mode or the common mode. In the expert mode, the presentation mode of the interactive guidance comprises the following steps: the patient can switch between the trapezoid and the ball according to personal preference, in the mode, the moving point moves along the track of the trapezoid or the ball according to the voice prompt, and the presentation mode of the trapezoid or the ball is to display different shapes and sizes according to the relative values of the set parameters, so that the synchronization of the voice and the presentation mode is realized; in a common mode, the presentation mode is trapezoidal, the moving point moves along a trapezoidal track according to the voice prompt, and the trapezoidal shape displays different sizes according to the relative values of the set parameters, so that the synchronization of the voice and the presentation mode is realized;

3. under an expert mode, real respiration and expert set respiration waveforms are displayed in real time, and the following degree of respiration of a patient is quantified in real time by comparing the real respiration and the expert set respiration waveforms with the displayed waveform coincidence degree data; the set parameters can be adjusted in real time, so that the patient can perform breathing training under the proper parameter setting;

4. under an expert mode, the chest/abdomen respiration waveform and the chest/abdomen respiration contribution ratio data are displayed in real time, the respiration mode is quantized, and the respiration mode of a patient is determined more intuitively;

5. in a common mode, the moving point moves along a trapezoidal track according to voice prompt, an actual motion curve of the breath of the patient is displayed in real time, the actual breath is compared with a breath waveform set by an expert in real time, the following degree of the patient can be more visually represented, the patient is guided to adjust the breath, and the patient is stimulated to exercise; meanwhile, displaying goodness of fit data in real time, scoring the training effect of the patient according to the goodness of fit data, and adjusting the enthusiasm of the patient for training to obtain a higher score;

6. in the normal mode, a figure demonstration image is set, and the figure demonstration image is synchronous with the voice prompt. Under the voice prompt, the figure demonstrates the motion picture to do inspiration or expiration, and prompts that the abdomen should be in a bulging or contraction state, so that the patient is guided from the two aspects of vision and hearing more clearly and accurately, and the interest of the patient in respiratory training is stimulated;

7. in the common mode, the character action, the voice prompt and the dynamic guidance (trapezia and ball) of the interactive guidance mode can be perfectly connected according to the set algorithm.

8. Under the ordinary mode, the system is equipped with self-adaptation breathing mode, can be according to the actual breathing result of patient, and automatic breathing training mode for its adjustment is suitable has compensatied the breathing parameter of manual setting probably not suitable for the patient and has carried out the breathing training not enough.

Unless defined otherwise, all technical and/or scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The materials, methods, and examples set forth in this application are illustrative only and not intended to be limiting.

Although the present invention has been described in conjunction with specific embodiments thereof, it is evident that many alternatives, modifications, and variations will be apparent to those skilled in the art in light of the teachings of this application and yet remain within the scope of this application.

Claims (10)

1. An individualized respiratory motion pattern reconstruction training system, comprising: the device comprises a physiological parameter sensor unit, a respiration reconstruction unit and a guide signal display unit;

the physiological parameter sensor unit is worn on a subject to measure a respiratory signal of the subject;

the respiratory reconstruction unit is implemented by a computer configured to include: the device comprises a physiological parameter receiving module, a guide signal module and a respiratory goodness of fit calculating module;

the physiological parameter receiving module is configured to receive a respiratory signal from the physiological parameter sensor unit;

the guiding signal module is configured to drive the guiding signal display unit, thereby outputting a guiding signal to the subject so that the subject performs respiratory motion according to the guiding signal;

the respiratory goodness of fit calculation module is configured to calculate goodness of fit between the respiratory signal received by the physiological parameter receiving module and the guide signal when the user makes respiratory movement under the guidance of the guide signal.

2. The individualized respiratory motion pattern reconstruction training system of claim 1, wherein the respiratory reconstruction unit further comprises: a baseline data module;

the baseline data module is configured to obtain breathing mode baseline data according to the breathing signals received by the physiological parameter receiving module during the resting spontaneous breathing of a predetermined time length before the subject performs breathing mode training;

the guidance signal module outputs a guidance signal based on the breathing pattern baseline data.

3. The individualized respiratory motion pattern reconstruction training system of claim 2, wherein:

the respiratory goodness of fit calculation module calculates at least one of the goodness of fit of tidal volume curve, goodness of fit of thoraco-abdominal respiratory curve and goodness of fit of respiratory rate:

wherein, the calculation of the goodness of fit of the tidal volume curve is as follows:

1) the respiratory waveform was fitted with the following interpolation function:

in [ a, b ]]N +1 points a ≦ x are given₀<x₁<…<x_nB, f (x) is [ a, b ]]Function of (a), function s (x; a)₀,...,a_n) The fit is as follows: s (x)_i；a₀,...,a_n)＝f(x_i),i＝0,1,…,n；

Wherein s (x) is f (x) in [ a, b ]]If s (x) is related to the parameter a₀,a₁,...,a_nIs a linear relationship, i.e.:

s(x)＝a₀s₀(x)+a₁s₁(x)+…+a_ns_n(x)

s (x) is a polynomial interpolation function;

2) calculating tidal volume curve waveform through thoracoabdominal respiratory wave: VT ═ K × RC + M × AB;

3) setting a curve tolerance range: range ═ 0.05 (maxS-minS);

wherein: range is the tolerance Range;

maxS, setting the wave peak value of the respiratory wave;

minS, setting the trough value of the respiratory wave;

4) setting a window to be 5s, and calculating the number N of each sampling point of the tidal volume waveform within the tolerance range within 5 s;

5) calculating the goodness of fit: G-N100/A

Wherein: g is goodness of fit, N is the number of sampling points within the tolerance range of 5s, and A is the number of all sampling points within 5 s;

wherein the content of the first and second substances,

[ a, b ]: intercepting respiratory signals of a-b time periods on a thoracic and abdominal respiratory curve;

f (x): a discrete function over the thoraco-abdominal breathing curve [ a, b ] time segment;

s (x): f (x) an interpolation function over [ a, b ];

VT: tidal volume;

m, K: fitting coefficients of thoracic and abdominal respiratory signals;

RC, AB: thoracic and abdominal respiration signals;

range: a tolerance range;

maxS, setting the wave peak value of the respiratory wave;

minS, setting the trough value of the respiratory wave;

g: tidal volume goodness of fit;

n: the number of sampling points within the tolerance range of 5 s;

a: the number of all sampling points in 5 s;

the goodness of fit of the thoraco-abdominal breathing curve is calculated as follows:

1) fitting C, A for the relevant thoracoabdominal respiration waveforms by setting the respiration rate and the thoracoabdominal respiration contribution ratio;

2) the actual thoracic and abdominal respiration wave forms are ch and ab;

3) setting the tolerance range of the thoraco-abdominal curve: crange, Arange

Crange＝±0.05(maxC-minC)

Arange＝±0.05(maxA-minA)

4) Setting a window to be 5s, and calculating the thoracoabdominal respiration waveform goodness of fit within 5s, wherein GC and GA are respectively

GC＝Nc*100/Ac；

GA＝Na*100/Aa；

Nc, Na: the number of sampling points of the chest respiration signal and the abdomen respiration signal within the tolerance range of 5 s;

ac. Aa: the number of all sampling points of the chest respiration signal and the abdomen respiration signal within 5 s;

5) calculating the final goodness of fit: g ═ 2 (GC + GA);

wherein the content of the first and second substances,

C. a: fitting thoracic and abdominal respiration waveforms;

ch. ab: actual thoracic and abdominal respiration waveforms;

crange, Arange: tolerance ranges of thoracic and abdominal curves;

maxC, minC: setting the wave peak value and the wave valley value of the chest respiratory wave signal;

maxA, minA: the peak value and the valley value of the set abdominal respiration signal;

GC. GA: the respiratory waveform goodness of fit of the chest and the abdomen;

nc, Na: the number of sampling points of the chest respiration signal and the abdomen respiration signal within the tolerance range of 5 s;

ac. Aa: the number of all sampling points of the chest respiration signal and the abdomen respiration signal within 5 s;

g: the respiratory signal goodness of fit;

the respiratory rate goodness of fit is calculated as follows:

the goodness of fit is calculated by G ═ a × 100/N, where,

g is goodness of fit;

a is the number of breaths with the respiratory rate difference less than 3;

n is the actual number of breaths.

4. The individualized respiratory motion pattern reconstruction training system of claim 1, wherein:

the guiding signal module generates a guiding signal based on the set training time, inspiration time, expiration time and breath holding time.

5. The individualized respiratory motion pattern reconstruction training system of claim 4, wherein:

the training time, the inspiration time, the expiration time and the breath holding time are set by an operator.

6. The individualized respiratory motion pattern reconstruction training system of claim 4, wherein:

the training duration, the inspiration time, the expiration time and the breath holding time are set according to the breathing mode baseline data obtained by the baseline data module.

7. The individualized respiratory motion pattern reconstruction training system of claim 1, wherein the respiratory reconstruction unit further comprises: a breathing pattern recognition module;

the breathing pattern recognition module is configured to calculate the chest-abdomen breathing contribution ratio of the subject in the breathing exercise training process according to the breathing signals of the chest and the abdomen of the subject received by the physiological parameter receiving module.

8. The individualized respiratory motion pattern reconstruction training system of claim 5 or 7, wherein:

the guide signal module outputs corresponding guide signals according to parameters set by an operator.

9. A method of using the individualized respiratory motion pattern reconstruction training system of claim 1, comprising:

receiving a respiratory signal from a physiological parameter sensor unit worn by a subject through a physiological parameter receiving module;

driving a guide signal display unit through a guide signal module, thereby outputting a guide signal to the subject so that the subject performs a respiratory motion in accordance with the guide signal;

calculating the goodness of fit between the respiratory signal received by the physiological parameter receiving module and the guide signal when the user makes respiratory movement under the guide of the guide signal through a respiratory goodness of fit calculation module, wherein the goodness of fit comprises at least one of the goodness of fit of a tidal volume curve, the goodness of fit of a thoraco-abdominal respiratory curve and the goodness of fit of a respiratory rate;

wherein, the calculation of the goodness of fit of the tidal volume curve is as follows:

1) the respiratory waveform was fitted with the following interpolation function:

in [ a, b ]]N +1 points a ≦ x are given₀<x₁<…<x_nB, f (x) is [ a, b ]]Function of (a), function s (x; a)₀,...,a_n) The fit is as follows: s (x)_i；a₀,...,a_n)＝f(x_i),i＝0,1,…,n；

Wherein s (x) is f (x) in [ a, b ]]If s (x) is related to the parameter a₀,a₁,...,a_nIs a linear relationship, i.e.:

s(x)＝a₀s₀(x)+a₁s₁(x)+…+a_ns_n(x)

s (x) is a polynomial interpolation function;

2) calculating tidal volume curve waveform through thoracoabdominal respiratory wave: VT ═ K × RC + M × AB;

3) setting a curve tolerance range: range ═ 0.05 (maxS-minS);

wherein: range is the tolerance Range;

maxS, setting the wave peak value of the respiratory wave;

minS, setting the trough value of the respiratory wave;

4) setting a window to be 5s, and calculating the number N of each sampling point of the tidal volume waveform within the tolerance range within 5 s;

5) calculating the goodness of fit: G-N100/A

Wherein: g is goodness of fit, N is the number of sampling points within the tolerance range of 5s, and A is the number of all sampling points within 5 s;

wherein the content of the first and second substances,

[ a, b ]: intercepting respiratory signals of a-b time periods on a thoracic and abdominal respiratory curve;

f (x): a discrete function over the thoraco-abdominal breathing curve [ a, b ] time segment;

s (x): f (x) an interpolation function over [ a, b ];

VT: tidal volume;

m, K: fitting coefficients of thoracic and abdominal respiratory signals;

RC, AB: thoracic and abdominal respiration signals;

range: a tolerance range;

maxS, setting the wave peak value of the respiratory wave;

minS, setting the trough value of the respiratory wave;

g: tidal volume goodness of fit;

n: the number of sampling points within the tolerance range of 5 s;

a: the number of all sampling points in 5 s;

the goodness of fit of the thoraco-abdominal breathing curve is calculated as follows:

1) fitting C, A for the relevant thoracoabdominal respiration waveforms by setting the respiration rate and the thoracoabdominal respiration contribution ratio;

2) the actual thoracic and abdominal respiration wave forms are ch and ab;

3) setting the tolerance range of the thoraco-abdominal curve: crange, Arange

Crange＝±0.05(maxC-minC)

Arange＝±0.05(maxA-minA)

4) Setting a window to be 5s, and calculating the thoracoabdominal respiration waveform goodness of fit within 5s, wherein GC and GA are respectively

GC＝Nc*100/Ac；

GA＝Na*100/Aa；

Nc, Na: the number of sampling points of the chest respiration signal and the abdomen respiration signal within the tolerance range of 5 s;

ac. Aa: the number of all sampling points of the chest respiration signal and the abdomen respiration signal within 5 s;

5) calculating the final goodness of fit: g ═ 2 (GC + GA);

wherein the content of the first and second substances,

C. a: fitting thoracic and abdominal respiration waveforms;

ch. ab: actual thoracic and abdominal respiration waveforms;

crange, Arange: tolerance ranges of thoracic and abdominal curves;

maxC, minC: setting the wave peak value and the wave valley value of the chest respiratory wave signal;

maxA, minA: the peak value and the valley value of the set abdominal respiration signal;

GC. GA: the respiratory waveform goodness of fit of the chest and the abdomen;

nc, Na: the number of sampling points of the chest respiration signal and the abdomen respiration signal within the tolerance range of 5 s;

ac. Aa: the number of all sampling points of the chest respiration signal and the abdomen respiration signal within 5 s;

g: the respiratory signal goodness of fit;

the respiratory rate goodness of fit is calculated as follows:

the goodness of fit is calculated by G ═ a × 100/N, where,

g is goodness of fit;

a is the number of breaths with the respiratory rate difference less than 3;

n is the actual number of breaths.

10. The use of claim 9, wherein the breath reconstruction unit further comprises: a baseline data module;

acquiring breathing mode baseline data by configuring a breathing signal received by a physiological parameter receiving module according to a predetermined length of rest spontaneous breathing before a subject performs breathing mode training through a baseline data module;

the guiding signal module generates a guiding signal based on the set training time, the set inspiration time, the set expiration time and the set breath holding time;

the breathing pattern recognition module is configured to calculate the chest-abdomen breathing contribution ratio of the subject in the breathing exercise training process according to the breathing signals of the chest and the abdomen of the subject received by the physiological parameter receiving module.

Images