Multi-parameter feedback regulation and control method for postoperative lung function rehabilitation training

Abstract

The invention belongs to the technical field of intelligent rehabilitation equipment control, and relates to a multi-parameter feedback regulation and control method for postoperative lung function rehabilitation training, which comprises the following steps: acquiring an electrocardiosignal, a respiration signal and a limb movement signal of a patient; identifying a heart rate fluctuation form of the electrocardiosignal to generate an abnormal fluctuation time period, and analyzing a time difference between an inspiration phase and an expiration phase of the respiratory signal to generate a starting point of respiratory rhythm disorder; judging a cardiopulmonary risk level; the exercise intensity of rehabilitation training equipment is automatically adjusted based on the cardiopulmonary risk level, and meanwhile a regulation and control mode is dynamically selected according to the proportion change of the chest fluctuation amplitude and the abdomen fluctuation amplitude; when the heart rate recovery rate is lower than a preset reference and the respiratory rhythm stabilization time exceeds a critical value, gradually improving the exercise intensity; calculating a motion intensity correction coefficient and triggering a motion posture correction instruction; and generating a rating report containing the cardiopulmonary function fitness. According to the invention, the problem of lack of comprehensive quantitative evaluation of rehabilitation efficiency in the prior art is solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent rehabilitation equipment control and relates to a multi-parameter feedback control method for postoperative pulmonary function rehabilitation training. Background Art

[0002] In the field of rehabilitation medicine, traditional training models often face critical technical bottlenecks in real-time monitoring of patients' cardiopulmonary function and dynamic adaptation to exercise load. Existing technologies rely on single physiological parameter monitoring methods, such as independent analysis of electrocardiogram (ECG) signals or respiratory rate, but lack the ability to correlate abnormalities in cardiopulmonary coordination, resulting in an inability to promptly identify the risk of exercise-induced cardiopulmonary decompensation. Furthermore, intensity control in exercise equipment often relies on preset fixed thresholds or the therapist's empirical judgment, making it difficult to respond promptly to changes in the patient's individual physiological state.

[0003] Current solutions primarily rely on a combination of discrete monitoring devices and manual intervention. For example, medical staff manually adjust training parameters after an ECG monitor warns of an arrhythmia. While these methods can provide basic safety protection, they suffer from low data integration and significant response delays. Traditional respiratory monitoring technologies, often based on chest strap pressure sensors, struggle to distinguish between chest and abdominal breathing patterns. Movement posture assessment typically relies on visual observation or simple accelerometers, which cannot accurately quantify the correlation between three-dimensional motion trajectory and cardiopulmonary load.

[0004] Based on the above problems, the disadvantages of traditional methods are concentrated in the fact that existing technologies lack comprehensive quantitative evaluation of rehabilitation effectiveness, and feedback on training effects is mostly limited to single indicators such as heart rate recovery, which restricts the optimization process of personalized rehabilitation plans. Summary of the Invention

[0005] In order to solve the above problems, the present invention provides a multi-parameter feedback control method for postoperative pulmonary function rehabilitation training.

[0006] The multi-parameter feedback control method for postoperative pulmonary function rehabilitation training includes the following steps: S1. Acquire the patient's real-time electrocardiogram (ECG) signal, respiratory signal, and limb motion signal, wherein the respiratory signal includes a chest-to-abdomen fluctuation amplitude ratio parameter, and the limb motion signal includes a three-dimensional acceleration trajectory parameter; S2, identifying the heart rate fluctuation pattern of the ECG signal to generate an abnormal fluctuation period, and analyzing the time difference between the inhalation phase and the exhalation phase of the respiratory signal to generate the starting point of the respiratory rhythm disorder; S3. Determine the cardiopulmonary risk level based on the overlap between the abnormal fluctuation period and the starting point of the respiratory rhythm disorder; S4. Automatically adjust the exercise intensity of the rehabilitation training equipment based on the cardiopulmonary risk level, and dynamically select the control mode based on the ratio of chest and abdominal rise and fall; S5. Monitor the heart rate recovery rate and respiratory rhythm stabilization time at the adjusted exercise intensity. When the heart rate recovery rate is lower than the preset benchmark and the respiratory rhythm stabilization time exceeds the critical value, gradually increase the exercise intensity; S6. Calculate the exercise intensity correction coefficient and trigger the exercise posture correction instruction by combining the three-dimensional acceleration trajectory parameters of the limb movement signal with the real-time heart rate and respiratory rate correlation curve parameters; S7. After completing each stage of training, a cardiopulmonary fitness rating report is generated based on the normalized summation of heart rate fluctuation recovery time, abdominal breathing maintenance time, and acceleration trajectory smoothness.

[0007] A further solution of the present invention is to obtain a patient's real-time electrocardiogram signal, respiratory signal, and limb movement signal, comprising the following steps: A flexible ECG patch attached to the patient's chest continuously records the heart's ECG signals; A breathing belt is placed between the patient's sternum and navel to detect the rise and fall of the chest and abdomen during breathing; The motion sensing device deployed at the end of the limb obtains the fusion data of the three-axis accelerometer and gyroscope, and calculates the three-dimensional acceleration trajectory parameters.

[0008] A further embodiment of the present invention, wherein the respiratory signal includes a chest and abdomen fluctuation amplitude ratio parameter, comprises the following steps: The peak-to-peak value of the piezoelectric sensor output voltage in the sternum motion area is recorded as A, and the peak-to-peak value of the piezoelectric sensor output voltage in the rectus abdominis motion area is recorded as B. The respiratory signal contains the ratio parameter of the chest rise and fall amplitude A to the abdomen rise and fall amplitude B; The breathing ratio threshold is determined based on the breathing pattern ratio threshold of historical healthy people at rest; If the breathing ratio reaches the threshold, it is determined to be an abdominal breathing dominant state; If the breathing ratio reaches the threshold, it is determined to be a state of chest breathing dominance.

[0009] A further solution of the present invention is to identify the heart rate fluctuation pattern of the electrocardiogram signal to generate an abnormal fluctuation period, including the following steps: A flexible ECG patch attached to the patient's chest continuously records the heart's ECG signals; The peak point of the QRS complex is detected by the adaptive threshold method. The time interval between the peak points of two adjacent QRS complexes is defined as the RR interval. When the coefficient of variation RR-CV of the RR interval exceeds the first threshold, the period is determined to be an abnormal fluctuation period. The first threshold is the RR interval variation coefficient threshold, which is set based on the clinical standard of heart rate variability and the calibration of individual patient differences; The ratio of the standard deviation of the RR interval series to the mean of the RR interval gives the dimensionless coefficient of variation RR-CV of the RR interval.

[0010] A further solution of the present invention is to analyze the time difference between the inspiratory phase and the expiratory phase of the respiratory signal to generate the starting point of the respiratory rhythm disorder, comprising the following steps: The duration from the rising edge to the falling edge of the output voltage of the piezoelectric sensor in the sternal motion area is the duration of the inspiratory phase, and the duration from the falling edge to the next rising edge of the output voltage of the piezoelectric sensor in the sternal motion area is the duration of the expiratory phase; Calculate the absolute value of the difference between the duration of the inspiratory phase and the duration of the expiratory phase in each respiratory cycle; If the absolute value of the difference between three consecutive respiratory cycles exceeds a second threshold, marking the starting point of the respiratory cycle as the starting point of respiratory rhythm disorder; The second threshold is the respiratory rhythm symmetry deviation threshold. The setting of the second threshold is based on the physiological standard of respiratory rhythm symmetry and disease adaptation.

[0011] A further embodiment of the present invention determines the cardiopulmonary risk level, comprising the following steps: For each abnormal fluctuation period, the preset time window is extended forward and backward based on the start time and end time; for each starting point of respiratory rhythm disorder, a coverage interval with the same time window length as the center is generated; If the coverage interval of the starting point of a respiratory rhythm disorder intersects with the extended time window of any abnormal fluctuation period, the two are considered synchronous events, triggering an increase in the cardiopulmonary risk level by one level; If only a single type of abnormality is present or there is no temporal overlap between the two types of abnormalities, the baseline cardiopulmonary risk level should be maintained.

[0012] A further solution of the present invention is to gradually increase the exercise intensity when the heart rate recovery rate is lower than a preset benchmark and the respiratory rhythm stabilization time exceeds a critical value, comprising the following steps: Automatically adjust the exercise intensity of rehabilitation training equipment based on cardiopulmonary risk level. This adjustment includes reducing the resistance of the exercise equipment or slowing down the exercise frequency. Dynamically select the control mode based on the ratio of chest and abdominal rise and fall. If the breathing ratio threshold is reached and it is determined that the patient is in an abdominal breathing dominant state, the breathing guidance instruction will be triggered. The breathing guidance instruction includes a pre-recorded abdominal breathing guidance voice, which guides the patient to increase the depth of abdominal breathing through audio prompts; if the breathing ratio threshold is reached and it is determined that the patient is in a chest breathing dominant state, the current exercise parameters will be maintained.

[0013] A further solution of the present invention calculates the exercise intensity correction coefficient and triggers the exercise posture correction instruction, including the following steps: Extract data from the three-axis accelerometer and gyroscope of the motion sensing device and calculate the angular change rate of the limb motion vector; If the product of the angular change rates of the sagittal, coronal, and horizontal planes at a certain moment exceeds the preset angle change rate threshold, it is determined to be an acceleration direction sudden change event; When a sudden change in acceleration occurs, if the heart rate to respiratory rate ratio exceeds the baseline range and persists for longer than the set duration, it is determined that the exercise posture does not match the cardiorespiratory load. A correction factor for the exercise intensity adjustment range is generated, triggering a posture correction instruction.

[0014] A further solution of the present invention, which calculates the exercise intensity correction coefficient and triggers the exercise posture correction instruction, further includes the following steps:

[0015] in, is the correction factor; The adjustment coefficient determined in step S4; It is the ratio of real-time heart rate to respiratory rate; It is the center value of the baseline interval of healthy people in the resting state recorded in history; is the duration of the sudden change in acceleration direction; For reference time, it is set according to industry standards.

[0016] A further embodiment of the present invention generates a cardiopulmonary fitness rating report, comprising the following steps: The length of the time period during which the heart rate recovery rate reaches the standard is extracted as the heart rate fluctuation recovery time; The continuous maintenance time of the abdominal breathing dominant state is counted in the recorded breathing pattern ratio data; In the three-dimensional acceleration trajectory, the inverse of the standard deviation of the acceleration changes in the sagittal, coronal, and horizontal planes was calculated as the trajectory smoothness index; The three indicators are normalized to values ​​between 0 and 1 and then summed to obtain the fitness rating result.

[0017] In summary, the present invention has the following beneficial technical effects: 1. Through real-time synchronous analysis of the spatiotemporal correlation between abnormal ECG signal fluctuations and respiratory rhythm disorders, a dynamic cardiopulmonary risk warning level is established. This system can automatically trigger graded exercise intensity control when patients experience abnormal cardiopulmonary function coupling. This effectively avoids the risk of overload caused by delayed physiological status monitoring in traditional rehabilitation training, and reduces the incidence of cardiovascular accidents. 2. Based on a collaborative judgment mechanism combining chest and abdominal breathing pattern recognition with three-dimensional motion trajectory analysis, combined with the patient's real-time cardiopulmonary function and posture stability data, a self-learning intensity control model is established. This overcomes the limitations of traditional fixed training models and enables exercise parameter adjustments to meet medical safety standards while adapting to individual rehabilitation progress. 3. By integrating heterogeneous data such as heart rate recovery dynamics, breathing pattern maintenance ability, and motion trajectory smoothness, a quantitative fitness rating is established, expanding traditional single heart rate monitoring to a cardiopulmonary and exercise synergy performance assessment, providing clinicians with structured feedback including risk warning, training effect, functional compensation and other factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. The drawings are used to provide a further understanding of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 A schematic diagram of the flow chart in the embodiment of the present application is disclosed.

[0020] Figure 2 The present invention discloses a schematic structural diagram in an embodiment of the present application. DETAILED DESCRIPTION

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0022] The following is combined with Figure 1-Figure 2 The preferred embodiments of the present invention are described in detail.

[0023] Refer to the attached Figure 1 The present invention proposes a multi-parameter feedback control method for postoperative pulmonary function rehabilitation training, comprising the following steps: S1. Acquire the patient's real-time electrocardiogram (ECG) signal, respiratory signal, and limb motion signal, wherein the respiratory signal includes a chest-to-abdomen fluctuation amplitude ratio parameter, and the limb motion signal includes a three-dimensional acceleration trajectory parameter; S2, identifying the heart rate fluctuation pattern of the ECG signal to generate an abnormal fluctuation period, and analyzing the time difference between the inhalation phase and the exhalation phase of the respiratory signal to generate the starting point of the respiratory rhythm disorder; S3. Determine the cardiopulmonary risk level based on the overlap between the abnormal fluctuation period and the starting point of the respiratory rhythm disorder; S4. Automatically adjust the exercise intensity of the rehabilitation training equipment based on the cardiopulmonary risk level, and dynamically select the control mode based on the ratio of chest and abdominal rise and fall; S5. Monitor the heart rate recovery rate and respiratory rhythm stabilization time at the adjusted exercise intensity. When the heart rate recovery rate is lower than the preset benchmark and the respiratory rhythm stabilization time exceeds the critical value, gradually increase the exercise intensity; S6. Calculate the exercise intensity correction coefficient and trigger the exercise posture correction instruction by combining the three-dimensional acceleration trajectory parameters of the limb movement signal with the real-time heart rate and respiratory rate correlation curve parameters; S7. After completing each stage of training, a cardiopulmonary fitness rating report is generated based on the normalized summation of heart rate fluctuation recovery time, abdominal breathing maintenance time, and acceleration trajectory smoothness.

[0024] In one embodiment of the present invention, step S1 includes the following steps: Acquire the patient's real-time ECG signal, respiratory signal, and limb movement signal. The respiratory signal contains the ratio parameter of the chest and abdominal undulation amplitudes, and the limb movement signal contains the acceleration change trajectory in three-dimensional space.

[0025] Specifically, based on existing clinical anatomy and biomechanical principles, a flexible ECG patch attached to the patient's chest is used to continuously record the heart's ECG signals. The flexible ECG patch contains three electrode contacts, which are placed respectively between the third and fifth intercostal spaces on the right edge of the sternum (for monitoring right ventricular electrical activity), between the fourth and sixth intercostal spaces on the left midclavicular line (for monitoring right ventricular electrical activity), and in the right groin area (the electrode contacts here serve as reference electrodes to eliminate common-mode interference) to obtain complete ECG signals.

[0026] An elastic breathing belt is secured between the patient's xiphoid process and the umbilicus. Two sets of piezoelectric sensors are built into the belt, corresponding to the sternal and rectus abdominis movement areas, respectively. These sensors monitor the rise and fall of the chest and abdomen during breathing in real time. The elastic breathing belt, secured between the xiphoid process and the umbilicus, uses chest cage movement in the xiphoid region and contraction of the rectus abdominis in the umbilicus to quantify the thoracic and abdominal breathing amplitudes, accurately distinguishing breathing patterns.

[0027] Motion sensors are fixed to the patient's wrists and ankles. These devices, equipped with three-axis accelerometers and gyroscopes, continuously record changes in limb acceleration in the forward, backward, left, right, and up and down directions. These sensors are deployed at the patient's wrists and ankles, which are exposed and suitable for long-term wear. The integration of three-dimensional acceleration and angular velocity at these extremities captures the trajectory of limb joint movement and postural stability during rehabilitation training, while avoiding postoperative wound areas and meeting non-invasive monitoring requirements.

[0028] The fusion of three-dimensional acceleration and angular velocity satisfies the following formula:

[0029] in, is the motion vector, which is the three-dimensional acceleration trajectory parameter; and The instantaneous acceleration of the x-axis and y-axis measured by the three-axis accelerometer (in m / s²); is the acceleration due to gravity (in m / s²), which is used to compensate for the gravity component when the patient is tilted; is the pitch angle around the y-axis measured by the gyroscope; is the roll angle around the x-axis measured by the gyroscope; is the accelerometer range normalization coefficient (in m / s²), determined according to the sensor specifications; is the integral variable, which represents the process of time accumulation.

[0030] The ratio parameter of the chest rise and fall amplitude to the abdomen rise and fall amplitude is obtained by the following method: The peak-to-peak value of the piezoelectric sensor output voltage in the sternum motion area is recorded as A, and the peak-to-peak value of the piezoelectric sensor output voltage in the rectus abdominis motion area is recorded as B. The respiratory signal contains the ratio parameter of the chest fluctuation amplitude A to the abdomen fluctuation amplitude B. The respiratory ratio threshold is determined based on the historical respiratory pattern ratio threshold of healthy people at rest; if When the breathing ratio threshold is reached, it is determined to be a state of abdominal breathing dominance; if When the breathing ratio threshold is reached, it is determined to be a state of chest breathing dominance.

[0031] In one embodiment of the present invention, step S2 includes the following steps: Based on the ECG signal and respiratory signal obtained in step S1, the heart rate fluctuation pattern in the ECG signal is identified and the abnormal fluctuation period is marked; the time difference between the inhalation phase and the exhalation phase in the respiratory signal is analyzed and the starting point of the respiratory rhythm disorder is marked.

[0032] Specifically, the flexible ECG patch records continuous ECG signal waveforms, and uses an adaptive threshold method to detect the peaks of the QRS complexes. The time interval between two adjacent QRS complex peaks is defined as the RR interval. When the coefficient of variation (RR-CV) of the RR interval exceeds a first threshold, the period is identified as an abnormal fluctuation period.

[0033] The coefficient of variation RR-CV of the RR interval is calculated as follows: the ratio of the standard deviation of the RR interval sequence to the mean of the RR interval to obtain the dimensionless coefficient of variation RR-CV of the RR interval. For the respiratory signal collected by the respiratory belt, the duration from the rising edge to the falling edge of the output voltage of the piezoelectric sensor in the sternal motion area is the duration of the inspiratory phase, and the duration from the falling edge to the next rising edge of the output voltage of the piezoelectric sensor in the sternal motion area is the duration of the expiratory phase. The absolute value of the difference between the inspiratory phase and the expiratory phase in each respiratory cycle is calculated to quantify the degree of symmetry deviation of the respiratory rhythm. If the absolute value of the difference between three consecutive respiratory cycles exceeds the second threshold, the starting point of the respiratory cycle is marked as the starting point of the respiratory rhythm disorder.

[0034] The peak point of the QRS complex refers to the highest amplitude point of the QRS complex in the ECG signal waveform, representing the peak moment of ventricular depolarization. The RR interval refers to the time interval between two adjacent QRS complex peak points, reflecting the length of the heartbeat cycle. The starting point of respiratory rhythm disorder refers to the starting moment of the first respiratory cycle that meets the symmetry deviation standard for three consecutive respiratory cycles. The adaptive threshold method refers to an algorithm that dynamically adjusts the QRS wave detection threshold, updating the threshold in real time according to the signal noise level.

[0035] The first threshold is the RR interval coefficient of variation threshold. When the coefficient of variation RR-CV of the RR interval exceeds the first threshold, the patient's heart is overloaded or there is a potential risk of arrhythmia. The setting of the first threshold is based on the clinical standards of heart rate variability and calibration of individual patient differences.

[0036] The second threshold is the respiratory rhythm symmetry deviation threshold. Symmetry deviation reflects abnormal breathing pattern (such as wheezing, respiratory muscle fatigue); the setting of the second threshold is based on the physiological standards of respiratory rhythm symmetry and disease adaptation.

[0037] The mean RR interval is the arithmetic mean of all RR intervals (intervals between adjacent heartbeats) within a period of time, and satisfies the following formula:

[0038] The standard deviation of the RR interval series refers to the degree of dispersion of the RR interval series, quantifying the fluctuation range of the heartbeat interval and satisfying the following formula:

[0039] in, is the mean RR interval, which represents the average heartbeat interval time; For the The RR interval represents the time interval between the peak points of adjacent QRS complexes; is the total number of heartbeats; is the standard deviation of the RR interval, which indicates the fluctuation amplitude of the heartbeat interval.

[0040] For example, when the patient performs upper limb stretching training, the QRS wave group intervals recorded by the flexible ECG patch are 0.85 seconds, 1.12 seconds, 0.78 seconds, and 1.05 seconds in 20 consecutive seconds. The mean RR interval is calculated as The standard deviation of the RR interval is 0.95 seconds. The time interval is 0.15 seconds, the coefficient of variation is 0.15 to 0.95, which is about 0.158. The first threshold is set to 0.12, and it is determined that there is abnormal heart rate fluctuation in this period.

[0041] The piezoelectric sensor in the sternum area measured that the inspiratory phase of the respiratory cycle lasted 1.2 seconds and the expiratory phase lasted 2.8 seconds. The absolute value of the difference was 1.2 minus 2.8, which was 1.6 seconds. The second threshold was set to the absolute value of the difference accounting for 20% of the inspiratory phase duration. The absolute value of the difference accounted for 133% of the inspiratory phase duration. The absolute value of the difference between the two subsequent consecutive respiratory cycles accounted for more than 20% of the inspiratory phase duration. The starting moment of the first respiratory cycle that exceeded the standard was marked as the starting point of the respiratory rhythm disorder and was associated with the three-dimensional limb motion trajectory data at the corresponding moment.

[0042] In one embodiment of the present invention, step S3 includes the following steps: Based on the abnormal fluctuation period and the starting point of respiratory rhythm disorder marked in step S2, the cardiopulmonary risk level is determined through spatiotemporal correlation analysis. When the two occur in the same time window, the cardiopulmonary risk level is increased.

[0043] Specifically, the abnormal fluctuation period output by step S2 is defined as a continuous time period in which the coefficient of variation of the RR interval in the electrocardiogram signal continues to exceed the standard. The starting point of the respiratory rhythm disorder output by step S2 is defined as the first time point in which the absolute value of the difference between the inspiratory phase and the expiratory phase in the respiratory signal continues to exceed the standard. Each abnormal fluctuation period, with its start time and end time as the benchmark, extends the preset time window forward and backward; for each starting point of respiratory rhythm disorder, a coverage interval with the point as the center and the same time window length is generated. If the coverage interval of the starting point of a respiratory rhythm disorder intersects with the extended time window of any abnormal fluctuation period, the two are determined to be synchronous events, triggering an increase in the cardiopulmonary risk level by one level. If there is only a single type of abnormality or there is no time overlap between the two types of abnormalities, the basic cardiopulmonary risk level is maintained.

[0044] The pre-set time window is expanded forward and backward, using the start and end times of the abnormal fluctuation period as a benchmark. A fixed duration is set based on the average duration of the rehabilitation training movement cycle, and this fixed duration is expanded forward and backward to form a larger time interval. For example, upper limb training movements are expanded forward and backward by 1.5 seconds each, for a total window length of 3 seconds; lower limb training movements are expanded forward and backward by 2.5 seconds each, for a total window length of 5 seconds. The coverage interval is centered at the starting point of the respiratory rhythm disorder, generating a time interval of the same length as the expanded window during the abnormal fluctuation period.

[0045] Synchronous event, the coverage interval of the starting point of respiratory rhythm disorder overlaps with the extended time window of any abnormal fluctuation period; the conditions for determining synchronous events are: the starting time of the coverage interval of the starting point of respiratory rhythm disorder The end time of the extended time window during the abnormal fluctuation period, and the end time of the interval covered by the starting point of the respiratory rhythm disorder The start time of the extended time window during the abnormal fluctuation period.

[0046] Cardiopulmonary risk level, a risk level determined by the number of simultaneous events, is used to quantify the cardiopulmonary load risk during training. There are three levels of cardiopulmonary risk: the baseline level is Level 1, which increases by one level with each simultaneous event, up to a maximum of Level 3.

[0047] For example, when the patient was doing weighted squat training, the abnormal fluctuation period was detected from the 10th to the 25th second, and the coefficient of variation RR-CV of the calculated RR interval was continuously 0.18, exceeding the set first threshold of 0.12, and the expanded time window was from the 7th to the 28th second (extended 3 seconds forward and backward). The starting point of the respiratory rhythm disorder was marked at the 15th second, and its coverage interval was from the 12th to the 18th second (extended 3 seconds forward and backward, with a window length of 6 seconds). The 12th to 18th second overlapped with the 7th to 28th second, and was determined to be a synchronous event. The cardiopulmonary risk level was raised from the basic level 1 to level 2. Subsequently, a synchronous event occurred again at the 40th second, and the cardiopulmonary risk level further rose to level 3, triggering a real-time alarm prompting intervention.

[0048] In one embodiment of the present invention, step S4 includes the following steps: The exercise intensity of the rehabilitation training equipment is automatically adjusted according to the cardiopulmonary risk level. The adjustment includes reducing the resistance of the exercise equipment or slowing down the exercise frequency. The control mode is dynamically selected according to the changes in the ratio of the chest and abdominal rise and fall.

[0049] Combined with step S1, if When the breathing ratio threshold is reached, if it is determined to be abdominal breathing dominant state, the breathing guidance instruction will be triggered; if When the breathing ratio threshold is reached, it is determined that the chest breathing is dominant and the current movement parameters are maintained.

[0050] Specifically, when the cardiopulmonary risk level reaches level 2 or 3, an intensity adjustment instruction is sent to the rehabilitation training equipment: For resistance-adjustable devices, the resistance value driven by the motor is reduced according to a preset proportional gradient to meet the following formula:

[0051] in, The resistance adjustment amount is the resistance value that the rehabilitation training equipment needs to reduce. It is the basic resistance value, indicating the current output resistance of the rehabilitation training equipment. The cardiopulmonary risk level is divided according to expert experience and clinical trials. Level 1 is valued at 1, level 2 is valued at 2, and level 3 is valued at 3. It is an adjustment coefficient that is dynamically set based on the patient's cardiopulmonary function assessment results, and its value range is usually 0.1-0.3.

[0052] For frequency-adjustable devices, the following formula is satisfied by slowing down the periodic motion frequency of the motion platform:

[0053] in, Output frequency adjusted for rehabilitation training equipment; The current output frequency of the rehabilitation training equipment; The cardiopulmonary risk level is divided according to expert experience and clinical trials. Level 1 is valued at 1, level 2 is valued at 2, and level 3 is valued at 3. It is an adjustment coefficient that is dynamically set based on the patient's cardiopulmonary function assessment results, and its value range is usually 0.1-0.3.

[0054] Obtain the peak-to-peak value A of the piezoelectric sensor output voltage in the sternum motion area and the peak-to-peak value B of the piezoelectric sensor output voltage in the rectus abdominis motion area in step S1, and calculate the ratio of the current chest fluctuation amplitude to the abdomen fluctuation amplitude. If When the breathing ratio threshold is reached, if it is determined that the abdominal breathing is dominant, the breathing guidance instruction is triggered. The breathing guidance instruction contains a pre-recorded abdominal breathing guidance voice, which guides the patient to increase the depth of abdominal breathing through audio prompts; if When the breathing ratio threshold is reached, it is determined that the chest breathing is dominant and the current movement parameters are maintained unchanged.

[0055] For example, when a patient is training on a rowing machine and the cardiopulmonary risk level is determined to be level 2, the initial resistance value of the rehabilitation training equipment is 50N, the adjustment coefficient is set to 0.2, and the resistance adjustment amount is calculated , the resistance value of the rehabilitation training equipment is reduced from 50N to 40N. The peak-to-peak voltage measured by the piezoelectric sensor in the sternum movement area is A=2.8mV, and the peak-to-peak voltage measured by the piezoelectric sensor in the rectus abdominis movement area is B=3.5mV. If the set breathing ratio threshold is 0.9, =0.8 When the breathing ratio threshold is 0.9, abdominal breathing is determined to be dominant, triggering the breathing guidance instruction and playing the voice prompt "Please slowly contract your abdomen and take a deep breath."

[0056] If the cardiopulmonary risk level rises to level 3, the resistance adjustment is calculated as , the resistance value of the rehabilitation training equipment was reduced from 50N to 30N, and the changes in the breathing ratio were continuously monitored until it recovered to above the breathing ratio threshold.

[0057] In one embodiment of the present invention, step S5 includes the following steps: Under the adjusted exercise intensity, continuously monitor the heart rate recovery rate in the ECG signal and the rhythm stabilization time in the respiratory signal. When the heart rate recovery rate is lower than the preset benchmark and the respiratory rhythm stabilization time exceeds the critical value, gradually increase the exercise intensity.

[0058] Specifically, for the RR interval sequence recorded by the flexible ECG patch, the difference between two adjacent RR intervals is calculated. Within the first minute after the exercise intensity is adjusted, if the difference between adjacent RR intervals continues to increase and its cumulative value reaches the preset baseline, the heart rate recovery rate is determined to be in line with expectations; if the difference between adjacent RR intervals continues to increase and its cumulative value does not reach the preset baseline, the heart rate recovery rate is determined to be insufficient. For the respiratory signal collected by the elastic respiratory belt, the cumulative time of continuous normal respiratory cycles since the starting point of the last respiratory rhythm disorder is counted. If the cumulative time exceeds the critical value and the absolute value of the difference between the inhalation phase and the exhalation phase during the period does not exceed the second threshold, the respiratory rhythm is determined to have reached a stable state. When the heart rate recovery rate is insufficient and the respiratory rhythm stabilization time exceeds the limit, the resistance value or exercise frequency of the rehabilitation training equipment is gradually increased according to the preset gradient until the initial exercise intensity is restored or the conditions for increasing the cardiopulmonary risk level are triggered again.

[0059] The cumulative difference in heart rate recovery rate is defined as the sum of the absolute differences between consecutive RR intervals per minute after adjustment for exercise intensity. The baseline is calculated from the patient's average resting heart rate variability. The critical value for respiratory rhythm stabilization time is set based on the patient's age and baseline lung function, for example, 90 seconds for young, healthy individuals and 120 seconds for elderly patients.

[0060] For example, when the patient is rowing with a resistance of 30N after adjustment in step S4, the cumulative difference in RR intervals within the first minute after adjustment is monitored to be 0.6 seconds. The cumulative difference of 0.6 seconds is lower than the preset baseline of 0.8 seconds, and it is determined that the heart rate recovery rate is insufficient. The respiratory rhythm has been stable for 130 seconds since the last disturbance, exceeding the critical value of 120 seconds for elderly patients. The control mode is triggered, and the adjustment coefficient of 0.2 is multiplied by the safety gain factor of 0.5 (the safety gain factor is a constant less than 1, which is used to control the smoothness of intensity recovery and is set according to the patient's age and basic lung function). The resistance is increased by 30N×0.2×0.5=3N each time, and the resistance is increased every 2 minutes. If the cardiopulmonary risk level does not increase, the resistance is continued to be increased according to the gradient until it returns to the initial 50N.

[0061] In one embodiment of the present invention, step S6 includes the following steps: According to the changes in the three-dimensional acceleration trajectory of the limb movement signal and the correlation curve between the real-time heart rate and respiratory rate, the exercise intensity adjustment amplitude is corrected. When the acceleration direction suddenly changes and the ratio of heart rate to respiratory rate deviates from the normal range, the movement posture correction instruction is triggered.

[0062] Specifically, the data of the three-axis accelerometer and gyroscope of the motion sensing device are extracted, and the angular change rate of the limb motion vector is calculated. If the product of the angular change rate of the sagittal plane, the coronal plane, and the horizontal plane at a certain moment exceeds the threshold value of the preset angle change rate, it is determined to be an acceleration direction mutation event. The real-time heart rate is calculated based on the inverse of the RR interval mean of step S2, and the real-time respiratory rate is calculated based on the number of respiratory cycles in step S2. The ratio of heart rate to respiratory rate is compared with the baseline interval of historical healthy people at rest. When an acceleration direction mutation event occurs, if the ratio of heart rate to respiratory rate exceeds the baseline interval and continues to exceed the set mutation time, it is determined to be a mismatch between the exercise posture and the cardiopulmonary load, and a correction coefficient for the exercise intensity adjustment amplitude is generated and a posture correction instruction is triggered. The correction coefficient is calculated in the following way:

[0063] in, is the correction factor; The adjustment coefficient determined in step S4; It is the ratio of real-time heart rate to respiratory rate; It is the center value of the baseline interval of healthy people in the resting state recorded in history; is the duration of the sudden change in acceleration direction; For reference time, it is set according to industry standards.

[0064] Among them, the product of the direction angle change rate is defined as the sagittal plane pitch angle change rate , coronal roll angle change rate , horizontal plane yaw angle change rate The threshold value of the preset angle change rate is set according to the standard joint range of motion of the rehabilitation training action.

[0065] The baseline interval is determined by taking the mean plus or minus two standard deviations of the heart rate and respiratory rate data of healthy subjects undergoing the same exercise pattern. Posture correction instructions include voice prompts such as "Please adjust your torso upright angle" and "Please tighten your core and keep your back straight."

[0066] For example, when a patient performs seated rowing training, the motion sensing device detects the rate of change of the sagittal plane pitch angle. , coronal roll angle change rate , horizontal plane yaw angle change rate The product of the angular change rate is 15 × 8 × 20 = 2400, exceeding the preset angle change rate threshold of 2000, and is determined to be a sudden change in acceleration direction. The real-time heart rate is 110 beats / minute, the respiratory rate is 24 breaths / minute, and the ratio is 4.58, exceeding the baseline range of 3.2-4.5 for healthy people. The center value of the baseline range is 3.85. The duration of the sudden change in acceleration direction is 5 seconds, and the reference time is set to 1 second. Substituting into the correction coefficient formula:

[0067] From the above calculation, it can be seen that if the correction coefficient is 0.4, the resistance reduction is corrected to 50N×0.4=20N, and the voice prompt "Please tighten your core and keep your back straight" is triggered at the same time.

[0068] In one embodiment of the present invention, step S7 includes the following steps: After completing each stage of training, the multi-dimensional monitoring data from S1 to S6 is integrated to generate a feedback report containing a cardiopulmonary function fitness rating. The fitness rating is determined by the normalized sum of the heart rate fluctuation recovery time, the duration of abdominal breathing maintenance, and the smoothness of the acceleration trajectory.

[0069] Specifically, step S5 extracts the length of the time period in which the heart rate recovery rate meets the standard as the heart rate fluctuation recovery time, the continuous maintenance time of the abdominal breathing advantage state is counted in the breathing pattern ratio data recorded in step S4, and the inverse of the standard deviation of the acceleration changes in the sagittal, coronal, and horizontal planes is calculated in the three-dimensional acceleration trajectory of step S6 as the trajectory smoothness index. The three indicators are normalized to values ​​between 0 and 1 and then summed to obtain the fitness rating result. The fitness rating is divided into five levels, with level 1 being the lowest fitness and level 5 being the best fitness. The grading interval of the fitness rating is determined by cluster analysis of historical data of healthy people. For example, the grading interval set for level 1 is [0-1.2), the grading interval set for level 2 is [1.2-1.8), the grading interval set for level 3 is [1.8-2.4), the grading interval set for level 4 is [2.4-2.7), and the grading interval set for level 5 is [2.7-3.0).

[0070] The duration of continuous maintenance of the abdominal breathing advantage state is defined as the cumulative time during which the peak-to-peak ratio of the output voltage of the piezoelectric sensor in the sternum area and the rectus abdominis area is continuously less than the breathing ratio threshold in step S4.

[0071] The trajectory smoothness index is calculated using the following formula:

[0072] in, represents the trajectory smoothness index; It represents the standard deviation of the acceleration changes in the sagittal, coronal, and transverse planes recorded by the triaxial accelerometer. 、 、 is the sensitivity coefficient of the corresponding direction, which is obtained through the instrument calibration experiment. For example, in stepping training, the sagittal plane is set to 0.6, the coronal plane is set to 0.2, and the horizontal plane is set to 0.2.

[0073] Determine the upper limit of each indicator based on cluster analysis of historical healthy population data and lower limit , the three indicators are normalized separately using the following normalization formula:

[0074] in, is the normalized value; The real-time value of each indicator; is the minimum value of this indicator in healthy people; This is the maximum value of this indicator in healthy people.

[0075] For example, after a patient completes 30 minutes of elliptical machine training, the heart rate fluctuation recovery time is 280 seconds (the target period in step S5), and the abdominal breathing maintenance time is 820 seconds (the cumulative time when A / B is less than 0.9 in step S4). The trajectory smoothness is calculated as: ,set up =0.5, =0.3, = 0.2, resulting in a trajectory smoothness index of approximately 2.7. The minimum heart rate fluctuation recovery time is 100s, the maximum heart rate fluctuation recovery time is 300s, and the normalized heart rate fluctuation recovery time value is 0.9. The minimum abdominal breathing maintenance time is 0s, the maximum abdominal breathing maintenance time is 1000s, and the normalized abdominal breathing maintenance time value is 0.82. The worst trajectory smoothness index is 1, the best trajectory smoothness index is 4, and the normalized trajectory smoothness index value is 0.57.

[0076] The fitness score, the normalized sum of heart rate fluctuation recovery time, abdominal breathing maintenance duration, and acceleration trajectory smoothness, is 0.9 + 0.82 + 0.57 = 2.29. Based on the fitness rating ranges (Level 1: [0-1.2], Level 2: [1.2-1.8], Level 3: [1.8-2.4], Level 4: [2.4-2.7], and Level 5: [2.7-3.0]), the corresponding fitness rating is 3.

[0077] See attached Figure 2 The present invention also proposes a multi-parameter feedback control system for postoperative pulmonary function rehabilitation training, including the following modules: Signal acquisition module, used to obtain the patient's real-time ECG signal, respiratory signal, and limb movement signal; Signal analysis module, used to identify the heart rate fluctuation pattern of the ECG signal and generate abnormal fluctuation period, used to analyze the time difference between the inspiration phase and the expiration phase of the respiratory signal and generate the starting point of the respiratory rhythm disorder; The cardiopulmonary risk dynamic assessment module determines the cardiopulmonary risk level based on the coincidence of abnormal fluctuation periods and the starting points of respiratory rhythm disorders; The adaptive exercise intensity control module automatically adjusts the exercise intensity of the rehabilitation training equipment based on the cardiopulmonary risk level, and dynamically selects the control mode based on the ratio of chest and abdominal rise and fall; The cardiopulmonary function dynamic monitoring module monitors the heart rate recovery rate and respiratory rhythm stabilization time under adjusted exercise intensity. When the heart rate recovery rate is lower than the preset benchmark and the respiratory rhythm stabilization time exceeds the critical value, the exercise intensity is gradually increased; The motion and physiological coordination correction module combines the three-dimensional acceleration trajectory parameters of the limb motion signal with the parameters of the real-time heart rate and respiratory rate correlation curve to calculate the motion intensity correction coefficient and trigger the motion posture correction instruction; Intelligent feedback generation module, used to generate a cardiopulmonary fitness rating report.

[0078] It should be noted that the formulas described above, through the principle of dimensional consistency and mathematical standardization (e.g., normalization, dimensionless parameter conversion, or unified unit system), can translate physical quantities of different attributes into unitless standard values ​​or homogeneous, superimposable parameters. This eliminates the interference of different dimensions on operational logic, ensuring that the formulas retain the distribution characteristics of the original data while maintaining mathematical rationality and adaptability to objective laws. These are merely exemplary embodiments of the present invention and are not intended to limit the scope of the invention.

[0079] The modules can be implemented in whole or in part through software, hardware, or a combination thereof, supporting hardware embedded in or independent of a processor in a computer device, and also supporting software stored in a memory in a computer device, so that the processor can call and execute operations corresponding to the modules.

[0080] It should be noted that the human body information (including but not limited to human device information and personal information, etc.) and data (including but not limited to data used for analysis, stored data and displayed data, etc.) involved in the present invention are all information and data authorized by the human body or fully authorized by all parties. The collection, use and processing of relevant data require relevant legal standards.

[0081] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A multi-parameter feedback control method for postoperative pulmonary function rehabilitation training, characterized in that: The following steps are involved: S1. Acquire the patient's real-time electrocardiogram (ECG) signal, respiratory signal, and limb motion signal, wherein the respiratory signal includes a chest-to-abdomen fluctuation amplitude ratio parameter, and the limb motion signal includes a three-dimensional acceleration trajectory parameter; S2, identifying the heart rate fluctuation pattern of the ECG signal to generate an abnormal fluctuation period, and analyzing the time difference between the inhalation phase and the exhalation phase of the respiratory signal to generate the starting point of the respiratory rhythm disorder; S3. Determine the cardiopulmonary risk level based on the overlap between the abnormal fluctuation period and the starting point of the respiratory rhythm disorder; S4. Automatically adjust the exercise intensity of the rehabilitation training equipment based on the cardiopulmonary risk level, and dynamically select the control mode based on the ratio of chest and abdominal rise and fall; S5. Monitor the heart rate recovery rate and respiratory rhythm stabilization time at the adjusted exercise intensity. When the heart rate recovery rate is lower than the preset benchmark and the respiratory rhythm stabilization time exceeds the critical value, gradually increase the exercise intensity; S6. Calculate the exercise intensity correction coefficient and trigger the exercise posture correction instruction by combining the three-dimensional acceleration trajectory parameters of the limb movement signal with the real-time heart rate and respiratory rate correlation curve parameters; S7. After completing each stage of training, a cardiopulmonary fitness rating report is generated based on the normalized summation of heart rate fluctuation recovery time, abdominal breathing maintenance time, and acceleration trajectory smoothness.

2. The multi-parameter feedback control method for postoperative pulmonary function rehabilitation training according to claim 1, characterized in that: Acquiring the patient's real-time ECG signal, respiratory signal, and limb movement signal includes the following steps: A flexible ECG patch attached to the patient's chest continuously records the heart's ECG signals; A breathing belt is placed between the patient's sternum and navel to detect the rise and fall of the chest and abdomen during breathing; The motion sensing device deployed at the end of the limb obtains the fusion data of the three-axis accelerometer and gyroscope, and calculates the three-dimensional acceleration trajectory parameters.

3. The multi-parameter feedback control method for postoperative pulmonary function rehabilitation training according to claim 2, characterized in that: The respiratory signal includes chest and abdomen fluctuation amplitude ratio parameters, including the following steps: The peak-to-peak value of the piezoelectric sensor output voltage in the sternum motion area is recorded as A, and the peak-to-peak value of the piezoelectric sensor output voltage in the rectus abdominis motion area is recorded as B. The respiratory signal contains the ratio parameter of the chest rise and fall amplitude A to the abdomen rise and fall amplitude B; The breathing ratio threshold is determined based on the breathing pattern ratio threshold of historical healthy people at rest; like When the breathing ratio threshold is reached, it is determined to be a state of abdominal breathing dominance; like When the breathing ratio threshold is reached, it is determined to be a state of chest breathing dominance.

4. The multi-parameter feedback control method for postoperative pulmonary function rehabilitation training according to claim 2, characterized in that: Identifying the heart rate fluctuation pattern of the ECG signal to generate an abnormal fluctuation period includes the following steps: A flexible ECG patch attached to the patient's chest continuously records the heart's ECG signals; The peak point of the QRS complex is detected by the adaptive threshold method. The time interval between the peak points of two adjacent QRS complexes is defined as the RR interval. When the coefficient of variation RR-CV of the RR interval exceeds the first threshold, the period is determined to be an abnormal fluctuation period. The first threshold is the RR interval variation coefficient threshold, which is set based on the clinical standard of heart rate variability and the calibration of individual patient differences; The ratio of the standard deviation of the RR interval series to the mean of the RR interval gives the dimensionless coefficient of variation RR-CV of the RR interval.

5. The multi-parameter feedback control method for postoperative pulmonary function rehabilitation training according to claim 4, characterized in that: Analyzing the time difference between the inspiratory phase and the expiratory phase of the respiratory signal to generate the starting point of the respiratory rhythm disorder includes the following steps: The duration from the rising edge to the falling edge of the output voltage of the piezoelectric sensor in the sternal motion area is the duration of the inspiratory phase, and the duration from the falling edge to the next rising edge of the output voltage of the piezoelectric sensor in the sternal motion area is the duration of the expiratory phase; Calculate the absolute value of the difference between the duration of the inspiratory phase and the duration of the expiratory phase in each respiratory cycle; If the absolute value of the difference between three consecutive respiratory cycles exceeds a second threshold, marking the starting point of the respiratory cycle as the starting point of respiratory rhythm disorder; The second threshold is the respiratory rhythm symmetry deviation threshold. The setting of the second threshold is based on the physiological standard of respiratory rhythm symmetry and disease adaptation.

6. The multi-parameter feedback control method for postoperative pulmonary function rehabilitation training according to claim 4, characterized in that: Determining the cardiopulmonary risk level involves the following steps: For each abnormal fluctuation period, the preset time window is extended forward and backward based on the start time and end time; for each starting point of respiratory rhythm disorder, a coverage interval with the same time window length as the center is generated; If the coverage interval of the starting point of a respiratory rhythm disorder intersects with the extended time window of any abnormal fluctuation period, the two are considered synchronous events, triggering an increase in the cardiopulmonary risk level by one level; If only a single type of abnormality is present or there is no temporal overlap between the two types of abnormalities, the baseline cardiopulmonary risk level should be maintained.

7. The multi-parameter feedback control method for postoperative pulmonary function rehabilitation training according to claim 3, characterized in that: When the heart rate recovery rate is lower than the preset benchmark and the respiratory rhythm stability time exceeds the critical value, gradually increase the exercise intensity, including the following steps: Automatically adjust the exercise intensity of rehabilitation training equipment based on cardiopulmonary risk level. This adjustment includes reducing the resistance of the exercise equipment or slowing down the exercise frequency. Dynamically select the control mode based on the ratio of chest and abdominal rise and fall. if When the breathing ratio threshold is reached, if it is determined that the abdominal breathing is dominant, the breathing guidance instruction is triggered. The breathing guidance instruction contains a pre-recorded abdominal breathing guidance voice, which guides the patient to increase the depth of abdominal breathing through audio prompts; if When the breathing ratio threshold is reached, it is determined that the chest breathing is dominant and the current movement parameters are maintained.

8. The multi-parameter feedback control method for postoperative pulmonary function rehabilitation training according to claim 7, characterized in that: Calculating the exercise intensity correction coefficient and triggering the exercise posture correction instruction includes the following steps: Extract data from the three-axis accelerometer and gyroscope of the motion sensing device and calculate the angular change rate of the limb motion vector; If the product of the angular change rates of the sagittal, coronal, and horizontal planes at a certain moment exceeds the preset angle change rate threshold, it is determined to be an acceleration direction sudden change event; When a sudden change in acceleration occurs, if the heart rate to respiratory rate ratio exceeds the baseline range and persists for longer than the set duration, it is determined that the exercise posture does not match the cardiorespiratory load. A correction factor for the exercise intensity adjustment range is generated, triggering a posture correction instruction.

9. The multi-parameter feedback control method for postoperative pulmonary function rehabilitation training according to claim 8, characterized in that: Calculating the exercise intensity correction coefficient and triggering the exercise posture correction instruction also includes the following steps: in, is the correction factor; The adjustment coefficient determined in step S4; It is the ratio of real-time heart rate to respiratory rate; It is the center value of the baseline interval of healthy people in the resting state recorded in history; is the duration of the sudden change in acceleration direction; For reference time, it is set according to industry standards.

10. The multi-parameter feedback control method for postoperative pulmonary function rehabilitation training according to claim 9, characterized in that: Generating a report containing a cardiorespiratory fitness rating involves the following steps: The length of the time period during which the heart rate recovery rate reaches the standard is extracted as the heart rate fluctuation recovery time; The continuous maintenance time of the abdominal breathing dominant state is counted in the recorded breathing pattern ratio data; In the three-dimensional acceleration trajectory, the inverse of the standard deviation of the acceleration changes in the sagittal, coronal, and horizontal planes was calculated as the trajectory smoothness index; The three indicators are normalized to values ​​between 0 and 1 and then summed to obtain the fitness rating result.

Images