Allergy intervention analysis system and method based on drug inspection big data

Abstract

The invention relates to an allergy intervention analysis system and method based on inspection drug use big data, and the analysis method comprises the steps: obtaining patient data in response to an allergy analysis request; the patient data comprises a medical history, an allergy history and a medicine taking history; obtaining target data based on the patient data; the target data comprises target disease data, target allergy data and target medicine taking data; obtaining an allergy analysis model, and inputting the target data into the allergy analysis model to obtain an allergy analysis result; the analysis result comprises the allergy risk. The technical problem that in the prior art, in the CT enhanced inspection process, analysis on the medication allergy condition of a patient is not accurate is solved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of big data analysis, and in particular to an allergy intervention analysis method based on big data of medication examination, a medication allergy analysis system based on big data, and electronic equipment. Background Art

[0002] CT enhancement examination is a medical imaging examination method that injects contrast agent into the blood vessels and then uses a CT scanner to scan the lesion multiple times to more clearly show the shape, size, location and relationship of the lesion tissue with the surrounding tissue. Because the contrast agent used in CT enhancement contains a certain amount of iodine, some patients may have allergic reactions. Severe cases may even cause shock, respiratory and circulatory failure, etc., which are life-threatening.

[0003] In the prior art, doctors ask patients about their medical and allergy history to obtain allergy information and select the corresponding contrast agent. However, different doctors have different experiences, and patients are unclear when describing their medical and allergy history, which leads to inaccurate analysis of patients' medication allergies.

[0004] It can be seen that during the CT enhanced examination, how to accurately analyze the patient's drug allergy is an urgent problem to be solved.

[0005] Therefore, the following technical problems still exist in clinical allergy examinations:

[0006] 1. Allergic reactions are unavoidable during CT enhanced examinations, with a probability of 0.3%-0.5%, and a small number of cases may develop severe anaphylactic shock;

[0007] 2. A small number of patients will have allergic reactions again when they are re-examined after the first allergic reaction. When it happens again, after questioning, it is learned that the patient has a history of allergic reactions;

[0008] 3. The doctor was unaware of the patient's history of allergy to enhanced testing, and the patient himself did not remember it clearly;

[0009] 4. Statistics from the past two years show that cancer patients have a higher incidence of allergic reactions. Summary of the invention

[0010] In order to solve the above problems, this application proposes an allergy intervention analysis method based on big data of medication inspection, and the analysis method includes:

[0011] In response to an allergy analysis request, obtaining patient data; the patient data includes medical history, allergy history, and medication history;

[0012] Based on the patient data, target data is acquired; the target data includes target disease data, target allergy data, and target medication data;

[0013] An allergy analysis model is obtained, and target data is input into the allergy analysis model to obtain an allergy analysis result; the analysis result includes allergy risk.

[0014] Optionally, based on the patient data, target data is obtained, including:

[0015] Based on the medical history in the patient data, a target disease and a disease degree of the target disease are obtained as target disease data;

[0016] Based on the patient's allergy history, a target allergen and the allergy degree of the target allergen are obtained as target allergy data;

[0017] Based on the patient's medication history, the target drug and the dosage of the target drug are obtained as target medication data.

[0018] Optionally, obtaining the allergy analysis model includes:

[0019] Obtain contrast agent information;

[0020] According to the contrast agent information, an allergy relationship database is obtained, wherein the allergy relationship database includes target disease data, target allergy data, target medication data, allergy risk, and a mapping relationship among the target disease data, target allergy data, target medication data, and allergy risk;

[0021] The allergy relationship database is used to train a neural network model to obtain an allergy analysis model.

[0022] Optionally, obtain an allergy relationship database, including:

[0023] Through big data, several cases of the same contrast agent are obtained, as well as the medical history, allergy history, and medication history of each case; the several cases include allergic cases and non-allergic cases;

[0024] Obtain target influencing factors based on the case's medical history, allergy history, and medication history; target influencing factors include target diseases, target allergens, and target drugs;

[0025] Based on the target influencing factors, the medical history, allergy history and medication history of each case are screened to obtain the target disease data, target allergy data and target medication data of each case;

[0026] Based on the target disease data, target allergy data and target medication data of each case, a number of cases are clustered to obtain a number of allergy categories and the allergy probability of each allergy category;

[0027] Based on the allergy probability of the allergy category, and the target disease data, target allergy data and target medication data of each allergy case in the allergy category, the allergy risk corresponding to each allergy case is obtained.

[0028] Optionally, based on the target disease data, target allergy data, and target medication data of each case, a clustering process is performed on a number of cases to obtain a number of allergy categories and the allergy probability of each allergy category, including:

[0029] Based on the target disease data of each case, a number of disease combinations are obtained; each disease combination includes a number of target diseases;

[0030] Based on the target allergy data of each case, a number of allergen combinations are obtained; each allergen combination includes a number of target allergens;

[0031] Based on the target medication data of each case, a number of drug combinations are obtained; each drug combination includes a number of target drugs;

[0032] Obtain several allergy categories based on several disease combinations, several allergen combinations and several drug combinations;

[0033] Based on several allergy categories, each case is clustered, and the allergy probability corresponding to each allergy category is counted.

[0034] Optionally, based on the allergy probability of the allergy category, and the target disease data, target allergy data, and target medication data of each allergy case in the allergy category, the allergy risk corresponding to each allergy case is obtained, including:

[0035] Based on preset processing rules, target disease data, target allergy data and target medication data of each allergy case in the allergy category are processed to obtain evaluation values ​​of the target disease, target allergen and target drug;

[0036] Obtaining a number of characteristic allergy cases, and evaluation values ​​of target diseases, target allergens, and target drugs for each characteristic allergy case;

[0037] Through expert experience, the allergy probability of allergy categories and the evaluation values ​​of target diseases, target allergens and target drugs for each characteristic allergy case are analyzed to obtain the allergy risk of each characteristic allergy case;

[0038] Obtain a risk assessment model based on the allergy risk of each characteristic allergy case, as well as the evaluation values ​​of the target disease, target allergen, and target drug;

[0039] Based on the risk assessment model, the allergic risk of each allergic case in the allergy category is obtained.

[0040] Optionally, the risk assessment model comprises a linear regression model.

[0041] Optionally, the analysis method further comprises:

[0042] When the allergy risk of the patient is higher than the set risk in the allergy analysis results, an alarm message is generated and sent to the user end.

[0043] Optionally, the user end includes a patient end and a doctor end.

[0044] In another aspect, the present application further provides an electronic device, comprising:

[0045] processor;

[0046] a memory for storing processor-executable instructions;

[0047] Wherein, the processor is configured to implement the allergy intervention analysis method based on the examination of medication big data when executing the executable instructions.

[0048] Technical effects of the present invention:

[0049] This application solves the problem that patients are unclear about or cannot accurately describe their past medical and allergy history by obtaining the patient's medical history, allergy history, and medication history; obtaining target data based on the patient's medical history, allergy history, and medication history can prevent doctors from asking wrong questions or missing questions about patients; and analyzing the patient's target data through an allergy analysis model can make the patient's medication allergy analysis more accurate. This solves the technical problem that the existing technology inaccurately analyzes the patient's medication allergy during CT enhanced examination.

[0050] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0052] Figure 1 It is a schematic diagram showing the implementation process of the allergy intervention analysis method based on the big data of medication inspection of the present invention;

[0053] Figure 2 FIG. 1 is a schematic diagram showing an implementation process of obtaining an allergy analysis model according to the present invention;

[0054] Figure 3 Shown is a schematic diagram of the system structure of the present invention;

[0055] Figure 4 The application diagram of the electronic device of the present invention is shown as follows DETAILED DESCRIPTION

[0056] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0057] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0058] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the main purpose of the present disclosure.

[0059] Example 1

[0060] like Figure 1 As shown in the figure, the allergy intervention analysis method based on the big data of drug examination includes:

[0061] S10: Respond to the allergy analysis request and obtain patient data; the patient data includes medical history, allergy history, and medication history;

[0062] In this embodiment, when the doctor prescribes a CT enhanced examination for the patient, an allergy analysis request is generated; the allergy analysis request includes the name of the disease the patient is currently seeing, the name of the contrast agent, the patient's electronic signature, and the doctor's electronic signature; responding to the allergy analysis request includes checking the patient's electronic signature and the doctor's electronic signature. After the verification, it is determined whether a CT enhanced examination is necessary based on the name of the disease the patient is currently seeing; if so, the patient data is obtained based on the patient's electronic signature; in this embodiment, the patient data is obtained by connecting to the data interface of the HIS system of multiple hospitals where the patient has been treated. Avoiding the situation where the patient describes the past medical history and allergy history inaccurately makes the patient data more complete.

[0063] In this embodiment, the doctor side can add a contrast agent name when generating an allergy analysis request; in some embodiments, the doctor side can also add more than one contrast agent name, and the doctor side can also set the analysis order of several contrast agents; the analysis order can be in the order of contrast agent price from low to high, and the analysis order can also be in the order of contrast agent use effect from good to bad.

[0064] S20: acquiring target data based on the patient data; the target data includes target disease data, target allergy data, and target medication data;

[0065] In this embodiment, the patient data includes all the patient's medical history, allergy history, and medication history; some of the medical history, allergy history, and medication history are not related to contrast agent allergy, so this part of the data needs to be deleted to obtain the target disease data, target allergy data, and target medication data. This makes the patient's data more accurate and reduces the workload of manually deleting irrelevant data.

[0066] In some other embodiments, each contrast agent corresponds to different target data, and when obtaining the target data of the patient, it is necessary to obtain multiple sub-target data according to the name of the contrast agent;

[0067] S30: Obtain an allergy analysis model, and input the target data into the allergy analysis model to obtain an allergy analysis result; the analysis result includes allergy risk.

[0068] In this embodiment, each contrast agent corresponds to an allergy analysis model; the corresponding allergy analysis model is obtained according to the contrast agent name in the patient's request; and the allergy analysis result can be obtained by inputting the target data into the allergy analysis model.

[0069] In some other embodiments, when the allergy analysis request includes multiple contrast agents, the target data is input into multiple allergy analysis models respectively to obtain the analysis results of each allergy analysis model.

[0070] In some other embodiments, in step S20, the target order is obtained according to the analysis order; and in step S30, the allergy analysis model is obtained according to the name of the contrast agent, the target data is analyzed by the allergy analysis model to obtain the analysis result, and it is determined whether the allergy risk meets the preset requirements; if not, return to step S20, obtain the target data corresponding to the next contrast agent according to the preset analysis order, and repeat steps S20-S30 until the allergy risk of the contrast agent meets the preset requirements.

[0071] The allergy analysis model is generated by inputting all the patient examination data in the past five years for data training. By inputting all the patient examination data in the past five years for analysis, it can be regulated according to the conditions:

[0072] A high incidence of adverse reactions to a certain drug;

[0073] A certain type of patient has a high incidence of adverse reactions;

[0074] The adverse reactions are more common in patients of a certain age group, etc.

[0075] The specific implementation process of this embodiment includes:

[0076] In this embodiment, the target data is obtained based on the patient data, including:

[0077] Based on the medical history in the patient data, the target disease and the disease severity of the target disease are obtained as target disease data; based on the patient's allergy history, the target allergen and the allergy severity of the target allergen are obtained as target allergy data; based on the patient's medication history, the target drug and the dosage of the target drug are obtained as target medication data.

[0078] In this embodiment, target diseases include diabetes, renal dysfunction, etc.; target allergens include iodine, contrast agents, etc.; target drugs include metformin, anticoagulants, etc.

[0079] like Figure 2 In the embodiment shown, obtaining the allergy analysis model includes:

[0080] S31: obtaining contrast agent information;

[0081] S32: obtaining an allergy relationship database according to the contrast agent information, wherein the allergy relationship database includes target disease data, target allergy data, target medication data, allergy risk, and a mapping relationship among the target disease data, target allergy data, target medication data, and allergy risk;

[0082] S33: Using the allergy relationship database to train a neural network model to obtain an allergy analysis model.

[0083] In this embodiment, the allergy analysis model is a neural network model and has the characteristics of a neural network model. The neural network model is a neural network model in machine learning. It is a deep feedforward neural network with characteristics such as local connection and weight sharing. It is a highly complex nonlinear dynamic learning system.

[0084] The structure of the neural network model includes:

[0085] The input layer includes a plurality of input neurons, the number of the input neurons being equal to the sum of the number of target diseases, the number of target allergens, and the number of target drugs;

[0086] A number of hidden layers, each hidden layer including a number of hidden neurons;

[0087] The output layer includes a number of output neurons, and the number of output neurons is equal to the number of allergy risks.

[0088] The present invention pre-establishes an allergy intervention analysis system and method for enhancing patient medication big data. By importing data, this system can collect the examination patient data of the entire radiology discipline in recent years and regularize the data of allergy patients;

[0089] Conduct data analysis on the examinations, medications and items of patients with the same medical card;

[0090] Analyze the examination and medication for the same disease and the same examination items (such as CT or MRI);

[0091] After the data is sorted, it can be fed back to the corresponding ports such as outpatient doctors, wards, and radiology departments. When patients visit the doctor, are hospitalized, or undergo radiological examinations, reminders will pop up automatically to provide special checks and attention to the patients, ensuring that the examinations are completed safely and smoothly.

[0092] The specific model training process can include the following steps:

[0093] 1. Divide the allergy relationship database into training set and verification set

[0094] 2. Initialization parameters: Randomly initialize the weight parameters in the neural network;

[0095] 3. Forward propagation: forward propagate the target data in the training set through the neural network to obtain the prediction results;

[0096] 3. Calculate the loss: Use the loss function to calculate the difference between the predicted result and the actual allergy risk. The calculation formula of the loss function in this embodiment is as follows:

[0097]

[0098] Among them, L(Y, f(X)) is the difference, Y i is the actual allergy risk; f(Xi) is the predicted result; n is the number of samples in the training set.

[0099] 4. Back propagation: According to the gradient of the loss function, the weight parameters and biases in the neural network are updated through the back propagation algorithm to reduce the loss value;

[0100] 5. Iterative training: Repeat the process of forward propagation, loss calculation, and back propagation until the preset number of iterations is reached or the loss value is less than the preset loss value to obtain the allergy analysis model.

[0101] After the training is completed, the allergy analysis model is verified using the verification set to obtain the F1 score of the allergy analysis model, draw the ROC curve, and calculate the area under the ROC curve AUC value; in this embodiment, when the F1 score is greater than the preset score and the AUC value is greater than the set threshold, the allergy analysis model training is judged to be completed.

[0102] When analyzing patients' medication allergies, it is necessary to conduct allergy information analysis and feature extraction based on historical medication big data, build a corresponding allergy intervention analysis model, monitor patients for drug allergies, and perform corresponding interventions. The system will output corresponding intervention warnings or measures.

[0103] Feature extraction, see the relational feature processing method of the above mapping relationship. Feature engineering can be processed by using a convolutional neural network model or other text entity relationship extraction algorithms.

[0104] The corresponding intervention warning or measure may be an intervention warning or measure that has been generated for the patient, or an intervention warning or measure that is added to the training set (while constructing a mapping relationship between the corresponding allergic disease and the corresponding intervention warning or measure).

[0105] Among them, the allergy relationship database is obtained, including:

[0106] Several cases of the same contrast agent, as well as the medical history, allergy history and medication history of each case are obtained through big data; the several cases include allergic cases and non-allergic cases; in this embodiment, cases of CT enhanced examination using the same contrast agent are obtained through the HIS system of each hospital; cases that are allergic to the contrast agent are allergic cases, and cases that are not allergic to the contrast agent are non-allergic cases; and whether the patient is allergic to the contrast agent is determined by the radiologist of each hospital evaluating the patient's physical condition.

[0107] Based on the medical history, allergy history and medication history of the case, the target influencing factor is obtained; the target influencing factor includes the target disease, target allergen and target drug; in this embodiment, when the probability of allergy of patients with the same influencing factor is greater than the preset probability, the influencing factor is judged to be the target influencing factor.

[0108] Based on the target influencing factors, the medical history, allergy history and medication history of each case are screened to obtain the target disease data, target allergy data and target medication data of each case;

[0109] Based on the target disease data, target allergy data and target medication data of each case, a number of cases are clustered to obtain a number of allergy categories and the allergy probability of each allergy category;

[0110] Based on the allergy probability of the allergy category, as well as the target disease data, target allergy data and target medication data of each allergy case in the allergy category, the allergy risk corresponding to each allergy case is obtained.

[0111] It should be noted that after each hospital performs enhanced CT examination on the patient, the radiologist fills out a form to generate a case and uploads it to the allergy relationship database of the corresponding contrast agent.

[0112] In this embodiment, the allergy relationship database is regularly updated and the neural network model is trained to update the allergy analysis model.

[0113] Among them, based on the target disease data, target allergy data and target medication data of each case, several cases are clustered to obtain several allergy categories and the allergy probability of each allergy category, including:

[0114] Based on the target disease data of each case, a number of disease combinations are obtained; each disease combination includes a number of target diseases;

[0115] Based on the target allergy data of each case, a number of allergen combinations are obtained; each allergen combination includes a number of target allergens;

[0116] Based on the target medication data of each case, a number of drug combinations are obtained; each drug combination includes a number of target drugs;

[0117] Based on a number of disease combinations, a number of allergen combinations, and a number of drug combinations, a number of allergy categories are obtained; in this embodiment, a number of disease combinations, a number of allergen combinations, and a number of drug combinations are permuted and combined to obtain a number of allergy categories;

[0118] Based on several allergy categories, each case is clustered and the allergy probability corresponding to each allergy category is counted. By counting the number of allergy cases in each allergy category, the allergy probability corresponding to the allergy category can be obtained.

[0119] In this embodiment, based on the allergy probability of the allergy category, and the target disease data, target allergy data, and target medication data of each allergy case in the allergy category, the allergy risk corresponding to each allergy case is obtained, including:

[0120] Based on preset processing rules, target disease data, target allergy data and target medication data of each allergy case in the allergy category are processed to obtain evaluation values ​​of the target disease, target allergen and target drug;

[0121] For allergic cases of the same allergy category, the disease degree of the target disease, the allergy degree of the target allergen and the dosage of the target drug are different, and the degree of their impact on the allergy risk of individuals is also different; the preset processing rules in this embodiment include normalization processing; the evaluation value range of the disease degree includes [0,1], and the larger the evaluation value, the more serious the disease; the evaluation value range of the allergy degree includes [0,1], and the larger the evaluation value, the more serious the allergy; the evaluation value range of the dosage includes [0,1], and the larger the evaluation value, the larger the dosage;

[0122] Obtaining a number of characteristic allergy cases, and evaluation values ​​of target diseases, target allergens, and target drugs for each characteristic allergy case;

[0123] In this embodiment, acquiring characteristic allergy cases includes: randomly acquiring a preset number of allergy cases from a number of allergy cases as characteristic allergy cases.

[0124] Through expert experience, the allergy probability of allergy categories and the evaluation values ​​of target diseases, target allergens and target drugs for each characteristic allergy case are analyzed to obtain the allergy risk of each characteristic allergy case;

[0125] Based on the allergic risk of each characteristic allergic case, and the evaluation values ​​of the target disease, target allergen, and target drug, a risk assessment model is obtained; in this embodiment, the risk assessment model includes a linear regression model.

[0126] Based on the risk assessment model, the allergy risk of each allergy case in the allergy category is obtained.

[0127] In some embodiments, the analysis method further comprises:

[0128] When the allergy risk of a patient is higher than the set risk in the allergy analysis results, an alarm message is generated and sent to the user end. The user end includes the patient end and the doctor end. The patient end includes the user's smartphone; the doctor end includes the doctor's smartphone, laptop, desktop computer and tablet computer.

[0129] In clinical applications, the model can be deployed on the backend system. After the patient is seen or hospitalized, the examination data is imported into the model for AI big data analysis, and the model determines whether the patient is allergic. Subsequently, the administrator (attending physician) can send the patient to a different department based on the allergy judgment results. If the patient is not allergic, the next step is to go to the next step of seeing a doctor, checking the patient, changing the dressing, etc.

[0130] Therefore, this application solves the problem that patients are unclear about or cannot accurately describe their past medical history and allergy history by obtaining the patient's medical history, allergy history, and medication history; obtaining target data based on the patient's medical history, allergy history, and medication history can prevent doctors from asking wrong questions or missing questions about patients; and analyzing the patient's target data through an allergy analysis model can make the patient's medication allergy analysis more accurate. This solves the technical problem that the prior art inaccurately analyzes the patient's medication allergy during CT enhanced examination.

[0131] Obviously, those skilled in the art should understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive, abbreviated as: HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0132] Example 2

[0133] Furthermore, if Figure 3 On the other hand, the present application also proposes a structural diagram of a medication allergy analysis system based on big data; Figure 3 As shown, the system includes:

[0134] The request response module 910 is used to respond to the allergy analysis request and obtain patient data; the patient data includes medical history, allergy history and medication history;

[0135] The data processing module 920 is used to obtain target data based on the patient data; the target data includes target disease data, target allergy data and target medication data;

[0136] The data analysis module 930 obtains an allergy analysis model and inputs the target data into the allergy analysis model to obtain an allergy analysis result; the analysis result includes the allergy risk.

[0137] Example 3

[0138] Furthermore, if Figure 4 In another aspect, the present application further provides an electronic device, comprising:

[0139] processor;

[0140] a memory for storing processor-executable instructions;

[0141] Wherein, the processor is configured to implement the allergy intervention analysis method based on the examination of medication big data when executing the executable instructions.

[0142] The electronic device according to the embodiment of the present disclosure includes a processor and a memory for storing instructions executable by the processor, wherein the processor is configured to implement any one of the above when executing the executable instructions.

[0143] Here, it should be noted that the number of processors can be one or more. At the same time, the electronic device of the embodiment of the present disclosure may also include an input system and an output system. Among them, the processor, memory, input system and output system may be connected through a bus or in other ways, which are not specifically limited here.

[0144] The memory is a computer-readable storage medium that can be used to store software programs, computer executable programs, and various modules, such as a program or module corresponding to one of the embodiments of the present disclosure. The processor executes various functional applications and data processing of the electronic device by running the software programs or modules stored in the memory.

[0145] The input system can be used to receive input numbers or signals. The signal can be a key signal related to user settings and function control of the device / terminal / server. The output system can include display devices such as display screens.

[0146] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. An allergy intervention analysis method based on big data of medication inspection, characterized in that: The analysis method comprises: In response to an allergy analysis request, obtaining patient data; the patient data includes medical history, allergy history, and medication history; Based on the patient data, target data is acquired; the target data includes target disease data, target allergy data, and target medication data; An allergy analysis model is obtained, and target data is input into the allergy analysis model to obtain an allergy analysis result; the analysis result includes allergy risk.

2. The allergy intervention analysis method based on big data of medication inspection according to claim 1, characterized in that: Based on patient data, obtain target data, including: Based on the medical history in the patient data, a target disease and a disease degree of the target disease are obtained as target disease data; Based on the patient's allergy history, a target allergen and the allergy degree of the target allergen are obtained as target allergy data; Based on the patient's medication history, the target drug and the dosage of the target drug are obtained as target medication data.

3. The allergy intervention analysis method based on big data of medication inspection according to claim 1, characterized in that: Get the Allergy Analysis Model including: Obtain contrast agent information; According to the contrast agent information, an allergy relationship database is obtained, wherein the allergy relationship database includes target disease data, target allergy data, target medication data, allergy risk, and a mapping relationship among the target disease data, target allergy data, target medication data, and allergy risk; The allergy relationship database is used to train a neural network model to obtain an allergy analysis model.

4. The allergy intervention analysis method based on big data of medication inspection according to claim 3 is characterized in that: Access to the allergy database, including: Through big data, several cases of the same contrast agent are obtained, as well as the medical history, allergy history, and medication history of each case; the several cases include allergic cases and non-allergic cases; Obtain target influencing factors based on the case's medical history, allergy history, and medication history; target influencing factors include target diseases, target allergens, and target drugs; Based on the target influencing factors, the medical history, allergy history and medication history of each case are screened to obtain the target disease data, target allergy data and target medication data of each case; Based on the target disease data, target allergy data and target medication data of each case, a number of cases are clustered to obtain a number of allergy categories and the allergy probability of each allergy category; Based on the allergy probability of the allergy category, and the target disease data, target allergy data and target medication data of each allergy case in the allergy category, the allergy risk corresponding to each allergy case is obtained.

5. The allergy intervention analysis method based on big data of medication inspection according to claim 4 is characterized in that: Based on the target disease data, target allergy data, and target medication data of each case, several cases are clustered to obtain several allergy categories and the allergy probability of each allergy category, including: Based on the target disease data of each case, a number of disease combinations are obtained; each disease combination includes a number of target diseases; Based on the target allergy data of each case, a number of allergen combinations are obtained; each allergen combination includes a number of target allergens; Based on the target medication data of each case, a number of drug combinations are obtained; each drug combination includes a number of target drugs; Obtain several allergy categories based on several disease combinations, several allergen combinations, and several drug combinations; Based on several allergy categories, each case is clustered, and the allergy probability corresponding to each allergy category is counted.

6. The allergy intervention analysis method based on big data of medication inspection according to claim 5, characterized in that: Based on the allergy probability of the allergy category, and the target disease data, target allergy data, and target medication data of each allergy case in the allergy category, the allergy risk corresponding to each allergy case is obtained, including: Based on preset processing rules, target disease data, target allergy data and target medication data of each allergy case in the allergy category are processed to obtain evaluation values ​​of the target disease, target allergen and target drug; Obtaining a number of characteristic allergy cases, and evaluation values ​​of target diseases, target allergens, and target drugs for each characteristic allergy case; Through expert experience, the allergy probability of allergy categories and the evaluation values ​​of target diseases, target allergens and target drugs for each characteristic allergy case are analyzed to obtain the allergy risk of each characteristic allergy case; Obtain a risk assessment model based on the allergy risk of each characteristic allergy case, as well as the evaluation values ​​of the target disease, target allergen, and target drug; Based on the risk assessment model, the allergic risk of each allergic case in the allergy category is obtained.

7. The allergy intervention analysis method based on big data of medication inspection according to claim 6 is characterized in that: The risk assessment model includes a linear regression model.

8. The allergy intervention analysis method based on big data of medication inspection according to claim 3 is characterized in that: The analysis method further comprises: When the allergy risk of the patient is higher than the set risk in the allergy analysis results, an alarm message is generated and sent to the user end.

9. A medication allergy analysis system based on big data, used to implement the allergy intervention analysis method based on medication big data inspection according to any one of claims 1 to 8, characterized in that: The system comprises: A request response module, used to respond to allergy analysis requests and obtain patient data; the patient data includes medical history, allergy history, and medication history; A data processing module, used to obtain target data based on patient data; the target data includes target disease data, target allergy data and target medication data; The data analysis module obtains an allergy analysis model and inputs the target data into the allergy analysis model to obtain an allergy analysis result; the analysis result includes the allergy risk.

10. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the allergy intervention analysis method based on examination of medication big data as described in any one of claims 1-8 when executing the executable instructions.

Images