A method and system for automatically determining dosage of individualized medication adjustment

Abstract

The present invention provides a method and system for automatically determining the dosage of personalized medication adjustment. The present invention calculates the initial medication regimen based on the patient's physiological data and medication types, using the weighted results of a one-compartment model and a two-compartment model. At the same time, when the patient's initial medication regimen is ineffective or has adverse reactions, the patient's medication regimen is adjusted. Compared with the prior art, the present invention can not only accurately predict and adjust the medication dosage, but also provide adjustment suggestions in real time through a feedback mechanism to ensure the safety and efficacy of personalized medication.

Description

Technical Field

[0001] The present invention relates to the field of intelligent recommendation technology, and in particular to an automatic determination method and system for adjusting dosage of individualized medication. Background Art

[0002] In clinical practice, the physiological and pathological characteristics of patients often change, resulting in the pharmacokinetic properties of drugs being different from the standard values ​​of healthy volunteers, which in turn affects the efficacy of drugs. Some patients may have poor efficacy due to low blood drug concentrations, while others may have adverse reactions due to high blood drug concentrations. Therefore, the standard dose recommended in the drug instructions is often not suitable for all patients. To solve this problem, clinicians need to develop individualized drug dosing plans based on the individual characteristics of patients through blood drug concentration monitoring. At present, the first dose of the current patient can be estimated in the clinic by combining the one-compartment or two-compartment model of the population pharmacokinetic model with the patient's physiological data and the historical medical records of the same population. However, the existing population pharmacokinetic model also has some problems in actual use. Due to individual differences among patients, the first dose is crucial to the entire treatment process, but because there is no drug test data as a reference before the first dose, the first dose is often the most difficult part to determine in the entire treatment process.

[0003] This experimental team has been browsing and studying a large number of relevant records and materials for the relevant technologies of individualized medication dosage optimization for a long time. At the same time, relying on relevant resources and conducting a large number of relevant experiments, after a large number of searches, it was found that there are existing technologies such as CN113255735A, CN113255735B, CN112712870B, and CN107799160B disclosed in the prior art, such as a method and device for determining a medication plan for an Internet hospital disclosed in the prior art, including: establishing a drug information set according to historical prescriptions; the drug information set includes drug information corresponding to at least one drug; determining at least one alternative prescription template according to the drug information set, and determining the alternative drug information corresponding to each of the alternative prescription templates from the drug information; determining the corresponding target prescription template of the patient from each of the alternative prescription templates according to the first information of the patient, the target prescription template includes at least one alternative drug information matched by the first information; determining the target drug information from each of the alternative drug information of the target prescription template according to the second information of the patient; determining the corresponding medication plan of the patient according to the target prescription template and the target drug information.

[0004] The present invention is made to solve the problem that the existing population pharmacokinetic model is insufficiently accurate and cannot fully consider individual differences, resulting in difficulty in accurately determining the first medication dose. Summary of the invention

[0005] The purpose of the present invention is to propose an automatic determination system for adjusting the dosage of individualized medication in view of the shortcomings currently existing in the art.

[0006] In order to overcome the shortcomings of the prior art, the present invention adopts the following technical solutions:

[0007] An automatic determination system for adjusting the dosage of individualized medication, the automatic determination system for adjusting the dosage of individualized medication comprising:

[0008] The initial dosing module obtains the initial dose of the patient's first use of the drug K based on the patient's physiological data and the drug used under the combination of the one-compartment model and the two-compartment model;

[0009] and a medication adjustment module, which is used to provide suggestions for adjusting the patient's medication regimen when the medication regimen of the patient's initial medication module is ineffective or has adverse reactions;

[0010] Wherein, further, the drug administration adjustment module implements the following steps:

[0011] S301: Let the patient take the initial dose of drug K D12 K , continuously monitoring the patient's routine physiological parameters related to adverse drug reactions, the physiological parameters including liver and kidney function, blood sugar, heart rate and blood pressure, and selecting two physiological parameters as markers of adverse drug reactions based on the physiological parameters of the patient one day before taking the initial dose of drug K, the two physiological parameters as markers are correspondingly represented as A and B;

[0012] S302: During the continuous monitoring period, with a preset time interval as a time point, the physiological parameter Ai is the parameter value of the physiological parameter A at the i-th time point when the patient takes the initial dose of drug K, and the physiological parameter Bi is the parameter value of the physiological parameter B at the i-th time point when the patient takes the initial dose of drug K, i={1,2,3…j}, and the parameter value of the patient one day before taking the initial dose of drug K is recorded at the same time;

[0013] S303: Analyze the situation before and after the patient takes the initial dose of drug K to calculate the A abnormality index Adif and the B abnormality index Bdif after the patient takes the initial dose of drug K;

[0014] S304: Calculate the comprehensive adverse reaction score BGI of the patient before and after medication:

[0015] ;

[0016] Among them, α and β are the weight coefficients of abnormal physiological parameters after medication in patients with the greatest response to changes in physiological parameters A and B;

[0017] S305: Recommendations for individualized adjustment of the dose of drug K based on changes in the patient's physiological parameters:

[0018] In BGI≤BGI threshold When the patient's adverse reactions are judged to be within the expected range, if the drug treatment effect is lower than expected, it is recommended to increase the dose of drug K appropriately to improve the treatment effect;

[0019] At BGI>BGI threshold When the patient's current intake of drug K is judged to have adverse reactions greater than the expected range, the warning mechanism is triggered to remind the doctor that when the patient's medication effect reaches the expected level, the patient's K drug intake can be adjusted to PL to reduce the risk of adverse reactions of drug K to the patient and avoid serious adverse reactions after medication.

[0020] in, ;

[0021] Among them, BGI threshold is the comprehensive abnormal reaction score threshold used to evaluate the patient's response to the adverse reaction of drug K, e is the natural base, and γ is the drug adjustment coefficient.

[0022] Furthermore, the initial drug administration module implements the following steps:

[0023] S101: collecting physiological data of the patient, wherein the physiological data includes the patient's weight, age, gender, height, gene polymorphism, liver and kidney function parameters, blood sugar, heart rate and blood pressure parameters, wherein the liver and kidney function parameters include the concentration of alanine aminotransferase, aspartate aminotransferase, total bilirubin, albumin, serum creatinine, glomerular filtration rate and urea nitrogen in the patient's blood, wherein the liver and kidney function parameters are obtained through a blood test report;

[0024] Collect the characteristic pharmacokinetic data of drug K, wherein the characteristic pharmacokinetic data of drug K includes the distribution volume Vd of drug K in the one-compartment model. K , the volume of distribution V1 of the central compartment in the two-compartment model of drug K K , the peripheral distribution volume V2 in the two-compartment model of drug K K , K drug clearance rate from the body CL K and the target peak concentration Ctar1 required for drug treatment in patients with K K and target trough concentration Ctar2 K , the characteristic pharmacokinetic data of drug K are obtained through pharmacokinetic study data;

[0025] S102: Input the patient's physiological data and the characteristic pharmacokinetic data of drug K, and use a one-compartment model to calculate the initial recommended dose D1K of drug K;

[0026] S103: Input the patient's physiological data and the characteristic pharmacokinetic data of drug K, and use the two-compartment model to calculate the initial recommended dose D2K of drug K;

[0027] Among them, one-compartment model calculation and two-compartment model calculation can be obtained by using existing pharmacokinetic calculation software LixoftMonolix or PhoenixWinNonlin;

[0028] S104: Weighted combination of the results of the one-compartment model and the two-compartment model to obtain the initial dose D12 of the patient's first use of drug K K :

[0029] D12 K =w1 K ×D1 K +w2 K ×D2 K ;

[0030] Among them, w1 K is the weighted coefficient of the first chamber, w2 K is the weighted coefficient of the second chamber, satisfying w1 K +w2 K =1,w1 K and w2 K Update in real time based on the patient's medication data, and w1 K and w2 K The real-time update of is realized by the weight update unit, and the medication data is the peak concentration and trough concentration of the medication after the historical patient starts taking the initial dose of drug K.

[0031] Furthermore, the weight updating unit implements the following steps:

[0032] S201: Record and store the peak concentration CA1 and trough concentration CA2 of drug K after administration of the initial dose;

[0033] S202: Obtain the actual peak concentration difference ΔC1 and the actual trough concentration difference ΔC2 of the patient:

[0034] ;

[0035] ;

[0036] S203: Calculate the actual effect difference value ΔC under the initial dose of the patient, and store and record the calculated difference value:

[0037] ;

[0038] S204: When the actual effect difference value ΔC of the patient exceeds 20%, w1 is continuously adjusted based on the difference value of the historical patient records through the Bayesian maximum a posteriori and reinforcement model. K and w2 K , so that the difference value ΔC is minimized.

[0039] Furthermore, the method for automatically determining the individualized medication dosage adjustment comprises the following steps:

[0040] Step 1: Input the patient's physiological data and the characteristic pharmacokinetic data of the drug K used into the initial drug administration module;

[0041] Step 2: The patient takes the initial dose of drug K, continuously monitors the patient's physiological parameters, and monitors the patient's physiological parameters one day before the patient takes the initial dose of drug K, inputs the patient's physiological parameter values ​​after taking the initial dose of drug K into the drug administration adjustment module, and at the same time inputs the patient's physiological parameter values ​​monitored one day before the patient takes the initial dose of drug K into the drug administration adjustment module;

[0042] Step 3: The medication adjustment module outputs medication adjustment recommendations for patient K's medication.

[0043] In addition, the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that when the processor executes the computer program, the processor implements the steps of an automatic determination system for individualized medication adjustment dosage.

[0044] In addition, the present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of an automatic determination system for adjusting the dosage of individualized medication are implemented.

[0045] The beneficial effects achieved by the present invention are:

[0046] 1. The initial dosing module of the present invention generates a more accurate initial dose based on the patient's physiological data and the pharmacokinetic characteristics of drug K by combining the one-compartment model and the two-compartment model. At the same time, the weight coefficient w1 in the weight update unit module in the initial dosing module is updated. K and w2 K Real-time updates ensure that the system dynamically optimizes dosage through Bayesian maximum a posteriori and reinforcement modeling or reinforcement learning at different stages, flexibly responds to different data volumes, and provides more accurate individualized medication decisions.

[0047] 2. After the patient takes the initial dose of drug K, the drug administration adjustment module of the present invention continuously monitors the changes in physiological parameters and calculates the comprehensive abnormal reaction score. This module effectively reduces the risk of adverse reactions that may occur during medication while ensuring the efficacy through advance evaluation and dynamic feedback mechanism. When the abnormal reaction score exceeds the preset threshold, the system automatically gives dosage adjustment suggestions and issues an early warning, which is particularly suitable for drugs with a higher risk of adverse reactions, reducing the occurrence of toxic reactions and ensuring the treatment effect.

[0048] 3. The present invention provides an individualized real-time feedback mechanism to continuously monitor the patient's physiological parameters before and after medication, ensuring that the dosage recommendation is not only based on preliminary predictions, but also further optimized based on the patient's actual physiological response. This approach improves medication safety and treatment efficiency, and provides doctors with a real-time adjustment reference.

[0049] 4. The present invention gradually optimizes the dosage setting according to the drug response of each patient to ensure the safety and effectiveness of medication. Compared with the traditional unified dosage method, this individualized dosage recommendation significantly improves the accuracy of treatment, provides patients with individualized dosage references, reduces the occurrence of adverse reactions, and improves the overall efficacy. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The present invention can be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily drawn to scale, but the emphasis is placed on illustrating the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0051] Figure 1 The modular schematic diagram of the automatic determination system for adjusting the dosage of individualized medication according to the present invention.

[0052] Figure 2 It is a modular schematic diagram of the weight updating unit of the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with its embodiments; it should be pointed out that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present case. For those skilled in the art, after reviewing the following detailed description, other systems, methods and / or features of this embodiment will become apparent. And the terms describing the positional relationship in the accompanying drawings are only used for illustrative purposes and cannot be understood as limitations on the present invention. For those of ordinary skill in the art, the specific meanings of the above terms can be understood according to the specific circumstances.

[0054] Embodiment 1: Combining with Figure 1 and attached Figure 2This embodiment constructs an automatic determination system for adjusting the dosage of individualized medication, and the automatic determination system for adjusting the dosage of individualized medication includes:

[0055] The initial dosing module obtains the initial dose of the patient's first use of the drug K based on the patient's physiological data and the drug used under the combination of the one-compartment model and the two-compartment model;

[0056] and a medication adjustment module, which is used to provide suggestions for adjusting the patient's medication regimen when the medication regimen of the patient's initial medication module is ineffective or adverse reactions occur.

[0057] The initial drug administration module implements the following steps:

[0058] S101: collecting physiological data of the patient, wherein the physiological data includes the patient's weight, age, gender, height, gene polymorphism, liver and kidney function parameters, blood sugar, heart rate and blood pressure parameters, wherein the liver and kidney function parameters include the concentration of alanine aminotransferase, aspartate aminotransferase, total bilirubin, albumin, serum creatinine, glomerular filtration rate and urea nitrogen in the patient's blood, wherein the liver and kidney function parameters are obtained through a blood test report;

[0059] Collect the characteristic pharmacokinetic data of drug K, wherein the characteristic pharmacokinetic data of drug K includes the distribution volume Vd of drug K in the one-compartment model. K , the volume of distribution V1 of the central compartment in the two-compartment model of drug K K , the peripheral distribution volume V2 in the two-compartment model of drug K K , K drug clearance rate from the body CL K and the target peak concentration Ctar1 required for drug treatment in patients with K K and target trough concentration Ctar2 K The characteristic pharmacokinetic data of drug K is obtained through pharmacokinetic research data, and the characteristic pharmacokinetic data of drug K can be further adjusted and set by those skilled in the art in combination with clinical experience, the therapeutic window of the drug and the patient's condition characteristics, which is not limited here;

[0060] S102: Input the patient's physiological data and the characteristic pharmacokinetic data of drug K, and use a one-compartment model to calculate the initial recommended dose D1K of drug K;

[0061] S103: Input the patient's physiological data and the characteristic pharmacokinetic data of drug K, and use the two-compartment model to calculate the initial recommended dose D2K of drug K;

[0062] Among them, one-compartment model calculation and two-compartment model calculation can be obtained by using existing pharmacokinetic calculation software LixoftMonolix or PhoenixWinNonlin;

[0063] S104: Weighted combination of the results of the one-compartment model and the two-compartment model to obtain the initial dose D12 of the patient's first use of drug K K :

[0064] D12 K =w1 K ×D1 K +w2 K ×D2 K ;

[0065] Among them, w1 K is the weighted coefficient of the first chamber, w2 K is the weighted coefficient of the second chamber, satisfying w1 K +w2 K =1,w1 K and w2 K Update in real time based on the patient's medication data, and w1 K and w2 K The real-time update of is realized by the weight update unit, and the medication data is the peak concentration and trough concentration of the medication after the historical patient starts taking the initial dose of drug K.

[0066] Wherein, the weight updating unit implements the following steps:

[0067] S201: Record and store the peak concentration CA1 and trough concentration CA2 of drug K after administration of the initial dose;

[0068] S202: Obtain the actual peak concentration difference ΔC1 and the actual trough concentration difference ΔC2 of the patient:

[0069] ;

[0070] ;

[0071] S203: Calculate the actual effect difference value ΔC under the initial dose of the patient, and store and record the calculated difference value:

[0072] ;

[0073] S204: When the actual effect difference value ΔC of the patient exceeds 20%, w1 is continuously adjusted based on the difference value of the historical patient records through the Bayesian maximum a posteriori and reinforcement model. K and w2 K , so that the difference value ΔC is minimized.

[0074] The initial drug administration module of the present invention generates a more accurate initial dose based on the patient's physiological data and the pharmacokinetic characteristics of drug K by combining the one-compartment model and the two-compartment model. At the same time, the weight coefficient w1 in the weight update unit module in the initial drug administration module is updated. K and w2 K Real-time updates ensure that the system dynamically optimizes dosage through Bayesian maximum a posteriori and reinforcement modeling or reinforcement learning at different stages, flexibly responds to different data volumes, and provides more accurate individualized medication decisions.

[0075] Embodiment 2: Combining with Figure 1 and attached Figure 2 In addition to the contents of the above embodiments, the drug administration adjustment module implements the following steps:

[0076] S301: Let the patient take the initial dose of drug K D12 K , continuously monitor the patient's routine physiological parameters related to adverse drug reactions, the physiological parameters including liver and kidney function, blood sugar, heart rate and blood pressure, and select two physiological parameters as markers of adverse drug reactions based on the physiological parameters of the patient one day before taking the initial dose of drug K, the two physiological parameters as markers are correspondingly represented as A and B, and the specific number of physiological parameters as markers is selected by those skilled in the art based on the characteristics of drug K and actual conditions, and is not limited here;

[0077] S302: During the continuous monitoring period, with a preset time interval as a time point, the physiological parameter Ai is the parameter value of the physiological parameter A at the i-th time point when the patient takes the initial dose of drug K, and the physiological parameter Bi is the parameter value of the physiological parameter B at the i-th time point when the patient takes the initial dose of drug K, i={1,2,3…j}, and the parameter value of the patient one day before taking the initial dose of drug K is recorded at the same time;

[0078] S303: Analyze the situation before and after the patient takes the initial dose of drug K to calculate the A abnormality index Adif and B abnormality index Bdif after the patient takes the initial dose of drug K. The specific steps of analyzing the situation before and after the patient takes the initial dose of drug K are as follows S3031-S3037:

[0079] S3031: Calculate the change rate of patient A and the change rate of patient B:

[0080] ;

[0081] ;

[0082] ;

[0083] ;

[0084] in, is the average rate of change of A at each time interval on the day before the patient took the initial dose of drug K, is the average rate of change of B at each time interval on the day before the patient took the initial dose of drug K, is the average rate of change of A at each time interval after the patient takes the initial dose of drug K, is the average rate of change of B at each time interval after the patient takes the initial dose of drug K;

[0085] S3032: Get the maximum change difference between patient A and B:

[0086] ;

[0087] ;

[0088] ;

[0089] ;

[0090] is the maximum rate of change of B after the patient takes the initial dose of drug K, is the maximum rate of change of A after the patient takes the initial dose of drug K, is the maximum B change rate on the day before the patient takes the initial dose of drug K, The maximum rate of change in A on the day before the patient took the initial dose of drug K;

[0091] S3033: Calculate the mean change rate of A and the mean change rate of B before the patient takes the initial dose of drug K:

[0092] ;

[0093] ;

[0094] VHR is the average rate of change of A on the day before the patient takes the initial dose of drug K, and VBP is the average rate of change of B on the day before the patient takes the initial dose of drug K;

[0095] S3034: Calculate the mean change rate of A (SHR) and the mean change rate of B (SBP) before and after the patient takes the initial dose of drug K:

[0096] ;

[0097] ;

[0098] S3035: Calculate the maximum A change rate and the maximum B change rate before and after the patient takes the initial dose of drug K:

[0099] ;

[0100] ;

[0101] For all The maximum A change rate value in For all The maximum B change rate value in;

[0102] S3036: Calculate the abnormal index Adif after the patient takes the initial dose of drug K:

[0103] ;

[0104] S3037: Calculate the B abnormality index Bdif after the patient takes the initial dose of drug K:

[0105] ;

[0106] S304: Calculate the comprehensive adverse reaction score BGI of the patient before and after medication:

[0107] ;

[0108] Among them, α and β are weight coefficients that maximally reflect abnormal physiological parameters of patients after taking the medicine through changes in physiological parameters A and physiological parameters B. α and β are gradually adjusted by technicians in this field based on historical data of a patient group using drug K as samples after a large number of repeated trainings, and finally the values ​​of α and β for fitting the maximum abnormal physical reaction caused by changes in physiological parameters A and physiological parameters B after taking the medicine are obtained;

[0109] S305: Recommendations for individualized adjustment of the dose of drug K based on changes in the patient's physiological parameters:

[0110] In BGI≤BGI threshold When the patient's adverse reactions are judged to be within the expected range, if the drug treatment effect is lower than expected, it is recommended to increase the dose of drug K appropriately to improve the treatment effect;

[0111] At BGI>BGI threshold When the patient's current intake of drug K is judged to have adverse reactions greater than the expected range, the warning mechanism is triggered to remind the doctor that when the patient's medication effect reaches the expected level, the patient's K drug intake can be adjusted to PL to reduce the risk of adverse reactions of drug K to the patient and avoid serious adverse reactions after medication.

[0112] in, , BGI threshold BGI is the comprehensive abnormal reaction score threshold used to evaluate the patient's response to adverse reactions to drug K. threshold The determination of the BGI is based on historical data and clinical observations of patients treated with drugs. The abnormal reaction score distribution of a large number of patients at the initial dose is analyzed by statistical analysis, machine learning algorithms or ROC curve analysis, and a cut-off value that can effectively distinguish normal drug reactions from abnormal adverse reactions at the initial dose is set, thereby selecting the BGI that distinguishes normal reactions from abnormal adverse reactions. threshold value;

[0113] e is the natural base, γ is the drug adjustment coefficient, and γ is set by a technician in this field based on the historical data of the patient group, selecting samples with similar physiological characteristics to the current patient, and fitting the samples with a nonlinear regression model to obtain the initial γ value. The γ value is further adjusted through feedback from regression analysis or machine learning models to accurately match historical data and expected safety performance, so as to obtain the optimal γ value for controlling the impact of the progressive comprehensive abnormal reaction score on the medication adjustment dose of drug K.

[0114] After the patient takes the initial dose of drug K, the drug administration adjustment module of the present invention continuously monitors the changes in at least some of the patient's physiological parameters, analyzes the patient's pre-drug physiological reactions in detail, and calculates a comprehensive abnormal reaction score. Under the premise of ensuring the efficacy, the system reduces the potential risk of adverse reactions during medication through a dynamic feedback mechanism. When the abnormal reaction score exceeds the preset threshold, the system will automatically give a suggestion to reduce the dosage and issue an early warning. As an auxiliary means of medical treatment, it provides a reference for doctors to adjust the dosage and ensures the safety and rationality of the adjusted dosage. The present invention is particularly suitable for drugs with a higher risk of adverse reactions. Through precise dosage adjustment and continuous monitoring, toxic reactions can be reduced and the treatment effect of patients can be improved.

[0115] In the present invention, some physiological parameters are used as indicators to construct a convenient and practical monitoring system, which can quickly reflect the patient's initial physiological response, facilitate real-time feedback and timely adjustment of the system, especially for the need to quickly evaluate and adjust the dosage in a short period of time. At the same time, by calculating the comprehensive abnormal reaction score BGI as the overall quantitative indicator of adverse reactions, a concise and effective auxiliary judgment tool is provided for doctors. In the application of the system, if more complex indicator monitoring is required, other physiological indicators can be expanded or combined according to specific drug needs to improve medication safety and treatment effects.

[0116] Although the present invention has been described above with reference to various embodiments, it should be understood that many changes and modifications can be made without departing from the scope of the present invention. That is, the methods, systems and devices discussed above are examples. Various configurations can appropriately omit, replace or add various processes or components. For example, in alternative configurations, the method can be performed in an order different from the order described, and / or various components can be added, omitted and / or combined. Moreover, the features described with respect to certain configurations can be combined in various other configurations, such as different aspects and elements of the configuration can be combined in a similar manner. In addition, as the technology develops, the elements therein can be updated, that is, many elements are examples, and do not limit the scope of the present disclosure or claims. And it should be understood that after reading the contents of the record of the present invention, the technician can make various changes or modifications to the present invention, and these equivalent changes and modifications also fall within the scope defined by the claims of the present invention.

Claims

1. An automatic determination system for adjusting dosage of individualized medication, characterized in that: The automatic determination system for adjusting the dosage of individualized medication includes: The initial dosing module obtains the initial dose of the patient's first use of the drug K based on the patient's physiological data and the drug used under the combination of the one-compartment model and the two-compartment model; The medication adjustment module is used to provide suggestions for adjusting the patient's medication regimen when the medication regimen of the patient's initial medication module is ineffective or adverse reactions occur; Wherein, the drug administration adjustment module implements the following steps: S301: Let the patient take the initial dose of drug K D12 K , continuously monitoring the patient's routine physiological parameters related to adverse drug reactions, the physiological parameters including liver and kidney function, blood sugar, heart rate and blood pressure, and selecting two physiological parameters from the liver and kidney function, blood sugar, heart rate and blood pressure as markers of adverse drug reactions, the two physiological parameters as markers are correspondingly represented as A and B; S302: During the continuous monitoring period, with a preset time interval as a time point, the physiological parameter Ai is the parameter value of the physiological parameter A at the i-th time point when the patient takes the initial dose of drug K, and the physiological parameter Bi is the parameter value of the physiological parameter B at the i-th time point when the patient takes the initial dose of drug K, i={1,2,3…j}, and the parameter value of the patient one day before taking the initial dose of drug K is recorded at the same time; S303: Analyze the situation before and after the patient takes the initial dose of drug K to calculate the A abnormality index Adif and the B abnormality index Bdif after the patient takes the initial dose of drug K; S304: Calculate the comprehensive adverse reaction score BGI of the patient before and after medication: ； Among them, α and β are the weight coefficients of abnormal physiological parameters after medication in patients with the greatest response to changes in physiological parameters A and B; S305: Recommendations for individualized adjustment of the dose of drug K based on changes in the patient's physiological parameters: In BGI≤BGI threshold When the patient's adverse reactions are judged to be within the expected range, if the drug treatment effect is lower than expected, it is recommended to increase the dose of drug K appropriately to improve the treatment effect; At BGI>BGI threshold When the patient's current intake of drug K is judged to have adverse reactions greater than the expected range, the warning mechanism is triggered to remind the doctor that when the patient's medication effect reaches the expected level, the patient's edible dose of drug K can be adjusted to PL to reduce the risk of adverse reactions of drug K to the patient and avoid severe adverse reactions after medication. Among them, BGI threshold is the comprehensive abnormal reaction score threshold used to evaluate the patient's response to the adverse reaction of drug K, and BGI is the patient's comprehensive abnormal reaction score before and after medication; ； Among them, e is the natural base, γ is the agent adjustment coefficient, D12 K The initial dose of drug K that the patient first received; The initial drug administration module implements the following steps: S101: collecting physiological data of the patient, wherein the physiological data includes the patient's weight, age, gender, height, gene polymorphism, liver and kidney function parameters, blood sugar, heart rate and blood pressure parameters, wherein the liver and kidney function parameters include the concentration of alanine aminotransferase, aspartate aminotransferase, total bilirubin, albumin, serum creatinine, glomerular filtration rate and urea nitrogen in the patient's blood, wherein the liver and kidney function parameters are obtained through a blood test report; Collect the characteristic pharmacokinetic data of drug K, wherein the characteristic pharmacokinetic data of drug K includes the distribution volume Vd of drug K in a one-compartment model K , the volume of distribution V1 of the central compartment in the two-compartment model of drug K K , Peripheral distribution volume V2 in the two-compartment model of K drugs K , the clearance rate CLK of the drug from the body and the target peak concentration Ctar1 of the drug required for treatment of the patient K and target trough concentration Ctar2 K , the characteristic pharmacokinetic data of drug K are obtained through pharmacokinetic study data; S102: Input the patient's physiological data and the characteristic pharmacokinetic data of drug K, and use the one-compartment model to calculate the initial recommended dose D1 of drug K. K ; S103: Input the patient's physiological data and the characteristic pharmacokinetic data of drug K, and use the two-compartment model to calculate the initial recommended dose D2 of drug K. K ; Among them, the one-compartment model calculation and the two-compartment model calculation can be obtained by using the existing pharmacokinetic calculation software LixoftMonolix or PhoenixWinNonlin; S104: Weighted combination of the results of the one-compartment model and the two-compartment model to obtain the initial dose D12 of the patient's first use of drug K K : D12 K =w1 K ×D1 K +w2 K ×D2 K ; Among them, w1 K is the weighted coefficient of the first chamber, w2 K is the weighted coefficient of the second chamber, satisfying w1 K +w2 K =1,w1 K and w2 K Update in real time based on the patient's medication data, and w1 K and w2 K The real-time update of is realized by the weight update unit, and the medication data is the peak concentration and trough concentration of the medication after the historical patient starts taking the initial dose of drug K.

2. The automatic determination system for individualized medication dosage adjustment according to claim 1, characterized in that: The weight updating unit implements the following steps: S201: Record and store the peak concentration CA1 and trough concentration CA2 of drug K after administration of the initial dose. S202: Obtain the actual peak concentration difference ΔC1 and the actual trough concentration difference ΔC2 of the patient: ； ； S203: Calculate the actual effect difference value ΔC under the initial dose of the patient, and store and record the calculated difference value: ； S204: When the actual effect difference value ΔC of the patient exceeds 20%, w1 is continuously adjusted based on the difference value of the historical patient records through the Bayesian maximum a posteriori and reinforcement model. K and w2 K , so that the difference value ΔC is minimized.

3. A method for automatically determining an individualized medication dosage adjustment, which is applied to the system for automatically determining an individualized medication dosage adjustment according to claim 2, characterized in that: The method for automatically determining the dosage of individualized medication adjustment comprises the following steps: Step 1: Input the patient's physiological data and the characteristic pharmacokinetic data of the drug K used into the initial drug administration module; Step 2: The patient takes the initial dose of drug K, and the patient's physiological parameters are continuously monitored daily, and the physiological parameters of the patient on the day before the patient took the initial dose of drug K are also monitored, and the physiological parameter values ​​of the patient at each time point after the patient took the initial dose of drug K are input into the drug administration adjustment module, and the physiological parameter values ​​of the patient on the day before the patient took the initial dose of drug K are input into the drug administration adjustment module; Step 3: The medication adjustment module outputs medication adjustment recommendations for patient K's medication.

4. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the automatic determination system for adjusting the dosage of individualized medication according to any one of claims 1 to 2 are implemented.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the automatic determination system for adjusting the dosage of individualized medication according to any one of claims 1 to 2 are implemented.

Images