Medicine rash sensitization medicine intelligent identification system
Through an intelligent identification system for drug-escape sensitizing drugs that integrate clinical data and literature data, the problem of inaccurate judgment of existing traditional Chinese medicine sensitizing drugs is solved, and higher recognition accuracy and objectivity are achieved, and the treatment plan and patient treatment continuity is optimized.
Patent Information
- Application Number
- CN202510175840.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-18
- Publication Date
- 2025-06-10
AI Technical Summary
In the prior art, the determination of drug sensitizing drugs depends on the clinical experience of medical staff, and it is difficult to ensure the accuracy and objectivity of judgments. Moreover, the patient fails to report all the drugs used in full, resulting in the doctor being unable to obtain comprehensive information to make accurate judgments.
It provides an intelligent identification system for drug rash sensitization drugs. By integrating clinical data and literature data, the range of sensitization drugs can be quickly circled according to specific drug rash types, and sensitization drugs are identified based on patient individual data to improve the accuracy and objectivity of the identification.
It improves the accuracy and objectivity of drug sensitizing drugs, can quickly output the sensitizing drug analysis results that cause drug sensitizing drugs, optimizes the patient's treatment plan, reduces unnecessary drug interruption, and ensures the patient's treatment continuity.
Smart Images

Figure CN120126800A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of drug eruption judgment, and particularly relates to an intelligent identification system for drug eruption sensitizing drugs. Background Art
[0002] Drug Eruption is a type of skin reaction caused by drugs, usually manifested as rashes, itching, erythema, etc. In severe cases, it can lead to life-threatening conditions such as exfoliative dermatitis or Stevens-Johnson syndrome. The occurrence of drug eruption may be related to the abnormal reaction of the immune system to drug components, and the specific mechanism involves a complex immune response process.
[0003] In the prior art, the determination of sensitizing drugs usually relies on the clinical experience of medical staff, which is difficult to ensure the accuracy and objectivity of the judgment. Whether the sensitizing drug is discontinued directly affects the success or failure of the treatment of drug eruption. Specifically, the experience level of doctors, the depth of understanding of specific drugs, and the understanding of the patient's medical history will all affect the final diagnosis result. And because patients may not be able to report all the drugs used completely, or some over-the-counter drugs, herbal supplements, etc. are not recorded, doctors cannot obtain comprehensive information for accurate judgment.
[0004] In summary, how to solve the problem that only relying on medical staff to determine sensitizing drugs in the prior art, resulting in difficulty in ensuring the accuracy and objectivity of the judgment has become an urgent problem to be solved in the current field. Therefore, it is necessary to propose an intelligent identification system for drug eruption sensitizing drugs. Summary of the Invention
[0005] To solve the above problems, the present invention provides an intelligent identification system for drug eruption sensitizing drugs, which integrates clinical data and literature data, quickly delimits the range of sensitizing drugs according to specific drug eruption types, and identifies sensitizing drugs based on patient individual data, improving the accuracy and objectivity of the identification.
[0006] To achieve the above object, the technical solution of the present invention is as follows: An intelligent identification system for drug eruption sensitizing drugs, comprising the following modules:
[0007] An input module, configured to receive key data such as the basic information of the patient, the type of drug eruption, the name of the drug used before the rash occurred, and the medication time.
[0008] An interaction module, configured to provide an interaction interface and operation instructions for the input module.
[0009] A construction module, configured to establish a database of clinical data and literature data.
[0010] A retrieval module, configured to delimit the range of sensitizing drugs in the database with the name of the drug eruption as a clue.
[0011] An analysis module for analyzing the input key data to obtain the analysis results of the sensitizing drug data that causes drug eruption.
[0012] A calibration module for calibrating the analysis results according to the clinical data in the database.
[0013] Furthermore, the sources of clinical data include hospital cases, electronic health records, and drug databases, and the sources of literature data include literature resources related to medicine.
[0014] Furthermore, the retrieval module searches for the clinical data and literature resources of drug eruptions caused by sensitizing drugs to find the characteristics and laws related to drug eruptions; integrates the characteristics and laws related to drug eruptions, and formulates different rules according to the incidence rate, median latency, and risk factors.
[0015] Furthermore, the analysis module retrieves different rules according to the key data of different patients, calculates the difference between the incidence rates of different drugs, the actual latency and the median latency in the literature resources, and the number of risk factors, and sorts them according to the incidence rate, the size of the latency difference, and the number of risk factors; obtains the probabilities of different drugs causing drug eruptions.
[0016] Furthermore, the calibration module evaluates the relevance of each drug eruption report by retrieving the drug eruption reports of past hospital cases in the database; calibrates the analysis results.
[0017] Furthermore, the analysis module also includes a sensitizing drug identification unit and a pre-medication prevention unit.
[0018] The sensitizing drug identification unit is used to sequentially input the drug eruption type, the name of the drug used before the rash, and the interval time between medication and rash, provide the option of whether it is the first medication, and provide the option of risk factors; output the probability ranking of the drugs causing drug eruptions, drug information, and reference basis.
[0019] The pre-medication prevention unit is used to input the drug name and the basic information of the patient, provide the option of whether it is the first medication, and provide the option of risk factors; output the probability of the patient having a drug eruption after using a specific drug, the latency, and the potential risk factors.
[0020] Furthermore, there is also a judgment module. The judgment module is used to receive the drug name, drug classification, active ingredient, and symptoms corresponding to drug allergy to construct a judgment database.
[0021] Receive the subsequent allergic reactions and medications of the user, compare the drugs with a similarity greater than the preset similarity threshold with the drugs taken by the user based on the set similarity threshold, and output the same-name drugs with a similarity greater than the preset similarity threshold.
[0022] If the drug taken by the user does not exist in the judgment database, the active ingredients and classification of the drug are compared with the drugs in the judgment database, and the classification and active ingredients of the drug that cause the user's allergies are output.
[0023] Furthermore, drug allergy symptoms include non-physical characteristic description statements and latency periods collected during drug clinical trials.
[0024] Furthermore, the judgment module is also used to obtain information on drug-induced allergic symptoms based on clinical trial results, and to construct a correction model of allergic symptoms and individual differences of users and past medical records.
[0025] When comparing the allergy characteristics of the user, the judgment module preferentially adjusts the allergy characteristics of the user according to the correction model.
[0026] Furthermore, the interaction module also includes a voice collection unit, which is used to collect the non-body surface feature description spoken by the user.
[0027] Furthermore, the judgment database is generated based on the knowledge graph.
[0028] Furthermore, the judgment module is also used to analyze based on the user's adverse reactions; identify different reaction characteristics of different users induced by the same drug and identify the same reaction characteristics of users induced by different drugs, and obtain individual difference reaction results.
[0029] Furthermore, the judgment module is also used to analyze different regions, different economic levels and different environments, identify potential factors related to the user's allergic symptoms, and obtain analysis results of objective factors.
[0030] The above scheme has the following beneficial effects:
[0031] 1. The present invention integrates clinical data and literature data through the construction module, providing a rich and comprehensive information basis for the retrieval module and the analysis module, which has a stronger correlation than the existing single-source data and provides a richer basis for judgment. The retrieval module can quickly delineate the range of allergenic drugs based on specific drug eruption types, while the analysis module can further identify allergenic drugs based on individual patient data, improving the accuracy and objectivity of identification.
[0032] The system can quickly output the analysis results of allergenic drugs that cause drug rash, allowing doctors to quickly make decisions on whether to stop using specific drugs, avoid treatment conflicts caused by blind drug discontinuation, optimize patients' treatment plans, reduce unnecessary drug interruptions, and ensure the continuity of treatment for patients' original diseases. Compared with existing technologies that mainly rely on doctors' experience for judgment, it can output detailed probability estimates and reference bases, further improving the accuracy of drug rash judgments.
[0033] 2. The interaction module of the present invention provides a friendly user interface and operation guide, enabling medical staff to easily input patient information and obtain analysis results, effectively improving the efficiency of clinical work. At the same time, the system automatically processes a large amount of data, reducing the workload of medical staff. The sensitizing drug identification unit and pre-medication prevention unit in the analysis module can not only identify the sensitizing drugs for the drug eruptions that have occurred, but also predict the risk of drug eruptions in patients before medication, providing personalized medication guidance and prevention measures for patients, and effectively reducing the incidence of drug eruptions.
[0034] 3. The calibration module of the present invention verifies and adjusts the analysis results through clinical past consultation records; not only improves the practicability of the system, but also provides valuable data support for the clinical research on the sensitization mechanism of drug eruptions, promoting the update and development of knowledge in the medical field; compared with the existing mechanism lacking the ability to calibrate the analysis results, it has the ability to update and adjust, ensuring the long-term effectiveness of the system.
[0035] The application of the system can effectively reduce the treatment delays or inappropriate treatments caused by misjudging sensitizing drugs, improve the safety and effectiveness of treatment, thereby enhancing the trust and satisfaction of patients. At the same time, the risk assessment before medication helps to establish a more harmonious doctor-patient relationship and improve the overall quality of medical services.
[0036] 4. The judgment module of the present invention constructs a judgment database generated based on a knowledge graph by receiving drug names, classifications, active ingredients, and drug allergy symptoms. It can not only directly compare the subsequent allergic reactions and medications of users and quickly output possible sensitizing drugs, but also conduct in-depth comparisons based on active ingredients and drug classifications when there are no completely matching items in the database, so as to identify the specific drug ingredients and classifications that cause users' allergies.
[0037] And based on factors such as the user's age, gender, body type, and past medical records, a correction model is constructed, enabling the system to more accurately adjust the user's allergy characteristics when comparing the user's allergy characteristics, thereby providing more personalized treatment suggestions, reducing the possibility of misdiagnosis and missed diagnosis. Compared with the existing lack of consideration for individual differences, it has stronger customized diagnosis and treatment services and can conduct specific analysis for each user, thus further improving the accuracy of diagnosis and treatment.
[0038] The determination module of the present invention can also analyze based on the different reaction characteristics of the same drug for a user and the same reaction characteristic of different drugs for a user. It not only focuses on the allergy risk of a single drug but also can analyze the potential risks of combined drug use, providing support for doctors to formulate comprehensive treatment plans and increasing the pertinence and applicability of the system. In addition, the impacts of different regions, economic levels, and different environments on drug allergic reactions are also considered. This in-depth analysis helps the system to more comprehensively understand the complexity of drug allergic reactions, thereby providing treatment suggestions that are more in line with the actual situation of users. Compared with the existing technologies that only focus on the risk factors of single-drug allergies, it can comprehensively consider the differences in different regions and different environments, help identify potential risks, and ensure the feasibility and sustainability of treatment plans.
[0039] Additional aspects and advantages of the present invention will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] Figure 1 It is a structural block diagram of the intelligent identification system for drug eruption sensitizing drugs of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0041] The following will be further described in detail through specific embodiments:
[0042] Embodiment 1:
[0043] As shown in the appended Figure 1 figure: An intelligent identification system for drug eruption sensitizing drugs includes an input module, a construction module, a retrieval module, an analysis module, an interaction module, and a correction module; among them, the input module is mainly used to receive key data of patients. The interaction module is used to provide an interaction interface and operation instructions. The construction module is used to establish a database of clinical data and literature data. The retrieval module is used to delimit the range of sensitizing drugs. The analysis module is used to identify the sensitizing drugs that cause drug eruptions. The correction module is used to correct the analysis results.
[0044] The functions of each module will be explained in detail in the following order:
[0045] The input module is used to receive key data of the patient's basic information (such as name, gender, and age), drug eruption type, name of the drug used before the rash occurred, and medication time. In this embodiment, for complex information (such as medication time), a calendar selector or other auxiliary tools are provided to simplify the operation.
[0046] The interaction module is used to provide an interaction interface and operation instructions for the input module; in this embodiment, the interaction module is implemented through a terminal device (such as a computer or a mobile phone, etc.).
[0047] The construction module is used to establish a database of clinical data and literature data. Among them, the sources of clinical data include hospital cases, electronic health records, and drug databases (such as oral or injection types), and the sources of literature data include literature resources related to medicine, integrating domestic and foreign medical literature resources, such as PubMed or Cochrane Library, etc. In this embodiment, the clinical data mainly includes user case information, and the literature data mainly includes papers related to drug eruption. A relational database (such as MySQL, PostgreSQL) is used to manage large-scale structured data.
[0048] The retrieval module is used to delineate the range of sensitizing drugs in the database with the name of drug eruption as a clue (such as exanthematous drug eruption, urticaria, or eczematous type, etc.).
[0049] Specifically, the retrieval module searches for the clinical data and literature resources of drug eruption caused by sensitizing drugs, and looks for the characteristics and laws related to drug eruption, and its characteristics and laws include but are not limited to incidence rate, latency time, and risk factors; integrates the information of the characteristics and laws related to drug eruption, and formulates different rules according to the incidence rate, median latency time, and risk factors.
[0050] Among them, the incidence rate rule determines the occurrence frequency of a certain drug causing drug eruption according to the statistical data in clinical cases and literature resources. For example, sulfonamides have a relatively high incidence rate in certain types of drug eruption (such as fixed drug eruption), then this drug is given a higher incidence rate weight.
[0051] The median latency time rule considers the time interval from drug use to the appearance of symptoms, that is, the latency period; the latency periods of different drugs may vary. By comparing the actual eruption time with the median latency time in the literature resources, it can be inferred which drugs are more likely to be sensitizing sources. For example, penicillin antibiotics usually cause drug eruption within a few days after drug use, while some non-steroidal anti-inflammatory drugs (NSAIDs) may take several weeks to show a reaction.
[0052] The risk factor rule is based on individual characteristics or background conditions related to the occurrence of drug eruption, such as age, gender, genetic susceptibility, previous medical history, etc. When a patient has certain known risk factors, the probability of certain drugs causing drug eruption will increase. For example, patients with a history of antibiotic allergy are more sensitive to certain drugs (such as cephalosporin or amoxicillin, etc.).
[0053] The analysis module is used to analyze the input key data and obtain the analysis result of the sensitizing drug data that causes drug eruption.
[0054] Specifically, the analysis module retrieves different rules based on the key data of different patients, calculates the high and low incidence rates of different drugs, the difference between the actual latency period and the median latency period in the literature resources, and the number of risk factors, and sorts them according to the high and low incidence rates, the size of the latency period difference, and the number of risk factors; to obtain the probability estimate of drug eruption caused by different drugs. The scores of the three items of incidence rate, latency period difference, and risk factors are weighted and summed to obtain the comprehensive score of each drug; the drugs are sorted from high to low according to the comprehensive score; the drugs most likely to cause drug eruption are listed first.
[0055] The analysis module also includes a sensitizing drug identification unit and a pre-medication prevention unit.
[0056] The sensitizing drug identification unit is used to sequentially input the type of drug eruption (such as erythema or urticaria, etc.), the name of the drug used before the eruption, and the interval time between medication and eruption, provide an option for whether it is the first medication, and provide risk factor options (such as genetic background, past medical history, and comorbidities, etc.); output the probability ranking of the drug causing drug eruption, drug information, and reference basis (such as relevant literature links or clinical cases, etc.).
[0057] The pre-medication prevention unit is used to input the drug name and the basic information of the patient, provide an option for whether it is the first medication, and provide risk factor options for allergic history, comorbidities, past medical history, and concomitant medications; output the probability, latency period, and potential risk factors of the patient developing drug eruption after applying a specific drug. Combining the individual characteristics and historical data of the patient, predict the possible allergic reactions and their severity after the patient uses a certain drug.
[0058] Specifically, for example, the system receives the basic information of the patient (35 years old, female), the type of drug eruption (erythematous type), the name of the drug used before the eruption (A, B, C), and the medication time; according to the age, gender, and drug types of the patient, the system retrieves the relevant rules applicable to erythematous drug eruption. If the patient uses multiple drugs simultaneously, the system will consider the interaction rules between them.
[0059] According to the literature and clinical data, incidence rate weights are assigned to drugs A, B, and C respectively, the actual eruption time is compared with the median latency period reported in the literature, and the time difference of each drug is calculated; considering whether the patient has other allergic history or other diseases, an additional risk score is assigned to each drug.
[0060] The scores of the three items of incidence rate, latency period difference, and risk factors are weighted and summed to obtain the comprehensive score of each drug; drugs A, B, and C are sorted from high to low according to the comprehensive score, and the drugs most likely to cause drug eruption are listed first.
[0061] Predict the probability of each drug causing erythematous drug eruption based on comprehensive scores and auxiliary information; output a detailed report containing the drug name, probability estimate, references, and recommended measures for doctors' reference.
[0062] The correction module is used to correct the analysis results according to the clinical data in the database. Specifically, the correction module retrieves the drug eruption reports of clinical cases from departments such as dermatology and pharmacy in the database, evaluates the relevance of each drug eruption report using predefined criteria (such as the Naranjo algorithm or scoring mechanism), and screens out reports with a high probability of relevance (drug withdrawal or rechallenge positive); enters the relevant parameters at the initial onset of drug eruption into the system to correct the analysis results.
[0063] Specifically, extract the key parameters of patient information, medication information, and drug eruption characteristics from each selected report. Patient information mainly includes age, gender, body type, allergy history, and comorbidities, etc.; medication information mainly includes drug name, dosage, administration route, and treatment cycle, etc.; drug eruption characteristics mainly include symptom type, severity, latency period, and whether it is drug withdrawal or rechallenge positive, etc.
[0064] According to the Naranjo algorithm, answer the questions item by item and accumulate the scores. Example questions include: Is there a previous report supporting that this drug can cause this adverse reaction, does the symptom relieve after stopping the drug, and does the symptom reappear after using the drug again, etc. Classify the reports into different levels such as "highly likely", "likely", "doubtful", "unlikely", etc.; finally obtain the relevance score.
[0065] Compare the newly input data with the data in the existing database, and calculate the similarity between the newly input data and the existing data in the database using methods such as cosine similarity and Euclidean distance; if significant differences are found, further analyze the reasons, which may be that some key factors are not fully considered or the weight settings are inappropriate. Based on the results of the comparative analysis, correct the analysis results generated by the system before.
[0066] Example 2:
[0067] As shown in the appendix Figure 1 It is different from the above embodiment in that the system further includes a judgment module. The judgment module is used to receive the drug name, drug classification, active ingredient, and symptoms corresponding to drug allergy (including non - body surface feature description statements and latency period), and construct a judgment database; the judgment database is generated based on the knowledge graph of biomedicine and drug allergy, and structures the relationships between entities such as drugs, symptoms, and individual characteristics to form a highly relevant database.
[0068] Receive subsequent users' allergic reactions and medications, and extract key features (such as symptom type, severity, latent time, etc.) from the allergic reactions input by the user based on the set similarity threshold; compare the drugs with a similarity greater than the preset threshold with the drugs taken by the user, give priority to whether they have the same name as the actual drugs taken by the user, and output relevant results.
[0069] If the drug taken by the user does not exist in the judgment database, the active ingredients and the classification of the drug (such as antibiotics or anti-epileptic drugs, etc.) are compared with the drugs in the judgment database, and the classification and active ingredients of the drug that cause the user's allergies are output to help doctors develop alternative treatment plans.
[0070] The judgment module is also used to obtain information on drug-induced allergic symptoms based on clinical trial results, and to build a correction model of allergic symptoms and individual differences of users and past medical records to ensure a more personalized and accurate assessment. When comparing the allergic characteristics of users, the judgment module will give priority to adjusting the allergic characteristics of users based on the correction model.
[0071] The interactive module also includes a voice collection unit, which is used to collect non-surface feature descriptions spoken by the user. In this embodiment, the voice collection unit is based on natural language processing (NLP) technology to achieve a high-precision voice-to-text function; automatically parse the symptom description spoken by the user, extract key information and incorporate it into the analysis process. The converted text is semantically analyzed using NLP technology to identify and extract key symptom descriptions (such as "chest tightness" or "dyspnea", etc.), automatically classify symptom types (such as cardiovascular system, respiratory system, etc.), and associate with other data in the system.
[0072] The judgment module also analyzes the adverse reactions of users, identifies the different reaction characteristics of the same drug and the same reaction characteristics of different drugs, and obtains individual difference reaction results. It is also used to analyze different regions, different economic levels and different environments, identify potential factors related to the user's allergic symptoms, and obtain objective factor analysis results.
[0073] Specifically, by analyzing the different symptoms and severity caused by the same drug in different users, and analyzing the similar symptoms caused by different drugs in the same user, potential common mechanisms or risk factors can be discovered, and the differences and commonalities of allergenic drugs can be analyzed.
[0074] For example, some drugs may be more likely to cause severe allergic reactions in certain age groups or gender groups; analyze the reasons behind these differences, such as individual genetic differences, immune status, etc. Although some drugs have different mechanisms of action, they may cause similar respiratory problems; explore the possibility of cross-allergy or other interactions.
[0075] Comprehensively consider the impact of factors such as climate conditions and living habits in different regions on drug reactions; evaluate socio-economic factors such as the user's economic status and accessibility of medical resources to understand their impact on treatment options; analyze potential allergens or other irritants in the patient's environment to help identify potential risk factors.
[0076] Specifically, for example, integrate data from various geographic information systems (GIS), including climate conditions (such as temperature, humidity), air quality index (AQI), and pollen concentration, etc.; obtain information on living habits and dietary cultures in different regions to understand how these factors affect individual health. For example, certain drugs may be more likely to cause skin reactions in tropical regions, while more commonly present as respiratory problems in temperate regions; some drugs are more likely to cause respiratory discomfort when used in highly polluted areas, while being less common in clean environments. It is recommended to avoid using certain drugs known to cause skin reactions during the pollen season, or to prefer alternatives with fewer side effects in areas with severe pollution.
[0077] Obviously, the above embodiments are merely examples given for clear illustration and are not limitations on the implementation manners. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to enumerate all implementation manners here. And the obvious changes or modifications derived therefrom still fall within the protection scope of the present invention.
Claims
1. An intelligent identification system for drug rash allergy-causing drugs, characterized in that: Includes the following modules: An input module is used to receive key data of the patient's basic information, drug rash type, name of the drug used before the rash, and medication time; The interactive module is used to provide an interactive interface and operation instructions for the input module; Construction module for establishing a database of clinical data and literature data; A search module is used to identify the range of allergenic drugs in the database based on the name of the drug rash; An analysis module is used to analyze the input key data and obtain the analysis results of the data of allergenic drugs causing drug eruptions; The correction module is used to correct the analysis results according to the clinical data in the database.
2. The intelligent identification system for drug rash allergy-causing drugs according to claim 1, characterized in that: Clinical data sources include hospital cases, electronic health records, and drug databases, and literature data sources include literature resources related to medicine.
3. The intelligent identification system for drug rash allergy-causing drugs according to claim 2, characterized in that: The retrieval module searches for clinical data and literature resources on drug eruptions caused by allergenic drugs to find the characteristics and patterns related to drug eruptions; integrates the characteristics and patterns related to drug eruptions, and formulates different rules based on incidence, median incubation time and risk factors.
4. The intelligent identification system for drug rash allergy-causing drugs according to claim 3, characterized in that: The analysis module retrieves different rules based on the key data of different patients, calculates the incidence of different drugs, the difference between the actual incubation time and the median incubation time in literature resources, and the number of risk factors, and sorts them according to the incidence, the size of the difference in incubation time and the number of risk factors; and obtains the probability of different drugs causing drug rash.
5. The intelligent identification system for drug rash allergy-causing drugs according to claim 4, characterized in that: The correction module retrieves drug rash reports of past hospital cases from the database, evaluates the relevance of each drug rash report, and corrects the analysis results.
6. The intelligent identification system for drug rash allergy-causing drugs according to claim 5, characterized in that: The analysis module also includes an allergenic drug identification unit and a pre-medication prevention unit; The allergenic drug identification unit is used to sequentially input the drug eruption type, the name of the drug used before the eruption, and the interval between the use of the drug and the eruption, and provides an option of whether it is the first time to use the drug and an option of risk factors; Output the probability ranking, drug information and reference basis of drugs causing drug rash; The pre-medication prevention unit is used to input the drug name and basic patient information, provide an option of whether it is the first time to use the drug, and provide an option of risk factors; it outputs the probability, latent time and potential risk factors of drug rash after the patient uses a specific drug.
7. The intelligent identification system for drug rash allergy-inducing drugs according to claim 6, characterized in that: It also includes a judgment module, which is used to receive the drug name, drug classification, active ingredients and symptoms corresponding to drug allergies, and build a judgment database; Receive the subsequent user's allergic reactions and medications taken, compare the medications with a similarity greater than the preset threshold with the medications taken by the user based on the set similarity threshold, and output the medications with the same name with a similarity greater than the preset threshold; If the drug taken by the user does not exist in the judgment database, the active ingredients and classification of the drug are compared with the drugs in the judgment database, and the classification and active ingredients of the drug that cause the user's allergies are output.
8. The intelligent identification system for drug rash allergy-causing drugs according to claim 7, characterized in that: Drug allergy symptoms include non-physical characteristic descriptions and latency periods collected during drug clinical trials.
9. The intelligent identification system for drug rash allergy-causing drugs according to claim 8, characterized in that: The judgment module is also used to obtain information on drug-induced allergic symptoms based on clinical trial results and to construct a correction model of allergic symptoms and individual differences of users and past medical records; When comparing the allergy characteristics of the user, the judgment module preferentially adjusts the allergy characteristics of the user according to the correction model.
10. The intelligent identification system for drug rash allergy-causing drugs according to claim 9, characterized in that: The interaction module also includes a voice collection unit, which is used to collect the non-body surface feature description spoken by the user.
11. The intelligent identification system for drug rash allergy-causing drugs according to claim 10, characterized in that: The judgment database is generated based on the knowledge graph.
12. The intelligent identification system for drug rash allergy-causing drugs according to claim 11, characterized in that: The judgment module is also used to analyze based on the user's adverse reactions; identify different reaction characteristics of users induced by the same drug and identify the same reaction characteristics of users induced by different drugs, and obtain individual difference reaction results.
13. The intelligent identification system for drug rash allergy-causing drugs according to claim 12, characterized in that: The judgment module is also used to analyze different regions, different economic levels and different environments, identify potential factors related to the user's allergic symptoms, and obtain analysis results of objective factors.
