Drug side effect analysis method, device, electronic device and computer storage medium

Abstract

The present invention relates to artificial intelligence technology, and discloses a drug side effect analysis method, including: obtaining historical clinical data, using the historical clinical data to train a pre-constructed neural network, and obtaining a drug analysis model; obtaining the patient's personal information and medical examination data, generating case information, obtaining the drug information prescribed by the doctor for the patient, and using the drug analysis model to perform effect analysis on the case information and drug information to obtain a first side effect inference result; using a pre-constructed drug-drug interaction relationship system to perform interaction analysis on the drug information prescribed by the doctor for the patient to obtain a second side effect inference result; according to the first side effect inference result and the second side effect inference result, a final side effect inference result is obtained. The present invention also proposes a drug side effect analysis device, equipment, and readable storage medium. The present invention can combine drug differences with individual differences to improve the accuracy of pharmacological diagnosis.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to a drug side effect analysis method, device, electronic device and computer-readable storage medium. Background Art

[0002] In recent years, the number of medical visits has gradually increased, and the frequency of medical accidents has also increased. Among them, some of the medical accidents are caused by the interaction between the multiple drugs prescribed by the doctor for the patient, which leads to worsening of the condition or even death. The drug-drug interaction relationship system (Drug-Drug Interaction Module, referred to as DDI) can analyze the interactions between different drugs and reduce medical accidents caused by drug conflicts. However, DDI depends on the size and accuracy of the database, and the accuracy of early warning judgment is not high. It only targets the drug itself and cannot analyze individual differences, resulting in no conflict between drugs during testing, but there will still be harm after passing through the human body. Therefore, there is currently a problem of inaccurate judgment results when medical staff only use DDI to judge whether a drug has strong side effects on patients. Summary of the invention

[0003] The present invention provides a drug side effect analysis method, device, electronic equipment and computer-readable storage medium, the main purpose of which is to improve the accuracy of pharmacological diagnosis.

[0004] To achieve the above object, the present invention provides a method for analyzing drug side effects, comprising:

[0005] Acquiring historical clinical data, and using the historical clinical data to train a pre-built classification neural network to obtain a drug analysis model;

[0006] Obtaining the patient's personal information and medical examination data, generating case information, obtaining the drug information prescribed by the doctor for the patient, and using the drug analysis model to perform effect analysis on the case information and the drug information to obtain a first side effect inference result;

[0007] Using a pre-built drug-drug interaction relationship system to perform interaction analysis on drug information prescribed by the doctor for the patient, to obtain a second side effect inference result;

[0008] A final side effect inference result is obtained according to the first side effect inference result and the second side effect inference result.

[0009] Optionally, the obtaining of historical clinical data includes:

[0010] The historical clinical data are obtained by acquiring a case information set of historical patients and a corresponding case medication set, as well as clinical effects corresponding to the case information set and the case medication set from a pre-built hospital data management system.

[0011] Optionally, the use of the historical clinical data to train a pre-built classification neural network to obtain a drug analysis model includes:

[0012] Vectorizing the historical clinical data to obtain vectorized data, and cleaning the vectorized data to obtain cleaned quantitative data;

[0013] Constructing a disease-drug effect diagram based on the hospital clinical data;

[0014] According to the disease-drug effect diagram, a pre-constructed classification neural network is trained to obtain the drug analysis model.

[0015] Optionally, the training of a pre-built classification neural network to obtain the drug analysis model further includes:

[0016] Using a momentum algorithm, setting a gradient descent direction of the classification neural network;

[0017] K-fold cross validation is performed on the cleaned quantitative data to search for optimal parameters, and the drug analysis model is generated based on the optimal parameters.

[0018] Optionally, the use of a pre-built drug-drug interaction relationship system to perform interaction analysis on the drug information prescribed by the doctor for the patient to obtain a second side effect inference result includes:

[0019] According to the drug keywords or codes in the drug information, a search is performed in the drug-drug interaction relationship system to obtain the interaction results of the drug set in the four stages of absorption, distribution, metabolism, and excretion, and the interaction results are weighted in the four stages and the second side effect inference result is obtained based on the calculation results.

[0020] Optionally, obtaining a final side effect inference result according to the first side effect inference result and the second side effect inference result includes:

[0021] When the first side effect inference result and the second side effect inference result are not greater than a preset critical warning value, prompting the user that the drug information prescribed by the doctor for the patient is safe;

[0022] When the first side effect inference result or the second side effect inference result is greater than a preset critical warning value, an alarm message is output.

[0023] Optionally, after obtaining a final side effect inference result according to the first side effect inference result and the second side effect inference result, the method further includes:

[0024] The case information and drug information corresponding to the negative result are saved, and the drug-drug interaction relationship system is updated according to the case information and drug information corresponding to the negative result.

[0025] In order to solve the above problems, the present invention also provides a drug side effect analysis device, the device comprising:

[0026] Model building module: used to obtain historical clinical data, and use the historical clinical data to train the pre-built neural network to obtain a drug analysis model;

[0027] Detection module: used to obtain the patient's personal information and medical examination data, generate case information, obtain the drug information prescribed by the doctor for the patient, and use the drug analysis model to perform effect analysis on the case information and the drug information to obtain a first side effect inference result, and use a pre-built drug-drug interaction relationship system to perform interaction analysis on the drug information prescribed by the doctor for the patient to obtain a second side effect inference result;

[0028] A comparison module is used to obtain a final side effect inference result based on the first side effect inference result and the second side effect inference result.

[0029] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0030] at least one processor; and,

[0031] a memory communicatively connected to the at least one processor; wherein,

[0032] The memory stores computer program instructions that can be executed by the at least one processor, and the computer program instructions are executed by the at least one processor so that the at least one processor can execute the drug side effect analysis method described above.

[0033] In order to solve the above problems, the present invention also provides a computer-readable storage medium, including a data storage area and a program storage area, the data storage area stores created data, and the program storage area stores a computer program; wherein, when the computer program is executed by a processor, any one of the above-mentioned drug side effect analysis methods is implemented.

[0034] The embodiment of the present invention uses a pre-trained drug analysis model to analyze case information and drug information, and can obtain whether there is a negative reaction between the drug and the patient, and obtain a first side effect inference result. Then, through the pre-constructed drug-drug interaction relationship system analysis, whether there is a negative reaction between drugs, and obtain a second side effect inference result. Through the first side effect inference result and the second side effect inference result, it can be more accurately analyzed whether the drug prescribed by the hospital to the patient is reasonable. Therefore, the drug side effect analysis method, device, electronic device and storage medium described in the embodiment of the present invention can combine drug differences with personal differences to improve the accuracy of pharmacological diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A schematic diagram of a process for analyzing drug side effects provided by an embodiment of the present invention;

[0036] Figure 2 A schematic diagram of a module of a drug side effect analysis device provided by an embodiment of the present invention;

[0037] Figure 3 A schematic diagram of the internal structure of an electronic device for implementing a drug side effect analysis method provided by an embodiment of the present invention;

[0038] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0039] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0040] The embodiment of the present application provides a method for analyzing drug side effects. The execution subject of the drug side effect analysis method includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the drug side effect analysis method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0041] Reference Figure 1 FIG. 1 is a flow chart of a method for analyzing drug side effects according to an embodiment of the present invention. In this embodiment, the method for analyzing drug side effects includes:

[0042] S1. Obtain historical clinical data, and use the historical clinical data to train a pre-constructed classification neural network to obtain a drug analysis model.

[0043] In detail, in the embodiment of the present invention, the obtaining of historical clinical data includes:

[0044] The historical clinical data are obtained by acquiring a case information set of historical patients and a corresponding case medication set, as well as clinical effects corresponding to the case information set and the case medication set from a pre-built hospital data management system.

[0045] In the embodiment of the present invention, the hospital data management system is all the treatment records of the patients received by the hospital, including, but not limited to, the patient's personal identity information, disease symptom information, medical examination information, prescribed drug information and treatment effect information.

[0046] In detail, in an embodiment of the present invention, the use of the historical clinical data to train a pre-constructed classification neural network to obtain a drug analysis model includes:

[0047] The historical clinical data is vectorized to obtain vectorized data, and the vectorized data is cleaned to obtain cleaned quantitative data; a disease-drug effect diagram is constructed based on the hospital clinical data; a pre-constructed classification neural network is trained based on the disease-drug effect diagram to obtain the drug analysis model.

[0048] The vectorization process is a process of converting the sample set from text data into vectorized data of a format type that can be executed in the drug analysis model. The cleaning process is to remove duplicates, clear errors and privacy data.

[0049] In detail, in the embodiment of the present invention, constructing a disease-drug effect diagram based on the hospital clinical data includes:

[0050] Construct case information nodes, drug information nodes and effect information nodes; and build the relationship graph in the form of a document object model tree using a hypertext markup language interpreter based on the case information nodes, the drug information nodes and the effect information nodes.

[0051] The nodes are storage nodes and the nodes are connected to each other. The embodiment of the present invention utilizes the case information node, the drug information node and the effect information node to store the case information set, the drug information set and the corresponding clinical effect in the historical clinical data respectively.

[0052] Furthermore, the embodiment of the present invention organizes the nodes into a relationship graph in the form of a Document Object Model (DOM) tree through the Hypertext Markup Language (HTML) interpreter.

[0053] The HTML is called Hypertext Markup Language, which is an identification language. It can connect scattered Internet resources into a logical whole. The relationship map is in the form of a DOM node tree, showing the collection of the case information node, the drug information node and the effect information node. Through the relationship map, all nodes can be accessed, and the content in the node can be modified and deleted.

[0054] In an embodiment of the present invention, the classification neural network is a binary classification neural network trained using TensorFlow, which is composed of multiple neurons, and each of the neurons stores the data of each of the nodes respectively. According to the relationship graph, through continuous training, various types of case information and drug information are learned, and ultimately it is possible to determine which type of physique or disease the patient is allergic to or aggravated by which drug, and ultimately achieve different case information for the patient, and the results of judging the same drug may be different, thereby increasing the diversity of drug diagnosis.

[0055] In detail, in the embodiment of the present invention, the training of the pre-constructed classification neural network to obtain the drug analysis model includes:

[0056] The momentum algorithm is used to set the gradient descent direction of the classification neural network; K-fold cross validation is performed on the cleaned quantified data to search for optimal parameters, and the drug analysis model is generated based on the optimal parameters.

[0057] Among them, the momentum algorithm is an optimization method in the gradient descent process. By continuously accumulating the momentum of the gradient descent, the descent speed at the current moment is related to the speed at the previous moment, which can reduce the influence of interference factors, increase the stability of the descent process, and improve the optimization speed of the classification neural network.

[0058] The K-fold cross validation is to divide the clean quantitative data into K parts in equal proportion, use one part as test data, and the other K-1 parts as training data. The cross validation of the embodiment of the present invention is to train the drug analysis model K times, and each experiment selects a different feature vector from the K parts as test data, and the remaining K-1 feature vectors are used as training data, so as to obtain the optimal process. In the embodiment of the present invention, the K is set to 10, and the clean quantitative data is divided into 10 parts. S2. Obtain the patient's personal information and medical examination data, generate case information, obtain the drug information prescribed by the doctor for the patient, and use the drug analysis model to analyze the effect of the case information and the drug information to obtain the first side effect inference result.

[0059] In the embodiment of the present invention, the personal information includes various indicators of the patient, such as age, gender, medical history, known drug allergies, etc. The medical examination data includes user body indicator data obtained by various medical examination equipment, including, for example, blood pressure, blood lipids, folic acid, protein content, etc.

[0060] The personal information and the medical examination data constitute the case information of the patient, and the case information and the drug information prescribed by the doctor are imported into the drug analysis model to determine the first side effect result of the drug on the patient. In an embodiment of the present invention, the first side effect result can determine whether the drug meets the symptoms of the patient, or determine whether the drug causes allergic symptoms to the patient.

[0061] S3. Use a pre-constructed drug-drug interaction relationship system to perform interaction analysis on the drug information prescribed by the doctor for the patient to obtain a second side effect inference result.

[0062] In an embodiment of the present invention, the drug-drug interaction (DDI) system is a tool commonly used in the medical field for drug information conflict detection, which can retrieve the drug-drug interaction database, perform interaction detection on the drug information, and obtain interaction result detection results at each stage.

[0063] In detail, in the embodiment of the present invention, S3 includes:

[0064] According to the drug keywords or codes in the drug information, a search is performed in the drug-drug interaction relationship system to obtain the interaction results of the drug set in the four stages of absorption, distribution, metabolism, and excretion, and the interaction results are weighted in the four stages and the second side effect inference result is obtained based on the calculation results.

[0065] In the embodiment of the present invention, the interaction results of the absorption and metabolism stages can each account for 40% of the entire process, and the interaction results of the distribution and excretion stages can each account for 10% of the entire process, then the second side effect inference result is (absorption result + metabolism result)*0.4+(distribution result + excretion result)*0.1.

[0066] S4. Obtain a final side effect inference result based on the first side effect inference result and the second side effect inference result.

[0067] In detail, in a preferred embodiment of the present invention, the S4 comprises:

[0068] When both the first side effect inference result and the second side effect inference result are not greater than a preset critical warning value, prompting the user that the drug information prescribed by the doctor for the patient is safe;

[0069] When the first side effect inference result or the second side effect inference result is greater than a preset critical warning value, an alarm message is output.

[0070] In the embodiment of the present invention, as long as one of the first side effect inference result or the second side effect inference result is greater than a preset critical warning value, that is, when it is displayed as a negative effect, an alarm value is output. Further, when the first side effect inference result is greater than the preset critical warning value, and the second side effect inference result is not greater than the preset critical warning value, the embodiment of the present invention outputs an inference explanation, explaining the basis that the interaction results generated by the components of the drugs have no negative impact on the patient at each stage.

[0071] Furthermore, in the embodiment of the present invention, after outputting the alarm information, the embodiment of the present invention further includes:

[0072] The drug-drug interaction relationship system and the historical clinical data are updated using the case information and drug information corresponding to the alarm information.

[0073] In the embodiment of the present invention, the generation of the first side effect inference result depends on the case information node, the drug information node and the diagnosis information node, and the medical record database contains the case information node, the drug information node and the diagnosis information node. Continuously updating the medical record database is conducive to further optimization of the drug analysis model, making the analysis result more accurate.

[0074] The embodiment of the present invention uses a pre-trained drug analysis model to analyze case information and drug information, and can obtain whether there is a negative reaction between the drug and the patient, and obtain a first side effect inference result. Then, through a pre-constructed drug-drug interaction relationship system analysis, whether there is a negative reaction between drugs, and obtain a second side effect inference result. Through the first side effect inference result and the second side effect inference result, it can be more accurately analyzed whether the drug prescribed by the hospital to the patient is reasonable. Therefore, the embodiment of the present invention can combine drug differences with personal differences to improve the accuracy of pharmacological diagnosis.

[0075] like Figure 2 The figure shows a schematic diagram of the modules of the drug side effect analysis device of the present invention.

[0076] The drug side effect analysis device 100 of the present invention can be installed in an electronic device. According to the functions to be implemented, the drug side effect analysis device can include a model building module 101, a detection module 102, and a comparison module 103. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0077] In this embodiment, the functions of each module / unit are as follows:

[0078] The model building module 101 is used to obtain historical clinical data, and use the historical clinical data to train a pre-built classification neural network to obtain a drug analysis model.

[0079] In detail, in an embodiment of the present invention, the model building module 101 obtains the case information set of historical patients and the corresponding case-drug set, as well as the clinical effects corresponding to the case information set and the case-drug set from a pre-built hospital data management system to obtain the historical clinical data.

[0080] In the embodiment of the present invention, the hospital data management system is all the treatment records of the patients received by the hospital, including, but not limited to, the patient's personal identity information, disease symptom information, medical examination information, prescribed drug information and treatment effect information.

[0081] In detail, in the embodiment of the present invention, when the pre-built neural network is trained using the historical clinical data to obtain a drug analysis model, the model building module 101 is used to perform the following operations:

[0082] The historical clinical data is vectorized to obtain vectorized data, and the vectorized data is cleaned to obtain cleaned quantitative data; a disease-drug effect diagram is constructed based on the hospital clinical data; a pre-constructed classification neural network is trained based on the disease-drug effect diagram to obtain the drug analysis model.

[0083] The vectorization process is a process of converting the sample set from text data into vectorized data of a format type that can be executed in the drug analysis model. The cleaning process is to remove duplicates, clear errors and privacy data.

[0084] In detail, in the embodiment of the present invention, constructing a disease-drug effect diagram based on the hospital clinical data includes:

[0085] Construct case information nodes, drug information nodes and effect information nodes; and build the relationship graph in the form of a document object model tree using a hypertext markup language interpreter based on the case information nodes, the drug information nodes and the effect information nodes.

[0086] The nodes are storage nodes and the nodes are connected to each other. The embodiment of the present invention utilizes the case information node, the drug information node and the effect information node to store the case information set, the drug information set and the corresponding clinical effect in the historical clinical data respectively.

[0087] Furthermore, the embodiment of the present invention organizes the nodes into a relationship graph in the form of a Document Object Model (DOM) tree through the Hypertext Markup Language (HTML) interpreter.

[0088] The HTML is called Hypertext Markup Language, which is an identification language. It can connect scattered Internet resources into a logical whole. The relationship map is in the form of a DOM node tree, showing the collection of the case information node, the drug information node and the effect information node. Through the relationship map, all nodes can be accessed, and the content in the node can be modified and deleted.

[0089] In an embodiment of the present invention, the classification neural network is a binary classification neural network trained using TensorFlow, which is composed of multiple neurons, and each of the neurons stores the data of each of the nodes respectively. According to the relationship graph, through continuous training, the types of various case information and drug information are enriched, and ultimately it is possible to determine which type of physique or disease the patient is allergic to or aggravated by which drug, so that the case information of the patient is different, and the results of judging the same drug may be different, thereby increasing the diversity of drug diagnosis.

[0090] In detail, in the embodiment of the present invention, the training of the pre-constructed classification neural network to obtain the drug analysis model includes:

[0091] The momentum algorithm is used to set the gradient descent direction of the drug analysis model; K-fold cross validation is performed on the cleaned quantified data to search for optimal parameters, and the drug analysis model is generated based on the optimal parameters.

[0092] Among them, the momentum algorithm is an optimization method in the gradient descent process. By continuously accumulating the momentum of the gradient descent, the descent speed at the current moment is related to the speed at the previous moment, which can reduce the impact of interference factors, increase the stability of the descent process, and improve the optimization speed of the drug analysis model.

[0093] The K-fold cross validation is to divide the clean quantitative data into K parts in equal proportion, use one part as test data, and the other K-1 parts as training data. The cross validation of the embodiment of the present invention is to train the drug analysis model K times, and each experiment selects a different feature vector from the K parts as test data, and the remaining K-1 feature vectors are used as training data, so as to obtain the optimal process. In the embodiment of the present invention, the K is set to 10, and the clean quantitative data is divided into 10 parts. The detection module 102 is used to obtain the patient's personal information and medical examination data, generate case information, obtain the drug information prescribed by the doctor for the patient, and use the drug analysis model to perform effect analysis on the case information and the drug information to obtain the first side effect inference result, and use the pre-constructed drug-drug interaction relationship system to perform interaction analysis on the drug information prescribed by the doctor for the patient to obtain the second side effect inference result.

[0094] In the embodiment of the present invention, the personal information includes various indicators of the patient, such as age, gender, medical history, known drug allergies, etc. The medical examination data includes user body indicator data obtained by various medical examination equipment, including, for example, blood pressure, blood lipids, folic acid, protein content, etc.

[0095] The personal information and the medical examination data constitute the case information of the patient, and the case information and the drug information prescribed by the doctor are imported into the drug analysis model to determine the first side effect result of the drug on the patient. In an embodiment of the present invention, the first side effect result can determine whether the drug meets the symptoms of the patient, or determine whether the drug causes allergic symptoms to the patient.

[0096] In an embodiment of the present invention, the drug-drug interaction (DDI) system is a tool commonly used in the medical field for drug information conflict detection, which can retrieve the drug-drug interaction database, perform interaction detection on the drug information, and obtain interaction result detection results at each stage.

[0097] In detail, in the embodiment of the present invention, when the pre-constructed drug-drug interaction relationship system is used to perform interaction analysis on the drug information prescribed by the doctor for the patient to obtain the second side effect inference result, the detection module 102 is specifically used to:

[0098] According to the drug keywords or codes in the drug information, a search is performed in the drug-drug interaction relationship system to obtain the interaction results of the drug set in the four stages of absorption, distribution, metabolism, and excretion, and the interaction results are weighted in the four stages and the second side effect inference result is obtained based on the calculation results.

[0099] In the embodiment of the present invention, the interaction results of the absorption and metabolism stages can each account for 40% of the entire process, and the interaction results of the distribution and excretion stages can each account for 10% of the entire process, then the second side effect inference result is (absorption result + metabolism result)*0.4+(distribution result + excretion result)*0.1.

[0100] The comparison module 103 is used to obtain a final side effect inference result according to the first side effect inference result and the second side effect inference result.

[0101] In detail, in a preferred embodiment of the present invention, the comparison module 103 is specifically used for:

[0102] When both the first side effect inference result and the second side effect inference result are not greater than a preset critical warning value, prompting the user that the drug information prescribed by the doctor for the patient is safe;

[0103] When the first side effect inference result or the second side effect inference result is greater than a preset critical warning value, an alarm message is output.

[0104] In the embodiment of the present invention, as long as one of the first side effect inference result or the second side effect inference result is greater than a preset critical warning value, that is, when it is displayed as a negative effect, an alarm value is output. Further, when the first side effect inference result is greater than the preset critical warning value, and the second side effect inference result is not greater than the preset critical warning value, the embodiment of the present invention outputs an inference explanation, explaining the basis that the interaction results generated by the components of the drugs have no negative impact on the patient at each stage.

[0105] Furthermore, in the embodiment of the present invention, after outputting the alarm information, the embodiment of the present invention further includes:

[0106] The drug-drug interaction relationship system and the historical clinical data are updated using the case information and drug information corresponding to the alarm information.

[0107] In the embodiment of the present invention, the generation of the first side effect inference result depends on the case information node, the drug information node and the diagnosis information node, and the medical record database contains the case information node, the drug information node and the diagnosis information node. Continuously updating the medical record database is conducive to further optimization of the drug analysis model, making the analysis result more accurate.

[0108] like Figure 3 The figure is a schematic diagram of the structure of an electronic device for implementing the drug side effect analysis method of the present invention.

[0109] The electronic device 1 may include a processor 10 , a memory 11 , and a bus, and may also include a computer program stored in the memory 11 and executable on the processor 10 , such as a drug side effect analysis program 12 .

[0110] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. The memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as a mobile hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 11 may not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the drug side effect analysis program 12, etc., but may also be used to temporarily store data that has been output or is to be output.

[0111] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (for example, executing a drug side effect analysis program, etc.), and calls data stored in the memory 11, so as to execute various functions of the electronic device 1 and process data.

[0112] The bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0113] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0114] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, etc. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0115] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0116] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0117] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0118] The drug side effect analysis program 12 stored in the memory 11 of the electronic device 1 is a combination of multiple computer programs. When running in the processor 10, it can achieve:

[0119] Acquire historical clinical data, and use the historical clinical data to train a pre-built neural network to obtain a drug analysis model;

[0120] Obtaining the patient's personal information and medical examination data, generating case information, obtaining the drug information prescribed by the doctor for the patient, and using the drug analysis model to perform effect analysis on the case information and the drug information to obtain a first side effect inference result;

[0121] Using a pre-built drug-drug interaction relationship system to perform interaction analysis on drug information prescribed by the doctor for the patient, to obtain a second side effect inference result;

[0122] A final side effect inference result is obtained according to the first side effect inference result and the second side effect inference result.

[0123] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0124] Furthermore, the computer-usable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the blockchain node, etc.

[0125] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0126] Acquire historical clinical data, and use the historical clinical data to train a pre-built neural network to obtain a drug analysis model;

[0127] Obtaining the patient's personal information and medical examination data, generating case information, obtaining the drug information prescribed by the doctor for the patient, and using the drug analysis model to perform effect analysis on the case information and the drug information to obtain a first side effect inference result;

[0128] Using a pre-built drug-drug interaction relationship system to perform interaction analysis on drug information prescribed by the doctor for the patient, to obtain a second side effect inference result;

[0129] A final side effect inference result is obtained according to the first side effect inference result and the second side effect inference result.

[0130] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0131] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0132] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0133] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0134] Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any associated diagram mark in the claims should not be regarded as limiting the claims involved.

[0135] The blockchain referred to in this invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0136] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim can also be implemented by one unit or device through software or hardware. The second and other words are used to indicate names, but not to indicate any particular order.

[0137] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for analyzing drug side effects, characterized in that: The method comprises: Acquire historical clinical data, vectorize the historical clinical data to obtain vectorized data, and clean the vectorized data to obtain cleaned quantitative data; construct case information nodes, drug information nodes, and effect information nodes according to the cleaned quantitative data, and construct a disease-drug effect diagram in the form of a document object model tree according to the case information nodes, the drug information nodes, and the effect information nodes; train a pre-constructed classification neural network according to the disease-drug effect diagram to obtain the drug analysis model; Obtaining the patient's personal information and medical examination data, generating case information, obtaining the drug information prescribed by the doctor for the patient, and using the drug analysis model to perform effect analysis on the case information and the drug information to obtain a first side effect inference result; Using a pre-built drug-drug interaction relationship system to perform interaction analysis on drug information prescribed by the doctor for the patient, to obtain a second side effect inference result; A final side effect inference result is obtained according to the first side effect inference result and the second side effect inference result.

2. The drug side effect analysis method according to claim 1, characterized in that: The acquisition of historical clinical data includes: The historical clinical data are obtained by acquiring a case information set of historical patients and a corresponding case medication set, as well as clinical effects corresponding to the case information set and the case medication set from a pre-built hospital data management system.

3. The drug side effect analysis method according to claim 2, characterized in that: The training of the pre-built classification neural network to obtain the drug analysis model further includes: Using a momentum algorithm, setting a gradient descent direction of the classification neural network; K-fold cross validation is performed on the cleaned quantitative data to search for optimal parameters, and the drug analysis model is generated based on the optimal parameters.

4. The drug side effect analysis method according to claim 1, characterized in that: The pre-constructed drug-drug interaction relationship system is used to perform interaction analysis on the drug information prescribed by the doctor for the patient to obtain a second side effect inference result, including: According to the drug keywords or codes in the drug information, a search is performed in the drug-drug interaction relationship system to obtain the interaction results of the drug set in the four stages of absorption, distribution, metabolism, and excretion, and the interaction results are weighted in the four stages and the second side effect inference result is obtained based on the calculation results.

5. The drug side effect analysis method according to any one of claims 1 to 4, characterized in that: The step of obtaining a final side effect inference result according to the first side effect inference result and the second side effect inference result includes: When both the first side effect inference result and the second side effect inference result are not greater than a preset critical warning value, prompting the user that the drug information prescribed by the doctor for the patient is safe; When the first side effect inference result or the second side effect inference result is greater than a preset critical warning value, an alarm message is output.

6. The drug side effect analysis method according to claim 5, characterized in that: After outputting the alarm information, the method further includes: The drug-drug interaction relationship system and the historical clinical data are updated using the case information and drug information corresponding to the alarm information.

7. A drug side effect analysis device, characterized in that: The device comprises: Model building module: used to obtain historical clinical data, vectorize the historical clinical data to obtain vectorized data, and clean the vectorized data to obtain cleaned quantitative data; construct case information nodes, drug information nodes and effect information nodes according to the cleaned quantitative data, and construct a disease-drug effect diagram in the form of a document object model tree according to the case information nodes, the drug information nodes and the effect information nodes; according to the disease-drug effect diagram, train a pre-constructed classification neural network to obtain the drug analysis model; Detection module: used to obtain the patient's personal information and medical examination data, generate case information, obtain the drug information prescribed by the doctor for the patient, and use the drug analysis model to perform effect analysis on the case information and the drug information to obtain a first side effect inference result, and use a pre-built drug-drug interaction relationship system to perform interaction analysis on the drug information prescribed by the doctor for the patient to obtain a second side effect inference result; A comparison module is used to obtain a final side effect inference result based on the first side effect inference result and the second side effect inference result.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores computer program instructions that can be executed by the at least one processor, and the computer program instructions are executed by the at least one processor to enable the at least one processor to execute the drug side effect analysis method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, comprising a data storage area and a program storage area, wherein the data storage area stores created data and the program storage area stores a computer program; characterized in that: When the computer program is executed by a processor, the drug side effect analysis method according to any one of claims 1 to 6 is implemented.

Images