Intelligent multi-modal control rehabilitation method, device and equipment based on heart multi-dimensional indexes

Abstract

The invention provides an intelligent multi-modal control rehabilitation method based on heart multi-dimensional indexes. The method comprises the steps that personal basic information and medical record information of a patient are acquired; based on the personal basic information of the patient and the medical record information, calculating a patient targeted heart rate index; generating a rehabilitation training scheme suitable for the patient based on the targeted heart rate index of the patient; according to the rehabilitation training scheme suitable for the patient, rehabilitation training equipment is started for rehabilitation training, and heart multi-dimensional indexes of the patient are monitored; according to the rehabilitation training scheme and the heart multi-dimensional indexes of the patient, the power of rehabilitation training equipment is adjusted. According to the method, the patient can conduct rehabilitation training under the appropriate exercise intensity, then the power of rehabilitation training equipment is adjusted by monitoring the multi-dimensional indexes of the heart of the patient in the subsequent rehabilitation training process, the examination items of the heart indexes can be reduced, and the rehabilitation training efficiency is improved; and the patient can perform rehabilitation training in a safer state.

Description

Technical Field

[0001] The present invention relates to an intelligent multi-modal control rehabilitation method, device and equipment based on multi-dimensional cardiac indicators, which are applied in the field of rehabilitation training. Background Art

[0002] Rehabilitation is a treatment program designed for people with specific illnesses, injuries, or after surgery to help them regain function and improve their quality of daily life. The program is personalized and includes a variety of different exercises to achieve the best recovery results.

[0003] Before rehabilitation training, patients need to have their physical indicators checked, especially patients with heart disease need to have their heart indicators checked to prevent heart failure during rehabilitation training. Heart indicator checks include electrocardiogram, echocardiogram, myocardial tomography, etc. It takes a lot of time to conduct a series of examinations before rehabilitation training, which is inefficient. Patients need to wait a long time for training according to this method, which is not conducive to the patient's rehabilitation. Therefore, the present invention studies an intelligent multimodal control rehabilitation method, device and equipment based on multi-dimensional cardiac indicators to solve the above problems. Summary of the invention

[0004] The present invention provides an intelligent multi-modal control rehabilitation method, device and equipment based on multi-dimensional cardiac indicators, which can effectively solve the above problems.

[0005] The present invention is achieved in that:

[0006] An intelligent multi-modal control rehabilitation method based on multi-dimensional cardiac indicators, comprising:

[0007] Obtain the patient's basic personal information and medical records;

[0008] Calculate the patient's targeted heart rate index based on the patient's personal basic information and medical record information;

[0009] Generate a rehabilitation training program suitable for the patient based on the patient's targeted heart rate index;

[0010] According to the rehabilitation training program suitable for the patient, start the rehabilitation training equipment to conduct rehabilitation training and monitor the patient's multi-dimensional cardiac indicators;

[0011] Adjust the power of the rehabilitation training equipment according to the rehabilitation training plan and the patient's multi-dimensional cardiac indicators.

[0012] As a further improvement, the patient's basic personal information includes name, age, gender, height, and weight, and the medical record information can be divided into mild heart disease, moderate heart disease, and severe heart disease.

[0013] As a further improvement, based on the patient's personal basic information and medical record information, the step of calculating the patient's targeted heart rate index A includes: first, according to the patient's age X, calculating the maximum heart rate T=220-patient's age X.

[0014] As a further improvement, the target heart rate index A = T*K is calculated based on the patient's case information. i , where K i It indicates that the patient's medical record information can be divided into mild heart disease, moderate heart disease, and severe heart disease.

[0015] As a further improvement, K1=65-85%, K2=55-65%, K3=0-55%, wherein K1, K2, and K3 respectively represent the weights of the targeted heart rate index when the case information shows mild heart disease, moderate heart disease, and severe heart disease.

[0016] As a further improvement, K 1-1 =65~75%, K 1-2 =75~85%, among which, K 1-1 Indicates light intensity exercise, K 1-2 Indicates moderate intensity exercise.

[0017] As a further improvement, the multi-dimensional heart index includes heart rate, heart rate mean, and heart rate variability.

[0018] As a further improvement, the heart rate variability is measured by calculating the standard deviation of the RR intervals:

[0019]

[0020] Where SDNN is the standard deviation of the RR interval, RR i is the value of each RR interval and N is the number of RR intervals.

[0021] An intelligent multi-modal control rehabilitation device based on multi-dimensional cardiac indicators, comprising:

[0022] An acquisition unit, used to acquire the patient's basic personal information and medical record information;

[0023] A calculation unit, used to calculate the patient's targeted heart rate index based on the patient's personal basic information and medical record information;

[0024] A generating unit, used for generating a rehabilitation training program suitable for the patient based on the patient's targeted heart rate index;

[0025] The detection unit is used to preset the output power of the rehabilitation training equipment according to the rehabilitation training plan, start the rehabilitation training equipment to perform rehabilitation training, and monitor the multi-dimensional indicators of the patient's heart;

[0026] The regulating unit is used to adjust the output power of the rehabilitation training equipment according to the rehabilitation training program and the patient's multi-dimensional heart indicators.

[0027] An intelligent multimodal controlled rehabilitation device based on multidimensional cardiac indicators comprises a processor, a memory and a computer program stored in the memory, wherein the computer program can be executed by the processor to implement the intelligent multimodal controlled rehabilitation method based on multidimensional cardiac indicators.

[0028] The beneficial effects of the present invention are: first, the patient's basic personal information is obtained, including name, age, gender, height, weight, and medical history information, which can be divided into mild heart disease, moderate heart disease, and severe heart disease; then, based on the patient's basic personal information and medical history information, the patient's targeted heart rate index is calculated. The patient's targeted heart rate index can be used to preliminarily evaluate the patient's exercise status. If the patient reaches the targeted heart rate index, it means that for the patient, the power of the rehabilitation training equipment at the current power is too high, and the patient's exercise intensity is too high, then heart failure may occur. The equipment power can be appropriately reduced so that the patient can perform rehabilitation training at an appropriate exercise intensity, and then the patient's multi-dimensional heart indicators are monitored during the subsequent rehabilitation training process to adjust the power of the rehabilitation training equipment. This method can not only reduce the inspection items of heart indicators and improve the efficiency of rehabilitation training, but also enable patients to perform rehabilitation training in a safer state. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0030] Figure 1 It is a flow chart provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the invention claimed for protection, but merely represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0032] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0033] Reference Figure 1 As shown in the figure, an intelligent multi-modal control rehabilitation method based on multi-dimensional cardiac indicators is proposed.

[0034] include:

[0035] Obtain the patient's basic personal information and medical record information. The patient enters basic personal information, such as name, age, gender, etc. The system automatically captures or imports the patient's medical record information, pre-processes the patient's basic personal information and case information, and uses gray theory to process incomplete or uncertain data. By gray processing the original data, missing values ​​or abnormal values ​​in the data can be filled, making the data more complete and regular, which is helpful for subsequent feature extraction and model construction. In this embodiment, gray correlation analysis is used for data processing. Gray correlation analysis can be used to fill missing values ​​or perform smoothing. Gray correlation degree is a method of measuring the degree of correlation between factors. Its calculation formula is as follows;

[0036]

[0037] Among them, γ(x0-x i) represents the correlation between the reference sequence and the comparison sequence, n represents the length of the data sequence, that is, the number of samples, represents the value of the reference sequence at the kth data point, represents the value of the ith comparison sequence at the kth data point, represents the minimum difference of all data points in all comparison sequences, represents the maximum difference of all data points in all comparison sequences, represents the resolution coefficient, which usually takes a value in the range of (0,1) and is used to adjust the sensitivity of the correlation calculation. In this embodiment, it is taken as 0.5.

[0038] The patient's personal basic information includes name, age, gender, height, and weight. The medical record information can be divided into mild heart disease, moderate heart disease, and severe heart disease. Mild heart disease includes early hypertension or mild heart valve problems, etc. Moderate exercise can usually be performed, but strenuous exercise and competitive sports should be avoided. Moderate heart disease includes stable angina pectoris, mild to moderate heart failure, etc. Exercise needs to be performed under the guidance of a doctor, and the intensity and duration of exercise may need to be limited. Severe heart disease includes acute myocardial infarction, severe heart failure, and complex arrhythmias. In the acute stage or when the condition is unstable, physical activity should be limited and bed rest may be required. After the condition stabilizes, progressive cardiac rehabilitation exercises can be performed under the guidance of a doctor and rehabilitation team.

[0039] Based on the patient's personal basic information and medical record information, the patient's targeted heart rate index is calculated, and the doctor or rehabilitation therapist confirms or modifies the target: the doctor or rehabilitation therapist can confirm or modify these target indicators according to the specific situation. In this embodiment, this step includes: first, according to the patient's age X, the maximum heart rate T = 220-patient age X is calculated. This step adopts the scientific maximum heart rate percentage method. This method can preliminarily calculate the maximum heart rate T suitable for patients with age X. For ease of management, the patient's age X is rounded to ten integers, and then the targeted heart rate index A = T*K is calculated based on the patient's case information. i , where K i Indicates that the patient's medical record information can be divided into mild heart disease, moderate heart disease, and severe heart disease, where K1 = 65-85%, K2 = 55-65%, and K3 = 0-55%. K1, K2, and K3 represent the weights of the targeted heart rate indicators when the case information is displayed as mild heart disease, moderate heart disease, and severe heart disease, respectively. For mild heart disease, the exercise intensity can be selected according to the patient's recovery and exercise ability. K 1-1 =65~75%, K 1-2 =75~85%, doctors or rehabilitation therapists can choose different K values ​​according to the patient's recovery. 1-1 Indicates light intensity exercise, K 1-2Indicates moderate intensity exercise. Due to physiological differences, women's maximum exercise tolerance is usually lower than men's, which means that in high-intensity exercise, women's heart rate may rise faster than men's. Therefore, women need to increase the exercise coefficient J = 110%. In this embodiment, the patient Zhang San, male, 33 years old, suffers from early hypertension and mild heart disease. Therefore, Zhang San's maximum heart rate T = 220-30 = 190. The doctor believes that Zhang San's recovery is good, so select K 1-2 =80% moderate intensity exercise, then Zhang San's target heart rate index A=190*80%=152. In other embodiments, the patient Li Si, female, 41 years old this year, suffers from complex arrhythmias and severe heart disease. Therefore, Li Si's maximum heart rate T=220-40=180. The doctor believes that Li Si's disease state is more serious, so the target heart rate index weight K3=50% is selected, then Li Si's target heart rate index A=180*50%*110%=99, and simple rehabilitation exercises are performed. The target heart rate selection for rehabilitation training is performed according to the patient's age and different heart diseases, which can effectively prevent the patient from experiencing heart failure during training.

[0040] According to the rehabilitation training program suitable for the patient, the rehabilitation training equipment is started for rehabilitation training, and the patient wears the ECG patch according to the instructions to monitor the heart data in real time. Prepare the rehabilitation equipment: The patient gets ready on the rehabilitation equipment, starts the equipment to start rehabilitation, and monitors the patient's multi-dimensional heart indicators. As a further improvement, the multi-dimensional heart indicators include heart rate, heart rate mean, and heart rate variability. The feature extraction stage can be divided into static feature extraction and dynamic feature extraction. Static features such as age, gender, and medical history are extracted from the patient's basic information and medical records. Cluster analysis can be used to extract dynamic features from multimodal data. Cluster analysis is an unsupervised learning method used to divide data points into different groups or clusters. Commonly used clustering algorithms include K-means, hierarchical clustering, etc. Here, K-means clustering is taken as an example. Its key steps include initializing the cluster center, assigning data points to the nearest cluster center, and recalculating the cluster center.

[0041] The basic formula of K-means clustering is as follows:

[0042] (1) Initialize cluster centers

[0043] Select K initial cluster centers C = {c1, c2, ..., c k}.

[0044] (2) Assigning data points to cluster centers

[0045] For each data point xi, assign it to the nearest cluster center:

[0046] label i =argmin j ||x i- c j || 2

[0047] Among them, label i is the data point x i The cluster label, x i is the i-th data point in the data set, c j is the center point of the jth cluster, ||x i- c j || is the data point x i To cluster center c j Euclidean distance, argmin j It means finding the value of j that minimizes the following expression.

[0048] (3) Recalculate cluster centers

[0049] For each cluster i, recalculate its cluster center:

[0050]

[0051] Among them, c j is the center point of the jth cluster, n j is the number of data points belonging to the jth cluster.

[0052] (4) Iteration

[0053] Repeat steps (2) and (3) until the cluster center no longer changes significantly or the maximum number of iterations is reached.

[0054] By clustering ECG data, motion data, etc., we can find data patterns of different patients or in different states. These clustering results can be used as new features to describe the patient's dynamic behavior or state.

[0055] In this embodiment, the heart rate mean value can be obtained by calculating the average value of all heartbeat intervals within a period of time, and the specific formula is as follows:

[0056]

[0057] in:

[0058] Mean Heart Rate (MHR) indicates the average heart rate, expressed in beats per minute (bpm).

[0059] Mean RR Interval represents the mean RR interval in seconds.

[0060] The calculation steps are as follows:

[0061] (1) Measure or record the RR intervals between all adjacent heartbeats within a certain period of time.

[0062] (2) Calculate the average of all RR intervals.

[0063] (3) Using the above formula, divide 60 by the average RR interval to obtain the average heart rate.

[0064] For example, if the average RR interval is 0.8 seconds, then the average heart rate will be:

[0065] This means the heart beats an average of 75 times per minute.

[0066] This calculation is based on the fact that there are 60 seconds in a minute and if the heart beats every 0.8 seconds, then in one minute the heart will beat 75 times. This is a simple conversion to convert from time interval to frequency.

[0067] The heart rate variability is measured by calculating the standard deviation of the RR intervals:

[0068]

[0069] Where SDNN is the standard deviation of the RR interval, RR i is the value of each RR interval and N is the number of RR intervals.

[0070] Extracting dynamic features from motion data also includes motion intensity and duration, which usually involves statistics and analysis of motion data.

[0071] (1) Exercise intensity

[0072] Exercise intensity can be measured by calculating average exercise power, speed or other related indicators over a period of time. The specific calculation method depends on the type and format of exercise data.

[0073] (2) Exercise duration

[0074] Exercise duration can be directly extracted from exercise data, that is, the total time the patient exercises is recorded.

[0075] According to the rehabilitation training program and the patient's multi-dimensional heart indicators, the system adjusts the power of the rehabilitation training equipment. Based on the real-time collected heart rate data and the plan formulated by the doctor or rehabilitation therapist, the system automatically adjusts the power of the rehabilitation equipment. Monitoring and alarm: The system monitors various heart indicators in real time and issues an alarm when an abnormal situation occurs. Automatic adjustment plan: According to the alarm status and real-time data, the system automatically adjusts the rehabilitation training plan to ensure patient safety.

[0076] End and evaluation phase training evaluation report: After the patient's training is completed, the system automatically issues an evaluation report for this training. Recommendations for next rehabilitation training: Based on the training data and evaluation results, the system provides patients with recommendations for the next rehabilitation training. Output the calculated target heart rate and other recommended values ​​for cardiac indicators to the patient or doctor. Collect patient feedback on the recommended values, including whether to accept the recommendation, the effectiveness of the recommendation, etc. Use patient feedback for further optimization and iteration of the model, and improve prediction accuracy by adjusting model parameters or introducing new features.

[0077] An intelligent multi-modal control rehabilitation device based on multi-dimensional cardiac indicators, comprising:

[0078] An acquisition unit, used to acquire the patient's basic personal information and medical record information;

[0079] A calculation unit, used to calculate the patient's targeted heart rate index based on the patient's personal basic information and medical record information;

[0080] A generating unit, used for generating a rehabilitation training program suitable for the patient based on the patient's targeted heart rate index;

[0081] The detection unit is used to preset the output power of the rehabilitation training equipment according to the rehabilitation training plan, start the rehabilitation training equipment to perform rehabilitation training, and monitor the multi-dimensional indicators of the patient's heart;

[0082] The regulating unit is used to adjust the output power of the rehabilitation training equipment according to the rehabilitation training program and the patient's multi-dimensional heart indicators.

[0083] An intelligent multimodal controlled rehabilitation device based on multidimensional cardiac indicators comprises a processor, a memory and a computer program stored in the memory, wherein the computer program can be executed by the processor to implement the intelligent multimodal controlled rehabilitation method based on multidimensional cardiac indicators.

[0084] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent multi-modal control rehabilitation method based on multi-dimensional cardiac indicators, characterized in that: include: Obtain the patient's basic personal information and medical records; Calculate the patient's targeted heart rate index based on the patient's personal basic information and medical record information; Generate a rehabilitation training program suitable for the patient based on the patient's targeted heart rate index; According to the rehabilitation training program suitable for the patient, start the rehabilitation training equipment to conduct rehabilitation training and monitor the patient's multi-dimensional heart indicators; Adjust the power of the rehabilitation training equipment according to the rehabilitation training plan and the patient's multi-dimensional cardiac indicators.

2. The intelligent multi-modal control rehabilitation method based on multi-dimensional cardiac indicators according to claim 1, characterized in that: The patient's basic personal information includes name, age, gender, height, and weight, and the medical record information can be divided into mild heart disease, moderate heart disease, and severe heart disease.

3. The intelligent multi-modal control rehabilitation method based on multi-dimensional cardiac indicators according to claim 2, characterized in that: Based on the patient's personal basic information and medical record information, the step of calculating the patient's targeted heart rate index A includes: first, according to the patient's age X, calculating the maximum heart rate T=220-patient's age X.

4. The intelligent multi-modal control rehabilitation method based on multi-dimensional cardiac indicators according to claim 3, characterized in that: Then calculate the target heart rate index A=T*K based on the patient's case information i , where K i It indicates that the patient's medical record information can be divided into mild heart disease, moderate heart disease, and severe heart disease.

5. The intelligent multi-modal control rehabilitation method based on multi-dimensional cardiac indicators according to claim 4, characterized in that: K1=65-85%, K2=55-65%, K3=0-55%, wherein K1, K2, and K3 represent the weights of the targeted heart rate index when the case information indicates mild heart disease, moderate heart disease, and severe heart disease, respectively.

6. The intelligent multi-modal control rehabilitation method based on multi-dimensional cardiac indicators according to claim 5, characterized in that: K 1-1 =65~75%, K 1-2 =75~85%, among which, K 1-1 Indicates light intensity exercise, K 1-2 Indicates moderate intensity exercise.

7. The intelligent multi-modal control rehabilitation method based on multi-dimensional cardiac indicators according to claim 5, characterized in that: The multi-dimensional heart indicators include heart rate, heart rate mean, and heart rate variability.

8. The intelligent multi-modal control rehabilitation method based on multi-dimensional cardiac indicators according to claim 7, characterized in that: The heart rate variability is measured by calculating the standard deviation of the RR intervals: Where SDNN is the standard deviation of the RR interval, RR i is the value of each RR interval and N is the number of RR intervals.

9. An intelligent multi-modal control rehabilitation device based on multi-dimensional cardiac indicators, characterized in that: include: An acquisition unit, used to acquire the patient's basic personal information and medical record information; A calculation unit, used to calculate the patient's targeted heart rate index based on the patient's personal basic information and medical record information; A generating unit, used for generating a rehabilitation training program suitable for the patient based on the patient's targeted heart rate index; The detection unit is used to preset the output power of the rehabilitation training equipment according to the rehabilitation training plan, start the rehabilitation training equipment to perform rehabilitation training, and monitor the multi-dimensional indicators of the patient's heart; The regulating unit is used to adjust the output power of the rehabilitation training equipment according to the rehabilitation training program and the patient's multi-dimensional heart indicators.

10. An intelligent multi-modal control rehabilitation device based on multi-dimensional cardiac indicators, characterized in that: It comprises a processor, a memory and a computer program stored in the memory, wherein the computer program can be executed by the processor to implement an intelligent multimodal control rehabilitation method based on multi-dimensional cardiac indicators as described in any one of claims 1 to 8.

Images