Tibia auxiliary reduction evaluation method and system based on big data

Abstract

The invention relates to the technical field of medical evaluation, in particular to a tibia auxiliary reduction evaluation method and system based on big data. A tibia auxiliary reduction evaluation method based on big data comprises the following steps: S1, acquiring tibia daily monitoring data, and obtaining a tibia recovery score value by using a tibia recovery score value formula according to the tibia daily monitoring data; s2, performing preliminary detection on the tibia of the patient according to the tibia recovery score value; s3, acquiring real-time recovery data of the tibia of the patient, and inputting the real-time recovery data into the tibia recovery detection model to obtain a tibia recovery detection value; and S4, according to the tibia recovery score value and the tibia recovery detection value, obtaining a stage score value of the patient by using a stage score formula. According to the method, the daily monitoring data and the real-time recovery data of the tibia of the patient are quantitatively analyzed by adopting the tibia recovery scoring formula and the hidden monitoring formula, so that the accuracy and the scientificity of diagnosis are improved.

Description

Technical Field

[0001] The present invention relates to the field of medical assessment technology, and in particular to a tibial auxiliary reduction assessment method and system based on big data. Background Art

[0002] The tibia is the thicker and longer of the two bones in the human lower leg. The other thinner one is the fibula located on the inner side of the lower leg. The tibia plays a vital role in activities such as walking, running and jumping. Currently, in the field of tibial assisted reduction evaluation, traditional technology mainly relies on imaging examinations and subjective judgment of clinicians based on rich experience to judge the effect of tibial reduction. This method has the following shortcomings: single data source and incomplete information. The existing technology mainly relies on static imaging data, while the multi-dimensional dynamic data such as the patient's tibia usage and walking status in daily life has not been fully collected, resulting in limitations in the monitoring and evaluation of tibial recovery status; the problem of patient behavior interference. During the test, due to the patient's fear of pain, the patient will deliberately reduce or cover up activities to reduce the discomfort during the test. This behavior will affect the authenticity of the test data, and thus affect the objectivity and accuracy of the evaluation results. Summary of the invention

[0003] In order to overcome the shortcoming that the detection and evaluation results are inaccurate due to patients' fear of pain, the present invention provides a tibial assisted reduction evaluation method and system based on big data.

[0004] The technical solution is as follows: A tibial assisted reduction evaluation method based on big data, comprising the following steps:

[0005] S1: acquiring daily tibia monitoring data, and using a tibia recovery score formula according to the daily tibia monitoring data to obtain a tibia recovery score;

[0006] S2: performing a preliminary test on the patient's tibia according to the tibia recovery score;

[0007] S3: acquiring real-time recovery data of the patient's tibia, and inputting the real-time recovery data into a tibia recovery detection model to obtain a tibia recovery detection value;

[0008] S4: obtaining a stage score value of the patient using a stage score formula according to the tibial recovery score value and the tibial recovery detection value;

[0009] S5: Obtain the historical medical data of each doctor, and select an appropriate doctor to assist the patient in repositioning according to the historical medical data of each doctor and the stage score of the patient.

[0010] Preferably, the daily tibia monitoring data is obtained, and the tibia recovery score value formula is used according to the daily tibia monitoring data to obtain the tibia recovery score value, including: the daily tibia monitoring data includes the number of times the affected side of the tibia is used, the standard number of times the affected side of the tibia is used, and the number of stress errors, and the number of stress errors is the number of abnormal reflexes within a preset time period when the patient encounters sudden things; wherein the tibia recovery score value formula is:

[0011]

[0012] Where Q is the tibial recovery score; T is the number of times the affected side of the tibia is used; T 0 k is the standard number of times used on the affected side of the tibia; 2 is the daily walking height data; k is the patient's standard walking height data; P is the hidden value; x is the number of stress errors; α 1 , α 2 , α 3 , β 1 , β 2 is the adjustment factor.

[0013] Preferably, P is a hidden value, including: obtaining the patient's daily walking data, the daily walking data including the patient's daily walking height and amplitude data, the test walking height and amplitude data and the patient's standard walking height and amplitude data, inputting the daily walking data into a hidden monitoring formula to obtain a hidden value, the daily walking height and amplitude data is data collected after the test walking height and amplitude data, wherein the hidden monitoring formula is:

[0014] P=[max(k 0 , k 2 -k 1 )-k 0 ]*|k 2 -k|;

[0015] Where P is the hidden value; k 0 k is the amplitude fluctuation tolerance value; 2 The height data of daily walking; k 1 is the test walking height and amplitude data; k is the patient's standard walking height and amplitude data.

[0016] Preferably, the preliminary detection of the patient's tibia based on the tibia recovery score value includes: when the tibia recovery score value is greater than or equal to a first preset threshold, notifying relevant medical staff to conduct a quick and comprehensive diagnosis; when the tibia recovery score value is greater than a second preset threshold and less than the first preset threshold, obtaining real-time recovery data of the patient's tibia, and inputting the real-time recovery data into a tibia recovery detection model to obtain a tibia recovery detection value; when the tibia recovery score value is less than or equal to the second preset threshold, continuing to monitor the patient.

[0017] Preferably, the real-time recovery data of the patient's tibia is obtained, and the real-time recovery data is input into a tibia recovery detection model to obtain a tibia recovery detection value, including: the real-time recovery data contains the patient's tibia offset angle, tibia rotation angle and tibia biomechanical data, the tibia biomechanical data contains the patient's step length, step frequency, step speed, plantar pressure distribution data and tibia micro-vibration spectrum and damping coefficient collected by a bone conduction sensor; the tibia offset angle is the angle between the longitudinal growth direction of the tibia and the standard growth direction; the tibia rotation angle is the angle between the lateral torsion angle of the tibia and the standard angle; the real-time recovery data is input into the tibia recovery detection model trained by the CNN model to obtain the tibia recovery detection value.

[0018] Preferably, the step of obtaining the patient's stage score value using a stage score formula according to the tibia recovery score value and the tibia recovery detection value comprises: wherein the stage score formula is:

[0019] M=γ 1 *Q+γ 2 *Z;

[0020] Where M is the patient's stage score; Q is the tibial recovery score; Z is the tibial recovery test value; γ 1 , γ 2 is the adjustment factor.

[0021] Preferably, the method of obtaining the historical medical data of each doctor and selecting an appropriate doctor to perform auxiliary reduction on the patient according to the historical medical data of each doctor and the stage score of the patient includes: obtaining the historical medical data of each doctor, the historical medical data of each doctor including the number of tibia treatments for different affected sides handled by each doctor, the total number of tibia treatments and the most recent time interval between each doctor's treatment of each affected side tibia, and obtaining the most recent time interval between each doctor's treatment of the tibia through the most recent time interval between each doctor's treatment of each affected side tibia; obtaining the first matching value or the second matching value of each doctor using the first matching formula or the second matching formula according to the historical medical data of each doctor and the stage score of the patient, and selecting an appropriate doctor according to the first matching value or the second matching value of each doctor.

[0022] Preferably, the method of using the first matching formula or the second matching formula according to the historical medical data of each doctor and the stage score value of the patient to obtain the first matching value or the second matching value of each doctor, and selecting an adapted doctor according to the first matching value or the second matching value of each doctor, includes: when the stage score value is greater than or equal to a third preset threshold, using the first matching formula to obtain the first matching value, and selecting an adapted doctor according to the first matching value, wherein the first matching formula is:

[0023]

[0024] Where N 1 is the first matching value; T i The time interval between the last time the doctor treated the same tibia as the patient; Num i The number of tibia treatments performed by the physician on the same tibia as the patient; 1 , δ 2 , δ 3 is the adjustment factor.

[0025] Preferably, the first matching formula or the second matching formula is used according to the historical medical data of each doctor and the stage score value of the patient to obtain the first matching value or the second matching value of each doctor, and the matching doctor is selected according to the first matching value or the second matching value of each doctor, including: when the stage score value is greater than or equal to the fourth preset threshold and less than the third preset threshold, the second matching formula is used to obtain the second matching value, and the matching doctor is selected according to the second matching value, wherein the second matching formula is:

[0026]

[0027] Where N 2 is the second matching value; T a The time interval between the last time the doctor treated the tibia; Num a The total number of tibia treatments performed by the physician; 1 , ε 2 , ε 3 is the adjustment factor.

[0028] Preferably, a tibial assisted reduction evaluation system based on big data further includes:

[0029] A tibia recovery score value acquisition module is used to acquire daily tibia monitoring data, and use a tibia recovery score value formula according to the daily tibia monitoring data to obtain a tibia recovery score value;

[0030] A hidden value acquisition module, used for inputting the daily walking data into a hidden monitoring formula to obtain a hidden value;

[0031] A detection module, used for performing a preliminary detection of the patient's tibia according to the tibia recovery score;

[0032] A tibia recovery detection value acquisition module is used to acquire real-time recovery data of the patient's tibia, and input the real-time recovery data into a tibia recovery detection model to obtain a tibia recovery detection value;

[0033] A stage score value acquisition module, used to obtain the patient's stage score value using a stage score formula according to the tibia recovery score value and the tibia recovery detection value;

[0034] The doctor matching and intelligent selection module is used to obtain the historical medical data of each doctor, and select an appropriate doctor to assist the patient in repositioning according to the historical medical data of each doctor and the stage score value of the patient.

[0035] The present invention has the following advantages:

[0036] 1. The present invention adopts the tibia recovery scoring formula and the hidden monitoring formula to quantitatively analyze the daily monitoring data and real-time recovery data of the patient's tibia, monitor the patient's claudication phenomenon and significantly reduce the error caused by subjective judgment, and conduct a comprehensive assessment based on the problem that the patient deliberately hides the real symptoms or deliberately reduces activities during the test due to fear, as well as the problem of monitoring intermittent claudication;

[0037] 2. The present invention realizes all-round monitoring of the tibial reduction state by collecting multi-dimensional data including the deviation angle of the patient's tibia, the rotation angle of the tibia and the biomechanical data of the tibia, and using data preprocessing, fusion and deep learning (CNN) model for real-time detection;

[0038] 3. Through automated data collection, real-time calculation and intelligent doctor matching, the present invention can complete the evaluation of tibial reduction status in a relatively short time and quickly select the most suitable doctor for treatment, which significantly shortens the diagnosis and treatment cycle and improves emergency response capabilities;

[0039] 4. The present invention uses the first matching formula and the second matching formula, and combines the patient's stage score value to scientifically select the physician who is most suitable for handling the current case and provide the patient with a personalized repositioning treatment plan, thereby further improving the treatment success rate and patient satisfaction, while optimizing doctor resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a flow chart of a tibial assisted reduction evaluation method based on big data of the present invention;

[0041] Figure 2 This is a schematic diagram of a module of a tibial assisted reduction evaluation system based on big data in the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] Example 1: A tibial assisted reduction evaluation method based on big data, such as Figure 1 As shown, the following steps are included:

[0044] S1: acquiring daily tibia monitoring data, and using a tibia recovery score formula according to the daily tibia monitoring data to obtain a tibia recovery score;

[0045] The daily tibia monitoring data includes the number of times the affected side of the tibia is used, the standard number of times the affected side of the tibia is used, and the number of stress errors. The number of stress errors is the number of abnormal reflexes within a preset time period when the patient encounters sudden things; the tibia recovery score value formula is:

[0046] Q=β 1 e α1(k2-k)+α2|T-T0|+α3x +β 2 (e+1) P ;

[0047] Where Q is the tibial recovery score; T is the number of times the affected side of the tibia is used; T 0 k is the standard number of times used on the affected side of the tibia; 2 is the daily walking height data; k is the patient's standard walking height data; P is the hidden value; x is the number of stress errors; α 1 , α 2 , α 3 , β 1 , β 2 is the adjustment factor.

[0048] It should be noted that in the embodiment, a dedicated sensor and a monitoring device are configured to obtain daily monitoring data of the patient's tibia, T is the number of times the affected side of the tibia is used, and the total number of times the affected side of the tibia actually participates in exercise in daily activities is recorded. The affected side is the injured tibia of the patient's left leg or the injured tibia of the right leg; T 0is the standard number of uses of the affected side of the tibia, which refers to the normal number of uses of the tibia preset according to the patient's basic physiological indicators and standard activity level; x is the number of stress errors, which is the number of times the affected leg cannot quickly make reflex adjustments when encountering obstacles. It is used to show that neuromuscular control has not been restored, that is, abnormal tibial force line affects proprioception; by judging the deviation between the patient's daily walking height and amplitude data and the patient's standard walking height and amplitude data, it reflects whether the patient deliberately hides the true condition or intermittent claudication due to fear of pain, and whether the patient has normal gait in the initial stage of walking but abnormal gait due to fatigue in the later stage.

[0049] The patient's daily walking data is obtained, and the daily walking data includes the patient's daily walking height and amplitude data, the test walking height and amplitude data, and the patient's standard walking height and amplitude data. The daily walking data is input into the hidden monitoring formula to obtain a hidden value. The daily walking height and amplitude data is the data collected after the test walking height and amplitude data, wherein the hidden monitoring formula is:

[0050] P=[max(k 0 , k 2 -k 1 )-k 0 ]*|k 2 -k|;

[0051] Where P is the hidden value; k 0 k is the amplitude fluctuation tolerance value; 2 The height data of daily walking; k 1 is the test walking height and amplitude data; k is the patient's standard walking height and amplitude data.

[0052] It should be noted that k 2 For daily walking height data, the patient's tibial motion range is collected using daily wearable sensors; k 1 To test the walking height data, it is the patient's tibial movement data collected under the doctor's test, which is used to compare with daily data and reveal the activity masking or reduction phenomenon in the test process; k is the patient's standard walking height data, which is the reference data preset according to the patient's physiological characteristics and standard movement patterns.

[0053] S2: performing a preliminary test on the patient's tibia according to the tibia recovery score;

[0054] When the tibial recovery score value is greater than or equal to a first preset threshold, notify relevant medical staff to conduct a quick and comprehensive diagnosis; when the tibial recovery score value is greater than a second preset threshold and less than the first preset threshold, obtain the real-time recovery data of the patient's tibia, and input the real-time recovery data into the tibial recovery detection model to obtain a tibial recovery detection value; when the tibial recovery score value is less than or equal to the second preset threshold, continue to monitor the patient.

[0055] It should be noted that when the tibial recovery score value is greater than or equal to the first preset threshold value, indicating that there is a serious abnormality or reduction in the patient's tibia, an early warning notification is immediately and automatically sent to the relevant medical staff, requiring them to conduct a quick and comprehensive diagnosis. The notification content includes the patient's tibial recovery score value, relevant historical data and risk warnings, aiming to enable medical staff to take further intervention measures in the shortest time; when the tibial recovery score value is greater than the second preset threshold value and less than the first preset threshold value, it is determined that the patient's tibial status is in the intermediate risk range, which is not enough to trigger a comprehensive emergency diagnosis, but still requires further refined evaluation, and the real-time recovery data of the patient's tibia is automatically obtained and input into a pre-trained tibial recovery detection model (the model is trained using the CNN method in deep learning), and the tibial recovery detection value is obtained after model calculation; when the tibial recovery score value is less than or equal to the second preset threshold value, the patient's tibial recovery status is in a normal or low-risk state, and the patient continues to be monitored periodically or continuously.

[0056] S3: acquiring real-time recovery data of the patient's tibia, and inputting the real-time recovery data into a tibia recovery detection model to obtain a tibia recovery detection value;

[0057] The real-time recovery data includes the patient's tibia offset angle, tibia rotation angle and tibia biomechanical data, the tibia biomechanical data includes the patient's step length, step frequency, step speed, plantar pressure distribution data and tibia micro-vibration spectrum and damping coefficient collected by the bone conduction sensor; the tibia offset angle is the angle between the longitudinal growth direction of the tibia and the standard growth direction; the tibia rotation angle is the angle between the lateral torsion angle of the tibia and the standard angle; the real-time recovery data is input into the tibia recovery detection model trained by the CNN model to obtain the tibia recovery detection value.

[0058] It should be noted that the deviation angle of the patient's tibia represents the angle between the longitudinal growth direction of the patient's tibia and the standard growth direction, which is used to reflect the deviation of the tibia during the growth process; the rotation angle of the tibia, the difference between the lateral torsion angle of the tibia and the standard angle, can reveal whether there is abnormal torsion of the tibia during the rotation process; the biomechanical data of the tibia is further subdivided into the patient's stride length, stride frequency, stride speed, plantar pressure distribution data, and tibial micro-vibration spectrum and damping coefficient collected by the bone conduction sensor. These data comprehensively reflect the dynamic biomechanical characteristics of the patient during walking and exercise, and provide a multi-dimensional quantitative basis for tibial recovery detection. After noise filtering, data correction and unified format preprocessing, the above data are input into the tibial recovery detection model trained by the CNN model to obtain the tibial recovery detection value.

[0059] S4: obtaining a stage score value of the patient using a stage score formula according to the tibial recovery score value and the tibial recovery detection value;

[0060] The stage scoring formula is:

[0061] M=γ 1 *Q+γ 2 *Z;

[0062] Where M is the patient's stage score; Q is the tibial recovery score; Z is the tibial recovery test value; γ 1 , γ 2 is the adjustment factor.

[0063] It should be noted that Q is the tibial recovery score, which reflects the overall level of tibial recovery of the patient under daily conditions; Z is the tibial recovery detection value, which reflects the dynamic changes of tibial status during real-time monitoring; the patient's stage score is obtained by weighted summation and is used for the formulation of subsequent treatment plans and doctor matching decisions.

[0064] S5: Obtain the historical medical data of each doctor, and select an appropriate doctor to assist the patient in repositioning according to the historical medical data of each doctor and the stage score of the patient.

[0065] Acquire the historical medical data of each doctor, wherein the historical medical data of each doctor includes the number of tibia treatments for different affected sides handled by each doctor, the total number of tibia treatments and the most recent time interval for each doctor to treat the tibia on each affected side, and obtain the most recent time interval for each doctor to treat the tibia through the most recent time interval for each doctor to treat the tibia on each affected side; use the first matching formula or the second matching formula according to the historical medical data of each doctor and the stage score value of the patient to obtain the first matching value or the second matching value of each doctor, and select an adapted doctor according to the first matching value or the second matching value of each doctor.

[0066] It should be noted that the number of tibia treatments on different affected sides by each doctor reflects the doctor's actual treatment experience in treating the tibia of the left or right leg; the total number of tibia medical treatments indicates the total number of treatments performed by the doctor in the field of tibia treatment, and is an important indicator for measuring the doctor's overall treatment level; the most recent time interval between each doctor's treatment of each affected side of the tibia, that is, the interval between the last time the doctor treated the left leg tibia and the present time, or the interval between the last time the doctor treated the right leg tibia and the present time; the most recent time interval between each doctor's treatment of the tibia, that is, the shortest time interval between the last time the doctor treated the left leg tibia and the present time and the last time the doctor treated the right leg tibia and the present time; when the patient's stage score value is in the high-risk stage, the first matching formula is used to calculate the first matching value of each doctor; when the patient's stage score value is in the low-risk or intermediate stage, the second matching formula is used to calculate the second matching value of each doctor, wherein the third preset threshold is greater than the fourth preset threshold.

[0067] When the stage score value is greater than or equal to the third preset threshold, a first matching value is obtained using a first matching formula, and a matching doctor is selected according to the first matching value, wherein the first matching formula is:

[0068]

[0069] Where N 1 is the first matching value; T i The time interval between the last time the doctor treated the same tibia as the patient; Num i The number of tibia treatments performed by the physician on the same tibia as the patient; 1 , δ 2 , δ 3 is the adjustment factor.

[0070] It should be noted that T i The most recent time interval when the doctor treated the same tibia as the patient. For example, if the patient's tibia is the left leg tibia, the most recent time interval when the doctor treated the left leg tibia is obtained; Num i The number of tibial treatments the doctor has performed on the same affected tibia as the patient. For example, if the patient's affected tibia is the damaged tibia of the left leg, the number of tibial treatments the doctor has performed on the left leg tibia is obtained. After obtaining the first matching value, the doctors are sorted from large to small according to their first matching values, and matched in order from large to small to ensure that a doctor with high efficiency and rich experience in treating the same affected tibia is selected, thereby improving the success rate of auxiliary reduction treatment.

[0071] When the stage score value is greater than or equal to the fourth preset threshold and less than the third preset threshold, a second matching value is obtained using a second matching formula, and a matching doctor is selected according to the second matching value, wherein the second matching formula is:

[0072]

[0073] Where N 2 is the second matching value; T a The time interval between the last time the doctor treated the tibia; Num a The total number of tibia treatments performed by the physician; 1 , ε 2 , ε 3 is the adjustment factor.

[0074] It should be noted that T a The time interval for the doctor to treat the tibia most recently. At this time, the most recent time interval will not distinguish between the left and right legs, and directly obtain the time interval for the most recent treatment of the tibia; Num a is the total number of tibia treatments performed by the doctor, and is the total number of times the doctor has treated all tibias; when the stage score value is greater than or equal to the fourth preset threshold and less than the third preset threshold, it indicates that the patient is at medium risk. At this time, the selection of a doctor should focus on overall treatment experience and the overall allocation of medical resources.

[0075] Embodiment 2: Based on Embodiment 1, a tibial assisted reduction evaluation system based on big data, such as Figure 2 As shown, it also includes:

[0076] A tibia recovery score value acquisition module is used to acquire daily tibia monitoring data, and use a tibia recovery score value formula according to the daily tibia monitoring data to obtain a tibia recovery score value;

[0077] A hidden value acquisition module, used for inputting the daily walking data into a hidden monitoring formula to obtain a hidden value;

[0078] A detection module, used for performing a preliminary detection of the patient's tibia according to the tibia recovery score;

[0079] A tibia recovery detection value acquisition module is used to acquire real-time recovery data of the patient's tibia, and input the real-time recovery data into a tibia recovery detection model to obtain a tibia recovery detection value;

[0080] A stage score value acquisition module, used to obtain the patient's stage score value using a stage score formula according to the tibia recovery score value and the tibia recovery detection value;

[0081] The doctor matching and intelligent selection module is used to obtain the historical medical data of each doctor, and select an appropriate doctor to assist the patient in repositioning according to the historical medical data of each doctor and the stage score value of the patient.

[0082] The above description is only an example of the present invention and is not intended to limit the present invention. Any equivalent substitutions made within the principles of the present invention should be included in the protection scope of the present invention. The contents not elaborated in detail in the present invention belong to the existing technologies known to those skilled in the art.

Claims

1. A tibial assisted reduction evaluation method based on big data, characterized in that: The following steps are involved: S1: acquiring daily tibia monitoring data, and using a tibia recovery score formula according to the daily tibia monitoring data to obtain a tibia recovery score; S2: performing a preliminary test on the patient's tibia according to the tibia recovery score; S3: acquiring real-time recovery data of the patient's tibia, and inputting the real-time recovery data into a tibia recovery detection model to obtain a tibia recovery detection value; S4: obtaining a stage score value of the patient using a stage score formula according to the tibial recovery score value and the tibial recovery detection value; S5: Obtain the historical medical data of each doctor, and select an appropriate doctor to assist the patient in repositioning according to the historical medical data of each doctor and the stage score of the patient.

2. The tibial assisted reduction evaluation method based on big data according to claim 1, characterized in that: The method of obtaining daily tibia monitoring data and using a tibia recovery score formula according to the daily tibia monitoring data to obtain a tibia recovery score includes: the daily tibia monitoring data includes the number of times the affected side of the tibia is used, the standard number of times the affected side of the tibia is used, and the number of stress errors, wherein the number of stress errors is the number of abnormal reflexes within a preset time period when the patient encounters sudden things; wherein the tibia recovery score formula is: Q=β1e α1(k2-k)+α2|T-T0|+α3x +β2(e+1) P ; Where, Q is the tibial recovery score; T is the number of times the affected side of the tibia is used; T0 is the standard number of times the affected side of the tibia is used; k2 is the daily walking height data; k is the patient's standard walking height data; P is the hidden value; x is the number of stress errors; α1, α2, α3, β1, and β2 are adjustment coefficients.

3. A tibial assisted reduction evaluation method based on big data according to claim 2, characterized in that: The P is a hidden value, including: obtaining the patient's daily walking data, the daily walking data includes the patient's daily walking height and amplitude data, the test walking height and amplitude data and the patient's standard walking height and amplitude data, and inputting the daily walking data into the hidden monitoring formula to obtain the hidden value, the daily walking height and amplitude data is the data collected after the test walking height and amplitude data, wherein the hidden monitoring formula is: P=[max(k0,k2-k1)-k0]*|k2-k|; In the formula, P is the hidden value; k0 is the amplitude fluctuation tolerance value; k2 is the daily walking height and low amplitude data; k1 is the test walking height and low amplitude data; k is the patient's standard walking height and low amplitude data.

4. The big data-based tibial assisted reduction evaluation method according to claim 1, characterized in that: The preliminary detection of the patient's tibia based on the tibia recovery score value includes: when the tibia recovery score value is greater than or equal to a first preset threshold, notifying relevant medical staff to perform a quick and comprehensive diagnosis; when the tibia recovery score value is greater than a second preset threshold and less than the first preset threshold, obtaining real-time recovery data of the patient's tibia, and inputting the real-time recovery data into a tibia recovery detection model to obtain a tibia recovery detection value; when the tibia recovery score value is less than or equal to the second preset threshold, continuing to monitor the patient.

5. The big data-based tibial assisted reduction evaluation method according to claim 4, characterized in that: The method of acquiring real-time recovery data of the patient's tibia and inputting the real-time recovery data into a tibia recovery detection model to obtain a tibia recovery detection value includes: the real-time recovery data includes the offset angle of the patient's tibia, the rotation angle of the tibia and the biomechanical data of the tibia, the biomechanical data of the tibia includes the patient's step length, step frequency, step speed, plantar pressure distribution data and tibia micro-vibration spectrum and damping coefficient collected by a bone conduction sensor; the offset angle of the tibia is the angle between the longitudinal growth direction of the tibia and the standard growth direction; the rotation angle of the tibia is the angle between the lateral torsion angle of the tibia and the standard angle; the real-time recovery data is input into the tibia recovery detection model trained by the CNN model to obtain the tibia recovery detection value.

6. The big data-based tibial assisted reduction evaluation method according to claim 1, characterized in that: The step of obtaining the patient's stage score value using a stage score formula according to the tibia recovery score value and the tibia recovery detection value includes: wherein the stage score formula is: M = γ1*Q+γ2*Z; Wherein, M is the patient's stage score; Q is the tibial recovery score; Z is the tibial recovery detection value; γ1 and γ2 are adjustment coefficients.

7. The big data-based tibial assisted reduction evaluation method according to claim 1, characterized in that: The method of obtaining the historical medical data of each doctor and selecting an appropriate doctor to perform auxiliary reduction on the patient according to the historical medical data of each doctor and the stage score of the patient comprises: obtaining the historical medical data of each doctor, wherein the historical medical data of each doctor includes the number of tibia treatments for different affected sides handled by each doctor, the total number of tibia treatments and the most recent time interval for each doctor to treat the tibia on each affected side, and obtaining the most recent time interval for each doctor to treat the tibia through the most recent time interval for each doctor to treat the tibia on each affected side; obtaining the first matching value or the second matching value of each doctor by using the first matching formula or the second matching formula according to the historical medical data of each doctor and the stage score of the patient, and selecting an appropriate doctor according to the first matching value or the second matching value of each doctor.

8. The big data-based tibial assisted reduction evaluation method according to claim 7, characterized in that: The method of using the first matching formula or the second matching formula according to the historical medical data of each doctor and the stage score value of the patient to obtain the first matching value or the second matching value of each doctor, and selecting an adapted doctor according to the first matching value or the second matching value of each doctor, includes: when the stage score value is greater than or equal to a third preset threshold, using the first matching formula to obtain the first matching value, and selecting an adapted doctor according to the first matching value, wherein the first matching formula is: Where N1 is the first matching value; T i The time interval between the last time the doctor treated the same tibia as the patient; Num i It is the number of tibia treatments the doctor has performed on the same tibia as the patient; δ1, δ2, and δ3 are adjustment coefficients.

9. The big data-based tibial assisted reduction evaluation method according to claim 7, characterized in that: The method of using the first matching formula or the second matching formula according to the historical medical data of each doctor and the stage score value of the patient to obtain the first matching value or the second matching value of each doctor, and selecting an adapted doctor according to the first matching value or the second matching value of each doctor, includes: when the stage score value is greater than or equal to a fourth preset threshold and less than a third preset threshold, using the second matching formula to obtain a second matching value, and selecting an adapted doctor according to the second matching value, wherein the second matching formula is: Where N2 is the second matching value; T a The time interval between the last time the doctor treated the tibia; Num a is the total number of tibia medical treatments performed by the doctor; ε1, ε2, and ε3 are adjustment coefficients.

10. A tibial assisted reduction evaluation system based on big data, according to a tibial assisted reduction evaluation method based on big data according to any one of claims 1 to 9, characterized in that: Also includes: A tibia recovery score value acquisition module is used to acquire daily tibia monitoring data, and use a tibia recovery score value formula according to the daily tibia monitoring data to obtain a tibia recovery score value; A hidden value acquisition module, used for inputting the daily walking data into a hidden monitoring formula to obtain a hidden value; A detection module, used for performing a preliminary detection on the patient's tibia according to the tibia recovery score; A tibia recovery detection value acquisition module is used to acquire real-time recovery data of the patient's tibia, and input the real-time recovery data into a tibia recovery detection model to obtain a tibia recovery detection value; A stage score value acquisition module, used to obtain the patient's stage score value using a stage score formula according to the tibia recovery score value and the tibia recovery detection value; The doctor matching and intelligent selection module is used to obtain the historical medical data of each doctor, and select an appropriate doctor to assist the patient in repositioning according to the historical medical data of each doctor and the stage score value of the patient.

Images