CN117935949A - Early warning method and system for potential addiction causing magic medicine based on weighted judgment - Google Patents

Early warning method and system for potential addiction causing magic medicine based on weighted judgment Download PDF

Info

Publication number
CN117935949A
CN117935949A CN202311694068.XA CN202311694068A CN117935949A CN 117935949 A CN117935949 A CN 117935949A CN 202311694068 A CN202311694068 A CN 202311694068A CN 117935949 A CN117935949 A CN 117935949A
Authority
CN
China
Prior art keywords
information
medicine
data
module
metamorphosis
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311694068.XA
Other languages
Chinese (zh)
Inventor
林素静
赵振中
何利思
赵睿涵
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Vocational And Technical University
Original Assignee
Shenzhen Vocational And Technical University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Vocational And Technical University filed Critical Shenzhen Vocational And Technical University
Priority to CN202311694068.XA priority Critical patent/CN117935949A/en
Publication of CN117935949A publication Critical patent/CN117935949A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G01N21/31Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
    • G01N21/35Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
    • G01N21/3563Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G01N21/31Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
    • G01N21/35Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
    • G01N21/359Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16CCOMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C20/00Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
    • G16C20/10Analysis or design of chemical reactions, syntheses or processes
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16CCOMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C20/00Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
    • G16C20/20Identification of molecular entities, parts thereof or of chemical compositions
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16CCOMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C20/00Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
    • G16C20/70Machine learning, data mining or chemometrics

Landscapes

  • Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Analytical Chemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Crystallography & Structural Chemistry (AREA)
  • Computing Systems (AREA)
  • Immunology (AREA)
  • Biochemistry (AREA)
  • General Physics & Mathematics (AREA)
  • Pathology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Treatment And Welfare Office Work (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • Evolutionary Computation (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)

Abstract

The invention belongs to the technical field of prevention and monitoring of drug abuse, and discloses a method and a system for pre-warning potential addiction induced magic drugs based on weight judgment, wherein the pre-warning system for potential addiction induced magic drugs based on weight judgment comprises: the medicine weighing system comprises a data acquisition module, a medicine detection module, a central control module, a data weighting module, a medicine bad information acquisition module, a medicine prediction module, an early warning module and a display module. According to the invention, the parameter of traditional mathematical modeling is reduced and the complexity of chemometry is reduced by combining a medicine detection module with a machine learning algorithm, the types of various components can be rapidly matched in characteristics and detected simultaneously, and the content of the components can be evaluated by combining a standard working curve with a neural network, so that the types and the content of various addictive drug components can be rapidly and accurately detected; meanwhile, the poor medicine information can be quickly and accurately acquired by the poor medicine information acquisition module before medicine taking.

Description

Early warning method and system for potential addiction causing magic medicine based on weighted judgment
Technical Field
The invention belongs to the technical field of drug abuse prevention and monitoring, and particularly relates to a warning method and a warning system for potential addiction drugs based on weighted judgment.
Background
At present, the problem of drug abuse creates serious health and social problems worldwide. Previous early warning methods and systems are based primarily on the detection of pharmaceutical ingredients, which often fail to capture new addictive drugs because their ingredients often change. Thus, there is a need for a more efficient method and system for alerting the presence of potentially addictive drugs.
Through the above analysis, the problems and defects existing in the prior art are as follows:
(1) Previous early warning methods and systems are based primarily on the detection of pharmaceutical ingredients, which often fail to capture new addictive drugs because their ingredients often change.
(2) The existing pre-warning system for potential addiction causing drugs based on weight judgment is complicated in drug component type detection technology and long in time consumption; meanwhile, bad information of the medicine cannot be accurately and timely acquired.
Problems of the prior art:
1. data quality and integrity: FAERS the quality of the reports received varies, and some reports do not have enough detailed information to make data analysis and understanding difficult. Furthermore, due to the voluntary reporting system, there are a large number of unreported events, which lead to data skew and misinterpretation.
2. Data processing and analysis: FAERS provides raw data, requiring the researchers to perform data cleaning, processing and analysis themselves. This not only requires a lot of manpower and time, but also introduces additional errors in the data processing and analysis.
3. Early warning capability: although FAERS is capable of collecting and providing a large amount of drug adverse event data, it does not have predictive and warning capabilities itself. This means that even if a potentially problematic drug is found, it takes a period of time to perform the necessary risk assessment and management activities.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a warning method and a warning system for potential addiction causing drugs based on weight judgment.
The invention is realized in such a way that an early warning system of potential addiction induced drugs based on weight judgment comprises a drug bad information acquisition module and a drug prediction module, wherein:
The medicine adverse information acquisition module is responsible for collecting data about medicine adverse reactions from a plurality of sources (such as hospitals, clinical trials, medicine regulatory authorities and patient reports), including medicine names, adverse reaction types, severity, patient background information and the like, uploading the data after cleaning and formatting treatment to the central control module, and ensuring that proper safety measures are adopted to protect patient privacy and data safety when the data are processed and transmitted;
The medicine prediction module receives the data from the medicine bad information acquisition module, performs weighting processing on the data, adopts a machine learning algorithm or other suitable algorithms, such as a decision tree, a neural network or a random forest, and the like, performs analysis processing on the data so as to predict the occurrence of potential addictions or illusive medicines, including the components, effects and potential abuse risks of the medicines, and feeds back the prediction result to the central control module, and can be used for reference by related medical institutions and regulatory departments for medicine safety monitoring and risk management.
Further, the system specifically includes:
The system comprises a data acquisition module, a medicine detection module, a central control module, a data weighting module, a medicine bad information acquisition module, a medicine prediction module, an early warning module and a display module;
The data acquisition module is connected with the central control module and used for acquiring various data related to the medicines, including chemical components, biological activity, clinical effects, epidemiological data, social media information and the like;
The medicine detection module is connected with the central control module and used for detecting the types and the contents of components in the sample medicine;
The central control module is connected with the data acquisition module, the medicine detection module, the data weighting module, the medicine bad information acquisition module, the medicine prediction module, the early warning module and the display module and used for controlling the normal of each module;
the data weighting module is connected with the central control module and used for carrying out weighting processing on the acquired data and carrying out different weighting according to the importance and the credibility of each data;
The medicine adverse information acquisition module is connected with the central control module and used for acquiring medicine adverse reaction information;
The medicine prediction module is connected with the central control module and is used for predicting the occurrence of potential addiction causing medicines, including the components, effects and potential abuse risks, by using the weighted data and adopting a machine learning algorithm or other suitable algorithms;
The early warning module is connected with the central control module and used for transmitting the prediction result to an early warning system, and the system can inform related departments and institutions in time and take necessary measures to reduce the risk of abuse of medicines;
the display module is connected with the central control module and used for displaying the acquired data, the detection result, the acquired adverse reaction information, the prediction result and the early warning information.
Further, the drug detection module method is as follows:
(1) Preprocessing a sample of the addictive drug to be tested; carrying out infrared spectrum detection on the pretreated Chinese patent medicine sample; preprocessing infrared spectrum data obtained by infrared spectrum detection to obtain a standard infrared spectrum;
(2) Establishing a standard addictive drug component infrared database; establishing a qualitative identification model of infrared spectrum and carrying out qualitative identification;
(3) The spectral data is passed through the model of quantitative analysis of the addictive drug, and the content of the components in the addictive drug is measured by adopting a method of combining a neural network algorithm with the standard working curve of the addictive drug components.
Further, the pretreatment of the sample of the addiction causing drug to be tested is specifically as follows: according to the types of the Chinese addictive drug, a corresponding label data set { text1, text2, … }, which is then ground into particles with the size smaller than 2.5 μm, and then vacuum-dried.
Further, the specific process of infrared spectrum detection of the pretreated Chinese patent medicine sample comprises the following steps: and sequentially passing the marked addiction causing medicine data set to be detected through a Fourier transform spectrometer, and obtaining near infrared spectrum data of the sample with absorbance as an ordinate in a solid detection mode.
Further, the preprocessing of the infrared spectrum data includes:
correcting the base line of the spectrogram of the addictive drug, and correcting the inclined or drifting base line and interference fringes in the spectrogram point by point;
After the base line of the spectrogram of the drug causing addiction is corrected, carrying out spectrum normalization treatment, normalizing the absorbance of the maximum absorption peak in the spectrum to be 1, and normalizing the base line of the spectrum to be 0;
And carrying out linear processing on the normalized spectrum data to generate data so as to obtain the infrared spectrum of the standard middle addiction illusion-causing medicine.
Further, the method for obtaining the poor drug information comprises the following steps:
Acquiring prescription information, and extracting medication information and patient information from the prescription information; extracting medication component information corresponding to the medication information from an addiction causing medicine component information database;
invoking a crowd characteristic metamorphosis model, and generating a patient characteristic metamorphosis model according to the patient information, wherein the patient characteristic metamorphosis model comprises patient characteristic information, addiction causing medicine component information and adverse reaction information;
Judging whether the medication component information is matched with the addiction causing medicine component information in the characteristic metamorphosis model of the patient, if so, executing the next step;
obtaining medication information and adverse reaction information corresponding to the addiction causing medicine component information and outputting the medication information and the adverse reaction information;
the calling crowd characteristic metamorphosis model generates a patient characteristic metamorphosis model according to the patient information, wherein the patient characteristic metamorphosis model comprises patient characteristic information, addiction causing medicine component information and adverse reaction information, and the patient characteristic metamorphosis model specifically comprises the following components:
Extracting patient characteristic information from the patient information, wherein the patient characteristic information comprises gender, age, medical history and physique information;
Extracting at least one crowd characteristic metamorphosis sub-model matched with the patient characteristic information from the crowd characteristic metamorphosis model;
Generating the patient characteristic metamorphosis model by using the crowd characteristic metamorphosis sub-model;
The crowd characteristic metamorphosis model specifically comprises: sex metamorphosis submodel, age metamorphosis submodel, pathology metamorphosis submodel, constitution metamorphosis submodel.
And extracting medicine component information, corresponding organ system adverse reaction information and severity information from the addiction causing medicine component information database according to the clinical difference characteristic information of the medicine on the sex, and generating a sex metamorphosis sub-model.
And extracting the medicine component information, the corresponding organ system adverse reaction information and the severity information from the addiction causing medicine component information database according to the clinical difference characteristic information of the medicine on the age, and generating an age metamorphosis sub-model.
And extracting medicine component information, corresponding organ system adverse reaction information and severity information from the addiction causing medicine component information database according to the clinical difference characteristic information of the medicine on pathology, and generating a pathological metamorphosis sub-model.
And extracting medicine component information, corresponding organ system adverse reaction information and severity information from the addiction causing medicine component information database according to the clinical difference characteristic information of the medicine on the special physique, and generating a physique metamorphosis sub-model.
Inquiring adverse reaction information corresponding to the medication component information from the patient characteristic metamorphosis model;
Extracting medication information corresponding to the medication component information from an addiction causing medicine component information database;
acquiring adverse reaction information corresponding to the medication information according to the adverse reaction information corresponding to the medication component information;
and outputting the medication information and the adverse reaction information.
The invention provides another object of providing a warning method of potential addiction causing drugs based on weighted judgment, comprising the following steps:
Step one, various data related to medicines are collected through a data collection module, wherein the data comprise chemical components, biological activity, clinical effects, epidemiological data, social media information and the like; detecting the types and the contents of components in the sample medicines through a medicine detection module;
step two, the central control module carries out weighting processing on the acquired data through the data weighting module, and carries out different weighting according to the importance and the credibility of each data;
step three, acquiring adverse drug reaction information through a poor drug information acquisition module; predicting, by the drug prediction module, the occurrence of the potential addictive-causing drug, including its composition, effect, and potential abuse risk, using a machine learning algorithm or other suitable algorithm using the weighted data;
Step four, the prediction result is transmitted to an early warning system through an early warning module, the system can inform related departments and institutions in time, and necessary measures are taken to reduce the risk of abuse of medicines;
and fifthly, displaying the acquired data, the detection result, the acquired adverse reaction information, the prediction result and the early warning information through a display module.
A computer device, characterized in that the computer device comprises a memory and a processor, the memory storing a computer program, which when executed by the processor, causes the processor to execute the steps of the pre-warning method of potential addictive-causing drugs based on a weighted judgment.
A computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the pre-warning method of potentially addictive drugs based on weighted decisions.
The information data processing terminal is characterized by being used for realizing the early warning system of the potential addiction causing medicine based on the weighted judgment.
In combination with the technical scheme and the technical problems to be solved, the technical scheme to be protected has the following advantages and positive effects:
First, the invention can more accurately early warn the occurrence of potential addictive drugs, reduce the risk of drug abuse and protect public health. According to the invention, the drug detection module is combined with the machine learning algorithm, so that the parameter of traditional mathematical modeling is reduced, the complexity of chemometry is reduced, compared with the High Performance Liquid Chromatography (HPLC), the method has the advantages of simple operation process and high network learning efficiency, can rapidly and characteristic match and detect the types of various components at the same time, and can evaluate the content of the components by combining a standard working curve with a neural network, so that the types and the content of various addictive drug components can be rapidly and accurately detected; meanwhile, the poor medicine information can be quickly and accurately acquired by the poor medicine information acquisition module before medicine taking.
Secondly, the invention can more accurately early warn the occurrence of potential addictive drugs, reduce the risk of drug abuse and protect public health. According to the invention, the drug detection module is combined with the machine learning algorithm, so that the parameter of traditional mathematical modeling is reduced, the complexity of chemometry is reduced, compared with the High Performance Liquid Chromatography (HPLC), the method has the advantages of simple operation process and high network learning efficiency, can rapidly and characteristic match and detect the types of various components at the same time, and can evaluate the content of the components by combining a standard working curve with a neural network, so that the types and the content of various addictive drug components can be rapidly and accurately detected; meanwhile, the poor medicine information can be quickly and accurately acquired by the poor medicine information acquisition module before medicine taking.
Third, the significant technical improvements brought by the drug bad information acquisition module and the drug prediction module of the system provided by the invention include:
1) Efficiency and accuracy of medicine safety monitoring are improved: by automatically collecting and processing drug adverse reaction data from multiple sources, the system is able to more efficiently and accurately identify drug-related safety risks.
2) Enhancing drug risk prediction capability: the weighted data is analyzed by using an advanced machine learning algorithm, and the system can accurately predict potential addictive or illusive drugs and the abuse risk of the drugs discovered in advance.
3) Data driven decision support: the system provides data-based decision support for medical institutions and drug administration departments, helps them to better manage drug risks, and optimizes drug use and administration strategies.
4) Improving patient safety: through timely discernment and handling medicine adverse reaction information, the system can reduce patient's injury because of medicine adverse reaction causes, improves patient's safety.
5) Promoting personalized medicine: the system can predict drug response based on specific conditions of patients, support personalized drug treatment decisions and improve treatment effect.
6) Transparency and response speed of drug administration are enhanced: by quickly reacting and disclosing transparent drug safety information, the system enhances public trust in drug safety administration.
7) Cross source data integration and analysis: the system is able to integrate data from different sources, providing a more comprehensive drug safety perspective, which is difficult to achieve in conventional approaches.
8) Adaptability and extensibility: the machine learning model and algorithm employed can accommodate new data and new patterns, ensuring that the system is continually improved and updated over time and accumulation of data.
The system provided by the invention remarkably improves the efficiency, accuracy and prediction capability of drug safety monitoring by integrating and analyzing multi-source data and applying an advanced data analysis technology, thereby enhancing the overall effect of drug management and protecting public health and safety.
Drawings
FIG. 1 is a block diagram of a warning system for potential addictive drugs based on weighted judgment according to an embodiment of the present invention.
Fig. 2 is a flowchart of a method for early warning of potential addictive drugs based on weighted judgment according to an embodiment of the present invention.
Fig. 3 is a flowchart of a method for detecting a module of a drug according to an embodiment of the present invention.
In fig. 1: 1. a data acquisition module; 2.a drug detection module; 3. a central control module; 4. a data weighting module; 5. a medicine defect information acquisition module; 6. a drug prediction module; 7. an early warning module; 8. and a display module.
Detailed Description
The present invention will be described in further detail with reference to the following examples in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Example 1: pre-warning system based on deep learning
Medicine defect information acquisition module: the module may collect data from a variety of sources, including medical records, drug report databases, social media posts, and the like. These data may be cleaned and formatted by Natural Language Processing (NLP) techniques to extract the necessary information such as drug name, type of adverse reaction, severity, patient background information, etc. In processing and transmitting data, data encryption and anonymization techniques are required to ensure patient privacy and data security.
Medicine prediction module: the module may use a deep learning algorithm, such as Convolutional Neural Network (CNN) or Recurrent Neural Network (RNN), to weight and analyze the data. For example, the data may be weighted according to factors such as severity, frequency, and range of adverse effects of the drug. The data is then trained and tested by a deep learning algorithm to predict the appearance of potential addictive or fantasy drugs.
Example 2: early warning system based on ensemble learning
Medicine defect information acquisition module: the module can collect adverse reaction information of medicines from data sources such as medicine regulatory authorities, hospitals, medicine manufacturers and the like. The data may be cleaned and standardized by a data preprocessing technique and then uploaded to the central control module via a secure data transmission protocol.
Medicine prediction module: the module may weight and analyze the data using an ensemble learning algorithm, such as a random forest or gradient enhanced decision tree (GBDT). For example, the data may be weighted according to factors such as severity, frequency, and range of influence of adverse reactions. The data is then trained and tested by an ensemble learning algorithm to predict the occurrence of potential addictive or fantasy drugs. The advantage of the ensemble learning algorithm is that it can reduce the risk of overfitting and improve the accuracy of the predictions.
The invention is mainly aimed at improving the problems and defects of the following prior art, and realizes remarkable technical progress:
Insufficient data collection and analysis: traditional drug safety monitoring often relies on limited data sources and manual analysis, lacking comprehensiveness and real-time.
Potential risk identification is inaccurate: due to the lack of effective data processing and analysis means, it is difficult to accurately predict which drugs may have addictive or fantasy risks.
Reaction retardation: in the prior art, identification and response to potentially risky drugs is often delayed and risk management and control is not possible in a timely manner.
Privacy and data security issues: data protection and privacy security measures are often inadequate when processing sensitive patient data and drug information.
The invention adopts the solution:
Comprehensive data collection and weighting: the data acquisition module is used for collecting wide medicine data including chemical components, biological activity, clinical effects and the like, and the data weighting module is used for weighting the data so as to ensure the accuracy and the comprehensiveness of analysis.
Advanced predictive analysis techniques: the drug prediction module uses a machine learning algorithm or other suitable algorithm to analyze based on the weighted data to more accurately predict the occurrence of potential addictions or phantom drugs.
Timely early warning mechanism: the early warning module can rapidly transmit the prediction result to related departments and institutions, and rapid response and management of potential risk medicines are realized.
Enhanced data security and privacy protection: appropriate security measures are taken to protect patient privacy and data security when processing and transmitting sensitive data.
Visual information display: the display module provides clear data view, detection result and early warning information for the user, so that information interpretation and decision making are more efficient.
The invention achieves remarkable technical progress:
Higher prediction accuracy: by comprehensively analyzing the multi-source data and applying advanced analysis algorithms, the system can more accurately identify potential addictive or fantasy drugs.
Quick response and risk management: the real-time early warning mechanism allows potential risks to be responded quickly and measures to be taken in time, so that the efficiency of medicine safety supervision is improved.
Data driven decision support: and data-driven support is provided for decision makers, and the quality of medicine management and supervision is improved.
Enhanced data security and privacy protection: the security and privacy in the sensitive data processing process are ensured, and the standard of modern data protection is met.
As shown in fig. 1, the early warning system for potential addiction drugs based on weighted judgment provided by the embodiment of the invention includes:
The medicine quality control system comprises a data acquisition module 1, a medicine detection module 2, a central control module 3, a data weighting module 4, a medicine quality information acquisition module 5, a medicine prediction module 6, an early warning module 7 and a display module 8.
The data acquisition module 1 is connected with the central control module 3 and is used for acquiring various data related to the medicines, including chemical components, biological activity, clinical effects, epidemiological data, social media information and the like;
The medicine detection module 2 is connected with the central control module 3 and is used for detecting the types and the contents of components in the sample medicine;
The central control module 3 is connected with the data acquisition module 1, the medicine detection module 2, the data weighting module 4, the medicine bad information acquisition module 5, the medicine prediction module 6, the early warning module 7 and the display module 8 and is used for controlling the normal of each module;
The data weighting module 4 is connected with the central control module 3 and is used for carrying out weighting processing on the acquired data and carrying out different weighting according to the importance and the credibility of each data;
the medicine adverse information acquisition module 5 is connected with the central control module 3 and is used for acquiring medicine adverse reaction information;
A drug prediction module 6, connected to the central control module 3, for predicting the occurrence of potential addictive drugs, including their composition, effects and potential abuse risk, using a machine learning algorithm or other suitable algorithm using the weighted data;
The early warning module 7 is connected with the central control module 3 and is used for transmitting the prediction result to an early warning system, and the system can inform related departments and institutions in time and take necessary measures to reduce the risk of abusing medicines;
The display module 8 is connected with the central control module 3 and used for displaying the collected data, the detection result, the obtained adverse reaction information, the prediction result and the early warning information.
As shown in FIG. 2, the pre-warning method of potential addiction causing drugs based on weighted judgment provided by the invention comprises the following steps:
s101, various data related to the medicines are collected through a data collection module, wherein the data comprise chemical components, biological activities, clinical effects, epidemiological data, social media information and the like; detecting the types and the contents of components in the sample medicines through a medicine detection module;
S102, the central control module performs weighting processing on the acquired data through the data weighting module, and performs different weighting according to the importance and the credibility of each data;
s103, acquiring adverse drug reaction information through a poor drug information acquisition module; predicting, by the drug prediction module, the occurrence of the potential addictive-causing drug, including its composition, effect, and potential abuse risk, using a machine learning algorithm or other suitable algorithm using the weighted data;
S104, transmitting the prediction result to an early warning system through an early warning module, wherein the system can timely inform related departments and institutions, and taking necessary measures to reduce the risk of abusing medicines;
S105, the acquired data, the detection result, the acquired adverse reaction information, the prediction result and the early warning information are displayed through a display module.
As shown in fig. 3, the method for detecting the medicine provided by the invention is as follows:
S201, preprocessing a sample of the addiction causing magic medicine to be tested; carrying out infrared spectrum detection on the pretreated Chinese patent medicine sample; preprocessing infrared spectrum data obtained by infrared spectrum detection to obtain a standard infrared spectrum;
s202, establishing an infrared database of components of standard addictive drugs; establishing a qualitative identification model of infrared spectrum and carrying out qualitative identification;
S203, measuring the content of the components in the addictive drug by combining the spectral data with the addictive drug component standard working curve through a addictive drug quantitative analysis model by adopting a neural network algorithm.
The pretreatment of the sample of the addiction causing magic medicine to be tested provided by the invention comprises the following steps: according to the types of the Chinese addictive drug, a corresponding label data set { text1, text2, … }, which is then ground into particles with the size smaller than 2.5 μm, and then vacuum-dried.
The specific process for carrying out infrared spectrum detection on the pretreated Chinese patent medicine sample provided by the invention comprises the following steps: and sequentially passing the marked addiction causing medicine data set to be detected through a Fourier transform spectrometer, and obtaining near infrared spectrum data of the sample with absorbance as an ordinate in a solid detection mode.
The preprocessing of the infrared spectrum data provided by the invention comprises the following steps:
correcting the base line of the spectrogram of the addictive drug, and correcting the inclined or drifting base line and interference fringes in the spectrogram point by point;
After the base line of the spectrogram of the drug causing addiction is corrected, carrying out spectrum normalization treatment, normalizing the absorbance of the maximum absorption peak in the spectrum to be 1, and normalizing the base line of the spectrum to be 0;
And carrying out linear processing on the normalized spectrum data to generate data so as to obtain the infrared spectrum of the standard middle addiction illusion-causing medicine.
The method for acquiring the drug defect information provided by the invention comprises the following steps:
Acquiring prescription information, and extracting medication information and patient information from the prescription information; extracting medication component information corresponding to the medication information from an addiction causing medicine component information database;
invoking a crowd characteristic metamorphosis model, and generating a patient characteristic metamorphosis model according to the patient information, wherein the patient characteristic metamorphosis model comprises patient characteristic information, addiction causing medicine component information and adverse reaction information;
Judging whether the medication component information is matched with the addiction causing medicine component information in the characteristic metamorphosis model of the patient, if so, executing the next step;
obtaining medication information and adverse reaction information corresponding to the addiction causing medicine component information and outputting the medication information and the adverse reaction information;
the calling crowd characteristic metamorphosis model generates a patient characteristic metamorphosis model according to the patient information, wherein the patient characteristic metamorphosis model comprises patient characteristic information, addiction causing medicine component information and adverse reaction information, and the patient characteristic metamorphosis model specifically comprises the following components:
Extracting patient characteristic information from the patient information, wherein the patient characteristic information comprises gender, age, medical history and physique information;
Extracting at least one crowd characteristic metamorphosis sub-model matched with the patient characteristic information from the crowd characteristic metamorphosis model;
Generating the patient characteristic metamorphosis model by using the crowd characteristic metamorphosis sub-model;
The crowd characteristic metamorphosis model specifically comprises: sex metamorphosis submodel, age metamorphosis submodel, pathology metamorphosis submodel, constitution metamorphosis submodel.
And extracting medicine component information, corresponding organ system adverse reaction information and severity information from the addiction causing medicine component information database according to the clinical difference characteristic information of the medicine on the sex, and generating a sex metamorphosis sub-model.
And extracting the medicine component information, the corresponding organ system adverse reaction information and the severity information from the addiction causing medicine component information database according to the clinical difference characteristic information of the medicine on the age, and generating an age metamorphosis sub-model.
And extracting medicine component information, corresponding organ system adverse reaction information and severity information from the addiction causing medicine component information database according to the clinical difference characteristic information of the medicine on pathology, and generating a pathological metamorphosis sub-model.
And extracting medicine component information, corresponding organ system adverse reaction information and severity information from the addiction causing medicine component information database according to the clinical difference characteristic information of the medicine on the special physique, and generating a physique metamorphosis sub-model.
Inquiring adverse reaction information corresponding to the medication component information from the patient characteristic metamorphosis model;
Extracting medication information corresponding to the medication component information from an addiction causing medicine component information database;
acquiring adverse reaction information corresponding to the medication information according to the adverse reaction information corresponding to the medication component information;
and outputting the medication information and the adverse reaction information.
A computer device, characterized in that the computer device comprises a memory and a processor, the memory storing a computer program, which when executed by the processor, causes the processor to execute the steps of the pre-warning method of potential addictive-causing drugs based on a weighted judgment.
A computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the pre-warning method of potentially addictive drugs based on weighted decisions.
The information data processing terminal is characterized by being used for realizing the early warning system of the potential addiction causing medicine based on the weighted judgment.
The invention can more accurately early warn the occurrence of potential addictive drugs, reduce the risk of drug abuse and protect public health. According to the invention, the drug detection module is combined with the machine learning algorithm, so that the parameter of traditional mathematical modeling is reduced, the complexity of chemometry is reduced, compared with the High Performance Liquid Chromatography (HPLC), the method has the advantages of simple operation process and high network learning efficiency, can rapidly and characteristic match and detect the types of various components at the same time, and can evaluate the content of the components by combining a standard working curve with a neural network, so that the types and the content of various addictive drug components can be rapidly and accurately detected; meanwhile, the poor medicine information can be quickly and accurately acquired by the poor medicine information acquisition module before medicine taking.
It should be noted that the embodiments of the present invention can be realized in hardware, software, or a combination of software and hardware. The hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or special purpose design hardware. Those of ordinary skill in the art will appreciate that the apparatus and methods described above may be implemented using computer executable instructions and/or embodied in processor control code, such as provided on a carrier medium such as a magnetic disk, CD or DVD-ROM, a programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The device of the present invention and its modules may be implemented by hardware circuitry, such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., as well as software executed by various types of processors, or by a combination of the above hardware circuitry and software, such as firmware.
The invention can more accurately early warn the occurrence of potential addictive drugs, reduce the risk of drug abuse and protect public health. According to the invention, the drug detection module is combined with the machine learning algorithm, so that the parameter of traditional mathematical modeling is reduced, the complexity of chemometry is reduced, compared with the High Performance Liquid Chromatography (HPLC), the method has the advantages of simple operation process and high network learning efficiency, can rapidly and characteristic match and detect the types of various components at the same time, and can evaluate the content of the components by combining a standard working curve with a neural network, so that the types and the content of various addictive drug components can be rapidly and accurately detected; meanwhile, the poor medicine information can be quickly and accurately acquired by the poor medicine information acquisition module before medicine taking.
The foregoing is merely illustrative of specific embodiments of the present invention, and the scope of the invention is not limited thereto, but any modifications, equivalents, improvements and alternatives falling within the spirit and principles of the present invention will be apparent to those skilled in the art within the scope of the present invention.

Claims (10)

1. The utility model provides a potential addictive drug warning system based on weighted judgement, its characterized in that, the system includes medicine bad information acquisition module and medicine prediction module, wherein:
the medicine adverse information acquisition module is responsible for collecting data about medicine adverse reactions from a plurality of sources, including medicine names, adverse reaction types, severity, patient background information and the like, uploading the data after cleaning and formatting to the central control module, and ensuring that proper safety measures are adopted to protect privacy and data safety of patients when the data are processed and transmitted;
the medicine prediction module receives the data from the medicine bad information acquisition module, performs weighting processing on the data, and adopts a decision tree algorithm to analyze and process the data so as to predict the occurrence of potential addictions or illusive medicines, including the components, effects and potential abuse risks of the medicines, and the prediction result is fed back to the central control module and can be used for reference by related medical institutions and supervision departments for medicine safety monitoring and risk management.
2. The weighting-based alert system for potentially addictive drugs of claim 1, comprising:
The system comprises a data acquisition module, a medicine detection module, a central control module, a data weighting module, a medicine bad information acquisition module, a medicine prediction module, an early warning module and a display module;
The data acquisition module is connected with the central control module and used for acquiring various data related to the medicines, including chemical components, biological activity, clinical effects, epidemiological data, social media information and the like;
The medicine detection module is connected with the central control module and used for detecting the types and the contents of components in the sample medicine;
The central control module is connected with the data acquisition module, the medicine detection module, the data weighting module, the medicine bad information acquisition module, the medicine prediction module, the early warning module and the display module and used for controlling the normal of each module;
the data weighting module is connected with the central control module and used for carrying out weighting processing on the acquired data and carrying out different weighting according to the importance and the credibility of each data;
The medicine adverse information acquisition module is connected with the central control module and used for acquiring medicine adverse reaction information;
The medicine prediction module is connected with the central control module and is used for predicting the occurrence of potential addiction causing medicines, including the components, effects and potential abuse risks, by using the weighted data and adopting a machine learning algorithm or other suitable algorithms;
The early warning module is connected with the central control module and used for transmitting the prediction result to an early warning system, and the system can inform related departments and institutions in time and take necessary measures to reduce the risk of abuse of medicines;
the display module is connected with the central control module and used for displaying the acquired data, the detection result, the acquired adverse reaction information, the prediction result and the early warning information.
3. The pre-warning system of potential addictive drugs based on weight determination as set forth in claim 2, wherein the drug detection module method is as follows:
(1) Preprocessing a sample of the addictive drug to be tested; carrying out infrared spectrum detection on the pretreated Chinese patent medicine sample; preprocessing infrared spectrum data obtained by infrared spectrum detection to obtain a standard infrared spectrum;
(2) Establishing a standard addictive drug component infrared database; establishing a qualitative identification model of infrared spectrum and carrying out qualitative identification;
(3) The spectral data is passed through the model of quantitative analysis of the addictive drug, and the content of the components in the addictive drug is measured by adopting a method of combining a neural network algorithm with the standard working curve of the addictive drug components.
4. The pre-warning system for potential addictive drugs based on weighted judgment as claimed in claim 3, wherein the pre-treatment of the sample of the addictive drug under test is specifically: according to the types of the Chinese addictive drug, a corresponding label data set { text1, text2, … }, then polishing the label data set to be less than 2.5 mu m in particle size, and then carrying out vacuum drying;
The specific process for carrying out infrared spectrum detection on the pretreated Chinese patent medicine sample comprises the following steps: and sequentially passing the marked addiction causing medicine data set to be detected through a Fourier transform spectrometer, and obtaining near infrared spectrum data of the sample with absorbance as an ordinate in a solid detection mode.
5. The weighting-based alert system for potentially addictive drugs of claim 3, wherein the preprocessing of infrared spectral data comprises:
correcting the base line of the spectrogram of the addictive drug, and correcting the inclined or drifting base line and interference fringes in the spectrogram point by point;
After the base line of the spectrogram of the drug causing addiction is corrected, carrying out spectrum normalization treatment, normalizing the absorbance of the maximum absorption peak in the spectrum to be 1, and normalizing the base line of the spectrum to be 0;
And carrying out linear processing on the normalized spectrum data to generate data so as to obtain the infrared spectrum of the standard middle addiction illusion-causing medicine.
6. The pre-warning system of potential addictive drugs based on weight judgment as claimed in claim 2, wherein the drug bad information acquisition module method is as follows:
Acquiring prescription information, and extracting medication information and patient information from the prescription information; extracting medication component information corresponding to the medication information from an addiction causing medicine component information database;
invoking a crowd characteristic metamorphosis model, and generating a patient characteristic metamorphosis model according to the patient information, wherein the patient characteristic metamorphosis model comprises patient characteristic information, addiction causing medicine component information and adverse reaction information;
Judging whether the medication component information is matched with the addiction causing medicine component information in the characteristic metamorphosis model of the patient, if so, executing the next step;
obtaining medication information and adverse reaction information corresponding to the addiction causing medicine component information and outputting the medication information and the adverse reaction information;
the calling crowd characteristic metamorphosis model generates a patient characteristic metamorphosis model according to the patient information, wherein the patient characteristic metamorphosis model comprises patient characteristic information, addiction causing medicine component information and adverse reaction information, and the patient characteristic metamorphosis model specifically comprises the following components:
Extracting patient characteristic information from the patient information, wherein the patient characteristic information comprises gender, age, medical history and physique information;
Extracting at least one crowd characteristic metamorphosis sub-model matched with the patient characteristic information from the crowd characteristic metamorphosis model;
Generating the patient characteristic metamorphosis model by using the crowd characteristic metamorphosis sub-model;
The crowd characteristic metamorphosis model specifically comprises: sex metamorphosis submodel, age metamorphosis submodel, pathology metamorphosis submodel, constitution metamorphosis submodel.
And extracting medicine component information, corresponding organ system adverse reaction information and severity information from the addiction causing medicine component information database according to the clinical difference characteristic information of the medicine on the sex, and generating a sex metamorphosis sub-model.
And extracting the medicine component information, the corresponding organ system adverse reaction information and the severity information from the addiction causing medicine component information database according to the clinical difference characteristic information of the medicine on the age, and generating an age metamorphosis sub-model.
And extracting medicine component information, corresponding organ system adverse reaction information and severity information from the addiction causing medicine component information database according to the clinical difference characteristic information of the medicine on pathology, and generating a pathological metamorphosis sub-model.
And extracting medicine component information, corresponding organ system adverse reaction information and severity information from the addiction causing medicine component information database according to the clinical difference characteristic information of the medicine on the special physique, and generating a physique metamorphosis sub-model.
Inquiring adverse reaction information corresponding to the medication component information from the patient characteristic metamorphosis model;
Extracting medication information corresponding to the medication component information from an addiction causing medicine component information database;
acquiring adverse reaction information corresponding to the medication information according to the adverse reaction information corresponding to the medication component information;
and outputting the medication information and the adverse reaction information.
7. A method for pre-warning a potential addictive drug based on a weighted judgment for implementing the pre-warning system based on a weighted judgment for a potential addictive drug as claimed in any one of claims 1-6, wherein the pre-warning method based on a weighted judgment for a potential addictive drug comprises:
Step one, various data related to medicines are collected through a data collection module, wherein the data comprise chemical components, biological activity, clinical effects, epidemiological data, social media information and the like; detecting the types and the contents of components in the sample medicines through a medicine detection module;
step two, the central control module carries out weighting processing on the acquired data through the data weighting module, and carries out different weighting according to the importance and the credibility of each data;
step three, acquiring adverse drug reaction information through a poor drug information acquisition module; predicting, by the drug prediction module, the occurrence of the potential addictive-causing drug, including its composition, effect, and potential abuse risk, using a machine learning algorithm or other suitable algorithm using the weighted data;
Step four, the prediction result is transmitted to an early warning system through an early warning module, the system can inform related departments and institutions in time, and necessary measures are taken to reduce the risk of abuse of medicines;
and fifthly, displaying the acquired data, the detection result, the acquired adverse reaction information, the prediction result and the early warning information through a display module.
8. A computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the method of pre-warning potential addictive drugs based on a weighted decision as claimed in any one of claims 7.
9. A computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the weighting-based method of pre-warning a potentially addictive drug as claimed in any one of claims 7.
10. An information data processing terminal, wherein the information data processing terminal is used for realizing the pre-warning system of potential addiction causing drugs based on weighted judgment as set forth in claim 1.
CN202311694068.XA 2023-12-11 2023-12-11 Early warning method and system for potential addiction causing magic medicine based on weighted judgment Pending CN117935949A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311694068.XA CN117935949A (en) 2023-12-11 2023-12-11 Early warning method and system for potential addiction causing magic medicine based on weighted judgment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311694068.XA CN117935949A (en) 2023-12-11 2023-12-11 Early warning method and system for potential addiction causing magic medicine based on weighted judgment

Publications (1)

Publication Number Publication Date
CN117935949A true CN117935949A (en) 2024-04-26

Family

ID=90760192

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311694068.XA Pending CN117935949A (en) 2023-12-11 2023-12-11 Early warning method and system for potential addiction causing magic medicine based on weighted judgment

Country Status (1)

Country Link
CN (1) CN117935949A (en)

Similar Documents

Publication Publication Date Title
Ventola Big data and pharmacovigilance: data mining for adverse drug events and interactions
Galetsi et al. Values, challenges and future directions of big data analytics in healthcare: A systematic review
CN109346145B (en) Method and system for actively monitoring adverse drug reactions
CN111145844B (en) Comprehensive medical supervision platform
Loh et al. Recommendations for laboratory informatics specifications needed for the application of patient-based real time quality control
Griffies et al. Wearable sensor shown to specifically quantify pruritic behaviors in dogs
CN109545387B (en) Abnormal case recognition method and computing equipment based on neural network
CN117151655B (en) Comprehensive analysis management system and method for multiple project detection results
CN111383726B (en) Electronic medical record data processing method and device, electronic equipment and readable medium
CN115691722B (en) Quality control method, device, equipment, medium and program product for medical data detection
CN111180027B (en) Patient portrait correlation rule screening method and device based on medical big data
CN111383761A (en) Medical data analysis method and device, electronic equipment and computer readable medium
CN111143652A (en) Food and drug safety risk monitoring system
CN117387909B (en) Medical optical instrument performance detection system
CN114822872A (en) Training method and device of risk signal recognition model and drug risk signal mining method and device
CN110136412A (en) Routine urinalysis testing result audits early warning system and method automatically
CN117935949A (en) Early warning method and system for potential addiction causing magic medicine based on weighted judgment
CN117472979A (en) Big data analysis-based inspection detection informatization method and system
van Wyk et al. A cost-benefit analysis of automated physiological data acquisition systems using data-driven modeling
CN115312184A (en) Violence risk prediction preliminary screening method for serious mental disorder patients in community
Verman et al. A narrative review of adverse event detection, monitoring, and prevention in Indian hospitals
Dharmawan et al. Big Data Capabilities for Hospital: A Systematic Literature Review
KASUKURTHI Big data analytics in pharmacovigilance-A global trend
CN117219275A (en) Child drug-induced liver injury risk identification prediction method and system
CN115346344B (en) Method, device and storage medium for monitoring radioactive pollution

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination