A data processing device for diabetic peripheral neuropathy

Abstract

The application provides a data processing device for diabetic peripheral neuropathy, comprising: acquiring basic information and current clinical symptom data of a user, wherein the clinical symptom data comprises image data, user symptom description and detection data; when it is determined that the current clinical symptom data indicates that the user has diabetic peripheral neuropathy, it is determined whether the same symptom as the clinical symptom data exists in a preset historical period of the user; if yes, the current clinical symptom data of the user and the clinical symptom data of the last same symptom are processed to determine the change of oxidative stress level; if it is determined that the change of the oxidative stress level is a downward trend, it is determined that the last user processing scheme is effective. The application determines the change of the oxidative stress level by using the current clinical symptom data of the user and the last clinical symptom data, so as to determine the adjustment processing scheme by adjusting the oxidative stress level.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a data processing device for diabetic peripheral neuropathy. Background Technology

[0002] Diabetic peripheral neuropathy (DPN) is the most common type of diabetic neuropathy and one of the most common chronic complications of diabetes. Specifically, it refers to the symptoms related to peripheral nerve dysfunction in diabetic patients after excluding other causes. Clinically, it manifests as symmetrical pain and paresthesia, with lower limb symptoms being more common than upper limb symptoms, thus affecting the quality of life.

[0003] Currently, the nervous system is often screened manually to determine the degree of diabetic peripheral neuropathy by identifying moderate to severe peripheral neuropathy affecting large nerve fibers. Then, a treatment plan is given based on the doctor's experience. However, due to the scarcity of highly experienced doctors, it is difficult to provide the optimal treatment plan. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a data processing device for diabetic peripheral neuropathy to solve the problem that the prior art cannot provide an optimal processing solution.

[0005] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0006] The first aspect of this invention discloses a data processing method for diabetic peripheral neuropathy, the method comprising:

[0007] Obtain the user's basic information and current clinical symptom data, including image data, user symptom descriptions, and test data;

[0008] When it is determined that the current clinical symptom data indicates that the user has diabetic peripheral neuropathy, it is determined whether the user has symptoms identical to the clinical symptom data within a preset historical time period;

[0009] If present, the changes in oxidative stress levels are determined by processing the user's current clinical symptom data and the clinical symptom data of the same symptoms in the previous instance.

[0010] If the change in the oxidative stress level is determined to be a downward trend, the previous user's treatment plan is deemed effective.

[0011] Optional, also includes:

[0012] If it is determined that the change in the oxidative stress level is not a downward trend, the user's current clinical symptom data, the previous clinical symptom data, and the previous treatment plan are input into a pre-built treatment model, and the user's current treatment plan is output and displayed; wherein, the treatment model is pre-trained based on the clinical symptom data and corresponding treatment plans of different simulated experimental subjects at different times.

[0013] Optionally, determining that the current clinical symptom data indicates the presence of diabetic peripheral neuropathy in the user includes:

[0014] The image data, user symptom descriptions, and detection data are input into a preset recognition model, which is trained based on image data, user symptom descriptions, and detection data from different historical users.

[0015] A preset recognition model processes the image data, user symptom descriptions, and detection data, and outputs the recognition results;

[0016] If the identification result indicates that the user has diabetic peripheral neuropathy, then the current clinical symptom data is determined to indicate that the user has diabetic peripheral neuropathy.

[0017] Optionally, determining the presence of symptoms identical to the clinical symptom data within the user's preset historical time period includes:

[0018] Based on the user's basic information, the database is traversed to check whether there is historical clinical symptom data within a preset historical time period.

[0019] If available, retrieve historical clinical symptom data within the user's preset historical time period;

[0020] Based on the symptom similarity between each historical clinical symptom data and the clinical symptom data, determine whether there are symptoms identical to those in the clinical symptom data within the user's preset historical time period;

[0021] If present, the process is performed to determine the change in oxidative stress level based on the user's current clinical symptom data and the previous clinical symptom data.

[0022] Optionally, based on the user's current clinical symptom data and previous clinical symptom data, the changes in oxidative stress levels are determined, including:

[0023] The first parameter value is determined by processing the user's current clinical symptom data.

[0024] The second parameter value is determined by processing the clinical symptom data of the previous identical symptoms.

[0025] The change in the corresponding oxidative stress level is determined based on the first parameter value and the second parameter value.

[0026] Optional, also includes:

[0027] If it is determined that there are no symptoms identical to the clinical symptom data within the user's preset historical time period, the current clinical symptom data and the clinical symptom data of other users of the same type as the user are processed to determine the user's current treatment plan.

[0028] Optionally, based on the current clinical symptom data and the clinical symptom data of other users of the same type as the user, the current treatment plan for the user is determined, including:

[0029] Based on the user's basic information and clinical symptom data, other users of the same type as the user are identified;

[0030] The current clinical symptom data and the clinical symptom data of other users of the same type as the user are input into a pre-built processing model, and the current processing plan for the user is output.

[0031] A second aspect of the present invention discloses a data processing apparatus for diabetic peripheral neuropathy, the apparatus comprising:

[0032] The acquisition unit is used to acquire the user's basic information and current clinical symptom data, including image data, user symptom descriptions, and detection data.

[0033] The determining unit is used to determine whether the user has symptoms identical to the clinical symptom data within a preset historical time period when the current clinical symptom data indicates that the user has diabetic peripheral neuropathy.

[0034] The processing unit is configured to, if present, process the user's current clinical symptom data and the clinical symptom data of the same symptoms in the previous instance to determine the change in oxidative stress level; if the change in oxidative stress level is determined to be a downward trend, the user's previous treatment plan is deemed effective.

[0035] Optionally, the processing unit is further configured to:

[0036] If it is determined that the change in the oxidative stress level is not a downward trend, the user's current clinical symptom data, the previous clinical symptom data, and the previous treatment plan are input into a pre-built treatment model, and the user's current treatment plan is output and displayed; wherein, the treatment model is pre-trained based on the clinical symptom data and corresponding treatment plans of different simulated experimental subjects at different times.

[0037] Optionally, the processing unit is further configured to:

[0038] If it is determined that there are no symptoms identical to the clinical symptom data within the user's preset historical time period, the current clinical symptom data and the clinical symptom data corresponding to other users of the same type as the user are processed to determine the user's current treatment plan;

[0039] Based on the above embodiments of the present invention, a data processing method and apparatus for diabetic peripheral neuropathy are provided. The method includes: acquiring basic information and current clinical symptom data of a user, wherein the clinical symptom data includes image data, user symptom descriptions, and detection data; when it is determined that the current clinical symptom data indicates that the user has diabetic peripheral neuropathy, determining whether the user has symptoms identical to the clinical symptom data within a preset historical time period; if so, processing based on the user's current clinical symptom data and the previous clinical symptom data of the same symptoms to determine the change in oxidative stress level; if it is determined that the change in oxidative stress level is a downward trend, determining that the previous treatment plan for the user was effective. In the embodiments of the present invention, the change in oxidative stress level is determined by the user's current clinical symptom data and the previous clinical symptom data, and the optimal treatment plan is determined by adjusting the oxidative stress level. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0041] Figure 1 This is a schematic diagram illustrating the interaction between the server and the user in an embodiment of the present invention.

[0042] Figure 2 This is a flowchart illustrating a data processing method for diabetic peripheral neuropathy according to an embodiment of the present invention.

[0043] Figure 3This is a schematic diagram of the architecture of a data processing device for diabetic peripheral neuropathy, as shown in an embodiment of the present invention. Detailed Implementation

[0044] 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 embodiments of the present invention, and not all embodiments. 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.

[0045] It should be noted that the descriptions involving "first," "second," etc., in this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0046] In this application, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0047] See Figure 1 This is a schematic diagram illustrating the interaction between the server and the user in an embodiment of the present invention.

[0048] The server 10 and the user terminal 20 are wirelessly connected.

[0049] Specifically, the user terminal 20 has a display interface and an input interface. The display interface is used to display the processing scheme sent by the server and the result of whether the scheme is effective. The input interface is used to receive input from the user terminal.

[0050] Server 10 is used to process the user's basic information and current clinical symptom data input by client 20.

[0051] Based on the server-side and user-side diagrams shown above, the specific data processing procedure for diabetic peripheral neuropathy is implemented, such as... Figure 2The diagram shown is a flowchart illustrating a data processing method for diabetic peripheral neuropathy according to an embodiment of the present invention, applied to a server. The method includes:

[0052] Step S201: Obtain the user's basic information and current clinical symptom data, including image data, user symptom descriptions, and test data.

[0053] Optionally, firstly, medical staff upload the user's basic information and current clinical symptom data through the user terminal. The clinical symptom data includes image data, user symptom descriptions, and test data. The user terminal receives the corresponding basic information and current clinical symptom data and sends them to the server so that the server can obtain them.

[0054] It should be noted that the image data includes images of the area surrounding nerve fibers, the user symptom description includes the user's name, age, and description of the condition, and the test data includes blood glucose levels, electromyography indicators, hemorheology, and serum oxidative stress indicators.

[0055] Step S202: Determine whether the current clinical symptom data indicates that the user has diabetic peripheral neuropathy. If it does, proceed to step S203. If it does not, display the result that there is no diabetic peripheral neuropathy on the user terminal.

[0056] The specific implementation process of step S202 includes:

[0057] S11: Input the image data, user symptom description and detection data into a preset recognition model, which is trained based on image data, user symptom description and detection data of different historical users;

[0058] Specifically, the process of training a pre-defined recognition model based on historical image data, user symptom descriptions, and detection data from different users includes:

[0059] The server collects image data, symptom descriptions, and detection data from different historical users with diabetic peripheral neuropathy, as well as image data, symptom descriptions, and detection data from diabetic users without diabetic peripheral neuropathy, and uses this as a sample set. The sample set is divided into a training set and a test set according to a preset ratio. During the generation process, the initial model is first trained using the divided training set. Then, the initial model is used to identify symptoms using the test set to obtain identification results. If the identification results are inconsistent with the symptoms indicated by the sample set, the initial model is trained again based on the training set until the identification results are consistent with the symptoms indicated by the sample set. Otherwise, the trained initial model is used as the preset identification model.

[0060] It should be noted that the identification results include whether the user has diabetic peripheral neuropathy or not.

[0061] The initial model was built based on existing neural network algorithms or deep learning algorithms.

[0062] The preset ratio is also pre-built, and can generally be set to 9:1, with 9 parts of the training set and 1 part of the test set.

[0063] S12: The preset recognition model processes the image data, user symptom description, and detection data, and outputs the recognition result;

[0064] In the specific implementation of step S12, the preset recognition model obtained in step S11 is used to process the current clinical symptom data input by the user to obtain the recognition result.

[0065] S13: Determine whether the identification result indicates that the user has diabetic peripheral neuropathy. If yes, execute S14; otherwise, display the result that there is no diabetic peripheral neuropathy on the user terminal.

[0066] S14: Determine that the current clinical symptom data indicates that the user has diabetic peripheral neuropathy.

[0067] Step S203: Determine whether there are symptoms identical to the clinical symptom data within the user's preset historical time period. If there are, proceed to step S204; otherwise, proceed to step S208.

[0068] The specific implementation of step S203 includes the following steps:

[0069] S21: Based on the user's basic information, traverse the database to see if there is historical clinical symptom data within a preset historical time period. If it exists, proceed to step S22; otherwise, proceed directly to step S207.

[0070] It should be noted that the database pre-stores historical clinical symptom data, basic user information, and consultation time for all current users of a particular hospital.

[0071] A user's basic information may include their ID, age, gender, blood type, and phone number.

[0072] Specifically, each historical clinical symptom data in the data is traversed according to the user's basic information to determine whether there is data that is the same as the current user's basic information. If it exists, step S22 is executed; if it does not exist, step S208 is executed directly.

[0073] S22: Obtain historical clinical symptom data within a user-preset historical time period;

[0074] It should be noted that historical clinical symptom data may be from one or multiple studies.

[0075] S23: Based on the symptom similarity between each historical clinical symptom data and the clinical symptom data, determine whether there are symptoms in the user's preset historical time period that are the same as those in the clinical symptom data. If there are, proceed to step S204; otherwise, proceed to step S208.

[0076] In the specific implementation of step S23, the symptom similarity between each historical clinical symptom data and the clinical symptom data is calculated respectively. It is determined whether the symptom similarity is greater than the preset similarity. If it is greater, it is determined that there is a symptom with the same clinical symptom data in the user's preset historical time period, and step S204 is executed. Otherwise, it indicates that there is no symptom with the same clinical symptom data in the user's preset historical time period, and step S208 is executed.

[0077] The symptom similarity between each historical clinical symptom data point and the clinical symptom data can be calculated using a model or directly.

[0078] Step S204: Based on the user's current clinical symptom data and the previous clinical symptom data, process the data to determine the change in oxidative stress level.

[0079] It should be noted that the specific implementation of step S204 includes the following steps:

[0080] Step S31: Process the user's current clinical symptom data to determine the first parameter value.

[0081] The first parameter values ​​include those for malondialdehyde (MDA), superoxide dismutase (SOD), and total antioxidant capacity (T-AOC) as determined by enzyme-linked immunosorbent assay (ELISA).

[0082] Among them, MDA is an indicator that reflects the severity of lipid peroxidation in the body, SOD can reflect the body's antioxidant level, and T-AOC can reflect both the functional status of the body's antioxidant system and the activity of antioxidant enzymes, indirectly reflecting the degree of lipid peroxidation damage. In other words, the user's oxidative stress level can be determined by the values ​​of MDA, SOD and T-AOC.

[0083] In one embodiment, the current clinical symptom data is input into a serum analyzer to detect the values ​​of MDA, SOD, and T-AOC in the current clinical symptom data using enzyme-linked immunosorbent assay (ELISA).

[0084] In another embodiment, the current clinical symptom data is input into the detection model so that the detection model processes the current clinical symptom data to obtain the values ​​of MDA, SOD and T-AOC.

[0085] It should be noted that the detection model was trained based on historical clinical symptom data and the corresponding values ​​of MDA, SOD and T-AOC.

[0086] S32: Based on the clinical symptom data of the previous identical symptoms, process the data to determine the value of the second parameter.

[0087] It should be noted that the specific implementation process of step S32 is the same as that of step S31 and they can be referred to each other.

[0088] The second parameter value includes the values ​​of MDA, SOD, and T-AOC.

[0089] S33: Determine the corresponding change in oxidative stress level based on the first parameter value and the second parameter value.

[0090] In the specific implementation step S33, the first difference between MDA in the first parameter value and MDA in the second parameter value is calculated; the second difference between SOD in the first parameter value and SOD in the second parameter value is calculated; the third difference between T-AOC in the first parameter value and T-AOC in the second parameter value is calculated; and the first difference, the second difference, and the third difference are used as changes in oxidative stress level.

[0091] Step S205: Determine whether the change in the oxidative stress level is a downward trend. If it is determined that the change in the oxidative stress level is a downward trend, proceed to step S206; otherwise, proceed to step S207.

[0092] In the specific implementation of step S205, firstly, it is determined whether the first difference, the second difference, and the third difference are all negative. If at least two are negative, the change in the oxidative stress level is a downward trend, and step S206 is executed. Otherwise, it is not a downward trend, and step S207 is executed.

[0093] Step S206: Determine that the previous user's processing plan was valid.

[0094] It should be noted that the treatment plan is a diagnostic and treatment plan, which generally involves acupuncture at acupoints such as Hegu, Sanyinjiao, Xuehai, Fenglong, Quchi, Zusanli, Taixi, and Yongquan, using acupuncture treatment.

[0095] In the specific implementation of step S206, after determining that the previous user's treatment plan was effective, the previous user's treatment plan is used as the current treatment plan so that the previous user's treatment plan can be used again to continue treating the user.

[0096] Step S207: Based on the user's current clinical symptom data, the previous clinical symptom data, and the previous treatment plan for the user, input the pre-built treatment model, output the current user's treatment plan, and display it.

[0097] The processing model is pre-trained based on clinical symptom data of different simulated experimental subjects at different times and corresponding treatment plans.

[0098] Specifically, the server collects clinical symptom data and corresponding treatment plans from different simulated experimental subjects at different times in real time and uses them as a sample set. The preset algorithm is trained using the sample set to build an initial model. Then, a clinical symptom data from the sample set, its corresponding previous clinical symptom data, and the previous user's treatment plan are input into the pre-built treatment model to output the current user's treatment plan. If the treatment plan is consistent with the current treatment plan in the sample set, training is considered complete, and the trained initial model is used as the treatment model. If the treatment plan is inconsistent with the current treatment plan in the sample set, the initial model continues to be trained based on the sample set until training is complete.

[0099] It should be noted that the subjects of the simulation experiment were the experimental group of users with diabetic peripheral neuropathy.

[0100] In the specific implementation step S207, the processing model obtained from the above training is used to process the previous clinical symptom data and the previous user's treatment plan to obtain the current user's treatment plan, which is then displayed to the user through the user terminal.

[0101] Step S208: Based on the current clinical symptom data and the clinical symptom data of other users of the same type as the user, process the data to determine the current treatment plan for the user.

[0102] It should be noted that the specific implementation of step S208 includes the following steps:

[0103] S41: Based on the user's basic information and the clinical symptom data, identify other users of the same type as the user.

[0104] It should be noted that the user type is pre-classified based on the user's basic information and the clinical symptom data. For example, users who all have the same complication of diabetic peripheral neuropathy and are of similar age, gender and blood type are classified as the same type.

[0105] Other users can be either simulated users or real users. In other words, if they are simulated users, the effects of different processing schemes on this type of user can be simulated through simulation experiments, and the processing method with the highest effect can be recorded.

[0106] In the specific implementation step S41, other users of the same type as the user are searched in the data.

[0107] S42: Input the current clinical symptom data and the clinical symptom data of other users of the same type as the user into the pre-built processing model, and output the current processing plan for the user.

[0108] It should be noted that the pre-built processing model can also be trained using clinical symptom data of similar users and corresponding treatment plans.

[0109] The specific implementation process of step S42 is the same as that of step S207 described above, and they can be referred to each other.

[0110] In this embodiment of the invention, when it is determined that the current clinical symptom data indicates that the user has diabetic peripheral neuropathy, and the user has symptoms that are the same as the clinical symptom data within a preset historical time period, the change in oxidative stress level is determined by the user's current clinical symptom data and the previous clinical symptom data, so as to determine the adjustment treatment plan by adjusting the oxidative stress level.

[0111] Optionally, based on the data processing method for diabetic peripheral neuropathy according to embodiments of the present invention, the present invention also discloses a data processing device for diabetic peripheral neuropathy, such as... Figure 3 As shown, the device includes:

[0112] The acquisition unit 301 is used to acquire the user's basic information and current clinical symptom data, wherein the clinical symptom data includes image data, user symptom description and detection data;

[0113] The determining unit 302 is used to determine whether the same symptoms as the clinical symptom data exist in the user within a preset historical time period when the current clinical symptom data indicates that the user has diabetic peripheral neuropathy.

[0114] The processing unit 303 is used to, if present, process the user's current clinical symptom data and the clinical symptom data of the same symptoms in the previous instance to determine the change in oxidative stress level; if the change in oxidative stress level is determined to be a downward trend, the user's previous treatment plan is determined to be effective.

[0115] The specific principles and execution processes of each unit in the data processing system for diabetic peripheral neuropathy disclosed in the above embodiments of the present invention are the same as the corresponding contents in the data processing method for diabetic peripheral neuropathy provided in the above embodiments of the present invention. Please refer to the corresponding parts in the data processing method for diabetic peripheral neuropathy disclosed in the above embodiments of the present invention, and they will not be repeated here.

[0116] In this embodiment of the invention, when it is determined that the current clinical symptom data indicates that the user has diabetic peripheral neuropathy, and the user has symptoms that are the same as the clinical symptom data within a preset historical time period, the change in oxidative stress level is determined by the user's current clinical symptom data and the previous clinical symptom data, so as to determine the adjustment treatment plan by adjusting the oxidative stress level.

[0117] Optionally, the processing unit is further configured to:

[0118] If it is determined that the change in the oxidative stress level is not a downward trend, the user's current clinical symptom data, the previous clinical symptom data, and the previous treatment plan are input into a pre-built treatment model, and the user's current treatment plan is output and displayed; wherein, the treatment model is pre-trained based on the clinical symptom data and corresponding treatment plans of different simulated experimental subjects at different times.

[0119] Optionally, the processing unit is further configured to:

[0120] If it is determined that there are no symptoms identical to the clinical symptom data within the user's preset historical time period, the current clinical symptom data and the clinical symptom data of other users of the same type as the user are processed to determine the user's current treatment plan.

[0121] The process involves processing the current clinical symptom data and the clinical symptom data of other users of the same type as the user to determine the user's current treatment plan, including:

[0122] Based on the user's basic information and clinical symptom data, other users of the same type as the user are identified;

[0123] The current clinical symptom data and the clinical symptom data of other users of the same type as the user are input into a pre-built processing model, and the current processing plan for the user is output.

[0124] Optionally, the determining unit that identifies the current clinical symptom data as indicating diabetic peripheral neuropathy is specifically used for:

[0125] The image data, user symptom descriptions, and detection data are input into a preset recognition model, which is trained based on image data, user symptom descriptions, and detection data from different historical users.

[0126] A preset recognition model processes the image data, user symptom descriptions, and detection data, and outputs the recognition results;

[0127] If the identification result indicates that the user has diabetic peripheral neuropathy, then the current clinical symptom data is determined to indicate that the user has diabetic peripheral neuropathy.

[0128] Optionally, the unit for determining whether symptoms identical to the clinical symptom data exist within the user's preset historical time period is specifically used for:

[0129] Based on the user's basic information, the database is traversed to check whether there is historical clinical symptom data within a preset historical time period.

[0130] If available, retrieve historical clinical symptom data within the user's preset historical time period;

[0131] Based on the symptom similarity between each historical clinical symptom data and the clinical symptom data, determine whether there are symptoms identical to those in the clinical symptom data within the user's preset historical time period;

[0132] If present, the process is performed to determine the change in oxidative stress level based on the user's current clinical symptom data and the previous clinical symptom data.

[0133] Optionally, a processing unit that determines changes in oxidative stress levels based on the user's current clinical symptom data and previous clinical symptom data is specifically used for:

[0134] The first parameter value is determined by processing the user's current clinical symptom data.

[0135] The second parameter value is determined by processing the clinical symptom data of the previous identical symptoms.

[0136] The change in the corresponding oxidative stress level is determined based on the first parameter value and the second parameter value.

[0137] This application also provides a data processing system for diabetic peripheral neuropathy. The system includes a processor and a memory. The memory is used to store program code and data for data processing of diabetic peripheral neuropathy. The processor is used to call the program instructions in the memory to execute the data processing method for diabetic peripheral neuropathy as shown in the above embodiments.

[0138] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A data processing device for diabetic peripheral neuropathy, characterized in that, The device includes: The acquisition unit is used to acquire the user's basic information and current clinical symptom data. The clinical symptom data includes image data, user symptom descriptions, and detection data. The detection data includes blood glucose levels, electromyography indicators, hemorheology, and serum oxidative stress indicators. A determining unit is configured to input the image data, user symptom description, and detection data into a preset recognition model, which is trained based on historical image data, user symptom description, and detection data of different users; the preset recognition model processes the image data, user symptom description, and detection data, and outputs a recognition result; if the recognition result indicates that the user has diabetic peripheral neuropathy, the current clinical symptom data is determined to indicate that the user has diabetic peripheral neuropathy; based on the user's basic information, the system iterates through the database to check if there is historical clinical symptom data within a preset historical time period; if so, it obtains the user's historical clinical symptom data within the preset historical time period; based on the symptom similarity between each historical clinical symptom data and the clinical symptom data, it determines whether there are symptoms identical to the clinical symptom data within the user's preset historical time period. The processing unit is configured to, if present, process the user's current clinical symptom data to determine a first parameter value, the first parameter value including the values ​​of malondialdehyde (MDA), superoxide dismutase (SOD), and total antioxidant capacity (T-AOC) detected by enzyme-linked immunosorbent assay (ELISA); process the user's previous clinical symptom data to determine a second parameter value, the second parameter value including the values ​​of MDA, SOD, and T-AOC; calculate a first difference between the MDA values ​​in the first parameter value and the MDA values ​​in the second parameter value; calculate a second difference between the SOD values ​​in the first parameter value and the SOD values ​​in the second parameter value; calculate a third difference between the T-AOC values ​​in the first parameter value and the T-AOC values ​​in the second parameter value; use the first difference, the second difference, and the third difference as changes in oxidative stress levels; if the changes in oxidative stress levels are determined to be a downward trend, the user's previous treatment plan is deemed effective.

2. The apparatus according to claim 1, characterized in that, The processing unit is further configured to: If it is determined that the change in the oxidative stress level is not a downward trend, the user's current clinical symptom data, the previous clinical symptom data, and the previous treatment plan are input into a pre-built treatment model, and the user's current treatment plan is output and displayed; wherein, the treatment model is pre-trained based on the clinical symptom data and corresponding treatment plans of different simulated experimental subjects at different times.

3. The apparatus according to claim 1, characterized in that, The processing unit is further configured to: If it is determined that there are no symptoms identical to the clinical symptom data within the user's preset historical time period, the current clinical symptom data and the clinical symptom data corresponding to other users of the same type as the user are processed to determine the user's current treatment plan; The process involves processing the current clinical symptom data and the clinical symptom data of other users of the same type as the user to determine the user's current treatment plan, including: Based on the user's basic information and clinical symptom data, other users of the same type as the user are identified; The current clinical symptom data and the clinical symptom data of other users of the same type as the user are input into a pre-built processing model, and the current processing plan for the user is output.

Images