Chronic disease patient exercise rehabilitation risk early warning method based on data analysis

Abstract

The invention relates to the technical field of exercise rehabilitation, in particular to a chronic disease patient exercise rehabilitation risk early warning method based on data analysis. The method comprises the following steps: S1, presetting the exercise amount # imgabs0 # required by rehabilitation exercise of a patient in an intelligent wearable device; s2, collecting the exercise required by the patient at home before the rehabilitation exercise; s3, calculating the relevance between the exercise required by the home and the rehabilitation exercise, and calculating the influence state of the exercise required by the home on the rehabilitation exercise according to the relevance; according to the chronic disease patient exercise rehabilitation risk early warning method based on data analysis, an intelligent wearable device is used for obtaining the living habits of a patient before rehabilitation exercise, the exercise, except the rehabilitation exercise, of the patient is analyzed from the living habits, then the exercise serves as a part of the rehabilitation exercise, and dynamic adjustment of the rehabilitation exercise is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of sports rehabilitation, and more specifically, to a method for early warning of sports rehabilitation risks for chronic disease patients based on data analysis. Background Art

[0002] The importance of sports rehabilitation has been increasingly emphasized by medical practitioners in China. At present, home-based sports rehabilitation has gradually become a new trend in sports rehabilitation. Compared with traditional center-based rehabilitation, home-based rehabilitation offers more flexible time, less space requirement, and lower overall medical costs.

[0003] During the home-based sports rehabilitation process, since patients cannot communicate face-to-face with doctors, they usually carry out sports rehabilitation training according to the exercise indicators pre-established by doctors. The amount of exercise in these exercise indicators increases gradually according to the stage of sports rehabilitation treatment. During this process, to avoid unexpected risks, intelligent wearable devices are equipped for patients to monitor their vital sign data during exercise. For example, the Chinese patent with the publication number CN119673440A discloses the use of intelligent wearable devices to analyze data such as patients' heart rate, respiratory rate, and body temperature. When these data are abnormal, an early warning reminder is sent to the patients in a timely manner to prevent them from continuing to exercise. Although this method reduces the occurrence of unexpected risks, there are still the following deficiencies when facing home-based sports rehabilitation: During the home stay, in addition to sports rehabilitation, patients are also prone to have other sports needs in daily life, such as going up and down stairs, cooking, cleaning, etc. Some of the exercise amounts in these sports needs are easily superimposed on the exercise amount of sports rehabilitation, which easily leads to the phenomenon of over-exercise for patients.

[0004] Therefore, how to dynamically adjust the exercise indicators pre-established by doctors according to the sports needs of patients during the home stay is an important problem faced by current home-based sports rehabilitation. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for early warning of sports rehabilitation risks for chronic disease patients based on data analysis, which analyzes the patients' living habits and gives timely warnings to the patients according to the living habits, so as to solve the problem raised in the above background art, that is, some of the exercise amounts are easily superimposed on the exercise amount of sports rehabilitation, which easily leads to the phenomenon of over-exercise for patients.

[0006] To achieve the above purpose, the method for early warning of sports rehabilitation risks for chronic disease patients based on data analysis includes the following steps: S1. Preset the amount of exercise required for the patient to perform rehabilitation exercises in the intelligent wearable device ; S2. Collect the sports required for home stay generated by the patient before performing rehabilitation exercises; S3. Calculate the correlation between the home-based exercise required and the rehabilitation exercise, and calculate the influence status of the home-based exercise on the rehabilitation exercise based on the correlation; S4. When the rehabilitation exercise is affected by the home-based exercise required, generate a warning progress according to the proportion relationship between the home-based exercise required and the rehabilitation exercise; S5. When the patient reaches the warning progress during the rehabilitation exercise, give a warning reminder to the patient.

[0007] In the above technical solution, when it is predicted that the patient will perform the home-based exercise required, by combining the home-based exercise required to reduce the duration of the rehabilitation exercise, a timely reminder is given to the patient.

[0008] On this basis, the steps of presetting the exercise amount in S1 are as follows: S1.1. Collect the disease information of the patient and obtain the rehabilitation exercise type corresponding to the disease information ; S1.2. Analyze the rehabilitation exercise stage the patient is in, and establish an exercise amount for the patient according to the rehabilitation exercise stage ; S1.3. Store the exercise amount in the smart wearable device.

[0009] On this basis, the steps of collecting the home-based exercise required in S2 are as follows: S2.1. Set the home observation period; S2.2. Collect the behavior information of the patient within the observation period through the smart wearable device, and mark the behavior information with exercise as the home-based exercise required.

[0010] On this basis, the steps of calculating the correlation in S3 are as follows: S3.1. Obtain the home exercise type of the home-based exercise required ; S3.2. Set the correlation threshold , when the similarity between the home exercise type and the rehabilitation exercise type is ≥ the correlation threshold , it indicates that there is a correlation between the home-based exercise required and the rehabilitation exercise; when the similarity between the home exercise type and the rehabilitation exercise type is < the correlation threshold , it indicates that there is no correlation between the home-based exercise required and the rehabilitation exercise.

[0011] On this basis, the steps of calculating the influence status in S3 are as follows: S3.3. Obtain the start time of the exercise required at home , the end time and the exercise duration ; S3.4. Preset an influence time before the start time and after the end time to obtain an influence time period ; S3.5. Obtain the amount of exercise of the patient's rehabilitation exercise . When the amount of exercise coincides or partially coincides with the influence time period , mark the patient's current rehabilitation exercise as affected; when the amount of exercise does not coincide with the influence time period , mark the patient's current rehabilitation exercise as unaffected.

[0012] On this basis, the formula for generating the warning progress in S4 is as follows: ; In the formula, is the warning progress; is the total progress of the rehabilitation exercise; is the exercise duration of the exercise required at home; is the amount of exercise of the rehabilitation exercise.

[0013] In another technical solution, the following steps are further included: S6. Obtain the subsequent status of the patient after receiving the warning reminder, and the subsequent status includes stopping exercise and continuing exercise; S7. Set a judgment threshold. When the number of times of stopping exercise ≥ the judgment threshold and the patient chooses to continue exercise subsequently, change the rehabilitation exercise to the next stage; when the number of times of stopping exercise < the judgment threshold, do nothing.

[0014] In this technical solution, since the exercise required at home will be superimposed on the rehabilitation exercise, therefore, by obtaining the status of the patient after receiving the warning reminder, on the one hand, it is judged whether the patient is exercising according to the warning reminder; on the other hand, the number of times of execution of the patient can be used as a basis to identify the physical recovery of the patient, so as to dynamically adjust the rehabilitation exercise stage.

[0015] Compared with the prior art, the beneficial effects of the present invention: 1. In the method for warning of exercise rehabilitation risks for chronic disease patients based on data analysis, an intelligent wearable device is used to obtain the patient's living habits before rehabilitation exercise, analyze the patient's exercise other than rehabilitation exercise from the living habits, and then use this exercise as part of the rehabilitation exercise to achieve dynamic adjustment of the rehabilitation exercise and reduce the phenomenon of excessive exercise in patients during home stay.

[0016] 2. In the method for warning of exercise rehabilitation risks for chronic disease patients based on data analysis, obtaining the exercise required for the patient's home stay can not only avoid the phenomenon of excessive exercise in patients, but also test the recovery status of the patient's body during the rehabilitation exercise, so as to achieve dynamic adjustment of the rehabilitation exercise stage. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the overall method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0019] In view of the phenomenon that home patients are prone to excessive exercise, the present invention provides a method for warning of exercise rehabilitation risks for chronic disease patients based on data analysis. Please refer to Figure 1 As shown, the warning method includes the following steps: S1. Preset the amount of exercise required for the patient to perform rehabilitation exercise in an intelligent wearable device (such as a smart watch that can monitor data such as the patient's heart rate, respiratory rate, and body temperature) ; S2. Collect the home exercise required by the patient before performing rehabilitation exercise; S3. Calculate the correlation between the home exercise required and the rehabilitation exercise, and calculate the influence state of the home exercise required on the rehabilitation exercise according to the correlation; S4. When the rehabilitation exercise is affected by the home exercise required, generate a warning progress according to the proportion relationship between the home exercise required and the rehabilitation exercise; S5. When the patient reaches the warning progress during the rehabilitation exercise, give a warning reminder to the patient.

[0020] Specifically, the steps for presetting the amount of exercise in S1 are as follows: S1.1. Collect the patient's disease information and obtain the rehabilitation exercise type corresponding to the disease information ; S1.2. Analyze the rehabilitation exercise stage the patient is in, and establish the amount of exercise for the patient according to the rehabilitation exercise stage ; S1.3. Store the amount of exercise in the smart wearable device.

[0021] Among them, the amount of exercise in S1.2 is calculated in units of time. For example, when the patient's chronic disease is in the leg or hand, the type of rehabilitation exercise established by the doctor at this time is leg movement or hand movement. Then analyze the rehabilitation exercise stage required by the patient. Suppose it takes three stages to complete the treatment, and the training time for each stage is 15 days. The amount of exercise during this process increases step by step according to the stage sequence. For example, the amount of exercise when the patient is in the first stage is 20 minutes, the amount of exercise in the second stage is 30 minutes, and the amount of exercise in the third stage is 60 minutes. Then store the amount of exercise for these three stages in the smart wearable device.

[0022] Currently, the conventional warning method is basically to give a warning reminder to the patient after the patient reaches the corresponding amount of exercise . For example, the warning time for the patient corresponding to the first stage is 20 minutes after the rehabilitation exercise. This can avoid the phenomenon of the patient overexercising. However, due to the particularity of staying at home, some patients are also prone to other movements besides rehabilitation exercises, such as going up and down stairs or cooking, etc., and it is difficult for doctors to know the movements required by these patients at home. Therefore, suppose the patient has the behavior of going up and down stairs in a short time after finishing the rehabilitation exercise for the leg. At this time, the patient's leg is prone to the phenomenon of overexercising, thus affecting the rehabilitation progress.

[0023] For this reason, in the process of the patient staying at home, the present invention analyzes the patient's living habits and gives a timely warning to the patient according to the living habits, so as to reduce the phenomenon of overexercising in the above situation. Specifically, it is carried out through the following steps in S2: The steps of collecting the movements required at home in S2 are as follows: S2.1. Set the home observation period. The observation period is the period from when the patient stays at home to when the patient performs rehabilitation exercises. Therefore, during the observation period, the patient does not perform rehabilitation exercises in order to collect the patient's living habits. For example, the observation period is 3 days. At this time, after the patient returns home from the hospital, wait for 3 days to perform rehabilitation exercises. And within these 3 days, collect the patient's living habits; S2.2. Collect the patient's behavioral information during the observation period through the smart wearable device, and mark the behavioral information that generates movement as the movement required for home. For example, during a 3-day observation period, the patient performed behaviors such as going up and down the stairs (using the stairs), taking a walk, and cooking. Since going up and down the stairs, taking a walk, and cooking all generated movement, going up and down the stairs, taking a walk, and cooking are marked as the movement required for home.

[0024] On this basis, the steps for calculating the correlation and influence status in S3 are as follows: S3.1. Obtain the home movement type of the movement required for home , the home movement type is mainly identified through the smart wearable device. For example, the moving speed of the patient is obtained through GPS data, Beidou data, etc. in the smart wearable device, and then the patient's heart rate is measured. When the moving speed and heart rate exceed the threshold, it is marked as running (belonging to leg movement). Another example is that when the patient is moving, if the altitude of the patient's location shows a regular increase, it is marked as climbing the stairs (belonging to leg movement). For another example, it can also be assisted by calling the microphone of the smart wearable device for identification. When the patient's hand generates movement, at this time, the microphone is used to monitor the surrounding environment sound. When the sound of running water or the sound of the range hood is captured, it is marked as cooking (belonging to hand movement).

[0025] S3.2. Set the correlation threshold , when the similarity between the home movement type and the rehabilitation movement type ≥ the correlation threshold , it indicates that there is an association between the movement required for home and the rehabilitation movement; when the similarity between the home movement type and the rehabilitation movement type < the correlation threshold , it indicates that there is no association between the movement required for home and the rehabilitation movement.

[0026] For example, assume that the patient goes out for a walk every day and needs to go up and down the stairs through the stairs when going out. At this time, the home movement type of the patient is climbing the stairs, and the corresponding body movement part is the leg; at this time, if the rehabilitation movement type is squatting or jogging, then the corresponding body movement part is also the leg. At this time, it can be found that the home movement type and the rehabilitation movement type are related, and both belong to leg exercises. At the same time, since the two cannot be completely similar, therefore, a threshold is set for judgment. Assume that the threshold is 70%. At this time, as long as the home movement type Similarity with the type of rehabilitation exercise Greater than or equal to 70% can be considered that there is a correlation between the two.

[0027] S3.3. Obtain the start time of the exercise required at home , end time and exercise duration ; S3.4. Preset an impact time before the start time and after the end time to obtain the impact time period ; S3.5. Obtain the exercise amount of the patient's rehabilitation exercise . When the exercise amount overlaps or partially overlaps with the impact time period , mark the patient's current rehabilitation exercise as affected; when the exercise amount does not overlap with the impact time period , mark the patient's current rehabilitation exercise as not affected.

[0028] For example, the patient goes out every day and needs to go up and down stairs during the process of going out. Therefore, going up and down stairs is the exercise required at home for the patient. Assume that the patient goes out at 6 pm (i.e., the start time ), and returns home at 7 pm (i.e., the end time ). The time for going up and down stairs during this process is 5 minutes (i.e., the exercise duration ). Then, preset an impact time, assume the impact time is 20 minutes. At this time, it can also indicate that the impact time period of the exercise required at home is between 5:40 pm and 7:20 pm. Then, assume that the exercise amount of the patient's rehabilitation exercise is 20 minutes. Then, obtain the time when the patient clicks to start the rehabilitation exercise, assume it is 5:25 pm. After calculation, it can be known that the rehabilitation exercise should end at 5:45 pm. Therefore, the exercise amount will overlap with the impact time period for 5 minutes. At this time, the rehabilitation exercise can be marked as affected.

[0029] Going out and returning home in the above example are both identified through the positioning system of the smart wearable device.

[0030] Moreover, since the time when the patient goes out every day cannot be exactly the same, a time period can also be predicted based on the time when the patient goes out during the observation period. For example, on the first day, the patient goes out at 6 pm and returns home at 7 pm; on the second day, the patient goes out at 6:05 pm and returns home at 7 pm; on the third day, the patient goes out at 6:10 pm and returns home at 6:50 pm. At this time, based on the earliest going-out time and the latest returning-home time, that is, the start time is 6 pm, and the end time is 7 pm.

[0031] Specifically, the formula for generating the warning progress in S4 is as follows: ; In the formula, is the warning progress; is the total progress of the rehabilitation exercise; is the exercise duration of the exercise required at home; is the amount of exercise of the rehabilitation exercise. The total progress of the rehabilitation exercise is 100%. Assuming the exercise duration is 5 minutes and the amount of exercise is 20 minutes, it can be calculated that the warning progress is 75%. In this way, when the patient clicks to start the rehabilitation exercise on the smart wearable device, the progress of the rehabilitation exercise starts to be calculated from 1%. When the progress reaches 75%, the smart wearable device issues a warning reminder to remind the patient to pay attention. The remaining 25% of the progress is compensated by the exercise required at home. That is, after the patient goes out at 6 pm, the remaining 25% of the progress is compensated by the leg exercise when going up and down the stairs.

[0032] That is to say, the smart wearable device is used to obtain the patient's living habits before the rehabilitation exercise, analyze the patient's exercise other than the rehabilitation exercise from the living habits, and then use this exercise as a part of the rehabilitation exercise to achieve dynamic adjustment of the rehabilitation exercise and reduce the phenomenon of excessive exercise due to too much exercise during the patient's home stay.

[0033] It should be understood that any place involving privacy in the present invention will be informed to the user, and relevant data will be collected only after the user agrees to authorize the privacy.

[0034] Moreover, in some embodiments, the warning method further includes the following steps: S6. Obtain the subsequent state of the patient after receiving the warning reminder, and the subsequent state includes stopping the exercise and continuing the exercise; S7. Set a determination threshold. When the number of times of stopping the exercise ≥ the determination threshold and the patient chooses to continue the exercise subsequently, change the patient's rehabilitation exercise to the next stage; when the number of times of stopping the exercise < the determination threshold, do nothing.

[0035] For example, during a 7-day rehabilitation exercise process, the patient received 5 warning reminders and stopped exercising after receiving these 5 warning reminders. Assuming the judgment threshold is 3 times, this indicates that the patient's body is difficult to bear both the rehabilitation exercise and the exercise required for daily life at the same time. However, in the subsequent process, when the patient received a warning reminder again, but the patient chose to continue exercising, this indicates that the patient can bear both the rehabilitation exercise and the exercise required for daily life at the same time. That is to say, the patient's physical condition has recovered well, and at this time, the exercise volume can be increased to the next stage to achieve dynamic adjustment of the exercise volume according to the patient's own condition. .

[0036] In summary, obtaining the exercise required for the patient's daily life can not only avoid the phenomenon of over-exercising of the patient, but also test the recovery state of the patient's body during the rehabilitation exercise process, so as to achieve dynamic adjustment of the rehabilitation exercise stage.

[0037] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and the descriptions in the specification are only preferred examples of the present invention and are not used to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for early warning of exercise rehabilitation risks for chronic disease patients based on data analysis, characterized in that: It includes the following steps: S1. Preset the amount of exercise required for the patient's rehabilitation exercise in the smart wearable device ; S2. Collect the home-based movements required by the patient before performing rehabilitation exercises; S3. Calculate the correlation between the home-based movements required and the rehabilitation exercises, and calculate the influence status of the home-based movements required on the rehabilitation exercises based on the correlation; S4. When the rehabilitation exercises are affected by the home-based movements required, generate a warning progress according to the proportion relationship between the home-based movements required and the rehabilitation exercises; S5. When the patient reaches the warning progress during the rehabilitation exercises, give a warning reminder to the patient.

2. The method for early warning of exercise rehabilitation risks for chronic disease patients based on data analysis according to claim 1, wherein: The preset amount of exercise in S1 is as follows: S1.

1. Collect the disease information of the patient and obtain the rehabilitation exercise types corresponding to the disease information ; S1.

2. Analyze the rehabilitation exercise stage the patient is in and establish the amount of exercise for the patient according to the rehabilitation exercise stage ; S1.

3. Store the amount of exercise in the smart wearable device.

3. The method for early warning of exercise rehabilitation risks for chronic disease patients based on data analysis according to claim 2, wherein: The amount of exercise is calculated using time units.

4. The method for early warning of exercise rehabilitation risks for chronic disease patients based on data analysis according to claim 1, wherein: The steps for collecting the home-based movements required in S2 are as follows: S2.

1. Set a home observation period; S2.

2. Collect the patient's behavior information during the observation period through a smart wearable device, and mark the behavior information that generates movement as the home-based movements required.

5. The method for warning of exercise rehabilitation risks for chronic disease patients based on data analysis according to claim 4, characterized in that: During the observation period, the patient is in a state of not performing rehabilitation exercises.

6. The method for early warning of exercise rehabilitation risks for chronic disease patients based on data analysis according to claim 4, wherein: The steps for calculating the correlation in S3 are as follows: S3.

1. Obtain the home exercise types required for home exercise ; S3.

2. Set the correlation threshold When the similarity between the home exercise type and the rehabilitation exercise type ≥ the correlation threshold , it indicates that there is an association between the exercise required at home and the rehabilitation exercise; when the similarity between the home exercise type and the rehabilitation exercise type < the correlation threshold , it indicates that there is no association between the exercise required at home and the rehabilitation exercise.

7. The method for early warning of exercise rehabilitation risks for chronic disease patients based on data analysis according to claim 6, characterized in that: The steps for calculating the influence status in S3 are as follows: S3.

3. Obtain the start time of the exercise required at home , the end time and the exercise duration ; S3.

4. Preset an influence time before the start time and after the end time to obtain an influence time period ; S3.

5. Obtain the amount of exercise of the patient's rehabilitation exercise , when the amount of exercise coincides or partially coincides with the influence time period , mark this rehabilitation exercise of the patient as affected; when the amount of exercise does not coincide with the influence time period , mark this rehabilitation exercise of the patient as not affected.

8. The method for early warning of exercise rehabilitation risks for chronic disease patients based on data analysis according to claim 7, wherein: The formula for generating the warning progress in S4 is as follows: ； Wherein, is the early warning progress; is the total progress of the rehabilitation exercise; is the exercise duration of the exercise required at home; is the amount of exercise of the rehabilitation exercise.

9. The method for early warning of exercise rehabilitation risk for chronic disease patients based on data analysis according to claim 1, wherein: It also includes the following steps: S6. Obtain the patient's subsequent status after receiving the warning reminder, and the subsequent status includes stopping the exercise and continuing the exercise; S7. Set a judgment threshold. When the number of times of stopping the exercise ≥ the judgment threshold and the patient chooses to continue the exercise subsequently, change the rehabilitation exercise to the next stage; when the number of times of stopping the exercise < the judgment threshold, do nothing.

Images