Renal bone disease diagnosis and treatment scheme generation method and system, acupoint stimulation equipment and medium

Abstract

The invention belongs to the technical field of intelligent medical treatment, and particularly relates to a renal bone disease diagnosis and treatment scheme generation method and system, acupoint stimulation equipment and a medium, and the method comprises the steps: collecting clinical data, related to renal bone diseases, of a target object; on the basis of a pre-constructed clinical data and acupuncture point data relation library, acupuncture point data corresponding to the clinical data are obtained through matching, and the acupuncture point data comprise target acupuncture point identification and acupuncture point stimulation data corresponding to the target acupuncture point identification; acquiring a human body image of the target object, and acquiring acupuncture point position data of the target acupuncture point identification on the human body image; and generating an acupoint stimulation scheme of the acupoint stimulation device in multiple stimulation modes based on the acupoint position data and the acupoint stimulation data. According to the renal bone disease diagnosis and treatment scheme generation method, different stimulation modes and stimulation parameters can be flexibly selected and adjusted, a personalized acupoint stimulation scheme is formulated, and the accuracy and adaptability of acupoint stimulation are improved.

Description

Technical Field

[0001] This application belongs to the field of smart medical technology, specifically relating to a method, system, acupoint stimulation device and medium for generating a treatment plan for renal osteodystrophy. Background Technology

[0002] Renal osteodystrophy, a common complication of chronic kidney disease (CKD), has seen a continuous increase in the number of patients in recent years, coinciding with the rising incidence of CKD. This disease not only significantly reduces patients' quality of life but also greatly increases the risk of serious complications such as cardiovascular disease, posing a direct threat to patients' lives and health.

[0003] In clinical practice, acupoint stimulation devices can provide auxiliary diagnostic and treatment support for renal osteodystrophy through acupoint stimulation. However, current acupoint stimulation protocols rely on the physician's operational experience, resulting in a relatively high error rate during the diagnostic and treatment process, making it difficult to guarantee stable diagnostic and treatment accuracy. In addition, it is difficult to flexibly adjust the protocols according to the patient's specific condition and individual differences, thus limiting their clinical application effectiveness to some extent.

[0004] Application content To overcome the shortcomings of the prior art, this application proposes a method, system, acupoint stimulation device, and medium for generating a treatment plan for renal osteodystrophy, specifically implemented through the following technical solution: A method for generating a treatment plan for renal osteodystrophy, applied to an acupoint stimulation device, comprising: Collect clinical data related to renal osteodystrophy in the target subjects; Based on a pre-built database of clinical data and acupoint data, acupoint data corresponding to the clinical data is matched. The acupoint data includes target acupoint identifiers and acupoint stimulation data corresponding to the target acupoint identifiers. Acquire human images of the target object and obtain acupoint location data of the target acupoints on the human image; Based on the acupoint location data and the acupoint stimulation data, the acupoint stimulation device generates acupoint stimulation schemes under various stimulation modes.

[0005] In an optional embodiment, the method for generating a treatment plan for renal osteodystrophy further includes: Obtain physiological data related to renal osteodystrophy in target subjects during multimodal stimulation; Determine whether the physiological indicator data exceeds the preset physiological indicator data range; When the physiological index data exceeds the preset physiological index data range, the PID controller calculates the adjustment amount of the acupoint stimulation parameters based on the physiological index data. The acupoint stimulation scheme is updated based on the adjustment amount of the acupoint stimulation parameters.

[0006] In an optional embodiment, the step of calculating the adjustment amount of the acupoint stimulation parameters based on the physiological index data using a PID controller includes: The deviation value is calculated based on the physiological index data and the standard physiological index data; Based on the deviation value, the proportional coefficient, integral coefficient, and derivative coefficient of the PID controller are corrected in real time. The total adjustment of the PID controller output is determined based on the corrected proportional coefficient, integral coefficient, derivative coefficient, and the deviation value. Based on the preset physiological index correlation matrix of stimulation mode, the total adjustment amount is allocated as electrical stimulation intensity adjustment amount, magnetic stimulation frequency adjustment amount, and thermal stimulation duration adjustment amount.

[0007] In an optional embodiment, the allocation of the total adjustment amount into electrical stimulation intensity adjustment, magnetic stimulation frequency adjustment, and thermal stimulation duration adjustment based on a preset stimulation pattern physiological index correlation matrix includes: The adjustment amount of electrical stimulation intensity is obtained based on the partial derivative of the electrical stimulation intensity with respect to the preset physiological index data, the total adjustment amount, and the electrical stimulation weighting coefficient. The magnetic stimulation frequency adjustment amount is obtained based on the partial derivative of the preset physiological index data with respect to the magnetic stimulation frequency, the total adjustment amount, and the magnetic stimulation weight coefficient. The adjustment amount of the heat stimulation duration is obtained based on the partial derivative of the preset physiological index data with respect to the heat stimulation duration, the total adjustment amount, and the heat stimulation weighting coefficient. The constraint condition is that the sum of the weighting coefficients for electrical stimulation, magnetic stimulation, and thermal stimulation is 1.

[0008] In an optional embodiment, the real-time correction of the proportional coefficient, integral coefficient, and derivative coefficient of the PID controller based on the deviation value includes: The rate of change of deviation is calculated based on the deviation value. According to the preset correction rule library, the proportional coefficient correction factor, integral coefficient correction factor and differential coefficient correction factor corresponding to the deviation value and the deviation change rate are obtained. The proportional coefficient of the PID controller is corrected according to the proportional coefficient correction factor, the integral coefficient of the PID controller is corrected according to the integral coefficient correction factor, and the derivative coefficient of the PID controller is corrected according to the derivative coefficient correction factor.

[0009] In an optional embodiment, obtaining the acupoint location data of the target acupoint on the human body image includes: The human body image is input into a pre-trained acupoint location deep learning recognition model for recognition, to obtain multiple acupoint location data on the human body image and the acupoint location identifier corresponding to each acupoint location data; Match the acupoint location data corresponding to the target acupoint location identifier from the plurality of acupoint location data.

[0010] In an optional embodiment, the multiple stimulation modes include a radio frequency mode, an electrical stimulation mode, a laser mode, and an ultrasound mode. The acupoint stimulation device includes a first treatment head and a second treatment head. The first treatment head is configured to perform the radio frequency mode, the electrical stimulation mode, and the laser mode, and the second treatment head is configured to perform the ultrasound mode.

[0011] A system for generating treatment plans for renal osteodystrophy, running on an acupoint stimulation device, comprising: The data acquisition module is used to collect clinical data related to renal osteodystrophy in the target subjects. The identification module is used to match the acupoint data corresponding to the clinical data based on a pre-built database of clinical data and acupoint data. The acupoint data includes the target acupoint identification and the acupoint stimulation data corresponding to the target acupoint identification. The positioning module is used to acquire human images of the target object and obtain acupoint location data of the target acupoints on the human image; The generation module is used to generate acupoint stimulation schemes for the acupoint stimulation device under multiple stimulation modes based on the acupoint location data and the acupoint stimulation data.

[0012] An acupoint stimulation device includes dual treatment heads, a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the method for generating a treatment plan for renal osteodystrophy as described above.

[0013] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method for generating a treatment plan for renal osteodystrophy as described above.

[0014] This application has at least the following beneficial effects: This application collects clinical data related to renal osteodystrophy from target subjects and matches corresponding acupoint data with a database of acupoint data. This approach fully considers the individual differences of each patient, allowing for the creation of customized treatment plans for renal osteodystrophy, thus offering a degree of personalization. Furthermore, by matching acupoint data with a pre-built database of clinical data, the subjectivity and arbitrariness of traditional acupoint selection are avoided, improving the accuracy and reliability of acupoint selection. Moreover, by acquiring human images of target subjects and obtaining acupoint location data on these images, acupoint stimulation schemes for acupoint stimulation devices under various stimulation modes are generated based on the acupoint location data and stimulation data. This allows for flexible selection and adjustment of different stimulation modes and parameters, enabling the development of personalized acupoint stimulation schemes and improving the accuracy and adaptability of acupoint stimulation. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A first flowchart illustrating the method for generating a treatment plan for renal osteodystrophy provided in this application embodiment; Figure 2 A second flowchart illustrating the method for generating a treatment plan for renal osteodystrophy provided in this application embodiment; Figure 3 A third flowchart illustrating the method for generating a treatment plan for renal osteodystrophy provided in this application embodiment; Figure 4 This is the fourth flowchart of the method for generating a treatment plan for renal osteodystrophy in this application; Figure 5 This is the fifth flowchart of the method for generating a treatment plan for renal osteodystrophy in this application; Figure 6 This is a schematic diagram of the modules of the renal osteodystrophy diagnosis and treatment plan generation system of this application; Figure 7 This is a schematic diagram of the acupoint stimulation device of this application.

[0017] Figure label: 1-Acquisition module; 2-Identification module; 3-Location module; 4-Generation module; 5-Dual treatment heads; 6-Processor; 7-Memory; 51-First treatment head; 52-Second treatment head. Detailed Implementation

[0018] Various embodiments of this application will be described more fully below. This application may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this application to the specific embodiments disclosed herein, but rather this application should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this application.

[0019] In the following, the terms “comprising” or “may include” as used in the various embodiments of this application indicate the presence of the disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. Furthermore, as used in the various embodiments of this application, the terms “comprising,” “having,” and their cognates are intended only to indicate a particular feature, number, step, operation, element, component, or combination of the foregoing, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing, or the possibility of adding one or more combinations of features, numbers, steps, operations, elements, components, or combinations of the foregoing.

[0020] Example 1 like Figure 1 As shown, this application proposes a method for generating a treatment plan for renal osteodystrophy, which is applied to an acupoint stimulation device. The method includes: S1: Collect clinical data related to renal osteodystrophy in the target subjects; S2: Based on a pre-built database of clinical data and acupoint data, match the acupoint data corresponding to the clinical data. The acupoint data includes the target acupoint location identifier and the acupoint stimulation data corresponding to the target acupoint location identifier. S3: Acquire human images of the target object and obtain acupoint location data of the target acupoints on the human image; S4: Generate acupoint stimulation schemes for acupoint stimulation devices under various stimulation modes based on acupoint location data and acupoint stimulation data.

[0021] This application collects clinical data related to renal osteodystrophy from target subjects and matches corresponding acupoint data with a database of clinical data. This approach fully considers individual differences and allows for the creation of customized treatment plans for each target subject, offering a degree of personalization. Furthermore, by matching acupoint data with a pre-built database of clinical data, the subjectivity and arbitrariness of traditional acupoint selection are avoided, improving the accuracy and reliability of acupoint selection. Moreover, by acquiring human images of target subjects and obtaining acupoint location data on these images, acupoint stimulation schemes for acupoint stimulation devices under various stimulation modes are generated based on this location data and stimulation data. This allows for flexible selection and adjustment of different stimulation modes and parameters, enabling the development of personalized acupoint stimulation plans and improving the precision and adaptability of treatment.

[0022] Specifically, in S1, "Collecting Clinical Data Related to Renal Osteopathy in Target Subjects," the target subjects refer to patients who require auxiliary diagnosis and treatment for renal osteodystrophy. Clinical data related to renal osteodystrophy includes: basic information, medical history, and laboratory test results of the target subjects.

[0023] The basic information includes the target subject's age, gender, height, and weight. Medical history information includes the target subject's chronic kidney disease course, previous treatments, presence of other comorbidities (such as hypertension, diabetes, etc.), and family medical history. Laboratory test results include blood test results, urine test results, bone density test results, and kidney function test results. The target subject's basic information, medical history, and laboratory test results will be transmitted to the acupoint stimulation device for storage, providing data support for subsequent treatment plan generation.

[0024] S2, "Based on a pre-built database of clinical data and acupoint data relationships, it matches acupoint data corresponding to the clinical data. The acupoint data includes target acupoint identifiers and corresponding acupoint stimulation data," includes: S21: Preprocessing clinical data is performed on clinical data to obtain preprocessed clinical data.

[0025] Data preprocessing for clinical data includes cleaning and standardizing the clinical data, removing outliers and missing values, and converting the data into a uniform format to obtain preprocessed clinical data, which can then be compared with data in the clinical data and acupoint data relationship database.

[0026] S22: Calculate the matching similarity between the preprocessed clinical data and each standardized clinical indicator group in the pre-constructed clinical data and acupoint data relationship database, and screen out the target indicator group whose matching similarity meets the preset matching similarity threshold.

[0027] To achieve accurate matching from clinical data to acupoint data, it is necessary to first establish a connection between preprocessed clinical data and a database relating clinical data to acupoint data.

[0028] First, the preprocessed clinical data is used as a benchmark and compared one by one with the standardized clinical indicator groups stored in the clinical data and acupoint data relationship database. Each group contains core indicators related to the diagnosis and treatment of renal osteodystrophy, such as renal function stage, serum phosphorus / calcium level, bone mineral density T-score, and parathyroid hormone concentration, and the indicator format is completely consistent with the preprocessed data. The Euclidean distance or cosine similarity between the two is calculated using a weighted algorithm to obtain the matching similarity. Then, the calculated matching similarity is compared with a preset matching similarity threshold. Standardized clinical indicator groups with matching similarity reaching or exceeding the preset matching similarity threshold are selected as target indicator groups that can accurately correspond to the individual patient's condition, laying the foundation for subsequent extraction of appropriate acupoint data.

[0029] The preset matching similarity threshold is determined based on the effectiveness verification results of acupoint stimulation programs in clinical practice.

[0030] S23: Based on the preset mapping relationship between clinical indicator groups and acupoint data, obtain the target acupoint data corresponding to the target indicator group and obtain the target acupoint identification.

[0031] The target acupoints can be labeled as Shenshu (BL23) and Zusanli (ST36).

[0032] S24: Based on the target acupoint identification, obtain the corresponding acupoint stimulation data from the clinical data and acupoint data relationship database.

[0033] The acupoint stimulation data includes parameters such as stimulation mode (e.g., selecting radiofrequency, electrical stimulation, or laser), stimulation intensity (e.g., power of radiofrequency, current intensity of electrical stimulation, energy density of laser), and stimulation time (duration of each stimulation and treatment cycle).

[0034] This application uses a pre-constructed database of clinical data and acupoint data relationships, along with pre-processed clinical data, to calculate the similarity between the target object's clinical data and existing case data in the database. Based on the similarity calculation results, the case with the highest similarity is selected to determine the target acupoint identifier corresponding to the target object's clinical data, thereby accurately obtaining the location information of the target acupoint on the human body surface, greatly improving the accuracy and effectiveness of acupoint stimulation.

[0035] like Figure 5 As shown, S3 acquires human images of the target object and obtains acupoint location data of the target acupoints on the human image, including: S31: Uses binocular infrared imaging to acquire human images of the target object; Binocular infrared imaging technology uses dual cameras to simulate the visual principle of the human eye. Combined with the penetrating advantage of infrared imaging, it can clearly capture the outline of the human body surface and the characteristics of subcutaneous tissue. Even in scenarios with light clothing or insufficient light, it can avoid interference from differences in skin texture and skin color on acupoint location, ensuring that the acquired images have both spatial depth information and detail clarity.

[0036] S32: Input the human body image into the pre-trained acupoint location deep learning recognition model for recognition, and obtain multiple acupoint location data on the human body image and the acupoint location identifier corresponding to each acupoint location data; The pre-trained deep learning model for acupoint location recognition was obtained through the following method: Prepare multiple objects (e.g., 500) in advance, multi-position and multi-angle scan images as a dataset. Randomly select a portion of the dataset, such as 300 data points, as the training set, and use the remaining data as the validation set. The training set is input into the ResNet-50 deep learning model for training to output the trained model; the trained model is validated using the validation set, and the deep learning recognition model for acupoint locations is output when the validation conditions are met.

[0037] The pre-trained deep learning recognition model for acupoint locations can automatically extract features related to acupoints from images, quickly identify multiple acupoint location data (presented in coordinate form) on the image, and output the acupoint identifier corresponding to each location.

[0038] S33: Match the acupoint location data corresponding to the target acupoint location identifier from multiple acupoint location data.

[0039] The acupoint identifier corresponding to the target acupoint identifier is matched from multiple acupoint identifiers output by the deep learning recognition model for acupoint location. Then, the acupoint location data corresponding to the matched acupoint identifier is used as the acupoint location data corresponding to the target acupoint identifier, providing a spatial positioning basis for the precise action of the subsequent acupoint stimulation device.

[0040] This application obtains relatively accurate acupoint location data and corresponding acupoint identifiers on the human body image by inputting the human body image into a pre-trained deep learning recognition model for acupoint location. This process uses a deep learning model to quickly and accurately find the location data of the target acupoints on the human body image, reducing the interference of human factors and making the acquisition of acupoint location data more objective and reliable.

[0041] S4 "Generate acupoint stimulation schemes for acupoint stimulation devices under multiple stimulation modes based on acupoint location data and acupoint stimulation data" includes: S41: Generate a treatment plan for renal osteodystrophy based on acupoint location data and acupoint stimulation data, selecting the required stimulation mode, stimulation parameters under the stimulation mode, and stimulation sequence; S42: Generate acupoint stimulation schemes for acupoint stimulation devices under multiple stimulation modes based on the required stimulation mode, stimulation parameters under the stimulation mode, and stimulation sequence.

[0042] The stimulation modes can include one or more of the following: radiofrequency, electrical stimulation, laser, and ultrasound. Stimulation parameters include stimulation intensity, stimulation time, and stimulation frequency. The stimulation sequence includes the order of the stimulation modes and the order of the acupoints.

[0043] Based on acupoint location data and basic stimulation data, and combined with the patient's clinical information (such as renal function stage and bone pain severity), suitable stimulation mode combinations are selected. For example, for patients with severe bone mineral density loss, an electrical stimulation mode (regulating local metabolism) and a laser mode (promoting bone repair) can be used in combination. Stimulation parameters are set according to the characteristics of different modes, such as an intensity of 8-15mA, a frequency of 20-50Hz, and a single session of 15 minutes for the electrical stimulation mode, and a power of 50-100mW and an irradiation time of 3 minutes per acupoint for the laser mode. At the same time, the stimulation sequence is planned, including the order of modes (such as pre-treating the acupoint area with ultrasound mode first, and then enhancing the effect with electrical stimulation) and the order of acupoints (such as starting with the Shenshu acupoint on the lower back, and then stimulating the Zusanli acupoint and Taixi acupoint on the lower limbs in sequence), to ensure that the stimulation logic conforms to the meridian conduction law.

[0044] Based on the device's hardware parameters, such as the output ports of each mode and the switching response time, the selected stimulation modes, parameters, and sequence are converted into device instruction formats. The connection method when switching between different modes is clarified, such as starting the laser mode after a 2-minute interval after the radio frequency mode ends. The device positioning parameters when stimulating each acupoint are marked, such as the contact angle between the ultrasound probe and the skin. Finally, a standardized scheme containing mode combinations, parameter matrices, and execution sequences is formed to ensure that the device can accurately implement multi-mode acupoint stimulation according to the diagnostic and treatment needs.

[0045] This application generates acupoint stimulation schemes for acupoint stimulation devices under various stimulation modes based on acupoint location data and acupoint stimulation data, enabling the selection and combination of multiple stimulation modes, thus improving flexibility and personalization.

[0046] like Figure 2 As shown, the method for generating treatment plans for renal osteodystrophy also includes: Obtain physiological data related to renal osteodystrophy in target subjects during multimodal stimulation; Determine whether the physiological indicator data exceeds the preset physiological indicator data range; When the physiological index data exceeds the preset physiological index data range, the PID controller calculates the adjustment amount of the acupoint stimulation parameters based on the physiological index data. The acupoint stimulation program is updated based on the adjustment amount of the acupoint stimulation parameters.

[0047] Among them, physiological indicators such as bone density, blood calcium, blood phosphorus, and alkaline phosphatase are obtained by acquiring physiological indicators related to renal osteodystrophy in the target subjects during multimodal stimulation, so as to understand the physical response and changes in the condition of the target subjects in real time during the stimulation process, and provide a data basis for subsequent judgment and treatment.

[0048] The preset range of physiological indicators is a normal or reasonable range determined based on a large amount of clinical data and medical knowledge. By determining whether the actual physiological indicator data obtained exceeds this range, it is possible to quickly identify whether the target subject's physical condition is abnormal and the degree of abnormality, providing a basis for whether the treatment plan needs to be adjusted.

[0049] As can be seen, this application, by acquiring physiological index data related to renal osteodystrophy in the target subject during multimodal stimulation, can understand the target subject's body's response to the current acupoint stimulation program in real time and dynamically. Furthermore, by determining whether the physiological index data exceeds a preset range, it accurately judges whether the target subject's physiological indicators are within a normal and effective stimulation response range. When the physiological index data exceeds the preset range, the PID controller calculates the adjustment amount of the acupoint stimulation parameters based on the physiological index data, thereby updating the acupoint stimulation program accordingly. The PID controller has rapid calculation and response capabilities; it can calculate the adjustment amount of the acupoint stimulation parameters based on the physiological index data in a short time and quickly update the acupoint stimulation program. Simultaneously, by continuously acquiring physiological index data and adjusting the acupoint stimulation program in a timely manner, dynamic adjustment allows the program to better respond to various changes in the individual during the stimulation process, further enhancing the personalization level of the program.

[0050] like Figure 3 As shown, the adjustment amounts of acupoint stimulation parameters are obtained by calculating based on physiological index data using a PID controller, including: The deviation value was calculated based on the physiological index data and the standard physiological index data. The proportional, integral, and derivative coefficients of the PID controller are corrected in real time based on the deviation value. The total adjustment of the PID controller output is determined based on the corrected proportional coefficient, integral coefficient, derivative coefficient, and deviation value. Based on the preset correlation matrix of physiological indicators of stimulation patterns, the total regulation is allocated into electrical stimulation intensity adjustment, magnetic stimulation frequency adjustment, and thermal stimulation duration adjustment.

[0051] Among them, the standard physiological index data is a reference value reflecting the normal or ideal physiological state of patients with renal osteopathy, and its data source is based on the "Diagnosis and Treatment Guidelines for Chronic Kidney Disease-Mineral and Bone Disorders in China (2023 Edition)". The physiological index data of the acupoint stimulation area of the target object is collected in real time through the sensor equipped with the acupoint stimulation device. By calculating the deviation value between the actually obtained physiological index data and the standard physiological index data, the gap between the patient's current physiological state and the ideal state can be quantified, providing a basis for the adjustment of the subsequent PID controller.

[0052] The proportional coefficient (Kp) determines the response speed and amplitude of the system to the current deviation. The integral coefficient (Ki) is used to eliminate the steady-state error of the system. The derivative coefficient (Kd) reflects the rate of change of the deviation and can predict the future trend of the system.

[0053] Based on the deviation value, the proportional coefficient, integral coefficient, and derivative coefficient of the PID controller are corrected in real time. The control intensity can be dynamically adjusted according to the magnitude of the deviation, enabling the system to quickly respond to changes in physiological indicators. Moreover, by correcting the integral coefficient according to the accumulation of deviations, it can be ensured that the system can accurately adjust the physiological indicators to the target range during long-term operation. Furthermore, real-time correction of the derivative coefficient can enable the system to make adjustments in advance, avoiding overshoot or oscillation phenomena, and improving the stability and response speed of the system.

[0054] Based on the corrected proportional coefficient, integral coefficient, derivative coefficient, and the deviation value, the total adjustment amount output by the PID controller is determined.

[0055] The standard physiological index data includes the optimal physiological index thresholds corresponding to different disease stages (such as mild, moderate, and severe), different ages, and different weights. The device will automatically match the corresponding standard threshold combination according to the clinical data of the target object as the standard physiological index data r(t). The sliding window weighted average method is used to extract the eigenvalue as the final feedback quantity, that is, the physiological index data y(t). The deviation value e(t) = r(t) - y(t).

[0056] In an optional implementation manner, the real-time correction of the proportional coefficient, integral coefficient, and derivative coefficient of the PID controller based on the deviation value includes: Calculating the rate of change of the deviation based on the deviation value; According to the preset correction rule library, matching the proportional coefficient correction factor, integral coefficient correction factor, and derivative coefficient correction factor corresponding to the deviation value and the rate of change of the deviation; The proportional coefficient of the PID controller is corrected according to the proportional coefficient correction factor, the integral coefficient of the PID controller is corrected according to the integral coefficient correction factor, and the derivative coefficient of the PID controller is corrected according to the derivative coefficient correction factor.

[0057] Traditional PID coefficients (Kp, Ki, Kd) are fixed, but this is only true if the parameters of the controlled object are stable and the disturbances are predictable. However, in the scenario of acupoint stimulation-assisted treatment of renal osteodystrophy, the target is the matching relationship between the intensity and effect of acupoint stimulation. Multiple dynamic disturbances exist, such as changes in blood pressure, heart rate, and fluctuations in blood calcium and phosphorus metabolism levels, which alter the sensitivity of acupoints to stimulation. Adjustments in the target's posture and changes in muscle tension around the acupoints can alter the contact impedance between the stimulation electrode and the acupoint. Fixed coefficients can lead to adjustment lag, overshoot (actual value far exceeding the target value), or oscillations. Therefore, the coefficients need to be dynamically adjusted based on the deviation to avoid affecting the safety of the stimulation.

[0058] The proportional, integral, and derivative coefficients of the PID controller can be adjusted in real time based on a correction rule base. This rule base is pre-built based on clinical sample data and includes the correspondence between the deviation value e(t), the deviation change rate Δe(t), and the correction factors for the PID coefficients (Kp, Ki, Kd). The deviation change rate Δe(t) reflects the trend of deviation change and is calculated as Δe(t) = e(t) - e(t-1), where e(t-1) is the deviation value at the previous acquisition time. For example, if the current e(t) = 4 and the previous e(t-1) = 3, then Δe(t) = 1, indicating that the deviation is increasing; if e(t-1) = 5, then Δe(t) = -1, indicating that the deviation is decreasing.

[0059] The correction factor is a proportional coefficient used to adjust the PID coefficient. A correction factor greater than 1 indicates an increase in the corresponding PID coefficient, a correction factor less than 1 indicates a decrease in the corresponding PID coefficient, and a correction factor equal to 1 indicates no adjustment to the corresponding PID coefficient. For example, assuming the original proportional coefficient Kp = 10 and the correction factor Kp' = 1.2, then the corrected proportional coefficient Kp = 10 × 1.2 = 12.

[0060] By using a correction factor, the deviation state can be transformed into a coefficient adjustment command, avoiding random and blind corrections, ensuring that the adjustment logic conforms to the actual characteristics of the target object, and thus making the total regulation output of the PID controller more accurate.

[0061] The total adjustment Δu(t) = Kp×e(t) + Ki×∫e(t)dt + Kd×de(t) / dt. Where, Kp×e(t): proportional term, directly responding to the current deviation; the larger the deviation, the larger the output adjustment, quickly offsetting the deviation; Ki×∫e(t)dt: integral term, accumulating historical deviations and eliminating static errors (if small deviations exist for a long time, the integral term gradually increases, driving the adjustment to follow suit); Kd×de(t) / dt: derivative term, reflecting the rate of change of the deviation, predicting the deviation trend in advance, and suppressing overshoot (if the deviation increases rapidly, the derivative term outputs a negative adjustment, slowing down the adjustment speed).

[0062] The correlation matrix of physiological indicators for each stimulus pattern is pre-established. The experiment selects a number of healthy volunteers (e.g., 50) and a number of patients with renal osteodystrophy (e.g., 50). The parameters of the two stimulus patterns are fixed, and only the parameters of one stimulus pattern are changed. The magnitude of the change in physiological indicators is recorded to determine the correlation strength between each stimulus pattern and each physiological indicator. Based on a pre-defined correlation matrix of physiological indicators for different stimulation modes, the total adjustment amount is allocated to adjustments for electrical stimulation intensity, magnetic stimulation frequency, and thermal stimulation duration. This matrix establishes a quantitative relationship between different stimulation modes and physiological indicators, clarifying the degree of influence of each stimulation mode on different physiological indicators. Through this matrix, the total adjustment amount can be rationally allocated to each stimulation mode, ensuring that adjustments to each stimulation mode can specifically improve the patient's physiological indicators. This allocation method makes treatment more precise, allowing for targeted adjustments to the parameters of different stimulation modes based on the specific changes in the patient's physiological indicators.

[0063] As can be seen, this application, by calculating deviation values ​​in real time and correcting PID controller coefficients, can dynamically adjust acupoint stimulation parameters according to the patient's real-time physiological state, and allocate the total adjustment amount based on the correlation matrix of physiological indicators of stimulation modes, thus achieving precise control of parameters for different stimulation modes and improving the accuracy and effectiveness of treatment plan generation. Furthermore, by combining multiple stimulation modes and dynamic parameter adjustment methods, personalized treatment plans can be developed based on the individual differences of each patient, meeting the treatment needs of diverse patients.

[0064] like Figure 4 As shown, based on the preset physiological index correlation matrix of stimulation patterns, the total regulation is allocated into electrical stimulation intensity adjustment, magnetic stimulation frequency adjustment, and thermal stimulation duration adjustment, including: The adjustment amount of electrical stimulation intensity is obtained by using the partial derivative of the electrical stimulation intensity with respect to the preset physiological index data, the total adjustment amount, and the electrical stimulation weighting coefficient. The magnetic stimulation frequency adjustment amount is obtained by using the partial derivative of the magnetic stimulation frequency with respect to the preset physiological index data, the total adjustment amount, and the magnetic stimulation weight coefficient. The adjustment amount of heat stimulation duration is obtained based on the partial derivative of the heat stimulation duration with respect to preset physiological index data, the total adjustment amount, and the heat stimulation weight coefficient. The constraint condition is that the sum of the weighting coefficients for electrical stimulation, magnetic stimulation, and thermal stimulation is 1.

[0065] The partial derivatives of physiological index data with respect to each stimulation parameter reflect the degree of influence of a small change in that stimulation parameter on the physiological index data, assuming other parameters remain constant. For example, the larger the partial derivative of the physiological index data with respect to the electrical stimulation intensity, the more significant the impact of changes in the electrical stimulation intensity on the physiological index. The electrical stimulation weighting coefficient, magnetic stimulation weighting coefficient, and thermal stimulation weighting coefficient are used to measure the importance of each stimulation mode in the overall treatment. By rationally setting these weighting coefficients and combining them with partial derivatives and the total adjustment amount, precise allocation of the adjustment amount for each stimulation parameter can be achieved. Furthermore, the constraint requires that the sum of the electrical stimulation weighting coefficient, magnetic stimulation weighting coefficient, and thermal stimulation weighting coefficient be 1, ensuring the rationality and standardization of the weight allocation.

[0066] The formulas for adjusting the electrical stimulation intensity, magnetic stimulation frequency, and thermal stimulation duration are as follows: Electrical stimulation intensity adjustment = Partial derivative of preset physiological index data with respect to electrical stimulation intensity × Total adjustment × Electrical stimulation weight coefficient; Magnetic stimulation frequency adjustment = Partial derivative of preset physiological index data with respect to magnetic stimulation frequency × Total adjustment × Magnetic stimulation weight coefficient; Thermal stimulation duration adjustment = Partial derivative of preset physiological index data with respect to thermal stimulation duration × Total adjustment × Thermal stimulation weight coefficient.

[0067] As can be seen, this application, by combining partial derivatives and weighting coefficients, can precisely allocate the total modulus to each stimulation parameter based on the degree of influence of each stimulation mode on physiological indicators and its importance in the overall treatment. This avoids blind allocation of modulus and improves the precision of treatment. The weighting coefficients can be adjusted according to individual patient differences, enabling personalized treatment plans and improving the targeting and effectiveness of treatment. The total modulus is calculated using a PID controller based on the patient's real-time physiological indicator data, while the partial derivatives and weighting coefficients can be updated and optimized based on clinical experience and new research findings. Therefore, this allocation method can dynamically adapt to changes in the patient's condition and adjust the treatment plan in a timely manner.

[0068] The clinical data and acupoint data relationship database is constructed based on clinical research literature and combined with relevant data established for existing clinical patients.

[0069] In an optional embodiment, the clinical data and acupoint data relationship database records the correspondence between multi-dimensional clinical data and acupoint data.

[0070] By collecting multiple historical, multi-dimensional clinical data sets and historical acupoint stimulation protocols, a wealth of raw materials is provided for database construction. Further processing and analysis of these historical data sets and protocols generates a correspondence between multi-dimensional clinical data and acupoint data, making the resulting clinical data-acupoint data relationship database scientific, comprehensive, and significantly more reliable. Furthermore, by continuously collecting and updating multi-dimensional clinical and acupoint data, the clinical data-acupoint data relationship database continuously expands in terms of data coverage and dynamically updates in terms of data timeliness, gradually forming a complete data link from symptom to acupoint to therapeutic effect.

[0071] Historical multidimensional clinical data includes indicators from eight dimensions for each subject, including basic information indicators, symptom assessment indicators, physical examination indicators, laboratory test indicators, imaging examination indicators, bioelectrical impedance, anxiety scale, and muscle rating scale.

[0072] Basic information indicators include name, age, gender, registration number, primary disease, dialysis method, dialysis duration, and identification number. Symptom assessment indicators include skin itching and scores, bone pain and scores, lower limb weakness and scores, and numbness and scores. Physical examination indicators include general indicators and muscle function indicators. General indicators include height, weight, and BMI. Muscle function indicators include muscle strength, muscle tone, and calf circumference. Muscle strength grading standards: 0-5, assessing limb movement and muscle contraction ability; muscle tone is classified as normal, increased, and decreased, assessing resistance during passive movement; calf circumference is bilateral, assessing muscle loss. Laboratory test indicators include calcium and phosphorus metabolism, parathyroid function, bone metabolism markers, and nutritional status. Imaging examination indicators include pelvic X-ray, femoral X-ray, and musculoskeletal ultrasound. Bioelectrical impedance analysis includes body composition indicators such as protein, inorganic salts, body fat, skeletal muscle, and body fat percentage. Anxiety scales assess the patient's psychological state, including anxiety, tension, fear, and insomnia. The muscle rating scale includes muscle strength, assisted walking, seated standing, stair climbing, and number of falls.

[0073] Historical acupoint stimulation protocols include the specific protocols for each individual, including data on the stimulated acupoints, stimulation modes, stimulation parameters, and treatment cycles. Stimulation modes include radiofrequency, electrical stimulation, laser, and ultrasound. Stimulation parameters include stimulation intensity, frequency, and duration.

[0074] A preliminary review was conducted on the collected historical multidimensional clinical data and historical acupoint stimulation protocols, removing data records with duplicate, erroneous, or missing key information. Correlation analysis was used to obtain the relationship between clinical data indicators of each dimension and acupoint stimulation protocols. Based on the relationship between clinical data indicators of each dimension and acupoint stimulation protocols, multidimensional clinical data indicators that are significantly related to acupoint stimulation protocols were selected as key indicators. According to the different value ranges of the key indicators, combined with the corresponding acupoint stimulation protocols, a correspondence database between multidimensional clinical data and acupoint data was established.

[0075] The device incorporates multiple stimulation modes, including radiofrequency, electrical stimulation, laser, and ultrasound. The acupoint stimulation device includes a first treatment head and a second treatment head. The first treatment head is configured to execute radiofrequency, electrical stimulation, and laser modes, while the second treatment head is configured to execute ultrasound mode. This application utilizes multiple stimulation modes—radiofrequency, electrical stimulation, laser, and ultrasound—to facilitate personalized treatment plans. Furthermore, configuring the first treatment head to execute radiofrequency, electrical stimulation, and laser modes, and the second treatment head to execute ultrasound mode, allows for precise output of each stimulation mode through a specially optimized treatment head. The first treatment head can flexibly switch between the three stimulation modes to target different layers and needs of the lesion site, achieving comprehensive treatment of local tissues; the second treatment head focuses on ultrasound output, better leveraging the unique advantages of ultrasound for effective treatment of deep tissues. Simultaneously, the configuration of the first and second treatment heads makes the device more flexible and convenient to use, reducing interference between ultrasound, radiofrequency, electrical stimulation, and laser modes, and effectively improving the stability of the device.

[0076] Example 2 like Figure 6 As shown, a system for generating treatment plans for renal osteodystrophy, applied to acupoint stimulation devices, includes: Data acquisition module 1 is used to collect clinical data related to renal osteodystrophy in the target subjects; Identification module 2 is used to match acupoint data corresponding to clinical data based on a pre-built database of clinical data and acupoint data. The acupoint data includes the target acupoint identification and the acupoint stimulation data corresponding to the target acupoint identification. The positioning module 3 is used to acquire human images of the target object and obtain the acupoint location data of the target acupoints on the human image; The generation module 4 is used to generate acupoint stimulation schemes for acupoint stimulation devices under various stimulation modes based on acupoint location data and acupoint stimulation data.

[0077] This application, through the cooperation of the acquisition module, identification module, positioning module and generation module, can flexibly select and adjust different stimulation modes and stimulation parameters, formulate personalized acupoint stimulation programs, and improve the accuracy and adaptability of treatment.

[0078] The renal osteodystrophy diagnosis and treatment plan generation system of this application is also used to perform other steps described in the renal osteodystrophy diagnosis and treatment plan generation method of Example 1.

[0079] Example 3 like Figure 7 As shown, an acupoint stimulation device includes dual treatment heads 5, a memory 7, a processor 6, and a computer program stored in the memory 7 and executable on the processor. When the processor executes the computer program, it implements the steps of the method for generating a treatment plan for renal osteodystrophy as described in Embodiment 1 above. The acupoint stimulation device of this application can flexibly select and adjust different stimulation modes and stimulation parameters to formulate personalized acupoint stimulation plans, thereby improving the accuracy and adaptability of treatment.

[0080] Specifically, the dual treatment head 5 includes a first treatment head 51 and a second treatment head 52. The first treatment head 51 includes a radio frequency unit, an EMS unit, and a red light emitting unit. The radio frequency unit adopts an octet multipolar radio frequency with a frequency of 1.000 MHz / 1.600 MHz, 10 levels of energy ranging from 0.013 to 0.027 μC, and closed-loop temperature control of 37-52 ℃. The EMS unit has a constant current output of 1.35-10.10 mA, a pulse frequency of 50-100 Hz, and a hardware current limit of 120 mA. The red light emitting unit emits 630 nm / 900 mW red light, driven by constant current PWM, and derating for over-temperature conditions.

[0081] In this embodiment, the radio frequency unit is first driven to emit radio frequency signals and act on the object, followed by the combined action of the EMS unit and the red light emitting unit. The radio frequency unit first opens the tissue channels through micro-thermal damage, reducing the resistance to the EMS action; the EMS unit then dominates the clearance-synthesis process through rhythmic contractions, promoting collagen reconstruction and muscle function repair; the red light provides energy support and anti-inflammatory protection throughout the process, ensuring the safety and sustainability of the EMS action.

[0082] The second treatment head 52 includes an ultrasound unit that generates ultrasound waves and residual heat. The ultrasound unit uses a rectangular pulse ultrasound device with a frequency of 4 MHz, a focal depth of 4.5 mm, a sound intensity of 0-60 W / cm², and a duty cycle of 14-67%. The second treatment head indirectly assists the repair process through physical stimulation: on the one hand, it gently stretches muscle fibers and collagen bundles, activating the activity of osteoblasts, osteoclasts, and satellite cells, laying the foundation for cell proliferation and differentiation in core treatment; on the other hand, it accelerates the repair of local micro-damage and improves muscle elasticity by upregulating bone morphogenetic protein-2 (BMP-2) and downregulating receptor activator of nuclear factor κB (RANKL), indirectly enhancing the cellular response efficiency of subsequent core treatment. Furthermore, the microsecond-level cavitation bubbles induced by ultrasound can open cell membrane micropores during the expansion-collapse instant, increasing cell membrane permeability by 2-3 times. Simultaneously, relying on the inherent warming effect of ultrasound, it helps relieve bone-related pain and improve myopathic spasms.

[0083] Example 4 A computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method for generating a treatment plan for renal osteodystrophy as described in Embodiment 1 above. The computer-readable storage medium of this application allows for flexible selection and adjustment of different stimulation modes and parameters, enabling the development of personalized acupoint stimulation plans and improving the accuracy and adaptability of treatment.

[0084] In various embodiments of this application, the expression "or" or "at least one of A and / or B" includes any combination or all combinations of the words listed simultaneously. For example, the expression "A or B" or "at least one of A and / or B" may include A, may include B, or may include both A and B.

[0085] The terms used in the various embodiments of this application (such as "first," "second," etc.) may modify various constituent elements in the various embodiments, but do not limit the corresponding constituent elements. For example, the above terms do not limit the order and / or importance of the elements. The above terms are only used for the purpose of distinguishing one element from other elements. For example, a first user device and a second user device refer to different user devices, although both are user devices. For example, without departing from the scope of the various embodiments of this application, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element.

[0086] It should be noted that, in this application, unless otherwise explicitly specified and defined, terms such as "installation," "connection," and "fixation" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0087] In this application, those skilled in the art should understand that the terms indicating orientation or positional relationship are based on the orientation or positional relationship shown in the accompanying drawings and are only for the purpose of describing this application and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0088] The terminology used in the various embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the various embodiments of this application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of this application pertain. The terms (such as those defined in a generally used dictionary) are to be interpreted as having the same meaning as in the context of the relevant technical field and are not to be interpreted as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of this application.

Claims

1. A renal osteodystrophy diagnosis and treatment plan generation method applied to an acupoint stimulation device, characterized in that, The renal osteopathy diagnosis and treatment scheme generation method comprises: Collecting clinical data related to renal osteopathy of a target object; Based on the pre-constructed clinical data and acupoint data relationship database, matching the acupoint data corresponding to the clinical data, the acupoint data including target acupoint point identifiers and acupoint stimulation data corresponding to the target acupoint point identifiers; Collecting human body images of the target object and obtaining acupoint position data of the target acupoint point identifiers on the human body images; Based on the acupoint position data and the acupoint stimulation data, generating acupoint stimulation schemes of the acupoint stimulation device under multiple stimulation modes.

2. The renal bone disease diagnosis and treatment plan generation method of claim 1, wherein, The renal osteopathy diagnosis and treatment scheme generation method further comprises: Obtaining physiological index data related to renal osteopathy of a target object when performing multi-modal stimulation; Judging whether the physiological index data exceeds the preset physiological index data range; When the physiological index data exceeds the preset physiological index data range, calculating the adjustment amount of the acupoint stimulation parameter based on the physiological index data through the PID controller; Updating the acupoint stimulation scheme according to the adjustment amount of the acupoint stimulation parameter.

3. The renal bone disease diagnosis and treatment plan generation method according to claim 2, characterized by, The calculation of the adjustment amount of the acupoint stimulation parameter based on the physiological index data through the PID controller comprises: Calculating a deviation value based on the physiological index data and the standard physiological index data; Real-time correcting the proportional coefficient, integral coefficient, and differential coefficient of the PID controller based on the deviation value; Determining the total adjustment amount output by the PID controller based on the corrected proportional coefficient, integral coefficient, and differential coefficient and the deviation value; Based on the preset stimulation mode physiological index correlation matrix, the total adjustment amount is distributed as an electric stimulation intensity adjustment amount, a magnetic stimulation frequency adjustment amount, and a heat stimulation duration adjustment amount.

4. The renal bone disease diagnosis and treatment plan generation method according to claim 3, characterized by, The distribution of the total adjustment amount as an electric stimulation intensity adjustment amount, a magnetic stimulation frequency adjustment amount, and a heat stimulation duration adjustment amount based on the preset stimulation mode physiological index correlation matrix comprises: Obtaining the electric stimulation intensity adjustment amount according to the partial derivative of the preset physiological index data to the electric stimulation intensity, the total adjustment amount, and the electric stimulation weight coefficient; Obtaining the magnetic stimulation frequency adjustment amount according to the partial derivative of the preset physiological index data to the magnetic stimulation frequency, the total adjustment amount, and the magnetic stimulation weight coefficient; Obtaining the heat stimulation duration adjustment amount according to the partial derivative of the preset physiological index data to the heat stimulation duration, the total adjustment amount, and the heat stimulation weight coefficient; Wherein, the constraint condition is that the sum of the electric stimulation weight coefficient, the magnetic stimulation weight coefficient, and the heat stimulation weight coefficient is 1.

5. The renal bone disease diagnosis and treatment plan generation method according to claim 3 or 4, characterized by, The real-time correction of the proportional coefficient, integral coefficient, and differential coefficient of the PID controller based on the deviation value comprises: Calculating the deviation change rate based on the deviation value; According to the preset correction rule library, matching the proportional coefficient correction factor, integral coefficient correction factor, and differential coefficient correction factor corresponding to the deviation value and the deviation change rate; The proportional coefficient of the PID controller is corrected according to the proportional coefficient correction factor, the integral coefficient of the PID controller is corrected according to the integral coefficient correction factor, and the differential coefficient of the PID controller is corrected according to the differential coefficient correction factor.

6. The renal bone disease diagnosis and treatment plan generation method of claim 1, wherein, The obtaining of the acupoint position data of the target acupoint identifier on the human body image comprises: inputting the human body image into a pre-trained acupoint position deep learning identification model for identification to obtain a plurality of acupoint position data on the human body image and an acupoint identifier corresponding to each acupoint position data; matching the acupoint position data corresponding to the target acupoint identifier from the plurality of acupoint position data.

7. The renal bone disease diagnosis and treatment plan generation method of claim 1, wherein, The plurality of stimulation modes include radio frequency mode, electric stimulation mode, laser mode and ultrasonic mode, the acupoint stimulation device includes a first treatment head and a second treatment head, the first treatment head is configured to execute the radio frequency mode, the electric stimulation mode and the laser mode, and the second treatment head is configured to execute the ultrasonic mode.

8. A system for generating a diagnosis and treatment plan for renal osteodystrophy, running on an acupoint stimulation device, characterized in that, The renal osteopathy diagnosis and treatment scheme generation system comprises: a collection module for collecting clinical data related to renal osteopathy of a target object; an identification module for matching acupoint data corresponding to the clinical data based on a pre-constructed clinical data-acupoint data relationship database, the acupoint data including a target acupoint identifier and acupoint stimulation data corresponding to the target acupoint identifier; a positioning module for collecting a human body image of a target object and obtaining acupoint position data of the target acupoint identifier on the human body image; a generation module for generating an acupoint stimulation scheme of the acupoint stimulation device under a plurality of stimulation modes based on the acupoint position data and the acupoint stimulation data.

9. An acupoint stimulation device characterized by comprising: The acupoint stimulation device comprises a double treatment head, a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the steps of the renal osteopathy diagnosis and treatment scheme generation method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by the processor to implement the steps of the renal osteopathy diagnosis and treatment scheme generation method according to any one of claims 1 to 7.

Images