Risk detection method and system for adverse events of drug clinical test

Abstract

The invention provides a risk detection method and system for adverse events of a drug clinical test. The method comprises the following steps: constructing a clinical biological model according to a body health state, body parameters and a historical examination report of a subject; recording the trial information accepted by the subject, and generating a trial database; according to the physiological monitoring equipment and the health monitoring system, body function parameters and biological indexes of the subject after drug testing are monitored in real time, and drug testing data are obtained; screening and optimizing the drug test data based on a genetic algorithm to obtain drug test reaction characteristics; determining a risk score according to the reagent database and the reagent reaction characteristics; and dividing different risk levels according to the risk scores, and carrying out risk early warning according to the risk levels. According to the method, through screening of the drug reaction characteristics and calculation of the risk score, the monitoring efficiency of adverse events is improved, the data analysis capability is enhanced, and the scientificity and accuracy of the result are ensured.

Description

Technical Field

[0001] The present invention relates to the field of medical technology, and in particular to a risk detection method and system for adverse events in drug clinical trials. Background Art

[0002] Adverse events (AE) refer to all adverse medical events that occur after subjects receive trial drugs, which can be manifested as symptoms, signs, diseases or laboratory test abnormalities. They are one of the indicators for evaluating the safety of drug clinical trials. Whether the duration, severity and relationship between AEs experienced by subjects after receiving trial drugs and the trial drugs and their doses are correctly collected and evaluated will directly affect the safety evaluation of the trial drugs, and in turn affect the scientificity and reliability of the trial results and the safety of drug use after the drug is marketed. With the continuous strengthening of the state's supervision of drug clinical trials and the drug review and approval system, the level of drug clinical trials in my country has been greatly improved, but there are still many problems in the collection and evaluation of AEs, which affect the quality of drug clinical trials and the safety of subjects.

[0003] At present, many clinical trials use traditional monitoring methods to collect health data of subjects through regular physical examinations and questionnaires. Although these methods can provide certain information, they often have problems such as delayed data collection, low processing efficiency, neglect of individual differences, and inaccurate risk assessment. They also fail to fully consider the individual differences of subjects, resulting in a lack of pertinence and accuracy in risk assessment results. Therefore, it is very necessary to design a risk detection method and system for adverse events in drug clinical trials. Summary of the invention

[0004] The purpose of the present invention is to provide a risk detection method and system for adverse events in drug clinical trials, so as to improve the monitoring efficiency of adverse events, enhance data analysis capabilities, and ensure the scientificity and accuracy of the results by screening drug reaction characteristics and calculating risk scores.

[0005] To achieve the above object, the present invention provides the following solutions:

[0006] A method for risk detection of adverse events in drug clinical trials, comprising the following steps:

[0007] Construct a clinical biological model based on the subjects' physical health status, physical parameters and historical examination reports;

[0008] Record the information of the trial drugs received by the subjects and generate a trial drug database;

[0009] The physiological monitoring equipment and health monitoring system are used to monitor the physical function parameters and biological indicators of the subjects after the drug trial in real time to obtain drug trial data;

[0010] The drug test data is screened and optimized based on genetic algorithms to obtain drug test reaction characteristics;

[0011] Determine the risk score based on the drug trial database and drug trial reaction characteristics;

[0012] Different risk levels are divided according to risk scores, and risk warnings are issued based on risk levels.

[0013] Optionally, a clinical biological model is constructed based on the subject's physical health status, physical parameters and historical examination reports, including:

[0014] Collect physical parameters; physical parameters include: height, weight, body mass index, body temperature, blood data and metabolic indicators;

[0015] Physical health status is obtained through physical examination; physical health status is obtained by the physician's comprehensive assessment of the subject's physical examination report, living habits and mental health;

[0016] A clinical biological model was constructed using regression analysis based on physical health status, physical parameters, and historical examination reports.

[0017] Optionally, the drug trial database includes: drug name, dosage, route of administration and time of administration; routes of administration include: oral administration, injection and external application; time of administration includes: drug trial time point and time interval with the drug trial time point.

[0018] Optionally, the physical function parameters and biological indicators of the subjects after the drug trial are monitored in real time according to the physiological monitoring equipment and the health monitoring system to obtain the drug trial data. Specifically, the subjects wear physiological monitoring equipment after the drug trial, and the physiological monitoring equipment is used to collect data on the physical function parameters and biological indicators of the subjects, and the collected results are integrated through the health monitoring system to obtain the drug trial data.

[0019] Optionally, the drug test data is screened and optimized based on a genetic algorithm to obtain drug test reaction characteristics, including:

[0020] Perform preprocessing operations on drug test data to obtain preprocessed data; the preprocessing operations include: data cleaning, outlier detection, data standardization and feature selection;

[0021] Randomly generate a set of individuals, each of which represents a preprocessed data;

[0022] Evaluate the characteristics of individuals according to the fitness function;

[0023] Based on the tournament selection method, individuals with fitness higher than the preset threshold are selected as parents;

[0024] Through multiple crossovers and gene changes, the genes of the parents are recombined to obtain new individuals;

[0025] Merge the new individual with the individual to obtain an updated population;

[0026] The updated population is iteratively updated through the fitness function until the fitness converges to the preset convergence threshold to obtain the screening feature;

[0027] The influencing factors in the screening characteristics were removed through correlation analysis and LASSO regression method to obtain the drug reaction characteristics.

[0028] Optionally, the step of outlier detection includes:

[0029] Calculate the first and third quartiles of data for different test drugs;

[0030] The interquartile range was obtained based on the first and third quartiles;

[0031] The abnormal upper and lower boundaries are determined based on the interquartile range;

[0032] Drug test data that exceeds the upper or lower abnormal boundary are defined as suspected outliers;

[0033] The suspected abnormal values ​​were confirmed by a physician to obtain the true abnormal values.

[0034] Optionally, the fitness function is expressed as: Among them, F ( x ) is the fitness value of individual x, E ( x ) is the efficacy score of individual x, S ( x ) Score the side effects of individual x, C ( x ) is the individual difference score of individual x, D ( x ) is the tolerance score of individual x, α is the adjustment coefficient, ω1, ω2 and ω3 are all weight coefficients, ω1+ω2+ω3=1.

[0035] Optionally, the risk score is calculated as: Among them, Q is the risk score, A n is the nth physical data of the subject, T is the end time of observation, P ( t ) is the subject's status score at time t, R is the drug risk coefficient, M m is the mth drug characteristic.

[0036] Optionally, different risk levels are divided according to the risk scores, and risk warnings are issued according to the risk levels, including:

[0037] When the risk score is less than 5, the risk level is determined to be the first risk level;

[0038] When the risk score is greater than or equal to 5 and less than 10, the risk level is determined to be the second risk level;

[0039] When the risk score is greater than or equal to 10 and less than 15, the risk level is determined to be the third risk level;

[0040] When the risk score is greater than or equal to 15 and less than 20, the risk level is determined to be the fourth risk level;

[0041] When the risk score is greater than or equal to 20, the risk level is determined to be the fifth risk level.

[0042] A risk detection system for adverse events in drug clinical trials, comprising:

[0043] The human information module is used to build a clinical biological model based on the subject's physical health status, physical parameters and historical examination reports;

[0044] The drug trial information module is used to record the drug trial information received by the subjects and generate a drug trial database;

[0045] The monitoring module is used to monitor the physical function parameters and biological indicators of the subjects after the drug trial in real time based on the physiological monitoring equipment and health monitoring system to obtain drug trial data;

[0046] AE identification module, used to screen and optimize drug test data based on genetic algorithms to obtain drug test reaction characteristics;

[0047] An AE determination module is used to determine a risk score based on a drug trial database and drug trial reaction characteristics;

[0048] The AE warning module is used to classify different risk levels according to risk scores and issue risk warnings based on risk levels.

[0049] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects: the risk detection method for adverse events of drug clinical trials provided by the present invention, the method comprising: constructing a clinical biological model according to the physical health status, physical parameters and historical examination reports of the subjects; recording the drug trial information received by the subjects, and generating a drug trial database; monitoring the physical function parameters and biological indicators of the subjects after the drug trial in real time according to the physiological monitoring equipment and the health monitoring system, and obtaining drug trial data; screening and optimizing the drug trial data based on the genetic algorithm to obtain drug trial reaction characteristics; determining the risk score according to the drug trial database and the drug trial reaction characteristics; dividing different risk levels according to the risk score, and conducting risk warning according to the risk level. The present invention significantly improves the monitoring efficiency of adverse events, can timely discover potential risks, enhances data analysis capabilities, and ensures the scientificity and accuracy of the results. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0051] Figure 1 is a flow chart of the adverse event risk detection method of the present invention;

[0052] Figure 2 A flow chart for constructing a clinical biological model of the present invention;

[0053] Figure 3 The figure is a data flow chart of drug screening of the present invention. DETAILED DESCRIPTION

[0054] 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.

[0055] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0056] like Figure 1 As shown, the present invention provides a method for risk detection of adverse events in drug clinical trials, comprising the following steps:

[0057] Step 100: Construct a clinical biological model based on the subject's health status, physical parameters and historical examination reports; the specific steps are as follows Figure 2 As shown, including:

[0058] Step 101: Collecting physical parameters; physical parameters include: height, weight, body mass index, body temperature, blood data and metabolic indicators;

[0059] Specifically, this embodiment uses a height measuring instrument to measure accurate height data, a weight scale to measure weight, a body composition analyzer to calculate body mass index (BMI) and analyze body composition, such as body fat percentage and muscle mass, and a digital thermometer to quickly and accurately measure body temperature. A blood analyzer is also used to perform a comprehensive analysis of blood samples, test blood routine and biochemical indicators, such as blood sugar and cholesterol, and a metabolic monitoring device is used to measure physiological indicators such as the metabolic rate of the subject.

[0060] Step 102: obtaining the physical health status through physical examination; the physical health status is obtained by the physician through a comprehensive assessment of the subject's physical examination report, living habits and mental health;

[0061] Specifically, the doctor will carefully study the physical examination report, pay attention to the main health indicators of the subject, and collect information such as the subject's living habits, eating habits, and exercise frequency through questionnaires or one-on-one interviews. In terms of mental health, standardized psychological assessment tools such as the depression scale (PHQ-9) and the self-rating anxiety scale (GAD-7) are used to assess the mental health of the subject. Finally, all this information is summarized to form an overview of the subject's health status, and then a comprehensive assessment is conducted.

[0062] Step 103: Based on the physical health status, physical parameters and historical examination reports, a clinical biological model is constructed using regression analysis.

[0063] Specifically, the present embodiment uses ridge regression to construct a clinical biological model. Ridge regression is an improvement on linear regression. The core idea of ​​linear regression is: assuming that there is a linear relationship between the dependent variable and one or more independent variables, a straight line (or hyperplane) is fitted by the least squares method to minimize the difference (residual sum of squares) between the predicted value and the true value. Ridge regression limits the complexity of the model by adding an L2 regularization term to prevent overfitting. And by adjusting the size of the penalty regression coefficient, parameter estimation is made more stable, which is more suitable for large data sets with high correlation between features. Finally, the results are displayed with the help of visualization tools (such as Matplotlib or Seaborn), so as to more intuitively understand the data and model output. If the performance of the model is not ideal, the accuracy and effectiveness of the model can be improved by adjusting the parameters or selecting different input features.

[0064] Step 200: Record the information of the test drugs received by the subject and generate a test drug database;

[0065] Specifically, the drug trial database includes: drug name, dosage, route of administration and time of administration; routes of administration include: oral administration, injection and external application; time of administration includes: drug trial time point and the time interval with the drug trial time point.

[0066] Furthermore, this embodiment uses a relational database management system (such as MySQL, PostgreSQL) to build a drug trial database in combination with drug name, dosage, route of administration and time of administration. The drug trial database supports querying by subject ID, drug name, time of administration and other conditions, which is convenient for medical staff to quickly obtain relevant information, and provides a data export function to export drug trial information into CSV or Excel documents for further analysis and report generation.

[0067] It should be noted that recording the subjects' drug trial information and generating a drug trial database realizes systematic and standardized management, which not only helps the smooth progress of clinical trials, but also provides important data support for subsequent drug effect evaluation, thereby ensuring the accuracy and completeness of the data.

[0068] Step 300: Real-time monitoring of the body function parameters and biological indicators of the subject after the drug trial is performed using the physiological monitoring equipment and the health monitoring system to obtain drug trial data;

[0069] Specifically, the subjects wear physiological monitoring equipment after the drug trial, and the physiological monitoring equipment collects data on the subjects' body function parameters and biological indicators. The collected results are integrated through the health monitoring system to obtain drug trial data.

[0070] Furthermore, this embodiment uses Huawei Band 6 as a heart rate, step and sleep monitoring device, uses Canon blood pressure monitor HEM-7121 to monitor the subject's blood pressure, uses Oura Ring 2 to track the subject's sleep and activity, and uses Dexcom G6 continuous blood glucose monitor to monitor the subject's blood glucose level in real time.

[0071] Furthermore, the health monitoring system of this embodiment aggregates the data from various monitoring devices through cloud technology. First, the data is cleaned and standardized to ensure that the data of various types are comparable within the same time scale; then, the collected heart rate, blood pressure, blood sugar, sleep cycle and other physiological parameters are stored in a secure database through the data integration platform for subsequent analysis; finally, various charts and reports are generated to show the physiological trends and changes in biological indicators of the subjects.

[0072] It should be noted that the complete data collection and integration process not only provides changes in the subjects' physical functions after drug trials, but also can monitor and analyze drug effects and adverse reactions in real time, providing an important basis for further clinical decision-making and research.

[0073] Step 400: Screen and optimize the drug test data based on the genetic algorithm to obtain drug test reaction characteristics; the specific steps are as follows: Figure 3 As shown, including:

[0074] Step 401: preprocessing the drug test data to obtain preprocessed data; the preprocessing operation includes: data cleaning, outlier detection, data standardization and feature selection;

[0075] Specifically, the steps of outlier detection include:

[0076] Calculate the first quartile Q1 and the third quartile Q3 of the data for different test drugs. The quartiles are calculated by sorting the data in ascending order and finding the corresponding positions, where Q1 is the value at the 25% position in the sorted data and Q3 is the value at the 75% position in the sorted data.

[0077] The interquartile range IQR is obtained based on the first quartile and the third quartile; the calculation formula of the interquartile range is: IQR = Q3-Q1;

[0078] The abnormal upper boundary QS and the abnormal lower boundary QX are determined according to the interquartile range; the calculation formulas of QS and QX are: QX = Q3 + 1.5 * IQR; QX = Q1 - 1.5 * IQR;

[0079] Drug test data that exceeds the upper or lower abnormal boundary are defined as suspected outliers;

[0080] The suspected abnormal values ​​were confirmed by a physician to obtain the true abnormal values.

[0081] Step 402: randomly generate a group of individuals, each of which represents a preprocessed data; these individuals can be regarded as encapsulations of different feature subsets, and the random generation process ensures the diversity of individuals.

[0082] Step 403: Evaluate the characteristics of the individual according to the fitness function;

[0083] Specifically, the expression of the fitness function is:

[0084]

[0085] Among them, F ( x ) is the fitness value of individual x, E ( x )is the efficacy score of individual x, S ( x ) Score the side effects of individual x, C ( x ) is the individual difference score of individual x, D ( x ) is the tolerance score of individual x, α is the adjustment coefficient, ω1, ω2 and ω3 are all weight coefficients, ω1+ω2+ω3=1.

[0086] Furthermore, the side effect score indicates the degree of adverse reactions of the drug. A lower side effect score will be converted to a value closer to 1 through exponential mapping, thereby reducing the negative impact on fitness. The individual difference score indicates the physiological differences of individuals (such as age, gender, weight, etc.), and individual differences may affect the metabolism and response of the drug. The tolerance score reflects the subject's tolerance to the drug, and better tolerance will improve fitness. Different weight coefficients need to be adjusted according to the actual research objectives, and this embodiment does not make specific limitations. The adjustment coefficient is used to control the degree of influence of the side effect score on fitness. The larger α is, the more significant the impact of the side effects on fitness.

[0087] Furthermore, the fitness function smoothes the side effect score in the form of exponential mapping, so that higher side effect scores will significantly inhibit fitness, while lower scores will weaken the impact on fitness, effectively reducing the fitness of individuals with high side effects. By adding individual difference scores and tolerance scores to take into account the differences in the responses of different individuals to the same drug, the practicality and adaptability of the fitness function are further improved. The dynamically adjustable weight coefficient allows dynamic adjustments in efficacy, side effects, individual differences and tolerance according to specific subjects and drug characteristics, ensuring that the fitness function can accurately reflect the performance of the drug.

[0088] Step 404: selecting individuals with fitness higher than a preset threshold as parents based on the tournament selection method;

[0089] Specifically, the tournament selection method randomly selects several individuals for comparison and selects the one with the highest fitness as the parent of the next generation, thus maintaining the inheritance of individuals with stronger fitness.

[0090] Step 405: Perform gene recombination on the parent generation through multi-point crossover and gene change to obtain a new individual;

[0091] Specifically, multi-point crossover refers to randomly selecting multiple crossover points between parents and exchanging their characteristics to generate new offspring, while genetic modification refers to the random change of some characteristics. Such operations can introduce mutations and increase the diversity of the population.

[0092] Step 406: The new individual is merged with the individual to obtain an updated population; while ensuring that the excellent individuals in the current population are retained, new individuals are introduced, thereby maintaining the evolutionary potential of the population.

[0093] Step 407: iteratively updating the update population through the fitness function until the fitness converges to a preset convergence threshold, thereby obtaining the screening feature;

[0094] Step 408: Remove the influencing factors in the screening characteristics through correlation analysis and LASSO regression method to obtain the drug reaction characteristics.

[0095] Specifically, correlation analysis determines which features have a weak relationship with the target variable by calculating the correlation coefficient between each feature and the target variable (such as the Pearson correlation coefficient), thereby identifying redundant features. LASSO regression is a regularized linear regression method that effectively selects important features and removes influencing factors by adding an L1 penalty term to reduce the coefficients of certain features to zero.

[0096] It should be noted that the drug reaction characteristics optimized by genetic algorithms will have higher credibility and effectiveness, which not only improves the scientific nature of feature selection, but also reduces data dimensions, reduces the complexity of the model, and improves the model's generalization ability to new data. It also greatly improves the efficiency and accuracy of drug trial data analysis.

[0097] Step 500: Determine a risk score based on the drug trial database and drug trial reaction characteristics;

[0098] Specifically, the risk score calculation formula is:

[0099]

[0100] Among them, Q is the risk score, A n is the nth physical data of the subject, T is the end time of observation, P ( t ) is the subject's status score at time t, R is the drug risk coefficient, M m is the mth drug characteristic.

[0101] Furthermore, the exponential operation of physical data represents the nonlinear influence of physical data on risk. The dynamic health status of the subject is reflected by the definite integral of the natural logarithm of the subject's status score. The product operation represents the complex relationship between different drug characteristics and the occurrence of AEs.

[0102] It should be noted that risk assessment based on the drug trial database and drug trial reaction characteristics can effectively integrate and analyze the subject's physical condition and drug reaction characteristics, thereby ensuring the scientificity and accuracy of risk assessment. The calculation formula realizes the quantitative expression of the impact of different factors on the subject's risk, making clinical decisions clearer and more operational. The introduction of a dynamic monitoring mechanism can timely reflect individual risk changes by continuously updating the subject's status assessment, enhancing the foresight and effectiveness of risk management. In addition, the mathematical model is used to systematically evaluate the nonlinear relationship between risk factors, improve the adaptability and explanatory power of the model, and thus enhance the ability to predict potential risks.

[0103] Step 600: Different risk levels are divided according to the risk scores, and risk warnings are issued according to the risk levels. Specifically, it includes:

[0104] When the risk score is less than 5, the risk level is determined as the first risk level; the first risk level is a mild AE, which manifests as mild symptoms that do not affect the subject's daily activities;

[0105] When the risk score is greater than or equal to 5 and less than 10, the risk level is determined to be the second risk level; the second risk level is moderate AE, which manifests as obvious symptoms but has limited impact and requires continued observation;

[0106] When the risk score is greater than or equal to 10 and less than 15, the risk level is determined to be the third risk level; the third risk level is severe AE, which manifests as symptoms that seriously affect the life of the subject and require immediate treatment;

[0107] When the risk score is greater than or equal to 15 and less than 20, the risk level is determined to be the fourth risk level; the fourth risk level is life-threatening AE, which is manifested as a serious adverse reaction that may be life-threatening and requires emergency intervention;

[0108] When the risk score is greater than or equal to 20, the risk level is determined to be the fifth risk level; the fifth risk level is death AE, which is manifested as the death of the patient due to an adverse event.

[0109] The present invention also provides a risk detection system for adverse events in drug clinical trials, comprising:

[0110] The human information module is used to build a clinical biological model based on the subject's physical health status, physical parameters and historical examination reports;

[0111] The drug trial information module is used to record the drug trial information received by the subjects and generate a drug trial database;

[0112] The monitoring module is used to monitor the physical function parameters and biological indicators of the subjects after the drug trial in real time based on the physiological monitoring equipment and health monitoring system to obtain drug trial data;

[0113] AE identification module, used to screen and optimize drug test data based on genetic algorithms to obtain drug test reaction characteristics;

[0114] An AE determination module is used to determine a risk score based on a drug trial database and drug trial reaction characteristics;

[0115] The AE warning module is used to classify different risk levels according to risk scores and issue risk warnings based on risk levels.

[0116] The beneficial effects of the present invention are as follows:

[0117] 1) Genetic algorithms and correlation analysis methods are used to effectively extract drug reaction features with significant effects, thereby simplifying the data and improving the performance of the model, thereby increasing the accuracy of clinical decision-making.

[0118] 2) Risks are graded in detail so that medical staff can take appropriate measures for different levels of risks, thereby improving the timeliness and effectiveness of clinical responses and ensuring the safety of subjects.

[0119] 3) By integrating specific technologies of data analysis and risk assessment, the clinical research process is optimized, and research efficiency and data processing speed are improved.

[0120] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0121] The present invention uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only used to help understand the method and core ideas of the present invention. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for detecting the risk of adverse events in drug clinical trials, characterized in that: The steps include: Construct a clinical biological model based on the subjects' physical health status, physical parameters and historical examination reports; Recording the information of the test drugs received by the subject and generating a test drug database; Real-time monitoring of the physical function parameters and biological indicators of the subject after the drug trial is performed using physiological monitoring equipment and a health monitoring system to obtain drug trial data; Screening and optimizing the drug test data based on a genetic algorithm to obtain drug test reaction characteristics; Determining a risk score based on the drug test database and the drug test reaction characteristics; Different risk levels are divided according to the risk scores, and risk warnings are issued according to the risk levels.

2. The method for detecting adverse events in drug clinical trials according to claim 1, characterized in that: A clinical biological model is constructed based on the subject's physical health status, physical parameters and historical examination reports, including: Collecting the physical parameters; the physical parameters include: height, weight, body mass index, body temperature, blood data and metabolic index; The physical health status is obtained through physical examination; the physical health status is obtained by a physician through a comprehensive assessment of the physical examination report, living habits and mental health of the subject; The clinical biological model is constructed using regression analysis based on the physical health status, the physical parameters and the historical examination report.

3. The method for risk detection of adverse events in drug clinical trials according to claim 1, characterized in that: The drug trial database includes: drug name, dosage, route of administration and time of administration; the route of administration includes: oral administration, injection and external application; the time of administration includes: drug trial time point and the time interval with the drug trial time point.

4. The method for risk detection of adverse events in drug clinical trials according to claim 1, characterized in that: The physical function parameters and biological indicators of the subject after the drug trial are monitored in real time according to the physiological monitoring equipment and the health monitoring system to obtain the drug trial data. Specifically, the subject wears the physiological monitoring equipment after the drug trial, and the physical function parameters and biological indicators of the subject are collected through the physiological monitoring equipment, and the collected results are integrated through the health monitoring system to obtain the drug trial data.

5. The method for risk detection of adverse events in drug clinical trials according to claim 1, characterized in that: The drug test data is screened and optimized based on a genetic algorithm to obtain drug test reaction characteristics, including: Performing a preprocessing operation on the drug test data to obtain preprocessed data; the preprocessing operation includes: data cleaning, outlier detection, data standardization and feature selection; Randomly generate a group of individuals, each of which represents one of the preprocessed data; performing characteristic evaluation on the individuals according to a fitness function; Based on the tournament selection method, individuals with fitness higher than the preset threshold are selected as parents; Performing genetic recombination on the parent generation through multi-point crossover and gene change to obtain new individuals; Merging the new individual with the individual to obtain an updated population; Iteratively updating the update population through the fitness function until the fitness converges to a preset convergence threshold, thereby obtaining a screening feature; The influencing factors in the screening characteristics are removed by correlation analysis and LASSO regression method to obtain the drug reaction characteristics.

6. The method for risk detection of adverse events in drug clinical trials according to claim 5, characterized in that: The step of outlier detection comprises: Calculate the first quartile and the third quartile of the data of different test drugs; Obtaining an interquartile range according to the first quartile and the third quartile; Determine an abnormal upper boundary and an abnormal lower boundary according to the interquartile range; defining the drug test data exceeding the abnormal upper boundary or the abnormal lower boundary as suspected abnormal values; The suspected abnormal value is confirmed by a physician to obtain the true abnormal value.

7. The method for detecting the risk of adverse events in drug clinical trials according to claim 5, characterized in that: The expression of the fitness function is: Among them, F ( x ) is the fitness value of individual x, E ( x ) is the efficacy score of individual x, S ( x ) Score the side effects of individual x, C ( x ) is the individual difference score of individual x, D ( x ) is the tolerance score of individual x, α is the adjustment coefficient, ω1, ω2 and ω3 are all weight coefficients, ω1+ω2+ω3=1.

8. The method for risk detection of adverse events in drug clinical trials according to claim 1, characterized in that: The risk score is calculated as follows: Where Q is the risk score, A n is the nth physical data of the subject, T is the end time of observation, P ( t ) is the subject's status score at time t, R is the drug risk coefficient, M m is the mth drug characteristic.

9. The method for risk detection of adverse events in drug clinical trials according to claim 1, characterized in that: Different risk levels are divided according to the risk scores, and risk warnings are issued according to the risk levels, including: When the risk score is less than 5, the risk level is determined as the first risk level; When the risk score is greater than or equal to 5 and less than 10, the risk level is determined as a second risk level; When the risk score is greater than or equal to 10 and less than 15, the risk level is determined as the third risk level; When the risk score is greater than or equal to 15 and less than 20, the risk level is determined to be the fourth risk level; When the risk score is greater than or equal to 20, the risk level is determined to be a fifth risk level.

10. A risk detection system for adverse events in drug clinical trials, characterized in that: include: The human information module is used to build a clinical biological model based on the subject's physical health status, physical parameters and historical examination reports; A drug test information module, used to record the drug test information received by the subject and generate a drug test database; A monitoring module, used to monitor the physical function parameters and biological indicators of the subject after the drug trial in real time according to the physiological monitoring equipment and the health monitoring system to obtain drug trial data; An AE identification module is used to screen and optimize the drug test data based on a genetic algorithm to obtain drug test reaction characteristics; An AE determination module, used to determine a risk score based on the drug test database and the drug test reaction characteristics; The AE warning module is used to classify different risk levels according to the risk scores and to issue risk warnings according to the risk levels.

Images