Accurate dose control method and system for brucellosis traditional Chinese and western medicine combined medication

Abstract

The invention discloses an accurate dose control method and system for brucellosis traditional Chinese and western medicine combined medication, and relates to the technical field of medical treatment. According to the method, individualized data of a patient is obtained through a multi-modal data acquisition technology, a population pharmacokinetic-pharmacodynamic model is constructed by using the data, the population pharmacokinetic-pharmacodynamic model comprises a western medicine module, a traditional Chinese medicine module and a coupling interface, and pharmacokinetic modeling of traditional Chinese medicine and western medicine combined medication is achieved. By monitoring the physiological indexes and symptom data of a patient in real time and combining a traditional Chinese medicine syndrome dynamic scoring algorithm and a reinforcement learning dynamic dose adjustment algorithm, the real-time accurate adjustment of the drug dose is realized. In addition, the method further comprises a traditional Chinese and western medicine synergistic effect optimization step, a synergistic index is calculated based on the knowledge graph and the graph attention network, and a dosage optimization rule is formulated, and the implementation of the method is beneficial for improving the treatment effect of brucellosis and reducing side effects.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical treatment, and particularly relates to a precise dosage control method and system for combined traditional Chinese and Western medicine in the treatment of brucellosis. Background Art

[0002] Brucellosis is a zoonotic disease caused by Brucella, and its clinical manifestations mainly include fever, joint pain and other symptoms. At present, the treatment of brucellosis mainly uses Western medicines such as antibiotics. However, due to individual differences among patients, single Western medicine treatment often fails to achieve ideal therapeutic effects. Traditional Chinese medicine also plays an important role in the treatment of brucellosis, but the combined use of traditional Chinese and Western medicine lacks a scientific dosage control system and is difficult to give full play to the synergistic effect.

[0003] There are some deficiencies in the existing technology in terms of dosage control for the combined use of traditional Chinese and Western medicine in the treatment of brucellosis. First, it lacks sufficient consideration of individual differences among patients and cannot carry out personalized medication according to basic information such as the patient's age, weight, occupational exposure history, and pathological indicators such as Brucella typing and serum agglutination test titer. Second, the existing technology cannot monitor the patient's condition changes in real time and dynamically adjust the drug dosage, resulting in a lag in the adjustment of the treatment plan and affecting the therapeutic effect. In addition, the existing technology is difficult to optimize the synergistic effect of the combined use of traditional Chinese and Western medicine, lacks in-depth analysis of the interaction between traditional Chinese medicine components and Western medicines, and cannot formulate scientific rules for optimizing the combined medication dosage.

[0004] Therefore, an innovative dosage control system for the combined use of traditional Chinese and Western medicine in the treatment of brucellosis is needed, which can fully consider individual differences among patients, monitor the condition changes in real time and dynamically adjust the dosage, and optimize the synergistic effect of the combined use of traditional Chinese and Western medicine, so as to improve the precision and effectiveness of treatment. Summary of the Invention

[0005] The present invention provides a precise dosage control method and system for the combined use of traditional Chinese and Western medicine in the treatment of brucellosis, aiming to achieve precise control of drug dosage and improve the treatment effect through steps such as multi-modal data collection, combined traditional Chinese and Western medicine pharmacokinetic modeling, real-time dynamic dosage regulation, and optimization of the synergistic effect of traditional Chinese and Western medicine.

[0006] To solve the above technical problems, the present invention is realized through the following technical solutions:

[0007] The present invention is a precise dosage control method for the combined use of traditional Chinese and Western medicine in the treatment of brucellosis, including the following steps:

[0008] S1. Through multi-modal data collection, obtain the relevant individualized data of the patient, including basic physiological data, pathological feature data, quantified traditional Chinese medicine syndrome data, and environmental exposure data, and construct an individualized data set based on this;

[0009] S2. Integrated Pharmacokinetics Modeling of Traditional Chinese and Western Medicines:

[0010] Construct a population pharmacokinetics-pharmacodynamics (PPK-PD) model, which includes:

[0011] Western medicine module: Integrate the antibiotic blood concentration-time curve and minimum inhibitory concentration data using a non-linear mixed effect model;

[0012] Traditional Chinese medicine module: Determine the blood concentration of active ingredients in traditional Chinese medicine through liquid chromatography-mass spectrometry, and establish a syndrome-efficacy correlation equation;

[0013] Coupling interface: Define the inhibition coefficient Ki value of traditional Chinese medicine components on the activity of CYP450 enzymes, and map the traditional Chinese medicine syndrome score to pharmacodynamic parameters;

[0014] S2. Integrated Pharmacokinetics Modeling of Traditional Chinese and Western Medicines:

[0015] S3. Real-time Dynamic Dose Regulation, specifically including the following steps:

[0016] S31. Real-time monitor the patient's physiological indicators and symptom data, input the obtained data into the PPK-PD model, and optimize the doses of Western medicine and traditional Chinese medicine according to the output results of the model;

[0017] S32. Dynamically score the traditional Chinese medicine syndrome based on the dynamic scoring algorithm of traditional Chinese medicine syndrome;

[0018] S33. Based on the reinforcement learning dynamic dose adjustment algorithm, achieve real-time and precise adjustment of drug doses.

[0019] As a preferred technical solution of the present invention, the individualized data in S1 specifically includes:

[0020] Basic physiological data: age, gender, weight, BMI;

[0021] Pathological characteristic data: Brucella typing, serum agglutination test titer, visual analogue scale score for joint pain;

[0022] Quantitative data of traditional Chinese medicine syndrome: RGB value of tongue image obtained by spectral imaging, waveform entropy value of pulse condition obtained by pressure sensor array;

[0023] Environmental exposure data: working years in pastoral areas, frequency of livestock contact.

[0024] As a preferred technical solution of the present invention, the environmental exposure data further includes:

[0025] Brucella contamination level of pastures marked by geographic information system;

[0026] The livestock contact frequency is quantified by the daily close contact duration recorded by the intelligent collar.

[0027] As a preferred technical solution of the present invention, in the S2, the modeling of the traditional Chinese medicine module specifically includes

[0028] Using ultra-high performance liquid chromatography-quadrupole time-of-flight mass spectrometry to determine the AUC0-24 of saikosaponin d in Chailing Decoction;

[0029] Establish a response equation between the damp-heat syndrome score ΔS and the blood drug concentration C of baicalin: ΔS = 0.82 - 0.15 * ln(C), R 2 > 0.90.

[0030] As a preferred technical solution of the present invention, the S31 specifically includes:

[0031] Calculating the area under the target plasma concentration-time curve according to the minimum inhibitory concentration of the patient and the traditional Chinese medicine syndrome, and outputting the optimal dose of western medicine. Specifically: the optimization goal is that the area under the plasma concentration-time curve reaches 90 - 110% of the target value and the risk of elevated liver enzymes < 5%;

[0032] At the same time, by measuring the AUC0-24 of the main components in the traditional Chinese medicine prescription, establish the syndrome-efficacy relationship and dynamically adjust the dose of traditional Chinese medicine.

[0033] As a preferred technical solution of the present invention, the step S32 is specifically: developing a syndrome quantification and evaluation model based on machine learning, through spatio-temporal feature fusion, combining the patient's environmental exposure data with traditional Chinese medicine syndrome differentiation data such as the RGB value of the tongue image and the waveform entropy value of the pulse condition, dynamically scoring the traditional Chinese medicine syndrome, and dynamically adjusting the weights according to the importance of different data features for syndrome judgment.

[0034] As a preferred technical solution of the present invention, the step S33; specifically includes:

[0035] Develop an adaptive decision-making system based on real-time monitoring data, using reinforcement learning + multi-objective optimization design, balancing efficacy and safety in the reward function. The system continuously tries different drug dose adjustment strategies according to the real-time collected patient physiological indicators, symptom data and the dynamic scoring results of traditional Chinese medicine syndromes, evaluates and selects different strategies through the multi-objective optimization algorithm, and realizes real-time and precise adjustment of drug doses.

[0036] As a preferred technical solution of the present invention, it further includes S4, an optimization step for the synergistic effect of traditional Chinese and western medicine:

[0037] Based on the traditional Chinese and western medicine synergistic effect prediction algorithm, formulate dose optimization rules;

[0038] Construct a knowledge graph, where the nodes include western medicine molecular structures, traditional Chinese medicine ingredient targets, and traditional Chinese medicine syndrome characteristics;

[0039] Use a graph attention network to calculate the synergy index, and activate the dose combination adjustment rule base when the attention weight > 0.7.

[0040] As a preferred technical solution of the present invention, the dose combination adjustment rule base includes:

[0041] When it is detected that ALT > 80 U / L and the damp-heat syndrome score > 7:

[0042] Adjustment of western medicine dose: Reduce rifampicin by 20% and combine with silybin capsules 200 mg bid;

[0043] Adjustment of traditional Chinese medicine dose: Reduce the dose of Coptis chinensis in Chailing Decoction to 3 g, and add 10 g of Schisandra chinensis extract.

[0044] The present invention also provides a precise dose control system for the combined use of traditional Chinese and western medicine in the treatment of brucellosis, which is used to implement the above method. The system includes the following modules:

[0045] A data acquisition module, which is used to collect patient basic information, pathological data, traditional Chinese medicine syndrome data, and environmental exposure data;

[0046] A modeling and calculation module, which is used to execute population pharmacokinetics-pharmacodynamics modeling algorithms to calculate the optimal dose of western medicine and adjust the dose of traditional Chinese medicine;

[0047] A hardware monitoring module, which includes an intelligent bracelet, a microfluidic blood drug concentration detection card, and an insole for sensing joint pressure, and is used to monitor the patient's physiological indicators and symptom data in real time;

[0048] A traditional Chinese medicine syndrome evaluation module, which is used to implement a syndrome quantification evaluation model based on machine learning to dynamically score traditional Chinese medicine syndromes;

[0049] A dose adjustment decision module, which uses reinforcement learning + multi-objective optimization design to achieve real-time and precise adjustment of drug doses;

[0050] A synergy effect prediction module, which is used to establish a drug interaction prediction model based on deep learning to predict the synergy effect after combined drug use and formulate dose optimization rules.

[0051] The present invention has the following beneficial effects:

[0052] Through multi-modal data acquisition and combined traditional Chinese and western medicine pharmacokinetic modeling, the comprehensive integration and analysis of patient individual data are realized, providing a scientific basis for precise dose control. The real-time dynamic dose regulation and the optimization steps of the combined traditional Chinese and western medicine synergy effect further improve the treatment effect and safety and reduce side effects.

[0053] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for describing the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0055] Figure 1 It is a schematic diagram of the method flow in the present invention;

[0056] Figure 2 It is a multi-modal data acquisition flow chart in the present invention;

[0057] Figure 3 It is a schematic diagram of the integrated traditional Chinese and Western medicine PK / PD coupling model in the present invention;

[0058] Figure 4 It is a system architecture diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0060] As Figures 1 - 4 shown: The present invention provides a precise dosage control method for the combined use of traditional Chinese and Western medicines in the treatment of brucellosis, including the following steps:

[0061] S1 Multi-modal data acquisition and construction of individualized data sets:

[0062] Data content:

[0063] Basic physiological data: age, gender, weight, BMI;

[0064] Pathological characteristic data: Brucella typing (such as B. melitensis, B. abortus), serum agglutination test titer, visual analogue scale (VAS) score for joint pain;

[0065] Quantitative data of traditional Chinese medicine syndromes: Obtain the RGB values of the tongue image through a high-resolution spectral imager (such as HyperCamV1), and collect the pulse wave entropy value using a flexible pressure sensor array (sampling frequency 1 kHz);

[0066] Environmental exposure data: working years in pastoral areas, daily contact duration of livestock recorded by intelligent collars (accuracy ±5 minutes), Brucella contamination level of pastures marked by GIS (divided into three levels: low / medium / high).

[0067] S2 Integrated traditional Chinese and Western medicine pharmacokinetic modeling:

[0068] Western medicine module: Use NONMEM software to build a non-linear mixed effect model, integrate antibiotic plasma concentration-time curve and minimum inhibitory concentration (MIC) data, and calibrate individual parameters with Bayesian feedback algorithm.

[0069] Traditional Chinese medicine module: Use ultra-high performance liquid chromatography-quadrupole time-of-flight mass spectrometry (UPLC-QTOF / MS) to determine the AUC0-24 of saikosaponin d in Chailing Decoction;

[0070] Establish the response equation between damp-heat syndrome score (Y) and baicalin plasma concentration (C): Y = 0.82 - 0.15 * ln(C), R 2 > 0.90;

[0071] Coupling interface: Determine the inhibition coefficient Ki value of traditional Chinese medicine components (such as berberine) on CYP3A4 enzyme through in vitro liver microsome experiments, and map the traditional Chinese medicine syndrome score to pharmacodynamic parameters (such as EC50).

[0072] S3, Real-time dynamic dose regulation:

[0073] S31 (dose optimization): According to the output results of the PPK-PD model, with the area under the plasma concentration-time curve (AUC) reaching 90 - 110% of the target value and the risk of liver enzyme elevation <5% as the constraint conditions, use the sequential quadratic programming algorithm to calculate the optimal dose of Western medicine; synchronously adjust the dose of traditional Chinese medicine through the dynamic association equation between the AUC0-24 of traditional Chinese medicine components and the syndrome score;

[0074] S32 (syndrome dynamic scoring): Develop a convolutional neural network based on spatio-temporal feature fusion (CNN-LSTM hybrid model), input the RGB values of tongue images, pulse entropy values and environmental exposure data, output the dynamic syndrome score, and dynamically adjust the weights according to the feature importance (calculated by SHAP value);

[0075] S33 (reinforcement learning adjustment): Build a deep deterministic policy gradient (DDPG) framework, define the reward function R = α × efficacy index (such as body temperature decline rate) - β × liver toxicity risk, and screen the Pareto optimal dose plan through the multi-objective optimization algorithm (NSGA-II).

[0076] S4, Optimization of the synergistic effect of traditional Chinese and Western medicine

[0077] Construct a knowledge graph with nodes including western medicine molecular structures, traditional Chinese medicine ingredient targets, and traditional Chinese medicine syndrome characteristics;

[0078] Use a graph attention network (GAT) to calculate the drug-syndrome synergy index, and trigger the dose combination adjustment rule base when the attention weight > 0.7. For example: when it is detected that ALT > 80 U / L and the damp-heat syndrome score > 7, automatically execute the rule: reduce the rifampicin dose by 20% + take silybin capsules 200 mg bid, reduce the coptis chinensis dose in Chailing Decoction to 3 g and add 10 g of schisandra chinensis extract.

[0079] Meanwhile, the present invention also provides a precise dose control system for the combined use of traditional Chinese and western medicine in treating brucellosis to implement the above method. The system includes the following modules:

[0080] Data acquisition module: Integrate an intelligent bracelet (monitoring heart rate and body temperature), a microfluidic blood drug concentration detection card (detection limit 0.1 μg / mL), and an insole with joint pressure sensors (sampling frequency 100 Hz).

[0081] Modeling and calculation module: Deploy a PPK-PD model and a reinforcement learning algorithm, and use an NVIDIA IAA100 GPU to accelerate the calculation.

[0082] Traditional Chinese medicine syndrome evaluation module: Implement a syndrome scoring model based on the PyTorch framework, supporting online weight update.

[0083] Dose adjustment decision module: Use the Ray framework to implement distributed reinforcement learning training, and generate dose suggestions every 6 hours.

[0084] Synergy effect prediction module: Construct a knowledge graph based on Neo4j, and implement the GAT model using the DGL library.

[0085] A specific application of the present invention is as follows:

[0086] Formulation of an individualized treatment plan based on multimodal data

[0087] Patient information:

[0088] Male, 45 years old, BMI 28.5, working in a pastoral area for 18 years

[0089] Brucella typing: Brucella melitensis (biotype 3)

[0090] Serum agglutination test titer (SAT): 1:640

[0091] Traditional Chinese medicine syndrome: Damp-heat syndrome (initial score 8.2)

[0092] Environmental exposure: Average daily livestock contact for 5.3 hours, pasture pollution level III (GIS marked)

[0093] The treatment process is as follows:

[0094] S1 Individualized data collection and processing

[0095] Basic physiological data: Use a smart bracelet to continuously monitor heart rate, blood pressure, and body temperature in real time, and use a body fat scale to obtain body weight and BMI2;

[0096] Pathological feature data: Brucella typing: PCR detection; SAT titer: Tube agglutination method;

[0097] VAS score for joint pain: Continuously monitored by a pressure sensing insole;

[0098] Traditional Chinese medicine syndrome data: Tongue image collection: Hyperspectral imager (400 - 1000nm band), extract RGB values (R = 205, G = 120, B = 80);

[0099] Pulse condition detection: 64-channel pressure sensor array (sampling rate 1000Hz), calculate the waveform entropy value (0.72);

[0100] Environmental exposure data: The smart collar records the livestock contact duration (5.3 hours per day on average); The GIS system marks the pollution level of the pasture (based on the PCR results of soil samples);

[0101] Data preprocessing: Standardization: z-score normalization (e.g., BMI = 28.5 → z = 1.2)

[0102] Feature engineering: Working years in the pastoral area × pollution level = 18 × 3 = 54 (environmental risk index).

[0103] S2 Integrated traditional Chinese and Western medicine pharmacokinetics modeling: Specifically including

[0104] Western medicine module (rifampicin PPK-PD model)

[0105] Data source: Plasma drug concentration data of 500 patients (NONMEM database)

[0106] Model structure:

[0107]

[0108] Among them, the clearance rate k e = 0.05 + 0.001 × age - 0.02 × damp-heat syndrome score.

[0109] Target AUC: 40 - 50mg·h / L (based on MIC = 0.5mg / L)

[0110] Traditional Chinese medicine module (pharmacodynamic model of Chailing Decoction)

[0111] UHPLC-QTOF-MS parameters: Chromatographic column: ACQUITY UPLC BEH C18 (1.7 μm, 2.1×100 mm);

[0112] Mobile phase: Gradient elution with 0.1% formic acid in water (A) - acetonitrile (B).

[0113] Detection: ESI+ mode, m / z 785.4 → 521.2 (characteristic ion of saikosaponin d).

[0114] Verification of the pharmacodynamic equation: ΔS = 0.82 - 0.15 * ln(C), (R 2 > 0.90, p < 0.01)

[0115] When the concentration of baicalin C = 3.0 μg / mL, the syndrome score = 0.82 - 0.15×1.1 = 0.65 (error between theoretical value and measured value < 5%)

[0116] Coupling interface (CYP450 inhibitory effect)

[0117] Experimental determination: The Ki value of Chailing Decoction for CYP3A4 = 25 μM (based on HepG2 cell experiments) Model mapping: For every 1-point increase in the syndrome score, the clearance rate of rifampicin decreases by 8%.

[0118] S3 real-time dynamic dose regulation, specifically including:

[0119] S31 Multi-objective optimization;

[0120] Objective function:

[0121]

[0122] (λ = 0.5, the probability of liver enzyme risk is predicted by the Logistic regression model)

[0123] Optimization result: Rifampicin dose = 450 mg / d (AUC = 46.2 mg·h / L, risk probability = 3.2%).

[0124] S32 Syndrome dynamic scoring:

[0125] Spatio-temporal feature fusion model:

[0126] Input layer: Environmental risk index (54) + tongue image RGB (205, 120, 80) + pulse entropy (0.72) Feature extraction: CNN (ResNet-50) processes image data, and LSTM analyzes time-series data. Output: Damp-heat syndrome score (dynamically updated: drops to 6.5 on the 3rd day and 4.1 on the 7th day)

[0127] S33 Reinforcement learning adjustment;

[0128] State space: [AUC deviation, ALT value, syndrome score, contact duration].

[0129] Action space: Western medicine ±10% dose, traditional Chinese medicine ±20% dose.

[0130] Reward function:

[0131] R = 0.6·ΔSAT + 0.3·Δsyndrome score - 0.1ΔALT

[0132] Training result: After 10,000 iterations of the DQN model, the strategy converges to:

[0133] When AUC < 90%, Western medicine +15% dose, when syndrome score > 6, traditional Chinese medicine +20% dose.

[0134] S4 Optimization of the synergistic effect of traditional Chinese and Western medicine, specifically including:

[0135] Knowledge graph construction:

[0136] Node type:

[0137] Western medicine: Rifampicin (CAS No. 13292-46-1).

[0138] Traditional Chinese medicine ingredient: Saikosaponin d (PubChemC ID11022).

[0139] Syndrome characteristics: Damp-heat syndrome (symptom nodes: yellow and greasy tongue coating, slippery and rapid pulse). Edge attribute: inhibitory relationship (Rifampicin → CYP3A4, weight 0.8), activation relationship (Saikosaponin d → Nrf2, weight 0.75)

[0140] Calculation of the synergy index:

[0141] GAT model parameters:

[0142] Number of heads: 8, dimension of the attention mechanism: 64

[0143] Synergy index = 0.85 (triggering the rule base)

[0144] Triggering of the dose adjustment rule: ALT = 95 U / L, syndrome score = 7.2:

[0145] Adjustment of Western medicine: Reduce Rifampicin to 360 mg / d and combine with Silybin (200 mg b i d).

[0146] Adjustment of traditional Chinese medicine: Coptis chinensis 3 g in Chailing Decoction → Schisandra chinensis 10 g.

[0147] In the description of this specification, the descriptions referring to terms such as "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in a suitable manner in any one or more embodiments or examples.

[0148] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A precise dosage control method for combined traditional Chinese and Western medicine in the treatment of brucellosis, characterized in that, It includes the following steps: S1. Through multimodal data collection, obtain relevant individualized data of the patient, including basic physiological data, pathological feature data, quantified traditional Chinese medicine (TCM) syndrome data, and environmental exposure data, and construct an individualized dataset based on this; S2. Integrated pharmacokinetics modeling of traditional Chinese and Western medicine: Construct a population pharmacokinetics-pharmacodynamics (PPK-PD) model, which includes: Western medicine module: Use a nonlinear mixed-effects model to integrate antibiotic plasma concentration-time curve and minimum inhibitory concentration data; Traditional Chinese medicine module: Determine the plasma concentration of active ingredients of traditional Chinese medicine by liquid chromatography-mass spectrometry, and establish a syndrome-efficacy correlation equation; Coupling interface: Define the inhibition coefficient Ki value of traditional Chinese medicine components on CYP450 enzyme activity, and map the TCM syndrome score to pharmacodynamic parameters; S2. Integrated pharmacokinetics modeling of traditional Chinese and Western medicine: S3. Real-time dynamic dose regulation, specifically including the following steps: S31. Real-time monitor the patient's physiological indicators and symptom data, input the obtained data into the PPK-PD model, and optimize the doses of Western medicine and traditional Chinese medicine according to the output results of the model; S32. Based on the dynamic scoring algorithm of TCM syndromes, dynamically score the TCM syndromes; S33. Based on the reinforcement learning dynamic dose adjustment algorithm, achieve real-time and precise adjustment of drug doses.

2. The precise dosage control method for the combined use of traditional Chinese and Western medicines in the treatment of brucellosis according to claim 1, characterized in that, The individualized data in S1 specifically includes: Basic physiological data: age, gender, weight, BMI; Pathological feature data: Brucella typing, serum agglutination test titer, visual analogue scale score of joint pain; Quantified TCM syndrome data: tongue image RGB values obtained by spectral imaging, pulse waveform entropy values obtained by pressure sensor array; Environmental exposure data: working years in pastoral areas, livestock contact frequency.

3. The precise dosage control method for the combined use of traditional Chinese and Western medicines in the treatment of brucellosis according to claim 2, characterized in that, The environmental exposure data also includes: The Brucella contamination level of pastures marked by geographic information system; The livestock contact frequency is quantified by the daily close contact duration recorded by intelligent collars.

4. The precise dosage control method for the combined use of traditional Chinese and Western medicines in treating brucellosis according to claim 1, characterized in that, In S2, the modeling of the traditional Chinese medicine module specifically includes Use ultra-high performance liquid chromatography-quadrupole time-of-flight mass spectrometry to determine the AUC0-24 of saikosaponin d in Chailing Decoction; Establish the response equation between the damp-heat syndrome score ΔS and the blood drug concentration C of baicalin: ΔS = 0.82 - 0.15 * ln(C), R 2 > 0.

90.

5. The precise dosage control method for the combined use of traditional Chinese and Western medicines in the treatment of brucellosis according to claim 2, characterized in that, S31 specifically includes: Calculate the target area under the plasma concentration-time curve according to the patient's minimum inhibitory concentration and TCM syndromes, and output the optimal dose of Western medicine. Specifically, the optimization goal is: the area under the plasma concentration-time curve reaches 90-110% of the target value and the risk of elevated liver enzymes <5%; At the same time, by measuring the AUC0-24 of the main components in the traditional Chinese medicine prescription, establish a syndrome-efficacy relationship and dynamically adjust the dose of traditional Chinese medicine.

6. The precise dosage control method for the combined use of traditional Chinese and Western medicines in the treatment of brucellosis according to claim 5, characterized in that, Step S32 is specifically: Develop a syndrome quantification evaluation model based on machine learning. Through spatio-temporal feature fusion, combine the patient's environmental exposure data with TCM syndrome differentiation data such as tongue image RGB values and pulse waveform entropy values, dynamically score the TCM syndromes, and perform dynamic weight adjustment according to the importance of syndrome judgment for different data features.

7. The precise dosage control method for the combined use of traditional Chinese and Western medicines in treating brucellosis according to claim 6, characterized in that, Step S33 specifically includes: Develop an adaptive decision-making system based on real-time monitoring data, using reinforcement learning + multi-objective optimization design, balancing efficacy and safety in the reward function. The system continuously tries different drug dose adjustment strategies using the reinforcement learning algorithm based on the patient's physiological indicators, symptom data, and dynamic TCM syndrome scores collected in real time, and evaluates and selects different strategies through the multi-objective optimization algorithm to achieve real-time and precise adjustment of drug doses.

8. The precise dosage control method for the combined use of traditional Chinese and Western medicines in the treatment of brucellosis according to claim 1, wherein It also includes S4, the optimization step of the synergistic effect of traditional Chinese and Western medicine: Based on the prediction algorithm of the synergistic effect of traditional Chinese and Western medicine, formulate dose optimization rules; Construct a knowledge graph, with nodes including the molecular structure of Western medicine, the targets of traditional Chinese medicine components, and the characteristics of TCM syndromes; Use the graph attention network to calculate the synergy index, and activate the dose combination adjustment rule library when the attention weight > 0.

7.

9. The precise dosage control method for the combined use of traditional Chinese and Western medicines in treating brucellosis according to claim 8, characterized in that, The dose combination adjustment rule library includes: When it is detected that ALT > 80 U / L and the damp-heat syndrome score > 7: Adjustment of Western medicine dose: Reduce rifampicin by 20% and combine with silybin capsules 200 mg bid; Adjustment of traditional Chinese medicine dose: Reduce the dose of Coptis chinensis in Chailing Decoction to 3 g and add 10 g of Schisandra chinensis extract.

10. A precise dosage control system for the combined use of traditional Chinese and Western medicines in the treatment of brucellosis, which is used to implement the method described in the above claims 1-9, and is characterized in that, The system includes the following modules: The data acquisition module is used to collect the patient's basic information, pathological data, TCM syndrome data, and environmental exposure data; The modeling and calculation module is used to execute the population pharmacokinetics-pharmacodynamics modeling algorithm to calculate the optimal dose of Western medicine and adjust the dose of traditional Chinese medicine; The hardware monitoring module includes an intelligent bracelet, a microfluidic blood drug concentration detection card, and an insole for sensing joint pressure, which are used to monitor the patient's physiological indicators and symptom data in real time; The TCM syndrome evaluation module is used to implement a syndrome quantification evaluation model based on machine learning to dynamically score the TCM syndromes; The dose adjustment decision module uses reinforcement learning + multi-objective optimization design to achieve real-time and precise adjustment of drug doses; The synergistic effect prediction module is used to establish a drug interaction prediction model based on deep learning, predict the synergistic effect after combined medication, and formulate dose optimization rules.

Images