Nursing method for scoliosis rehabilitation process

Abstract

The invention provides a scoliosis rehabilitation process nursing method, and belongs to the technical field of scoliosis rehabilitation nursing, and the method comprises the following steps: firstly, collecting scoliosis posture data and medical image examination results of a patient, and establishing a rehabilitation training database containing spinal curvature, scoliosis types, heart rate variability and electromyographic signal reference values; and making a training plan according to the initial state information, wherein the training plan comprises an action sequence, intensity and duration. In the process that the core muscle group intensive training device is used for executing training, the spine position change of a patient is continuously monitored, and meanwhile physiological parameters such as heart rate variability and electromyographic signals are collected to form a feedback data set. The system calculates a fatigue coefficient through a fatigue degree evaluation function, and automatically adjusts the training intensity and the action sequence when the fatigue coefficient exceeds a preset threshold value. During training, daily life posture data are collected through the intelligent somatosensory equipment, the training database is continuously updated in combination with spine position change data in training, and the operation is circularly executed until the spine curvature reaches a preset rehabilitation target value.

Description

Technical Field

[0001] The present invention belongs to the technical field of scoliosis rehabilitation nursing, and in particular, relates to a nursing method for the scoliosis rehabilitation process. Background Art

[0002] Scoliosis is a common spinal orthopedic disease, which is mainly manifested by abnormal curvature of the spine in the sagittal and coronal planes. Severe scoliosis not only causes visual deformity, but may also lead to complications such as limited respiratory function, neurological symptoms, and joint pain. Clinically, the treatments for scoliosis mainly include surgical treatment and conservative treatment. Surgical treatment is suitable for severe progressive scoliosis cases, but the surgical risk is high and the postoperative recovery is relatively slow. In contrast, conservative treatment can effectively control the progression of mild to moderate scoliosis and gradually correct spinal deformity, which is a more ideal treatment option.

[0003] At present, the main methods of conservative treatment of scoliosis include various auxiliary brace corrections, physical therapy and rehabilitation training. Among them, targeted rehabilitation training is the key. By selecting specific exercise movements, the strength and coordination of the core muscles and back muscles can be strengthened in a targeted manner, thereby gradually improving the curvature of the spine. However, in the existing scoliosis rehabilitation nursing training, the training intensity and parameters are often determined by experience, and it is impossible to carry out targeted design for the type and severity of scoliosis of different patients, making it difficult to achieve ideal rehabilitation effects. Summary of the invention

[0004] In view of this, the present invention provides a nursing method for the scoliosis rehabilitation process, which can solve the technical problem that the training intensity and parameters are determined by experience, and it is difficult to carry out targeted design according to the scoliosis type and severity of different patients, and it is difficult to achieve the ideal rehabilitation effect.

[0005] The present invention is achieved in that:

[0006] The present invention provides a nursing method for scoliosis rehabilitation process, comprising the following steps:

[0007] S10, collecting the patient's scoliosis posture data, and obtaining the spinal curvature value and scoliosis type determination result through medical imaging equipment;

[0008] S20, based on the spinal curvature value and the scoliosis type determination result, establish a patient rehabilitation training database to record the patient's scoliosis initial state information, wherein the patient's scoliosis initial state information includes the spinal curvature value, the scoliosis type determination result, the heart rate variability baseline value before training, and the electromyography root mean square baseline value before training;

[0009] S30, formulating a rehabilitation training plan according to the initial state information of the patient's scoliosis, and determining a training action combination sequence, training intensity parameters, and planned training duration;

[0010] S40, executing the rehabilitation training plan, using the core muscle strengthening training device to complete the training action combination sequence, and recording the patient's spinal position change data during the training process;

[0011] S50, collecting physiological parameters of the patient during the training process, and establishing a training feedback data set, wherein the training feedback data set includes a current heart rate variability index, a current root mean square value of an electromyographic signal, and a current training duration;

[0012] S60, calculating a fatigue coefficient using a fatigue evaluation function according to the training feedback data set, wherein the fatigue coefficient is a value between 0 and 1, and the input of the fatigue evaluation function includes a ratio of the current heart rate variability index to the heart rate variability reference value before training, a ratio of the current electromyographic signal root mean square value to the electromyographic signal root mean square reference value before training, and a ratio of the current training duration to the planned training duration;

[0013] S70, when the fatigue coefficient exceeds a preset threshold, adjusting the training intensity parameter according to the fatigue coefficient to form a new training action combination sequence;

[0014] S80, collecting the patient's daily body posture data through the intelligent body sensing device, and updating the patient's rehabilitation training database in combination with the patient's spine position change data during the training process;

[0015] S90, repeating steps S40 to S80 until the patient's spinal curvature value reaches a preset rehabilitation target value.

[0016] Wherein, the step S10 specifically includes:

[0017] Step 101, collecting standing anteroposterior and lateral radiographs of the patient by X-ray imaging equipment;

[0018] Step 102: performing image enhancement processing on the frontal film and the lateral film through a medical image processing system;

[0019] Step 103, analyzing the anteroposterior and lateral films after the image enhancement processing to obtain the spinal curvature value;

[0020] Step 104: Determine a scoliosis type determination result according to the spinal curvature value.

[0021] Wherein, the step S20 specifically includes:

[0022] Step 201: Create a patient basic information data table to record the patient's age, height, weight, and medical history information;

[0023] Step 202: Collect the patient's physiological parameters before training, and obtain the heart rate variability baseline value before training and the root mean square baseline value of the electromyographic signal before training;

[0024] Step 203, writing the spinal curvature value, the scoliosis type determination result, the heart rate variability baseline value before training, the electromyographic signal root mean square baseline value before training and the patient basic information data table into the patient rehabilitation training database.

[0025] Wherein, the step S30 specifically includes:

[0026] Step 301, selecting a basic sequence of training movements according to the scoliosis type determination result in the patient rehabilitation training database;

[0027] Step 302, setting a training intensity parameter according to the spinal curvature value;

[0028] Step 303: setting the planned training duration according to the patient basic information data table;

[0029] Step 304: Combine the basic training action sequences to form a combined training action sequence.

[0030] Wherein, the step S40 specifically includes:

[0031] Step 401, turning on the core muscle strengthening training device and setting the training intensity parameters;

[0032] Step 402: guiding the patient to wear a spinal position monitoring sensor;

[0033] Step 403: instructing the patient to perform training according to the training action combination sequence;

[0034] Step 404: Collect the spinal position monitoring sensor data and record the patient's spinal position change data during the training process.

[0035] Wherein, the step S50 specifically includes:

[0036] Step 501: Collect the patient's ECG signal through an ECG monitoring device and calculate the current heart rate variability index;

[0037] Step 502: collect electromyographic signals through a surface electromyographic acquisition device, and calculate the root mean square value of the current electromyographic signals;

[0038] Step 503: Record the current training duration;

[0039] Step 504: store the current heart rate variability index, the current root mean square value of the electromyography signal, and the current training duration into a training feedback data set.

[0040] Wherein, the step S60 specifically includes:

[0041] Step 601, obtaining the current heart rate variability index and the heart rate variability baseline value before training in the training feedback data set;

[0042] Step 602: Obtain the current RMS value of the electromyographic signal and the RMS reference value of the electromyographic signal before training in the training feedback data set:

[0043] Step 603: Obtain the current training duration and the planned training duration;

[0044] Step 604: input the ratio of the current heart rate variability index to the heart rate variability reference value before training, the ratio of the current electromyographic signal root mean square value to the electromyographic signal root mean square reference value before training, and the ratio of the current training duration to the planned training duration into a fatigue assessment function;

[0045] Step 605: Calculate the fatigue coefficient using the fatigue evaluation function.

[0046] Wherein, the step S70 specifically includes:

[0047] Step 701, comparing the fatigue coefficient with a preset threshold;

[0048] Step 702: when the fatigue coefficient exceeds the preset threshold, a new training intensity parameter is calculated according to a training intensity adjustment function;

[0049] Step 703: Adjust the difficulty level and the number of repetitions in the training action combination sequence according to the new training intensity parameter.

[0050] Wherein, the step S80 specifically includes:

[0051] Step 801: Setting the patient's daily life posture monitoring parameters in the intelligent body sensing device;

[0052] Step 802: Collecting the patient's daily life posture data through the intelligent body sensing device;

[0053] Step 803: write the patient's daily life posture data and the patient's spine position change data during the training process into the patient rehabilitation training database.

[0054] It is characterized in that the step S90 specifically includes:

[0055] Step 901, return to execute step S40 to step S80;

[0056] Step 902: reacquire the patient's spinal curvature value through medical imaging equipment;

[0057] Step 903: compare the spinal curvature value with a preset rehabilitation target value, and continue to execute step 901 when the preset rehabilitation target value is not reached.

[0058] The fatigue evaluation function is specifically expressed as follows:

[0059]

[0060] Where F is the fatigue coefficient; HRV c HRV is the current heart rate variability index; b is the baseline value of heart rate variability before training; RMS c is the root mean square value of the current electromyographic signal; RMS b is the RMS baseline value of the electromyographic signal before training; T c is the current training duration; T p is the planned training duration; W1, W2, W3 are weight coefficients, and satisfy w1+W2+W3=1; α is the attenuation coefficient; β is the time scale parameter; t is the cumulative time from the start of training to the present; ε is the random error term.

[0061] The parameter acquisition method is:

[0062] 1.HRV c The ECG signal is acquired in real time and the specific calculation is as follows:

[0063]

[0064] In the formula, RR i is the i-th heartbeat interval; is the average value of N heartbeat intervals; N is the total number of heartbeats in the sampling window.

[0065] 2.RMS c It is obtained by calculating the surface electromyography signal. The specific calculation is as follows:

[0066]

[0067] Where, EMG i is the amplitude of the electromyographic signal at the i-th sampling point; M is the total number of sampling points in the sampling window.

[0068] 3.W1, W2, and W3 are obtained by solving the multi-objective optimization algorithm, and the optimization objective is:

[0069]

[0070] In the formula, F k is the calculated fatigue degree of the kth training sample; is the standard value of fatigue assessed by experts; K is the total number of training samples.

[0071] 4. The training intensity parameter adjustment function is specifically expressed as follows:

[0072] P new =P old ·(1-γ·(FF th ));

[0073] Where P new is the adjusted training intensity parameter; P old is the current training intensity parameter; γ is the intensity adjustment coefficient; F is the current fatigue coefficient; F th is the preset fatigue threshold.

[0074] Parameter value range:

[0075] α∈[0.1, 0.3]; β∈[0.001, 0.01]; ε∈[-0.05, 0.05]; γ∈[0.1, 0.5]; F th =0.7.

[0076] Equation principle explanation:

[0077] 1. The fatigue evaluation function adopts a multi-weighted structure, taking into account the rate of change of physiological signals, time accumulation effect and random disturbance: the heart rate variability ratio term reflects the fatigue degree of the autonomic nervous system; the electromyographic signal ratio term reflects the muscle fatigue degree; the time ratio term reflects the training progress; the exponential decay term describes the adaptability of the human body; and the error term contains other uncertain factors.

[0078] 2. The training intensity adjustment function adopts a proportional adjustment mechanism: intensity is attenuated based on the degree to which fatigue exceeds the threshold; an adjustment coefficient is introduced to ensure adjustment stability; and training intensity is kept within a reasonable range.

[0079] Compared with the prior art, the beneficial effects of the nursing method for scoliosis rehabilitation process provided by the present invention are:

[0080] 1. Personalized training plan formulation is achieved. This method first uses medical imaging equipment to comprehensively obtain the patient's spinal status data, including spinal curvature values ​​and scoliosis types, and establishes a comprehensive patient rehabilitation training database. Based on these data, targeted training action sequences, intensity parameters and training duration are formulated to fully meet the individual needs of different patients. This personalized training program can better improve the patient's spinal deformity and improve the treatment effect.

[0081] 2. Real-time dynamic adjustment of training intensity is achieved. This method collects the patient's heart rate variability index and electromyographic signal and other physiological parameters in real time during the training process, and calculates the current fatigue level through the fatigue evaluation function. When the fatigue level exceeds the preset threshold, the training intensity parameters, such as movement difficulty and number of repetitions, are automatically adjusted to ensure that the patient is in a moderate training state and avoid excessive fatigue. This dynamic adjustment mechanism greatly improves the scientificity and safety of training.

[0082] 3. Continuous optimization of training effects has been achieved. This method not only collects data on spinal position changes during training, but also obtains body posture information of patients in daily life through intelligent body sensing devices. Storing these data in the patient's rehabilitation training database can comprehensively evaluate the patient's overall rehabilitation progress and provide a basis for the optimization of subsequent training plans. This continuously optimized training model can ensure that the treatment effect remains stable in the long term.

[0083] In summary, the scoliosis rehabilitation nursing method proposed in the present invention, through the formulation of personalized training plans, adjustment of dynamic training intensity and optimization of continuous training effects, effectively solves the technical problem that the existing technology is unable to carry out targeted design for different patients' scoliosis types and severities, and is difficult to achieve ideal rehabilitation effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] Figure 1 A flow chart of the method provided by the present invention. DETAILED DESCRIPTION

[0085] In order to make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0086] like Figure 1 FIG. 1 is a flow chart of a nursing method for scoliosis rehabilitation process provided by the present invention, and the method comprises the following steps:

[0087] S10, collecting the patient's scoliosis posture data, and obtaining the spinal curvature value and scoliosis type determination result through medical imaging equipment;

[0088] S20, based on the spinal curvature value and the scoliosis type determination result, establish a patient rehabilitation training database to record the patient's scoliosis initial state information, the patient's scoliosis initial state information includes the spinal curvature value, the scoliosis type determination result, the heart rate variability baseline value before training, and the electromyography root mean square baseline value before training;

[0089] S30, formulating a rehabilitation training plan based on the patient's initial scoliosis status information, determining a training action combination sequence, training intensity parameters, and planned training duration;

[0090] S40, executing the rehabilitation training plan, using the core muscle strengthening training device to complete the training action combination sequence, and recording the patient's spinal position change data during the training process;

[0091] S50, collecting physiological parameters of the patient during the training process, and establishing a training feedback data set, where the training feedback data set includes a current heart rate variability index, a current root mean square value of an electromyographic signal, and a current training duration;

[0092] S60, calculating a fatigue coefficient using a fatigue evaluation function according to the training feedback data set, where the fatigue coefficient is a value between 0 and 1, and inputs of the fatigue evaluation function include a ratio of a current heart rate variability index to a heart rate variability baseline value before training, a ratio of a current electromyographic signal root mean square value to a electromyographic signal root mean square baseline value before training, and a ratio of a current training duration to a planned training duration;

[0093] S70, when the fatigue coefficient exceeds a preset threshold, adjusting the training intensity parameter according to the fatigue coefficient to form a new training action combination sequence;

[0094] S80, collecting the patient's daily posture data through the intelligent body sensing device, combining the patient's spine position change data during the training process, and updating the patient's rehabilitation training database;

[0095] S90, repeating steps S40 to S80 until the patient's spinal curvature value reaches a preset rehabilitation target value.

[0096] The specific implementation methods of the above steps are described in detail below:

[0097] The specific implementation method of step S10 is to use medical imaging equipment to obtain the patient's spinal status data. First, the patient's standing anteroposterior and lateral films are collected by X-ray imaging equipment. Then, these X-rays are subjected to image enhancement processing to improve image quality and resolution. Next, the processed anteroposterior and lateral films are analyzed to extract the curvature value of the spine. Finally, the patient's scoliosis type is determined based on the spinal curvature value. The purpose of this series of steps is to fully grasp the patient's initial spinal state and provide a basis for formulating a reasonable plan for subsequent rehabilitation training.

[0098] The specific implementation method of step S20 is to establish a rehabilitation training database for patients. First, record the patient's basic information, including age, height, weight, medical history, etc. Then, collect the patient's physiological parameters before the start of training, and obtain the heart rate variability index and the root mean square value of the electromyographic signal as the benchmark value. Finally, the above information such as spinal curvature value, scoliosis type, physiological parameters before training, etc. are uniformly stored in the database. The purpose of this step is to establish a comprehensive patient initial state information database to provide data support for subsequent personalized training plans.

[0099] The specific implementation method of step S30 is to formulate a targeted rehabilitation training plan. First, select a suitable basic sequence of training movements according to the patient's scoliosis type. Then, set the training intensity parameters according to the spinal curvature value, such as the movement difficulty level and the number of repetitions. In addition, it is necessary to determine the planned training duration based on the patient's basic information. Finally, combine the above elements into a complete training movement combination sequence. The purpose of this step is to formulate a scientific and reasonable personalized rehabilitation training plan to lay the foundation for subsequent training execution.

[0100] The specific implementation method of step S40 is to execute the formulated rehabilitation training plan. First, turn on the core muscle strengthening training device and set it according to the training intensity parameters. Then, instruct the patient to wear the spinal position monitoring sensor. Next, guide the patient to train according to the training action combination sequence. During the training process, collect data from the spinal position monitoring sensor and record the changes in the patient's spinal position. The purpose of this step is to perform rehabilitation training according to the formulated training plan and collect key data during the training process.

[0101] The specific implementation method of step S50 is to establish a training feedback data set. First, the patient's ECG signal is collected by an ECG monitoring device, and the current heart rate variability index is calculated. Then, the patient's electromyography signal is collected by a surface electromyography acquisition device, and the current root mean square value of the electromyography signal is calculated. In addition, the current training duration is recorded. Finally, the above indicators are stored in the training feedback data set. The purpose of this step is to collect physiological parameter data during the training process to provide a basis for subsequent fatigue assessment.

[0102] The specific implementation method of step S60 is to calculate the fatigue coefficient during the training process. First, the current heart rate variability index and the baseline value before training, the current root mean square value of the electromyographic signal and the baseline value before training, the current training duration and the planned training duration are obtained from the training feedback data set. Then, these data are input into the fatigue evaluation function for calculation. The fatigue evaluation function takes into account factors such as the rate of change of physiological signals, the cumulative effect of time and random disturbances, and comprehensively reflects the degree of fatigue during the training process. Finally, the current fatigue coefficient is obtained. The purpose of this step is to provide a basis for adjusting the subsequent training intensity through quantitative fatigue evaluation.

[0103] The specific implementation method of step S70 is to adjust the training intensity according to the fatigue coefficient. First, the current fatigue coefficient is compared with the preset fatigue threshold. When the fatigue coefficient exceeds the preset threshold, a new training intensity parameter is calculated according to the training intensity adjustment function. This adjustment function adopts a proportional adjustment mechanism to attenuate the training intensity based on the degree to which the fatigue exceeds the threshold, and introduces an adjustment coefficient to ensure the smoothness of the adjustment. Finally, the action difficulty level and the number of repetitions in the training action combination sequence are adjusted according to the new training intensity parameter. The purpose of this step is to dynamically adjust the training intensity to ensure that the patient will not be overly fatigued during the training process, thereby ensuring the training effect.

[0104] The specific implementation method of step S80 is to update the patient's rehabilitation training database. First, set the patient's daily life posture monitoring parameters on the intelligent body sensing device. Then, collect the patient's posture data in daily life through the intelligent device. Finally, these daily life posture data and the spinal position change data recorded during the training process are uniformly written into the patient's rehabilitation training database. The purpose of this step is to continuously enrich and update the patient's overall rehabilitation status information and provide more accurate data support for subsequent personalized training.

[0105] The specific implementation of step S90 is to repeatedly perform training adjustments until the expected effect is achieved. First, return to step S40 to step S80 to continue the cycle of training, fatigue assessment and training intensity adjustment. Then, the patient's spinal curvature value is reacquired through medical imaging equipment. Finally, the value is compared with the preset rehabilitation target value. If the target value is not reached, the aforementioned cycle is continued. The purpose of this step is to continuously optimize the training plan until the patient's spinal curvature value reaches the expected rehabilitation target.

[0106] Specifically, the principle of the present invention is to achieve accurate rehabilitation of scoliosis patients by establishing a personalized training database, dynamically adjusting the training intensity, and continuously optimizing the training effect. The technical principle can be summarized as follows:

[0107] 1. Construct a personalized training program based on comprehensive spinal status data. The present invention first uses X-ray imaging equipment to obtain the patient's spinal anteroposterior and lateral films, and extracts the spinal curvature value and scoliosis type through image processing technology as the basis for designing the training program. At the same time, the patient's basic information, physiological parameters before training, etc. are also recorded to establish a comprehensive patient rehabilitation training database. Based on these data, the present invention formulates targeted training action sequences, intensity parameters and training duration to meet the individual needs of different patients. This personalized training program can improve the patient's spinal deformity in a more targeted manner.

[0108] 2. A dynamic adjustment mechanism for real-time monitoring of physiological parameters and fatigue assessment is adopted. During the training process, the present invention collects the patient's heart rate variability index and the root mean square value of the electromyography signal in real time through the electrocardiogram monitoring device and the surface electromyography acquisition device. The fatigue assessment function is used to calculate the current fatigue coefficient by combining the change rate of these physiological parameters, the cumulative effect of training time, and random disturbances. When the fatigue exceeds the preset threshold, the training intensity parameters are automatically adjusted, such as reducing the difficulty of the action and the number of repetitions, to ensure that the patient is in a moderate training state and avoid excessive fatigue. This dynamic adjustment mechanism greatly improves the scientificity and safety of the training process.

[0109] 3. Optimization of continuous training effects based on comprehensive rehabilitation status information. In addition to the spinal position change data during training, the present invention also collects the patient's posture information in daily life through intelligent somatosensory equipment, and stores these data together with the rehabilitation training data in the patient's database. In this way, it is possible to comprehensively evaluate the patient's overall rehabilitation progress and provide a basis for the optimization of subsequent training programs. For example, according to the changes in posture in daily life, the training action sequence and intensity parameters are adjusted in a timely manner to ensure that the training effect remains stable in the long term. This continuously optimized training mode can greatly improve the overall efficacy of conservative treatment of scoliosis.

[0110] The following is an example of a specific application scenario of the present invention: the orthopedics department of a hospital is carrying out a rehabilitation training program for scoliosis patients, and the program adopts the scoliosis rehabilitation process nursing method proposed by the present invention. The specific situation of this example is described in detail below.

[0111] Patient Yao, female, 22 years old, 168cm tall, 55kg. Yao discovered that she had scoliosis 6 years ago due to long-term computer use. After diagnosis by the hospital, it was determined that she had mild scoliosis, mainly manifested as left lumbar scoliosis with a Cobb angle of about 25 degrees. After conservative treatment, the symptoms of scoliosis did not improve significantly, so Yao decided to accept the rehabilitation training program provided by the hospital.

[0112] According to the method of the present invention, the hospital's orthopedic team first collected Yao's spine anteroposterior and lateral radiographs through X-ray imaging equipment. Through image processing technology, the team obtained the specific curvature value of Yao's spine, the Cobb angle was 25 degrees, and it was determined that it was a left lumbar scoliosis type. Next, the team established a basic information data table for Yao, recording his age, height, weight and other information.

[0113] Then, the hospital organized Yao to collect physiological parameters before training. Through the ECG monitoring equipment, the team measured Yao's heart rate variability index HRV before training. b =45. At the same time, the team measured the root mean square value (RMS) of Yao's electromyographic signal before training through surface electromyographic acquisition equipment. b = 120 μV. The above information, including spinal curvature value, scoliosis type, pre-training physiological parameters and basic information, were all recorded in Yao's rehabilitation training database.

[0114] Based on Yao's scoliosis type and curvature value, the hospital team selected the following basic training sequence:

[0115] Table 1 Basic sequence of training actions

[0116] Serial number Training Action Difficulty level Repetitions 1 Side bending shoulder circular motion 2 15 2 Squat Hip Motion 3 12 3 push-up 2 10 4 Single Leg Raise 3 8 5 Supine Crunches 2 15

[0117] Based on Yao's spinal curvature value of 25 degrees Cobb angle, the hospital team set the training intensity parameters as follows: difficulty level 2-3, repetitions 8-15 times. In addition, based on Yao's age and weight, the team determined the planned training time to be 40 minutes.

[0118] Finally, the hospital team combined the above basic training action sequences into the following training action combination sequences:

[0119] 1. Side bending shoulder circular movement (15 times) 2. Squat hip joint movement (12 times) 3. Push-ups (10 times) 4. Single leg raise (8 times) 5. Supine crunch (15 times)

[0120] This is Yao’s personalized rehabilitation training plan.

[0121] Next, during the training execution, the hospital team took the following measures:

[0122] First, the core muscle strengthening training device was turned on and set accordingly according to the training intensity parameters. Then, Yao was instructed to wear a spinal position monitoring sensor. On this basis, the team gradually guided Yao to train according to the training action combination sequence. During the training process, the spinal position monitoring sensor collected real-time data on the changes in Yao's spinal position, providing a basis for the evaluation of subsequent training effects.

[0123] At the same time, the hospital team also collected Yao's ECG signals in real time through ECG monitoring equipment and calculated the current heart rate variability index HRV. c Through the surface electromyography acquisition equipment, the team also collected Yao's electromyography signals in real time and calculated the current root mean square value RMS of the electromyography signal. c In addition, the team also records the current training duration T c The above data are stored in the training feedback dataset.

[0124] Based on the training feedback data set, the hospital team calculated the current fatigue coefficient F. The specific process is as follows:

[0125] First, obtain the current heart rate variability index HRV from the training feedback dataset c =40 and the baseline HRV before training b =45, the current root mean square value of the electromyographic signal RMS c = 110μV and the baseline RMS before training b =120μV, current training duration T c =25min and planned training time T p =40min.

[0126] Then, substitute these data into the fatigue evaluation function for calculation:

[0127]

[0128] After calculation, the current fatigue coefficient F=0.75 is obtained.

[0129] Since F exceeds the preset fatigue threshold F th =0.7, the hospital team decided to dynamically adjust the training intensity according to the training intensity adjustment function:

[0130] P new =P old ·(1-0.3·(0.75-0.7))=P old 0.985;

[0131] That is to say, the difficulty level and number of repetitions in the training intensity parameters are reduced by about 1.5%. The adjusted training action combination sequence is as follows:

[0132] 1. Side bending shoulder circular movement (14 times) 2. Squat hip joint movement (12 times) 3. Push-ups (10 times) 4. Single leg raise (8 times) 5. Supine crunch (14 times)

[0133] During the following training, the hospital team continued to collect Yao's physiological parameter data and calculated the fatigue coefficient in real time. When the fatigue level exceeded the standard again, the training intensity parameters were dynamically adjusted in the above manner.

[0134] At the same time, the hospital also set up Yao's daily posture monitoring parameters on the intelligent body sensing device, and collected Yao's posture data in real time through the device. These data, together with the data on spinal position changes recorded during the training process, were uniformly written into Yao's rehabilitation training database.

[0135] After one month of training, Yao's spinal Cobb angle was gradually corrected from the initial 25 degrees to 20 degrees. At this time, the hospital team decided to re-obtain Yao's spinal X-ray and compare the new Cobb angle value with the preset rehabilitation target value of 20 degrees. Since Yao's spinal curvature has reached the expected target, the hospital team believes that there is no need to continue the training plan, but recommends that Yao maintain the current training intensity appropriately and have regular checkups to consolidate the treatment effect.

[0136] During the entire rehabilitation training process of Yao, the hospital team fully applied the method proposed by the present invention, which is specifically reflected in the following aspects:

[0137] 1. Establish a personalized training plan based on comprehensive spinal status data. Through X-ray analysis, Yao's spinal curvature value and scoliosis type were obtained. Combined with his basic information, a targeted training action sequence, intensity parameters and duration were developed to meet Yao's individual needs.

[0138] 2. Adopt a dynamic adjustment mechanism for real-time monitoring of physiological parameters and fatigue assessment. During the training process, the team collected Yao's heart rate variability index and electromyographic signal in real time, calculated the current fatigue coefficient, and adjusted the training intensity parameters in time to avoid Yao's excessive fatigue.

[0139] 3. Optimization of continuous training effects based on comprehensive rehabilitation status information. In addition to training data, the team also collected Yao's body posture data in daily life and recorded it together with the training data, providing a basis for the optimization of subsequent training plans.

[0140] Through the organic combination of the above measures, Yao's scoliosis condition has been continuously improved and the expected rehabilitation goal has been achieved. Compared with traditional conservative treatment methods, the method proposed in the present invention can manage the rehabilitation process of scoliosis patients more scientifically and efficiently, and has shown strong advantages in clinical applications.

[0141] It is also worth mentioning that during the specific implementation process, the hospital team also optimized the fatigue assessment function and training intensity adjustment function:

[0142] In the fatigue evaluation function, the specific values ​​of w1, w2, and w3 were finally determined to be w1 = 0.4, w2 = 0.3, and w3 = 0.3 after many practices and adjustments. This weight distribution better balances the effects of autonomic nervous system fatigue, muscle fatigue, and training progress on overall fatigue.

[0143] At the same time, in the training intensity adjustment function, the value of γ is optimized and determined to be 0.3. Such an adjustment coefficient can not only ensure the smooth adjustment of training intensity, but also ensure that the training intensity is significantly reduced in the case of excessive fatigue.

[0144] It should be noted that the variables involved in the present invention are shown in Table 2 below.

[0145] Table 2 Variable explanation table

[0146]

[0147] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A nursing method for the rehabilitation process of scoliosis, characterized in that: The following steps are involved: S10, collecting the patient's scoliosis posture data, and obtaining the spinal curvature value and scoliosis type determination result through medical imaging equipment; S20, based on the spinal curvature value and the scoliosis type determination result, establish a patient rehabilitation training database to record the patient's scoliosis initial state information, wherein the patient's scoliosis initial state information includes the spinal curvature value, the scoliosis type determination result, the heart rate variability baseline value before training, and the electromyography root mean square baseline value before training; S30, formulating a rehabilitation training plan according to the initial state information of the patient's scoliosis, and determining a training action combination sequence, training intensity parameters, and planned training duration; S40, executing the rehabilitation training plan, using the core muscle strengthening training device to complete the training action combination sequence, and recording the patient's spinal position change data during the training process; S50, collecting physiological parameters of the patient during the training process, and establishing a training feedback data set, wherein the training feedback data set includes a current heart rate variability index, a current root mean square value of an electromyographic signal, and a current training duration; S60, calculating a fatigue coefficient using a fatigue evaluation function according to the training feedback data set, wherein the fatigue coefficient is a value between 0 and 1, and the input of the fatigue evaluation function includes a ratio of the current heart rate variability index to the heart rate variability reference value before training, a ratio of the current electromyographic signal root mean square value to the electromyographic signal root mean square reference value before training, and a ratio of the current training duration to the planned training duration; S70, when the fatigue coefficient exceeds a preset threshold, adjusting the training intensity parameter according to the fatigue coefficient to form a new training action combination sequence; S80, collecting the patient's daily body posture data through the intelligent body sensing device, and updating the patient's rehabilitation training database in combination with the patient's spine position change data during the training process; S90, repeating steps S40 to S80 until the patient's spinal curvature value reaches a preset rehabilitation target value.

2. The method according to claim 1, characterized in that: The step S10 specifically includes: Step 101, collecting standing anteroposterior and lateral radiographs of the patient by X-ray imaging equipment; Step 102: performing image enhancement processing on the frontal film and the lateral film through a medical image processing system; Step 103, analyzing the anteroposterior and lateral films after the image enhancement processing to obtain the spinal curvature value; Step 104: Determine a scoliosis type determination result according to the spinal curvature value.

3. The method according to claim 1, characterized in that The step S20 specifically includes: Step 201: Create a patient basic information data table to record the patient's age, height, weight, and medical history information; Step 202: Collect the patient's physiological parameters before training, and obtain the heart rate variability baseline value before training and the root mean square baseline value of the electromyographic signal before training; Step 203, writing the spinal curvature value, the scoliosis type determination result, the heart rate variability baseline value before training, the electromyographic signal root mean square baseline value before training and the patient basic information data table into the patient rehabilitation training database.

4. The method according to claim 1, characterized in that The step S30 specifically includes: Step 301, selecting a basic sequence of training movements according to the scoliosis type determination result in the patient rehabilitation training database; Step 302, setting a training intensity parameter according to the spinal curvature value; Step 303: setting the planned training duration according to the patient basic information data table; Step 304: Combine the basic training action sequences to form a combined training action sequence.

5. The method according to claim 1, characterized in that The step S40 specifically includes: Step 401, turning on the core muscle strengthening training device and setting the training intensity parameters; Step 402: guiding the patient to wear a spinal position monitoring sensor; Step 403: instructing the patient to perform training according to the training action combination sequence; Step 404: Collect the spinal position monitoring sensor data and record the patient's spinal position change data during the training process.

6. The method according to claim 1, characterized in that The step S50 specifically includes: Step 501: Collect the patient's ECG signal through an ECG monitoring device and calculate the current heart rate variability index; Step 502: collect electromyographic signals through a surface electromyographic acquisition device, and calculate the root mean square value of the current electromyographic signals; Step 503: Record the current training duration; Step 504: store the current heart rate variability index, the current root mean square value of the electromyography signal, and the current training duration into a training feedback data set.

7. The method according to claim 1, characterized in that The step S60 specifically includes: Step 601, obtaining the current heart rate variability index and the heart rate variability baseline value before training in the training feedback data set; Step 602, obtaining the current root mean square value of the electromyographic signal and the root mean square reference value of the electromyographic signal before training in the training feedback data set; Step 603: Obtain the current training duration and the planned training duration; Step 604: input the ratio of the current heart rate variability index to the heart rate variability reference value before training, the ratio of the current electromyographic signal root mean square value to the electromyographic signal root mean square reference value before training, and the ratio of the current training duration to the planned training duration into a fatigue assessment function; Step 605: Calculate the fatigue coefficient using the fatigue evaluation function.

8. The method according to claim 1, characterized in that: The step S70 specifically includes: Step 701, comparing the fatigue coefficient with a preset threshold; Step 702: when the fatigue coefficient exceeds the preset threshold, a new training intensity parameter is calculated according to a training intensity adjustment function; Step 703: Adjust the difficulty level and the number of repetitions in the training action combination sequence according to the new training intensity parameter.

9. The method according to claim 1, characterized in that: The step S80 specifically includes: Step 801: Setting the patient's daily life posture monitoring parameters in the intelligent body sensing device; Step 802: Collecting the patient's daily life posture data through the intelligent body sensing device; Step 803: write the patient's daily life posture data and the patient's spine position change data during the training process into the patient rehabilitation training database.

10. The method according to claim 1, characterized in that The step S90 specifically includes: Step 901, return to execute step S40 to step S80; Step 902: reacquire the patient's spinal curvature value through medical imaging equipment; Step 903: compare the spinal curvature value with a preset rehabilitation target value, and continue to execute step 901 when the preset rehabilitation target value is not reached.

Images