A control method and system based on an ultra-shortwave therapy device
By recommending ultra-shortwave therapy parameters through machine learning models and combining them with real-time monitoring, the problem of improper parameter settings in ultra-shortwave therapy devices has been solved, resulting in more efficient and safer treatment effects.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XIANGYU MEDICAL REHABILITATION EQUIPMENT CHENGDU CO LTD
- Filing Date
- 2025-04-30
- Publication Date
- 2026-06-30
AI Technical Summary
The treatment parameters of existing shortwave diathermy devices rely on experience, resulting in poor treatment effects and the risk of burns, as they fail to take into account the differences in absorption of shortwave diathermy by human body components.
The system uses a machine learning model to recommend treatment parameters based on human body composition data and disease information, and monitors heart rate and temperature in real time to adjust output power or treatment time, generating multiple treatment options for selection.
It improves the accuracy and safety of treatment parameters, reduces operational errors, and ensures treatment effectiveness and user safety.
Smart Images
Figure CN120459540B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of rehabilitation equipment technology. More specifically, this invention relates to a control method and system based on a shortwave diathermy device. Background Technology
[0002] Shortwave diathermy is a commonly used physiotherapy device. It emits high-frequency electromagnetic waves through electrode plates, which penetrate clothing, human skin and subcutaneous tissue, and act directly on the affected area. This heats the body and produces necessary chemical reactions, which can accelerate blood circulation, dissolve rheumatism or deposits, and promote anti-inflammatory and swelling reduction. It is suitable for various acute and malignant inflammations such as wound healing and wound infection.
[0003] Shortwave diathermy devices typically generate shortwave currents with wavelengths of 1–10 m and frequencies of 30–300 MHz. When using such devices, medical staff or rehabilitation therapists usually manually set the output power and duration based on experience, and the patient then receives treatment according to these settings. However, because the treatment parameters are set based on experience, improper settings can easily lead to burns, fatigue, and other adverse effects, thus compromising the treatment outcome. Furthermore, the absorption of shortwave diathermy by the human body is often not considered when setting the parameters, resulting in some of the diathermy being absorbed before reaching the treatment area, thus failing to achieve the desired therapeutic effect.
[0004] Therefore, how to make the ultra-shortwave therapy device output corresponding parameters according to the user's actual situation and needs is a technical problem that urgently needs to be solved. Summary of the Invention
[0005] To address the technical problem of poor treatment effects caused by setting the parameters of a shortwave diathermy device based on experience, the present invention provides solutions in the following aspects.
[0006] In a first aspect, the present invention provides a control method based on a shortwave diathermy device, the method comprising: acquiring a user's medical condition information and body composition data; the medical condition information including the treatment site, cause, and duration of illness, and the body composition data including body fat percentage, water content, and muscle mass; inputting the body composition data and the medical condition information into a trained treatment parameter recommendation model to obtain the user's treatment parameters; the treatment parameters including output power and treatment time, and the treatment parameter recommendation model being a machine learning model; and outputting the treatment parameters so that the shortwave diathermy device emits shortwave diathermy waves corresponding to the treatment parameters.
[0007] Furthermore, the method for obtaining the treatment parameter recommendation model includes: acquiring body composition data, disease information, and corresponding treatment parameters; preprocessing the body composition data, disease information, and treatment parameters; and inputting the preprocessed data into a preset random forest model for training to obtain the treatment parameter recommendation model.
[0008] Furthermore, before obtaining the treatment parameter recommendation model, the method further includes: using a random forest model with a comprehensive root mean square error less than a preset threshold as the treatment parameter recommendation model, wherein the comprehensive root mean square error is calculated as follows:
[0009] MSE = w1MSE w +w2MSE t ;
[0010] In the formula, MSE is the comprehensive root mean square error, w1 is the weight of the output power, w2 is the weight of the treatment time, and w1 is greater than w2. w The root mean square error (RMSE) of the output power is... t denoted as the root mean square error at the time of treatment.
[0011] Furthermore, the treatment process also includes: collecting the temperature of the treatment site and the user's heart rate; determining the heart rate abnormality, which represents the possibility that the output power setting corresponding to the user exceeds the safe range, wherein the heart rate abnormality is positively correlated with the difference in heart rate between the user's current time and the treatment time before the current time, and is positively correlated with the difference in heart rate between the user and the corresponding first case; in response to the heart rate abnormality exceeding a preset abnormality threshold, reducing the output power or shortening the treatment time; in response to the temperature exceeding a preset temperature threshold, turning off the ultra-shortwave therapy device.
[0012] Furthermore, the expression for calculating the heart rate abnormality is as follows:
[0013]
[0014] In the formula, z i k represents the degree of heart rate abnormality of the user at time i. i Let μi represent the rate of change of the user's heart rate at time i, μ1 represent the average rate of change of the heart rate at all other times except time i, and σ1 represent the variance of the rate of change of the heart rate at all other times except time i. jσj represents the average heart rate change rate of the user in the j-th time period, μ2 represents the average heart rate change rate of the first case corresponding to the user under the same output power, σ2 represents the variance of the heart rate change rate of the first case corresponding to the user under the same output power; norm() is a normalization function used to normalize the heart rate abnormality to the range of 0 to 1.
[0015] Furthermore, the method for obtaining the user and the corresponding first case includes: searching for the first case most similar to the user in a preset case database using Euclidean distance based on the user's medical condition information and treatment parameters; the first case represents a case that uses the same output power as the user and the output power is within a safe range.
[0016] Furthermore, collecting the temperature of the treatment site and the user's heart rate includes: collecting the temperature via a temperature sensor and collecting the heart rate via a heart rate sensor.
[0017] Further, outputting the treatment parameters to cause the shortwave diathermy device to emit shortwave diathermy corresponding to the treatment parameters includes: using the treatment parameters as the original treatment parameters, and generating a first treatment parameter and a second treatment parameter based on the original treatment parameters; wherein all parameters in the first treatment parameters are less than the parameters in the original treatment parameters, and all parameters in the second treatment parameters are greater than the parameters in the original treatment parameters; displaying the original treatment parameters, the first treatment parameters, the second treatment parameters, and corresponding prompt information; and controlling the shortwave diathermy device to output the corresponding shortwave diathermy in response to receiving the treatment parameters selected by the user or medical personnel.
[0018] Furthermore, the method also includes: generating a treatment report in response to the end of treatment, the treatment report including treatment parameters, heart rate change curve, and temperature change curve.
[0019] In a second aspect, the present invention provides a control system based on a shortwave diathermy device, comprising a processor and a memory, the memory storing computer program instructions, which, when executed by the processor, implement a control method based on a shortwave diathermy device as described in the first aspect.
[0020] The beneficial effects of this invention are as follows: The method of this invention can automatically generate treatment parameters for the shortwave diathermy device based on the user's actual situation, avoiding the need to set treatment parameters based on experience, thereby improving treatment effectiveness and reducing operational errors. Furthermore, by considering that shortwave diathermy is subject to a certain degree of attenuation in the human body, this invention compensates for the treatment parameters by inputting human body composition data into a machine learning model, improving the accuracy and reliability of determining treatment parameters. Furthermore, by adjusting the output power or treatment time according to the user's abnormal heart rate data and the temperature of the treatment site during treatment, this invention avoids harm to the user caused by excessively high power settings, improving user safety during treatment. Attached Figure Description
[0021] Figure 1 This is a flowchart illustrating a control method based on a shortwave diathermy device according to an embodiment of the present invention;
[0022] Figure 2 This is a schematic diagram of a physical shortwave therapy device according to an embodiment of the present invention;
[0023] Figure 3 This is a schematic block diagram illustrating the structure of a control system based on an ultra-shortwave therapy device according to an embodiment of the present invention. Detailed Implementation
[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0025] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
[0026] Figure 1 This is a flowchart illustrating a control method based on a shortwave diathermy device according to an embodiment of the present invention.
[0027] In a first aspect, the present invention provides a control method based on an ultra-shortwave therapy device, such as... Figure 1 As shown, the control method of the present invention includes:
[0028] S1. Obtain the user's medical condition information and body composition data.
[0029] Specifically, the patient's condition information includes: treatment site, duration of illness, cause, age, and gender, which are entered into the system by the user or medical staff. Body composition data includes body fat percentage, muscle mass, and water content, which can be measured using a body composition analyzer.
[0030] S2. Input the human body composition data and the disease information into the trained treatment parameter recommendation model to obtain the user's treatment parameters.
[0031] In one embodiment, treatment parameters include treatment time and output power. It is understood that the higher the output power of the shortwave diathermy device, the greater the treatment energy intensity and depth, and the wider the treatment range. Therefore, different patients require different output power. Excessive output power may cause burns, tissue damage, or other complications, worsening the patient's condition and affecting the treatment progress. Therefore, it is necessary to set the treatment time and output power appropriately.
[0032] In this embodiment, the treatment parameter recommendation model is obtained based on a random forest model. Specifically, body composition data, disease information, and corresponding implemented treatment parameters are obtained from medical device records, hospital electronic medical record systems, etc. The collected data is preprocessed, including data cleaning, data labeling, and feature extraction. Then, the preprocessed data is input into a preset random forest model for training. The comprehensive root mean square error is used to evaluate the model's performance, and the random forest model with a comprehensive root mean square error less than a preset value is used as the final treatment parameter recommendation model.
[0033] In one embodiment, the formula for calculating the root mean square error is:
[0034] MSE = w1MSE w +w2MSE t ;
[0035] In the formula, MSE is the comprehensive root mean square error, w1 is the weight of the output power, w2 is the weight of the treatment time, and w1 is greater than w2. w The root mean square error (RMSE) of the output power is... t This is the root mean square error of the treatment time.
[0036] By assigning higher weights to output power, the model can focus on improving the accuracy of output power prediction, ensuring that the treatment site can accurately obtain the required energy, and avoiding tissue burns caused by excessive power, thereby improving treatment efficacy and safety.
[0037] It is understandable that shortwave diathermy is absorbed by the human body, resulting in some attenuation before reaching the treatment site. Therefore, power settings based on experience, without considering the varying attenuation levels due to different body compositions, can sometimes lead to treatment outcomes that do not meet expectations. To address this, a machine learning model is trained to consider the attenuation effect of body composition on shortwave diathermy. This model outputs different treatment parameters based on individual body composition and patient condition information, ensuring that the shortwave diathermy reaches the treatment site and achieves the desired therapeutic effect, thereby improving the treatment outcome for the user.
[0038] S3. Output the treatment parameters so that the shortwave therapy device emits shortwave waves corresponding to the treatment parameters.
[0039] In one embodiment, the treatment parameters output by the treatment parameter recommendation model can be directly sent to the shortwave diathermy device, causing the device to emit shortwave diathermy waves corresponding to the treatment parameters. In another embodiment, first and second treatment parameters can be generated based on the original treatment parameters (i.e., the treatment parameters output by the treatment parameter recommendation model) to meet the needs of different users. In this embodiment, all parameters in the first treatment parameters are less than those in the original treatment parameters, and all parameters in the second treatment parameters are greater than those in the original treatment parameters.
[0040] Understandably, compared to the original treatment parameters, the first treatment parameter actually reduces the treatment intensity. Specifically, the output power of the first treatment parameter can be 0.9 times that of the original treatment parameters, and the treatment time can also be 0.9 times that of the original treatment parameters.
[0041] Compared to the original treatment parameters, the second treatment parameters actually increase the treatment intensity. Specifically, the output power of the second treatment parameters can be 1.1 times that of the original treatment parameters, and the treatment time can also be 1.1 times that of the original treatment parameters.
[0042] Furthermore, the system displays the original treatment parameters, the first treatment parameter, the second treatment parameter, and the corresponding prompts. Specifically, the prompt for the original treatment parameter can be "This treatment parameter is a standard treatment plan", the prompt for the first treatment parameter can be "This treatment parameter is a conservative treatment plan", and the prompt for the second treatment parameter can be "This treatment parameter is an enhanced treatment plan".
[0043] After receiving the treatment parameters selected by the user or medical staff, the system sends these parameters to the shortwave diathermy device, causing it to emit the specified shortwave waves. By generating first and second treatment parameters based on the existing parameters, the system can meet the treatment needs of different users. For example, first-time users can choose the first treatment parameter, thus improving treatment flexibility. Furthermore, displaying the specific parameter values allows medical staff to make secondary confirmations.
[0044] In one embodiment, during the treatment process, the method of the present invention further includes: acquiring the temperature of the treatment site and the user's heart rate. Specifically, the temperature of the treatment site can be acquired using a temperature sensor, and the user's heart rate can be acquired using a heart rate sensor.
[0045] The system monitors the user's heart rate and temperature in real time. If these exceed a corresponding threshold, the output power or treatment time is adjusted. Specifically, during treatment, it determines whether the temperature of the treatment site exceeds a preset temperature threshold. If so, the shortwave diathermy device is turned off. In one embodiment, the temperature threshold can be set to 42°C or other values, which can be selected by those skilled in the art according to actual needs. By monitoring the temperature of the user's treatment site in real time, local burns caused by excessive power settings can be avoided, thereby improving the safety of the user's treatment.
[0046] Simultaneously, the system determines the heart rate abnormality level based on the user's heart rate and checks whether it exceeds a preset abnormality threshold. If so, the output power is reduced or the treatment time is shortened. The heart rate abnormality level indicates the likelihood of the output power being set too high. It is positively correlated with the difference in heart rate between the user's current moment and historical moments, and also positively correlated with the difference in heart rate between the user and the corresponding first case. Historical moments refer to all moments from the start of treatment to the current moment.
[0047] Specifically, based on the user's medical condition information and treatment parameters, Euclidean distance can be used to find the first case most similar to the user in a pre-defined case database. Specifically, in the case database, all cases with the same output power and treatment site as the user, and whose power settings are within a reasonable range (i.e., will not cause burns to the user, and the treatment can be successfully completed using this output power), are identified. Then, Euclidean distance is used to find the case most similar to the user among these cases, thus obtaining the first case corresponding to the user. In one embodiment, the importance of each feature can be determined based on a treatment parameter model, and then a corresponding weight can be assigned to each feature in the medical condition information. Based on this parameter and its corresponding weight, the first case closest to the user is found, avoiding interference from secondary features in the matching process, thereby improving the reliability of determining the first case.
[0048] In one embodiment, the expression for calculating the heart rate abnormality is:
[0049]
[0050] In the formula, z i k represents the degree of heart rate abnormality of the user at time i. i Let μi represent the rate of change of the user's heart rate at time i, μ1 represent the average rate of change of the heart rate at all other times except time i, and σ1 represent the variance of the rate of change of the heart rate at all other times except time i. j σj represents the average heart rate change rate of the user in the j-th time period (with one minute as a time period), μ2 represents the average heart rate change rate of the first case corresponding to the user under the same output power, σ2 represents the variance of the heart rate change rate of the first case corresponding to the user under the same output power; norm() is a normalization function used to normalize the heart rate abnormality to the range of 0 to 1.
[0051] When determining the user's own heart rate variation, by not considering the mean and variance at the current moment, it is possible to avoid the problem that a large change in heart rate at the current moment will raise the mean and variance, thus failing to detect this anomaly.
[0052] Because excessively high power settings can cause significant changes in heart rate, monitoring power allows us to verify whether the model's output power is reasonable, and to prevent user harm, ensuring treatment safety. Furthermore, by considering both the user's own heart rate differences and the heart rate differences between the user and the first patient (the greater the difference, the lower the likelihood of excessive power output), the reliability of determining whether the power setting is too high can be improved, avoiding misjudgments.
[0053] In one embodiment, the abnormal threshold is set to 0.6. When this threshold is exceeded, the user's output power or treatment time can be reduced to a certain extent, for example, the output power can be controlled at 90% of the original output power.
[0054] In another embodiment, heart rate data from cases with excessively high power settings can be included in the determination of heart rate abnormality to improve the reliability of the determination. Specifically, the heart rate abnormality is positively correlated with the difference in heart rate between the user's current and historical times, positively correlated with the difference in heart rate between the user and the corresponding first case, and negatively correlated with the difference in heart rate between the user and the corresponding second case. The specific expression for calculating the heart rate abnormality is as follows:
[0055]
[0056] In the formula, z ik represents the degree of heart rate abnormality of the user at time i. i Let μi represent the rate of change of the user's heart rate at time i, μ1 represent the average rate of change of the heart rate at all other times except time i, and σ1 represent the variance of the rate of change of the heart rate at all other times except time i. j μ1 represents the average heart rate change rate of the user in the j-th time period, μ2 represents the average heart rate change rate of the first patient corresponding to the user under the same output power, and σ2 represents the variance of the heart rate change rate of the first patient corresponding to the user under the same output power; μ3 represents the average heart rate change rate of the second patient corresponding to the user under an abnormal output power setting, and σ3 represents the variance of the heart rate change rate of the second patient corresponding to the user under an abnormal output power setting.
[0057] The process for identifying the second case is similar to that for the first case. However, the second case involves first identifying cases where the treatment site is the same but the power setting is outside the reasonable range (i.e., treatment is interrupted due to excessively high power setting or the treatment effect is poor due to excessively high power setting). Then, the case that is most similar to the user among these cases is selected as the second case.
[0058] By comprehensively considering the differences in heart rate between users at different times, the differences in heart rate between the user and the first case, and the differences in heart rate between the user and the second case, the reliability of determining the degree of heart rate abnormality can be further improved, thereby avoiding misjudgment.
[0059] After treatment, a treatment report is generated based on the user's treatment data. The report includes treatment parameters, heart rate change curves, temperature change curves, and other information.
[0060] Figure 3 This is a schematic block diagram illustrating the structure of a control system based on a shortwave diathermy device according to this embodiment.
[0061] In a second aspect, the present invention also provides a control system based on a shortwave diathermy device. For example... Figure 3 As shown, the control system of the present invention includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a control method based on an ultra-shortwave therapy device according to the first aspect of the present invention is implemented.
[0062] The control system also includes other components well known to those skilled in the art, such as communication interfaces. Their settings and functions are known in the art and will not be described in detail here.
[0063] In this invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used or combined with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store desired information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible to or connected to a device. Any application or module described in this invention can be implemented using computer-readable / executable instructions that can be stored or otherwise maintained by such a computer-readable medium.
[0064] While this specification has shown and described numerous embodiments of the invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will occur to those skilled in the art without departing from the spirit and essence of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in the practice of this invention.
Claims
1. A control system based on a shortwave diathermy device, characterized in that, The device includes a processor and a memory, the memory storing computer program instructions. When the processor executes the computer program instructions, it implements a control method based on a shortwave diathermy device. The method includes: The system obtains the user's medical condition information and body composition data; the medical condition information includes the treatment site, cause of the disease, and duration of the illness, and the body composition data includes body fat percentage, water content, and muscle mass. The human body composition data and the disease information are input into a trained treatment parameter recommendation model to obtain the user's treatment parameters; the treatment parameters include output power and treatment time, and the treatment parameter recommendation model is a machine learning model; The treatment parameters are output so that the shortwave therapy device emits shortwave waves corresponding to the treatment parameters. The method also includes the following during the treatment process: Based on the user's medical condition information and treatment parameters, the system uses Euclidean distance to search for the first case most similar to the user in a preset case database; the first case represents a case that uses the same output power as the user and that the output power is within a safe range. Collect the temperature of the treatment site and the user's heart rate; Determine the heart rate abnormality, which represents the possibility that the output power setting corresponding to the user is outside the safe range. The heart rate abnormality is positively correlated with the difference in heart rate between the user's current time and the treatment time before the current time, and is also positively correlated with the difference in heart rate between the user and the corresponding first case. The expression for calculating the heart rate abnormality is as follows: ； In the formula, This represents the degree of heart rate abnormality of the user at time i. This represents the rate of change of the user's heart rate at time i. This represents the average rate of change of heart rate at all times except the i-th time. This represents the variance of the rate of change of heart rate at all times except the i-th time. Indicates the first The average rate of change of heart rate for users over a time period. This represents the average rate of change of heart rate for the first case corresponding to the user at the same output power. This represents the variance of the rate of change of heart rate for the first case corresponding to the user at the same output power; () is a normalization function used to normalize the heart rate abnormality to the range of 0 to 1; In response to the heart rate abnormality exceeding a preset abnormality threshold, the output power is reduced or the treatment time is shortened. In response to the temperature exceeding a preset temperature threshold, the ultra-shortwave therapy device is turned off.
2. The control system based on the ultra-shortwave therapy device according to claim 1, characterized in that, The method for obtaining the treatment parameter recommendation model includes: To obtain human body composition data, disease information, and corresponding treatment parameters; The human body composition data, the disease information, and the treatment parameters are preprocessed; The preprocessed data is input into a preset random forest model for training to obtain the treatment parameter recommendation model.
3. The control system based on the ultra-shortwave therapy device according to claim 2, characterized in that, Before obtaining the treatment parameter recommendation model, the method further includes: using a random forest model with a comprehensive root mean square error less than a preset threshold as the treatment parameter recommendation model, wherein the comprehensive root mean square error is calculated as follows: ； In the formula, The comprehensive root mean square error is... The weight of the output power, As the weight of the treatment time, Greater than , The root mean square error of the output power. denoted as the root mean square error at the time of treatment.
4. The control system based on the ultra-shortwave therapy device according to claim 1, characterized in that, Collecting the temperature of the treatment site and the user's heart rate includes: collecting the temperature via a temperature sensor and collecting the heart rate via a heart rate sensor.
5. The control system based on the ultra-shortwave therapy device according to claim 1, characterized in that, Outputting the treatment parameters so that the shortwave therapy device emits shortwave waves corresponding to the treatment parameters includes: The treatment parameters are used as the original treatment parameters, and a first treatment parameter and a second treatment parameter are generated based on the original treatment parameters; wherein, all parameters in the first treatment parameter are less than the parameters in the original treatment parameters, and all parameters in the second treatment parameter are greater than the parameters in the original treatment parameters; The original treatment parameters, the first treatment parameters, the second treatment parameters, and the corresponding prompts are displayed. In response to receiving treatment parameters selected by the user or medical staff, the device controls the output of the corresponding shortwave therapy.
6. The control system based on the ultra-shortwave therapy device according to claim 1, characterized in that, The method further includes: generating a treatment report in response to the end of treatment, the treatment report including treatment parameters, heart rate change curve, and temperature change curve.