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 PDFInfo
- 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
Links
- 239000003814 drug Substances 0.000 title claims abstract description 337
- 206010012335 Dependence Diseases 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 46
- 229940079593 drug Drugs 0.000 claims abstract description 182
- 238000001514 detection method Methods 0.000 claims abstract description 43
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 33
- 238000010801 machine learning Methods 0.000 claims abstract description 15
- 238000013528 artificial neural network Methods 0.000 claims abstract description 10
- 238000012544 monitoring process Methods 0.000 claims abstract description 7
- 230000029052 metamorphosis Effects 0.000 claims description 66
- 206010067484 Adverse reaction Diseases 0.000 claims description 55
- 230000006838 adverse reaction Effects 0.000 claims description 55
- 238000002329 infrared spectrum Methods 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 25
- 201000009032 substance abuse Diseases 0.000 claims description 13
- 230000000694 effects Effects 0.000 claims description 12
- 210000004789 organ system Anatomy 0.000 claims description 12
- 238000001228 spectrum Methods 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 9
- 230000004071 biological effect Effects 0.000 claims description 7
- 230000007012 clinical effect Effects 0.000 claims description 7
- 239000000126 substance Substances 0.000 claims description 7
- 238000002835 absorbance Methods 0.000 claims description 6
- 230000002411 adverse Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 230000007170 pathology Effects 0.000 claims description 6
- 238000013480 data collection Methods 0.000 claims description 5
- 230000003595 spectral effect Effects 0.000 claims description 4
- 206010061623 Adverse drug reaction Diseases 0.000 claims description 3
- 208000030453 Drug-Related Side Effects and Adverse reaction Diseases 0.000 claims description 3
- 238000010521 absorption reaction Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 239000002245 particle Substances 0.000 claims description 3
- 230000001575 pathological effect Effects 0.000 claims description 3
- 238000004445 quantitative analysis Methods 0.000 claims description 3
- 239000007787 solid Substances 0.000 claims description 3
- 238000006757 chemical reactions by type Methods 0.000 claims description 2
- 238000005498 polishing Methods 0.000 claims 1
- 238000002203 pretreatment Methods 0.000 claims 1
- 238000012360 testing method Methods 0.000 claims 1
- 238000001291 vacuum drying Methods 0.000 claims 1
- 206010013654 Drug abuse Diseases 0.000 abstract description 7
- 208000011117 substance-related disease Diseases 0.000 abstract description 7
- 230000002265 prevention Effects 0.000 abstract description 2
- 238000005303 weighing Methods 0.000 abstract 1
- 238000004458 analytical method Methods 0.000 description 11
- 230000008901 benefit Effects 0.000 description 7
- 230000007547 defect Effects 0.000 description 6
- 230000005180 public health Effects 0.000 description 5
- 230000004044 response Effects 0.000 description 5
- 238000004128 high performance liquid chromatography Methods 0.000 description 4
- 239000004615 ingredient Substances 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000001647 drug administration Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 229940043263 traditional drug Drugs 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 230000002747 voluntary effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3563—Investigating 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/10—Analysis or design of chemical reactions, syntheses or processes
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/20—Identification of molecular entities, parts thereof or of chemical compositions
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine 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
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.
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) |
-
2023
- 2023-12-11 CN CN202311694068.XA patent/CN117935949A/en active Pending
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 |